aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGreg Kroah-Hartman <gregkh@linuxfoundation.org>2018-06-01 10:59:48 +0200
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2018-06-05 19:22:35 +0200
commitbe65f9ed267fd7d8b3146b7c4be9ecdd3e0aa3ed (patch)
treef9fddf1a58b26a1f2eaf2ed7fa350c1622abbdbb
parent3b93c0f4b6accb8105152900d7e414593a8b0c79 (diff)
downloadlinux-stericsson-be65f9ed267fd7d8b3146b7c4be9ecdd3e0aa3ed.tar.gz
staging: lustre: delete the filesystem from the tree.
The Lustre filesystem has been in the kernel tree for over 5 years now. While it has been an endless source of enjoyment for new kernel developers learning how to do basic codingstyle cleanups, as well as an semi-entertaining source of bewilderment from the vfs developers any time they have looked into the codebase to try to figure out how to port their latest api changes to this filesystem, it has not really moved forward into the "this is in shape to get out of staging" despite many half-completed attempts. And getting code out of staging is the main goal of that portion of the kernel tree. Code should not stagnate and it feels like having this code in staging is only causing the development cycle of the filesystem to take longer than it should. There is a whole separate out-of-tree copy of this codebase where the developers work on it, and then random changes are thrown over the wall at staging at some later point in time. This dual-tree development model has never worked, and the state of this codebase is proof of that. So, let's just delete the whole mess. Now the lustre developers can go off and work in their out-of-tree codebase and not have to worry about providing valid changelog entries and breaking their patches up into logical pieces. They can take the time they have spend doing those types of housekeeping chores and get the codebase into a much better shape, and it can be submitted for inclusion into the real part of the kernel tree when ready. Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Cc: James Simmons <jsimmons@infradead.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--MAINTAINERS9
-rw-r--r--drivers/staging/Kconfig2
-rw-r--r--drivers/staging/Makefile1
-rw-r--r--drivers/staging/lustre/Kconfig3
-rw-r--r--drivers/staging/lustre/Makefile2
-rw-r--r--drivers/staging/lustre/README.txt83
-rw-r--r--drivers/staging/lustre/TODO302
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs.h76
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_cpu.h434
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_crypto.h208
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_debug.h207
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h194
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_hash.h869
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_private.h200
-rw-r--r--drivers/staging/lustre/include/linux/libcfs/libcfs_string.h102
-rw-r--r--drivers/staging/lustre/include/linux/lnet/api.h212
-rw-r--r--drivers/staging/lustre/include/linux/lnet/lib-lnet.h652
-rw-r--r--drivers/staging/lustre/include/linux/lnet/lib-types.h666
-rw-r--r--drivers/staging/lustre/include/linux/lnet/socklnd.h87
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/libcfs_debug.h149
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h141
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/lnet-dlc.h150
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/lnet-types.h669
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/lnetctl.h123
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/lnetst.h556
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/nidstr.h119
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lnet/socklnd.h44
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_cfg.h261
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_fid.h293
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_fiemap.h72
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_idl.h2690
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_ioctl.h229
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_kernelcomm.h94
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_ostid.h236
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_param.h94
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_user.h1327
-rw-r--r--drivers/staging/lustre/include/uapi/linux/lustre/lustre_ver.h27
-rw-r--r--drivers/staging/lustre/lnet/Kconfig46
-rw-r--r--drivers/staging/lustre/lnet/Makefile1
-rw-r--r--drivers/staging/lustre/lnet/klnds/Makefile1
-rw-r--r--drivers/staging/lustre/lnet/klnds/o2iblnd/Makefile5
-rw-r--r--drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c2958
-rw-r--r--drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h1048
-rw-r--r--drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c3763
-rw-r--r--drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_modparams.c296
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/Makefile6
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/socklnd.c2921
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/socklnd.h704
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c2586
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib.c534
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/socklnd_modparams.c184
-rw-r--r--drivers/staging/lustre/lnet/klnds/socklnd/socklnd_proto.c810
-rw-r--r--drivers/staging/lustre/lnet/libcfs/Makefile16
-rw-r--r--drivers/staging/lustre/lnet/libcfs/debug.c461
-rw-r--r--drivers/staging/lustre/lnet/libcfs/fail.c146
-rw-r--r--drivers/staging/lustre/lnet/libcfs/hash.c2065
-rw-r--r--drivers/staging/lustre/lnet/libcfs/libcfs_cpu.c1086
-rw-r--r--drivers/staging/lustre/lnet/libcfs/libcfs_lock.c155
-rw-r--r--drivers/staging/lustre/lnet/libcfs/libcfs_mem.c171
-rw-r--r--drivers/staging/lustre/lnet/libcfs/libcfs_string.c562
-rw-r--r--drivers/staging/lustre/lnet/libcfs/linux-crypto-adler.c139
-rw-r--r--drivers/staging/lustre/lnet/libcfs/linux-crypto.c447
-rw-r--r--drivers/staging/lustre/lnet/libcfs/linux-crypto.h30
-rw-r--r--drivers/staging/lustre/lnet/libcfs/linux-debug.c142
-rw-r--r--drivers/staging/lustre/lnet/libcfs/linux-tracefile.c258
-rw-r--r--drivers/staging/lustre/lnet/libcfs/module.c758
-rw-r--r--drivers/staging/lustre/lnet/libcfs/tracefile.c1198
-rw-r--r--drivers/staging/lustre/lnet/libcfs/tracefile.h274
-rw-r--r--drivers/staging/lustre/lnet/lnet/Makefile10
-rw-r--r--drivers/staging/lustre/lnet/lnet/acceptor.c501
-rw-r--r--drivers/staging/lustre/lnet/lnet/api-ni.c2307
-rw-r--r--drivers/staging/lustre/lnet/lnet/config.c1235
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-eq.c426
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-md.c463
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-me.c274
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-move.c2386
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-msg.c625
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-ptl.c987
-rw-r--r--drivers/staging/lustre/lnet/lnet/lib-socket.c585
-rw-r--r--drivers/staging/lustre/lnet/lnet/lo.c105
-rw-r--r--drivers/staging/lustre/lnet/lnet/module.c239
-rw-r--r--drivers/staging/lustre/lnet/lnet/net_fault.c1023
-rw-r--r--drivers/staging/lustre/lnet/lnet/nidstrings.c1261
-rw-r--r--drivers/staging/lustre/lnet/lnet/peer.c456
-rw-r--r--drivers/staging/lustre/lnet/lnet/router.c1799
-rw-r--r--drivers/staging/lustre/lnet/lnet/router_proc.c907
-rw-r--r--drivers/staging/lustre/lnet/selftest/Makefile7
-rw-r--r--drivers/staging/lustre/lnet/selftest/brw_test.c526
-rw-r--r--drivers/staging/lustre/lnet/selftest/conctl.c801
-rw-r--r--drivers/staging/lustre/lnet/selftest/conrpc.c1396
-rw-r--r--drivers/staging/lustre/lnet/selftest/conrpc.h142
-rw-r--r--drivers/staging/lustre/lnet/selftest/console.c2104
-rw-r--r--drivers/staging/lustre/lnet/selftest/console.h244
-rw-r--r--drivers/staging/lustre/lnet/selftest/framework.c1786
-rw-r--r--drivers/staging/lustre/lnet/selftest/module.c169
-rw-r--r--drivers/staging/lustre/lnet/selftest/ping_test.c228
-rw-r--r--drivers/staging/lustre/lnet/selftest/rpc.c1682
-rw-r--r--drivers/staging/lustre/lnet/selftest/rpc.h295
-rw-r--r--drivers/staging/lustre/lnet/selftest/selftest.h622
-rw-r--r--drivers/staging/lustre/lnet/selftest/timer.c244
-rw-r--r--drivers/staging/lustre/lnet/selftest/timer.h50
-rw-r--r--drivers/staging/lustre/lustre/Kconfig45
-rw-r--r--drivers/staging/lustre/lustre/Makefile2
-rw-r--r--drivers/staging/lustre/lustre/fid/Makefile5
-rw-r--r--drivers/staging/lustre/lustre/fid/fid_internal.h46
-rw-r--r--drivers/staging/lustre/lustre/fid/fid_lib.c87
-rw-r--r--drivers/staging/lustre/lustre/fid/fid_request.c410
-rw-r--r--drivers/staging/lustre/lustre/fid/lproc_fid.c225
-rw-r--r--drivers/staging/lustre/lustre/fld/Makefile5
-rw-r--r--drivers/staging/lustre/lustre/fld/fld_cache.c516
-rw-r--r--drivers/staging/lustre/lustre/fld/fld_internal.h170
-rw-r--r--drivers/staging/lustre/lustre/fld/fld_request.c446
-rw-r--r--drivers/staging/lustre/lustre/fld/lproc_fld.c154
-rw-r--r--drivers/staging/lustre/lustre/include/cl_object.h2463
-rw-r--r--drivers/staging/lustre/lustre/include/interval_tree.h119
-rw-r--r--drivers/staging/lustre/lustre/include/llog_swab.h67
-rw-r--r--drivers/staging/lustre/lustre/include/lprocfs_status.h646
-rw-r--r--drivers/staging/lustre/lustre/include/lu_object.h1305
-rw-r--r--drivers/staging/lustre/lustre/include/lu_ref.h178
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_acl.h51
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_compat.h82
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_debug.h52
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_disk.h152
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_dlm.h1346
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_dlm_flags.h402
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_errno.h198
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_export.h250
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_fid.h676
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_fld.h137
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_ha.h61
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_handles.h91
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_import.h369
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_intent.h71
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_kernelcomm.h56
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_lib.h126
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_linkea.h93
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_lmv.h174
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_log.h382
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_mdc.h229
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_mds.h62
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_net.h2360
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_nrs.h718
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_nrs_fifo.h71
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_obdo.h55
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_patchless_compat.h68
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_req_layout.h307
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_sec.h1072
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_swab.h109
-rw-r--r--drivers/staging/lustre/lustre/include/obd.h1114
-rw-r--r--drivers/staging/lustre/lustre/include/obd_cksum.h153
-rw-r--r--drivers/staging/lustre/lustre/include/obd_class.h1603
-rw-r--r--drivers/staging/lustre/lustre/include/obd_support.h517
-rw-r--r--drivers/staging/lustre/lustre/include/seq_range.h200
-rw-r--r--drivers/staging/lustre/lustre/ldlm/interval_tree.c599
-rw-r--r--drivers/staging/lustre/lustre/ldlm/l_lock.c73
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_extent.c258
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_flock.c486
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_inodebits.c69
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_internal.h342
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_lib.c842
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_lock.c2135
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c1163
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_plain.c68
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_pool.c1013
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_request.c2033
-rw-r--r--drivers/staging/lustre/lustre/ldlm/ldlm_resource.c1318
-rw-r--r--drivers/staging/lustre/lustre/llite/Makefile13
-rw-r--r--drivers/staging/lustre/lustre/llite/acl.c108
-rw-r--r--drivers/staging/lustre/lustre/llite/dcache.c300
-rw-r--r--drivers/staging/lustre/lustre/llite/dir.c1708
-rw-r--r--drivers/staging/lustre/lustre/llite/file.c3580
-rw-r--r--drivers/staging/lustre/lustre/llite/glimpse.c205
-rw-r--r--drivers/staging/lustre/lustre/llite/lcommon_cl.c292
-rw-r--r--drivers/staging/lustre/lustre/llite/lcommon_misc.c186
-rw-r--r--drivers/staging/lustre/lustre/llite/llite_internal.h1344
-rw-r--r--drivers/staging/lustre/lustre/llite/llite_lib.c2668
-rw-r--r--drivers/staging/lustre/lustre/llite/llite_mmap.c480
-rw-r--r--drivers/staging/lustre/lustre/llite/llite_nfs.c375
-rw-r--r--drivers/staging/lustre/lustre/llite/lproc_llite.c1659
-rw-r--r--drivers/staging/lustre/lustre/llite/namei.c1207
-rw-r--r--drivers/staging/lustre/lustre/llite/range_lock.c241
-rw-r--r--drivers/staging/lustre/lustre/llite/range_lock.h83
-rw-r--r--drivers/staging/lustre/lustre/llite/rw.c1214
-rw-r--r--drivers/staging/lustre/lustre/llite/rw26.c641
-rw-r--r--drivers/staging/lustre/lustre/llite/statahead.c1577
-rw-r--r--drivers/staging/lustre/lustre/llite/super25.c189
-rw-r--r--drivers/staging/lustre/lustre/llite/symlink.c159
-rw-r--r--drivers/staging/lustre/lustre/llite/vvp_dev.c640
-rw-r--r--drivers/staging/lustre/lustre/llite/vvp_internal.h321
-rw-r--r--drivers/staging/lustre/lustre/llite/vvp_io.c1374
-rw-r--r--drivers/staging/lustre/lustre/llite/vvp_lock.c87
-rw-r--r--drivers/staging/lustre/lustre/llite/vvp_object.c303
-rw-r--r--drivers/staging/lustre/lustre/llite/vvp_page.c523
-rw-r--r--drivers/staging/lustre/lustre/llite/xattr.c665
-rw-r--r--drivers/staging/lustre/lustre/llite/xattr_cache.c504
-rw-r--r--drivers/staging/lustre/lustre/llite/xattr_security.c96
-rw-r--r--drivers/staging/lustre/lustre/lmv/Makefile5
-rw-r--r--drivers/staging/lustre/lustre/lmv/lmv_fld.c82
-rw-r--r--drivers/staging/lustre/lustre/lmv/lmv_intent.c521
-rw-r--r--drivers/staging/lustre/lustre/lmv/lmv_internal.h164
-rw-r--r--drivers/staging/lustre/lustre/lmv/lmv_obd.c3131
-rw-r--r--drivers/staging/lustre/lustre/lmv/lproc_lmv.c173
-rw-r--r--drivers/staging/lustre/lustre/lov/Makefile9
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_cl_internal.h639
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_dev.c384
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_ea.c331
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_internal.h286
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_io.c1023
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_lock.c348
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_merge.c105
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_obd.c1444
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_object.c1625
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_offset.c269
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_pack.c400
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_page.c136
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_pool.c546
-rw-r--r--drivers/staging/lustre/lustre/lov/lov_request.c354
-rw-r--r--drivers/staging/lustre/lustre/lov/lovsub_dev.c147
-rw-r--r--drivers/staging/lustre/lustre/lov/lovsub_lock.c81
-rw-r--r--drivers/staging/lustre/lustre/lov/lovsub_object.c180
-rw-r--r--drivers/staging/lustre/lustre/lov/lovsub_page.c68
-rw-r--r--drivers/staging/lustre/lustre/lov/lproc_lov.c299
-rw-r--r--drivers/staging/lustre/lustre/mdc/Makefile5
-rw-r--r--drivers/staging/lustre/lustre/mdc/lproc_mdc.c231
-rw-r--r--drivers/staging/lustre/lustre/mdc/mdc_internal.h144
-rw-r--r--drivers/staging/lustre/lustre/mdc/mdc_lib.c498
-rw-r--r--drivers/staging/lustre/lustre/mdc/mdc_locks.c1239
-rw-r--r--drivers/staging/lustre/lustre/mdc/mdc_reint.c421
-rw-r--r--drivers/staging/lustre/lustre/mdc/mdc_request.c2770
-rw-r--r--drivers/staging/lustre/lustre/mgc/Makefile5
-rw-r--r--drivers/staging/lustre/lustre/mgc/lproc_mgc.c69
-rw-r--r--drivers/staging/lustre/lustre/mgc/mgc_internal.h57
-rw-r--r--drivers/staging/lustre/lustre/mgc/mgc_request.c1851
-rw-r--r--drivers/staging/lustre/lustre/obdclass/Makefile12
-rw-r--r--drivers/staging/lustre/lustre/obdclass/cl_internal.h95
-rw-r--r--drivers/staging/lustre/lustre/obdclass/cl_io.c1151
-rw-r--r--drivers/staging/lustre/lustre/obdclass/cl_lock.c275
-rw-r--r--drivers/staging/lustre/lustre/obdclass/cl_object.c1059
-rw-r--r--drivers/staging/lustre/lustre/obdclass/cl_page.c1045
-rw-r--r--drivers/staging/lustre/lustre/obdclass/class_obd.c544
-rw-r--r--drivers/staging/lustre/lustre/obdclass/debug.c96
-rw-r--r--drivers/staging/lustre/lustre/obdclass/genops.c1480
-rw-r--r--drivers/staging/lustre/lustre/obdclass/kernelcomm.c240
-rw-r--r--drivers/staging/lustre/lustre/obdclass/linkea.c249
-rw-r--r--drivers/staging/lustre/lustre/obdclass/linux/linux-module.c514
-rw-r--r--drivers/staging/lustre/lustre/obdclass/linux/linux-sysctl.c162
-rw-r--r--drivers/staging/lustre/lustre/obdclass/llog.c524
-rw-r--r--drivers/staging/lustre/lustre/obdclass/llog_cat.c236
-rw-r--r--drivers/staging/lustre/lustre/obdclass/llog_internal.h79
-rw-r--r--drivers/staging/lustre/lustre/obdclass/llog_obd.c225
-rw-r--r--drivers/staging/lustre/lustre/obdclass/llog_swab.c412
-rw-r--r--drivers/staging/lustre/lustre/obdclass/lprocfs_counters.c134
-rw-r--r--drivers/staging/lustre/lustre/obdclass/lprocfs_status.c1698
-rw-r--r--drivers/staging/lustre/lustre/obdclass/lu_object.c2056
-rw-r--r--drivers/staging/lustre/lustre/obdclass/lu_ref.c45
-rw-r--r--drivers/staging/lustre/lustre/obdclass/lustre_handles.c241
-rw-r--r--drivers/staging/lustre/lustre/obdclass/lustre_peer.c214
-rw-r--r--drivers/staging/lustre/lustre/obdclass/obd_config.c1538
-rw-r--r--drivers/staging/lustre/lustre/obdclass/obd_mount.c1245
-rw-r--r--drivers/staging/lustre/lustre/obdclass/obdo.c181
-rw-r--r--drivers/staging/lustre/lustre/obdclass/statfs_pack.c58
-rw-r--r--drivers/staging/lustre/lustre/obdclass/uuid.c45
-rw-r--r--drivers/staging/lustre/lustre/obdecho/Makefile5
-rw-r--r--drivers/staging/lustre/lustre/obdecho/echo_client.c1729
-rw-r--r--drivers/staging/lustre/lustre/obdecho/echo_internal.h42
-rw-r--r--drivers/staging/lustre/lustre/osc/Makefile6
-rw-r--r--drivers/staging/lustre/lustre/osc/lproc_osc.c838
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_cache.c3306
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_cl_internal.h681
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_dev.c246
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_internal.h237
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_io.c918
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_lock.c1230
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_object.c473
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_page.c1094
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_quota.c236
-rw-r--r--drivers/staging/lustre/lustre/osc/osc_request.c2907
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/Makefile23
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/client.c3271
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/connection.c192
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/errno.c383
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/events.c585
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/import.c1677
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/layout.c2232
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/llog_client.c338
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/llog_net.c67
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/lproc_ptlrpc.c1316
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/niobuf.c771
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/nrs.c1613
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/nrs_fifo.c270
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/pack_generic.c2311
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/pers.c72
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/pinger.c474
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/ptlrpc_internal.h371
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/ptlrpc_module.c186
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/ptlrpcd.c914
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/recover.c374
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec.c2379
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c572
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec_config.c850
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec_gc.c190
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec_lproc.c170
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec_null.c459
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/sec_plain.c1023
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/service.c2807
-rw-r--r--drivers/staging/lustre/lustre/ptlrpc/wiretest.c4210
-rw-r--r--drivers/staging/lustre/sysfs-fs-lustre654
-rw-r--r--scripts/selinux/mdp/mdp.c1
308 files changed, 0 insertions, 195272 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 4b65225d443a..db158767de20 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13329,15 +13329,6 @@ S: Odd Fixes
F: Documentation/devicetree/bindings/staging/iio/
F: drivers/staging/iio/
-STAGING - LUSTRE PARALLEL FILESYSTEM
-M: Oleg Drokin <oleg.drokin@intel.com>
-M: Andreas Dilger <andreas.dilger@intel.com>
-M: James Simmons <jsimmons@infradead.org>
-L: lustre-devel@lists.lustre.org (moderated for non-subscribers)
-W: http://wiki.lustre.org/
-S: Maintained
-F: drivers/staging/lustre
-
STAGING - NVIDIA COMPLIANT EMBEDDED CONTROLLER INTERFACE (nvec)
M: Marc Dietrich <marvin24@gmx.de>
L: ac100@lists.launchpad.net (moderated for non-subscribers)
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index d5926f0d3f6c..1c357ef669ae 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -84,8 +84,6 @@ source "drivers/staging/netlogic/Kconfig"
source "drivers/staging/mt29f_spinand/Kconfig"
-source "drivers/staging/lustre/Kconfig"
-
source "drivers/staging/dgnc/Kconfig"
source "drivers/staging/gs_fpgaboot/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 919753c3d3f6..2edb9860931e 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -32,7 +32,6 @@ obj-$(CONFIG_STAGING_BOARD) += board/
obj-$(CONFIG_LTE_GDM724X) += gdm724x/
obj-$(CONFIG_FIREWIRE_SERIAL) += fwserial/
obj-$(CONFIG_GOLDFISH) += goldfish/
-obj-$(CONFIG_LNET) += lustre/
obj-$(CONFIG_DGNC) += dgnc/
obj-$(CONFIG_MTD_SPINAND_MT29F) += mt29f_spinand/
obj-$(CONFIG_GS_FPGABOOT) += gs_fpgaboot/
diff --git a/drivers/staging/lustre/Kconfig b/drivers/staging/lustre/Kconfig
deleted file mode 100644
index b7d81096eee9..000000000000
--- a/drivers/staging/lustre/Kconfig
+++ /dev/null
@@ -1,3 +0,0 @@
-source "drivers/staging/lustre/lnet/Kconfig"
-
-source "drivers/staging/lustre/lustre/Kconfig"
diff --git a/drivers/staging/lustre/Makefile b/drivers/staging/lustre/Makefile
deleted file mode 100644
index 95ffe337a80a..000000000000
--- a/drivers/staging/lustre/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-obj-$(CONFIG_LNET) += lnet/
-obj-$(CONFIG_LUSTRE_FS) += lustre/
diff --git a/drivers/staging/lustre/README.txt b/drivers/staging/lustre/README.txt
deleted file mode 100644
index 783959240490..000000000000
--- a/drivers/staging/lustre/README.txt
+++ /dev/null
@@ -1,83 +0,0 @@
-Lustre Parallel Filesystem Client
-=================================
-
-The Lustre file system is an open-source, parallel file system
-that supports many requirements of leadership class HPC simulation
-environments.
-Born from a research project at Carnegie Mellon University,
-the Lustre file system is a widely-used option in HPC.
-The Lustre file system provides a POSIX compliant file system interface,
-can scale to thousands of clients, petabytes of storage and
-hundreds of gigabytes per second of I/O bandwidth.
-
-Unlike shared disk storage cluster filesystems (e.g. OCFS2, GFS, GPFS),
-Lustre has independent Metadata and Data servers that clients can access
-in parallel to maximize performance.
-
-In order to use Lustre client you will need to download the "lustre-client"
-package that contains the userspace tools from http://lustre.org/download/
-
-You will need to install and configure your Lustre servers separately.
-
-Mount Syntax
-============
-After you installed the lustre-client tools including mount.lustre binary
-you can mount your Lustre filesystem with:
-
-mount -t lustre mgs:/fsname mnt
-
-where mgs is the host name or ip address of your Lustre MGS(management service)
-fsname is the name of the filesystem you would like to mount.
-
-
-Mount Options
-=============
-
- noflock
- Disable posix file locking (Applications trying to use
- the functionality will get ENOSYS)
-
- localflock
- Enable local flock support, using only client-local flock
- (faster, for applications that require flock but do not run
- on multiple nodes).
-
- flock
- Enable cluster-global posix file locking coherent across all
- client nodes.
-
- user_xattr, nouser_xattr
- Support "user." extended attributes (or not)
-
- user_fid2path, nouser_fid2path
- Enable FID to path translation by regular users (or not)
-
- checksum, nochecksum
- Verify data consistency on the wire and in memory as it passes
- between the layers (or not).
-
- lruresize, nolruresize
- Allow lock LRU to be controlled by memory pressure on the server
- (or only 100 (default, controlled by lru_size proc parameter) locks
- per CPU per server on this client).
-
- lazystatfs, nolazystatfs
- Do not block in statfs() if some of the servers are down.
-
- 32bitapi
- Shrink inode numbers to fit into 32 bits. This is necessary
- if you plan to reexport Lustre filesystem from this client via
- NFSv4.
-
- verbose, noverbose
- Enable mount/umount console messages (or not)
-
-More Information
-================
-You can get more information at the Lustre website: http://wiki.lustre.org/
-
-Source for the userspace tools and out-of-tree client and server code
-is available at: http://git.hpdd.intel.com/fs/lustre-release.git
-
-Latest binary packages:
-http://lustre.org/download/
diff --git a/drivers/staging/lustre/TODO b/drivers/staging/lustre/TODO
deleted file mode 100644
index 5332cdb19bfa..000000000000
--- a/drivers/staging/lustre/TODO
+++ /dev/null
@@ -1,302 +0,0 @@
-Currently all the work directed toward the lustre upstream client is tracked
-at the following link:
-
-https://jira.hpdd.intel.com/browse/LU-9679
-
-Under this ticket you will see the following work items that need to be
-addressed:
-
-******************************************************************************
-* libcfs cleanup
-*
-* https://jira.hpdd.intel.com/browse/LU-9859
-*
-* Track all the cleanups and simplification of the libcfs module. Remove
-* functions the kernel provides. Possibly integrate some of the functionality
-* into the kernel proper.
-*
-******************************************************************************
-
-https://jira.hpdd.intel.com/browse/LU-100086
-
-LNET_MINOR conflicts with USERIO_MINOR
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8130
-
-Fix and simplify libcfs hash handling
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8703
-
-The current way we handle SMP is wrong. Platforms like ARM and KNL can have
-core and NUMA setups with things like NUMA nodes with no cores. We need to
-handle such cases. This work also greatly simplified the lustre SMP code.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9019
-
-Replace libcfs time API with standard kernel APIs. Also migrate away from
-jiffies. We found jiffies can vary on nodes which can lead to corner cases
-that can break the file system due to nodes having inconsistent behavior.
-So move to time64_t and ktime_t as much as possible.
-
-******************************************************************************
-* Proper IB support for ko2iblnd
-******************************************************************************
-https://jira.hpdd.intel.com/browse/LU-9179
-
-Poor performance for the ko2iblnd driver. This is related to many of the
-patches below that are missing from the linux client.
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9886
-
-Crash in upstream kiblnd_handle_early_rxs()
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10394 / LU-10526 / LU-10089
-
-Default to default to using MEM_REG
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10459
-
-throttle tx based on queue depth
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9943
-
-correct WR fast reg accounting
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10291
-
-remove concurrent_sends tunable
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10213
-
-calculate qp max_send_wrs properly
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9810
-
-use less CQ entries for each connection
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10129 / LU-9180
-
-rework map_on_demand behavior
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10129
-
-query device capabilities
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10015
-
-fix race at kiblnd_connect_peer
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9983
-
-allow for discontiguous fragments
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9500
-
-Don't Page Align remote_addr with FastReg
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9448
-
-handle empty CPTs
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9507
-
-Don't Assert On Reconnect with MultiQP
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9472
-
-Fix FastReg map/unmap for MLX5
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9425
-
-Turn on 2 sges by default
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8943
-
-Enable Multiple OPA Endpoints between Nodes
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-5718
-
-multiple sges for work request
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9094
-
-kill timedout txs from ibp_tx_queue
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9094
-
-reconnect peer for REJ_INVALID_SERVICE_ID
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8752
-
-Stop MLX5 triggering a dump_cqe
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8874
-
-Move ko2iblnd to latest RDMA changes
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8875 / LU-8874
-
-Change to new RDMA done callback mechanism
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9164 / LU-8874
-
-Incorporate RDMA map/unamp API's into ko2iblnd
-
-******************************************************************************
-* sysfs/debugfs fixes
-*
-* https://jira.hpdd.intel.com/browse/LU-8066
-*
-* The original migration to sysfs was done in haste without properly working
-* utilities to test the changes. This covers the work to restore the proper
-* behavior. Huge project to make this right.
-*
-******************************************************************************
-
-https://jira.hpdd.intel.com/browse/LU-9431
-
-The function class_process_proc_param was used for our mass updates of proc
-tunables. It didn't work with sysfs and it was just ugly so it was removed.
-In the process the ability to mass update thousands of clients was lost. This
-work restores this in a sane way.
-
-------------------------------------------------------------------------------
-https://jira.hpdd.intel.com/browse/LU-9091
-
-One the major request of users is the ability to pass in parameters into a
-sysfs file in various different units. For example we can set max_pages_per_rpc
-but this can vary on platforms due to different platform sizes. So you can
-set this like max_pages_per_rpc=16MiB. The original code to handle this written
-before the string helpers were created so the code doesn't follow that format
-but it would be easy to move to. Currently the string helpers does the reverse
-of what we need, changing bytes to string. We need to change a string to bytes.
-
-******************************************************************************
-* Proper user land to kernel space interface for Lustre
-*
-* https://jira.hpdd.intel.com/browse/LU-9680
-*
-******************************************************************************
-
-https://jira.hpdd.intel.com/browse/LU-8915
-
-Don't use linux list structure as user land arguments for lnet selftest.
-This code is pretty poor quality and really needs to be reworked.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8834
-
-The lustre ioctl LL_IOC_FUTIMES_3 is very generic. Need to either work with
-other file systems with similar functionality and make a common syscall
-interface or rework our server code to automagically do it for us.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-6202
-
-Cleanup up ioctl handling. We have many obsolete ioctls. Also the way we do
-ioctls can be changed over to netlink. This also has the benefit of working
-better with HPC systems that do IO forwarding. Such systems don't like ioctls
-very well.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9667
-
-More cleanups by making our utilities use sysfs instead of ioctls for LNet.
-Also it has been requested to move the remaining ioctls to the netlink API.
-
-******************************************************************************
-* Misc
-******************************************************************************
-
-------------------------------------------------------------------------------
-https://jira.hpdd.intel.com/browse/LU-9855
-
-Clean up obdclass preprocessor code. One of the major eye sores is the various
-pointer redirections and macros used by the obdclass. This makes the code very
-difficult to understand. It was requested by the Al Viro to clean this up before
-we leave staging.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9633
-
-Migrate to sphinx kernel-doc style comments. Add documents in Documentation.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-6142
-
-Possible remaining coding style fix. Remove deadcode. Enforce kernel code
-style. Other minor misc cleanups...
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8837
-
-Separate client/server functionality. Functions only used by server can be
-removed from client. Most of this has been done but we need a inspect of the
-code to make sure.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-8964
-
-Lustre client readahead/writeback control needs to better suit kernel providings.
-Currently its being explored. We could end up replacing the CLIO read ahead
-abstract with the kernel proper version.
-
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9862
-
-Patch that landed for LU-7890 leads to static checker errors
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-9868
-
-dcache/namei fixes for lustre
-------------------------------------------------------------------------------
-
-https://jira.hpdd.intel.com/browse/LU-10467
-
-use standard linux wait_events macros work by Neil Brown
-
-------------------------------------------------------------------------------
-
-Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, Andreas Dilger
-<andreas.dilger@intel.com>, James Simmons <jsimmons@infradead.org> and
-Oleg Drokin <oleg.drokin@intel.com>.
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs.h b/drivers/staging/lustre/include/linux/libcfs/libcfs.h
deleted file mode 100644
index edc7ed0dcb94..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs.h
+++ /dev/null
@@ -1,76 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- */
-
-#ifndef __LIBCFS_LIBCFS_H__
-#define __LIBCFS_LIBCFS_H__
-
-#include <linux/notifier.h>
-#include <linux/workqueue.h>
-#include <linux/sysctl.h>
-
-#include <linux/libcfs/libcfs_debug.h>
-#include <linux/libcfs/libcfs_private.h>
-#include <linux/libcfs/libcfs_fail.h>
-
-#define LIBCFS_VERSION "0.7.0"
-
-extern struct blocking_notifier_head libcfs_ioctl_list;
-static inline int notifier_from_ioctl_errno(int err)
-{
- if (err == -EINVAL)
- return NOTIFY_OK;
- return notifier_from_errno(err) | NOTIFY_STOP_MASK;
-}
-
-int libcfs_setup(void);
-
-extern struct workqueue_struct *cfs_rehash_wq;
-
-void lustre_insert_debugfs(struct ctl_table *table);
-int lprocfs_call_handler(void *data, int write, loff_t *ppos,
- void __user *buffer, size_t *lenp,
- int (*handler)(void *data, int write, loff_t pos,
- void __user *buffer, int len));
-
-/*
- * Memory
- */
-#if BITS_PER_LONG == 32
-/* limit to lowmem on 32-bit systems */
-#define NUM_CACHEPAGES \
- min(totalram_pages, 1UL << (30 - PAGE_SHIFT) * 3 / 4)
-#else
-#define NUM_CACHEPAGES totalram_pages
-#endif
-
-#endif /* __LIBCFS_LIBCFS_H__ */
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_cpu.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_cpu.h
deleted file mode 100644
index 61641c41c492..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_cpu.h
+++ /dev/null
@@ -1,434 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved.
- *
- * Copyright (c) 2012, 2015 Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_cpu.h
- *
- * CPU partition
- * . CPU partition is virtual processing unit
- *
- * . CPU partition can present 1-N cores, or 1-N NUMA nodes,
- * in other words, CPU partition is a processors pool.
- *
- * CPU Partition Table (CPT)
- * . a set of CPU partitions
- *
- * . There are two modes for CPT: CFS_CPU_MODE_NUMA and CFS_CPU_MODE_SMP
- *
- * . User can specify total number of CPU partitions while creating a
- * CPT, ID of CPU partition is always start from 0.
- *
- * Example: if there are 8 cores on the system, while creating a CPT
- * with cpu_npartitions=4:
- * core[0, 1] = partition[0], core[2, 3] = partition[1]
- * core[4, 5] = partition[2], core[6, 7] = partition[3]
- *
- * cpu_npartitions=1:
- * core[0, 1, ... 7] = partition[0]
- *
- * . User can also specify CPU partitions by string pattern
- *
- * Examples: cpu_partitions="0[0,1], 1[2,3]"
- * cpu_partitions="N 0[0-3], 1[4-8]"
- *
- * The first character "N" means following numbers are numa ID
- *
- * . NUMA allocators, CPU affinity threads are built over CPU partitions,
- * instead of HW CPUs or HW nodes.
- *
- * . By default, Lustre modules should refer to the global cfs_cpt_tab,
- * instead of accessing HW CPUs directly, so concurrency of Lustre can be
- * configured by cpu_npartitions of the global cfs_cpt_tab
- *
- * . If cpu_npartitions=1(all CPUs in one pool), lustre should work the
- * same way as 2.2 or earlier versions
- *
- * Author: liang@whamcloud.com
- */
-
-#ifndef __LIBCFS_CPU_H__
-#define __LIBCFS_CPU_H__
-
-#include <linux/cpu.h>
-#include <linux/cpuset.h>
-#include <linux/topology.h>
-
-/* any CPU partition */
-#define CFS_CPT_ANY (-1)
-
-#ifdef CONFIG_SMP
-/** virtual processing unit */
-struct cfs_cpu_partition {
- /* CPUs mask for this partition */
- cpumask_var_t cpt_cpumask;
- /* nodes mask for this partition */
- nodemask_t *cpt_nodemask;
- /* spread rotor for NUMA allocator */
- unsigned int cpt_spread_rotor;
-};
-
-
-/** descriptor for CPU partitions */
-struct cfs_cpt_table {
- /* version, reserved for hotplug */
- unsigned int ctb_version;
- /* spread rotor for NUMA allocator */
- unsigned int ctb_spread_rotor;
- /* # of CPU partitions */
- unsigned int ctb_nparts;
- /* partitions tables */
- struct cfs_cpu_partition *ctb_parts;
- /* shadow HW CPU to CPU partition ID */
- int *ctb_cpu2cpt;
- /* all cpus in this partition table */
- cpumask_var_t ctb_cpumask;
- /* all nodes in this partition table */
- nodemask_t *ctb_nodemask;
-};
-
-extern struct cfs_cpt_table *cfs_cpt_tab;
-
-/**
- * return cpumask of CPU partition \a cpt
- */
-cpumask_var_t *cfs_cpt_cpumask(struct cfs_cpt_table *cptab, int cpt);
-/**
- * print string information of cpt-table
- */
-int cfs_cpt_table_print(struct cfs_cpt_table *cptab, char *buf, int len);
-/**
- * return total number of CPU partitions in \a cptab
- */
-int
-cfs_cpt_number(struct cfs_cpt_table *cptab);
-/**
- * return number of HW cores or hyper-threadings in a CPU partition \a cpt
- */
-int cfs_cpt_weight(struct cfs_cpt_table *cptab, int cpt);
-/**
- * is there any online CPU in CPU partition \a cpt
- */
-int cfs_cpt_online(struct cfs_cpt_table *cptab, int cpt);
-/**
- * return nodemask of CPU partition \a cpt
- */
-nodemask_t *cfs_cpt_nodemask(struct cfs_cpt_table *cptab, int cpt);
-/**
- * shadow current HW processor ID to CPU-partition ID of \a cptab
- */
-int cfs_cpt_current(struct cfs_cpt_table *cptab, int remap);
-/**
- * shadow HW processor ID \a CPU to CPU-partition ID by \a cptab
- */
-int cfs_cpt_of_cpu(struct cfs_cpt_table *cptab, int cpu);
-/**
- * bind current thread on a CPU-partition \a cpt of \a cptab
- */
-int cfs_cpt_bind(struct cfs_cpt_table *cptab, int cpt);
-/**
- * add \a cpu to CPU partition @cpt of \a cptab, return 1 for success,
- * otherwise 0 is returned
- */
-int cfs_cpt_set_cpu(struct cfs_cpt_table *cptab, int cpt, int cpu);
-/**
- * remove \a cpu from CPU partition \a cpt of \a cptab
- */
-void cfs_cpt_unset_cpu(struct cfs_cpt_table *cptab, int cpt, int cpu);
-/**
- * add all cpus in \a mask to CPU partition \a cpt
- * return 1 if successfully set all CPUs, otherwise return 0
- */
-int cfs_cpt_set_cpumask(struct cfs_cpt_table *cptab,
- int cpt, cpumask_t *mask);
-/**
- * remove all cpus in \a mask from CPU partition \a cpt
- */
-void cfs_cpt_unset_cpumask(struct cfs_cpt_table *cptab,
- int cpt, cpumask_t *mask);
-/**
- * add all cpus in NUMA node \a node to CPU partition \a cpt
- * return 1 if successfully set all CPUs, otherwise return 0
- */
-int cfs_cpt_set_node(struct cfs_cpt_table *cptab, int cpt, int node);
-/**
- * remove all cpus in NUMA node \a node from CPU partition \a cpt
- */
-void cfs_cpt_unset_node(struct cfs_cpt_table *cptab, int cpt, int node);
-
-/**
- * add all cpus in node mask \a mask to CPU partition \a cpt
- * return 1 if successfully set all CPUs, otherwise return 0
- */
-int cfs_cpt_set_nodemask(struct cfs_cpt_table *cptab,
- int cpt, nodemask_t *mask);
-/**
- * remove all cpus in node mask \a mask from CPU partition \a cpt
- */
-void cfs_cpt_unset_nodemask(struct cfs_cpt_table *cptab,
- int cpt, nodemask_t *mask);
-/**
- * unset all cpus for CPU partition \a cpt
- */
-void cfs_cpt_clear(struct cfs_cpt_table *cptab, int cpt);
-/**
- * convert partition id \a cpt to numa node id, if there are more than one
- * nodes in this partition, it might return a different node id each time.
- */
-int cfs_cpt_spread_node(struct cfs_cpt_table *cptab, int cpt);
-
-/**
- * return number of HTs in the same core of \a cpu
- */
-int cfs_cpu_ht_nsiblings(int cpu);
-
-int cfs_cpu_init(void);
-void cfs_cpu_fini(void);
-
-#else /* !CONFIG_SMP */
-struct cfs_cpt_table;
-#define cfs_cpt_tab ((struct cfs_cpt_table *)NULL)
-
-static inline cpumask_var_t *
-cfs_cpt_cpumask(struct cfs_cpt_table *cptab, int cpt)
-{
- return NULL;
-}
-
-static inline int
-cfs_cpt_table_print(struct cfs_cpt_table *cptab, char *buf, int len)
-{
- return 0;
-}
-static inline int
-cfs_cpt_number(struct cfs_cpt_table *cptab)
-{
- return 1;
-}
-
-static inline int
-cfs_cpt_weight(struct cfs_cpt_table *cptab, int cpt)
-{
- return 1;
-}
-
-static inline int
-cfs_cpt_online(struct cfs_cpt_table *cptab, int cpt)
-{
- return 1;
-}
-
-static inline nodemask_t *
-cfs_cpt_nodemask(struct cfs_cpt_table *cptab, int cpt)
-{
- return NULL;
-}
-
-static inline int
-cfs_cpt_set_cpu(struct cfs_cpt_table *cptab, int cpt, int cpu)
-{
- return 1;
-}
-
-static inline void
-cfs_cpt_unset_cpu(struct cfs_cpt_table *cptab, int cpt, int cpu)
-{
-}
-
-static inline int
-cfs_cpt_set_cpumask(struct cfs_cpt_table *cptab, int cpt, cpumask_t *mask)
-{
- return 1;
-}
-
-static inline void
-cfs_cpt_unset_cpumask(struct cfs_cpt_table *cptab, int cpt, cpumask_t *mask)
-{
-}
-
-static inline int
-cfs_cpt_set_node(struct cfs_cpt_table *cptab, int cpt, int node)
-{
- return 1;
-}
-
-static inline void
-cfs_cpt_unset_node(struct cfs_cpt_table *cptab, int cpt, int node)
-{
-}
-
-static inline int
-cfs_cpt_set_nodemask(struct cfs_cpt_table *cptab, int cpt, nodemask_t *mask)
-{
- return 1;
-}
-
-static inline void
-cfs_cpt_unset_nodemask(struct cfs_cpt_table *cptab, int cpt, nodemask_t *mask)
-{
-}
-
-static inline void
-cfs_cpt_clear(struct cfs_cpt_table *cptab, int cpt)
-{
-}
-
-static inline int
-cfs_cpt_spread_node(struct cfs_cpt_table *cptab, int cpt)
-{
- return 0;
-}
-
-static inline int
-cfs_cpu_ht_nsiblings(int cpu)
-{
- return 1;
-}
-
-static inline int
-cfs_cpt_current(struct cfs_cpt_table *cptab, int remap)
-{
- return 0;
-}
-
-static inline int
-cfs_cpt_of_cpu(struct cfs_cpt_table *cptab, int cpu)
-{
- return 0;
-}
-
-static inline int
-cfs_cpt_bind(struct cfs_cpt_table *cptab, int cpt)
-{
- return 0;
-}
-
-static inline int
-cfs_cpu_init(void)
-{
- return 0;
-}
-
-static inline void cfs_cpu_fini(void)
-{
-}
-
-#endif /* CONFIG_SMP */
-
-/**
- * destroy a CPU partition table
- */
-void cfs_cpt_table_free(struct cfs_cpt_table *cptab);
-/**
- * create a cfs_cpt_table with \a ncpt number of partitions
- */
-struct cfs_cpt_table *cfs_cpt_table_alloc(unsigned int ncpt);
-
-/*
- * allocate per-cpu-partition data, returned value is an array of pointers,
- * variable can be indexed by CPU ID.
- * cptab != NULL: size of array is number of CPU partitions
- * cptab == NULL: size of array is number of HW cores
- */
-void *cfs_percpt_alloc(struct cfs_cpt_table *cptab, unsigned int size);
-/*
- * destroy per-cpu-partition variable
- */
-void cfs_percpt_free(void *vars);
-int cfs_percpt_number(void *vars);
-
-#define cfs_percpt_for_each(var, i, vars) \
- for (i = 0; i < cfs_percpt_number(vars) && \
- ((var) = (vars)[i]) != NULL; i++)
-
-/*
- * percpu partition lock
- *
- * There are some use-cases like this in Lustre:
- * . each CPU partition has it's own private data which is frequently changed,
- * and mostly by the local CPU partition.
- * . all CPU partitions share some global data, these data are rarely changed.
- *
- * LNet is typical example.
- * CPU partition lock is designed for this kind of use-cases:
- * . each CPU partition has it's own private lock
- * . change on private data just needs to take the private lock
- * . read on shared data just needs to take _any_ of private locks
- * . change on shared data needs to take _all_ private locks,
- * which is slow and should be really rare.
- */
-enum {
- CFS_PERCPT_LOCK_EX = -1, /* negative */
-};
-
-struct cfs_percpt_lock {
- /* cpu-partition-table for this lock */
- struct cfs_cpt_table *pcl_cptab;
- /* exclusively locked */
- unsigned int pcl_locked;
- /* private lock table */
- spinlock_t **pcl_locks;
-};
-
-/* return number of private locks */
-#define cfs_percpt_lock_num(pcl) cfs_cpt_number(pcl->pcl_cptab)
-
-/*
- * create a cpu-partition lock based on CPU partition table \a cptab,
- * each private lock has extra \a psize bytes padding data
- */
-struct cfs_percpt_lock *cfs_percpt_lock_create(struct cfs_cpt_table *cptab,
- struct lock_class_key *keys);
-/* destroy a cpu-partition lock */
-void cfs_percpt_lock_free(struct cfs_percpt_lock *pcl);
-
-/* lock private lock \a index of \a pcl */
-void cfs_percpt_lock(struct cfs_percpt_lock *pcl, int index);
-
-/* unlock private lock \a index of \a pcl */
-void cfs_percpt_unlock(struct cfs_percpt_lock *pcl, int index);
-
-#define CFS_PERCPT_LOCK_KEYS 256
-
-/* NB: don't allocate keys dynamically, lockdep needs them to be in ".data" */
-#define cfs_percpt_lock_alloc(cptab) \
-({ \
- static struct lock_class_key ___keys[CFS_PERCPT_LOCK_KEYS]; \
- struct cfs_percpt_lock *___lk; \
- \
- if (cfs_cpt_number(cptab) > CFS_PERCPT_LOCK_KEYS) \
- ___lk = cfs_percpt_lock_create(cptab, NULL); \
- else \
- ___lk = cfs_percpt_lock_create(cptab, ___keys); \
- ___lk; \
-})
-
-/**
- * iterate over all CPU partitions in \a cptab
- */
-#define cfs_cpt_for_each(i, cptab) \
- for (i = 0; i < cfs_cpt_number(cptab); i++)
-
-#endif /* __LIBCFS_CPU_H__ */
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_crypto.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_crypto.h
deleted file mode 100644
index 176fae7319e3..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_crypto.h
+++ /dev/null
@@ -1,208 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see http://www.gnu.org/licenses
- *
- * Please visit http://www.xyratex.com/contact if you need additional
- * information or have any questions.
- *
- * GPL HEADER END
- */
-
-/*
- * Copyright 2012 Xyratex Technology Limited
- */
-
-#ifndef _LIBCFS_CRYPTO_H
-#define _LIBCFS_CRYPTO_H
-
-#include <linux/string.h>
-struct page;
-
-struct cfs_crypto_hash_type {
- char *cht_name; /*< hash algorithm name, equal to
- * format name for crypto api
- */
- unsigned int cht_key; /*< init key by default (valid for
- * 4 bytes context like crc32, adler
- */
- unsigned int cht_size; /**< hash digest size */
-};
-
-enum cfs_crypto_hash_alg {
- CFS_HASH_ALG_NULL = 0,
- CFS_HASH_ALG_ADLER32,
- CFS_HASH_ALG_CRC32,
- CFS_HASH_ALG_MD5,
- CFS_HASH_ALG_SHA1,
- CFS_HASH_ALG_SHA256,
- CFS_HASH_ALG_SHA384,
- CFS_HASH_ALG_SHA512,
- CFS_HASH_ALG_CRC32C,
- CFS_HASH_ALG_MAX,
- CFS_HASH_ALG_UNKNOWN = 0xff
-};
-
-static struct cfs_crypto_hash_type hash_types[] = {
- [CFS_HASH_ALG_NULL] = {
- .cht_name = "null",
- .cht_key = 0,
- .cht_size = 0
- },
- [CFS_HASH_ALG_ADLER32] = {
- .cht_name = "adler32",
- .cht_key = 1,
- .cht_size = 4
- },
- [CFS_HASH_ALG_CRC32] = {
- .cht_name = "crc32",
- .cht_key = ~0,
- .cht_size = 4
- },
- [CFS_HASH_ALG_CRC32C] = {
- .cht_name = "crc32c",
- .cht_key = ~0,
- .cht_size = 4
- },
- [CFS_HASH_ALG_MD5] = {
- .cht_name = "md5",
- .cht_key = 0,
- .cht_size = 16
- },
- [CFS_HASH_ALG_SHA1] = {
- .cht_name = "sha1",
- .cht_key = 0,
- .cht_size = 20
- },
- [CFS_HASH_ALG_SHA256] = {
- .cht_name = "sha256",
- .cht_key = 0,
- .cht_size = 32
- },
- [CFS_HASH_ALG_SHA384] = {
- .cht_name = "sha384",
- .cht_key = 0,
- .cht_size = 48
- },
- [CFS_HASH_ALG_SHA512] = {
- .cht_name = "sha512",
- .cht_key = 0,
- .cht_size = 64
- },
- [CFS_HASH_ALG_MAX] = {
- .cht_name = NULL,
- .cht_key = 0,
- .cht_size = 64
- },
-};
-
-/* Maximum size of hash_types[].cht_size */
-#define CFS_CRYPTO_HASH_DIGESTSIZE_MAX 64
-
-/**
- * Return hash algorithm information for the specified algorithm identifier
- *
- * Hash information includes algorithm name, initial seed, hash size.
- *
- * \retval cfs_crypto_hash_type for valid ID (CFS_HASH_ALG_*)
- * \retval NULL for unknown algorithm identifier
- */
-static inline const struct cfs_crypto_hash_type *
-cfs_crypto_hash_type(enum cfs_crypto_hash_alg hash_alg)
-{
- struct cfs_crypto_hash_type *ht;
-
- if (hash_alg < CFS_HASH_ALG_MAX) {
- ht = &hash_types[hash_alg];
- if (ht->cht_name)
- return ht;
- }
- return NULL;
-}
-
-/**
- * Return hash name for hash algorithm identifier
- *
- * \param[in] hash_alg hash alrgorithm id (CFS_HASH_ALG_*)
- *
- * \retval string name of known hash algorithm
- * \retval "unknown" if hash algorithm is unknown
- */
-static inline const char *
-cfs_crypto_hash_name(enum cfs_crypto_hash_alg hash_alg)
-{
- const struct cfs_crypto_hash_type *ht;
-
- ht = cfs_crypto_hash_type(hash_alg);
- if (ht)
- return ht->cht_name;
- return "unknown";
-}
-
-/**
- * Return digest size for hash algorithm type
- *
- * \param[in] hash_alg hash alrgorithm id (CFS_HASH_ALG_*)
- *
- * \retval hash algorithm digest size in bytes
- * \retval 0 if hash algorithm type is unknown
- */
-static inline int cfs_crypto_hash_digestsize(enum cfs_crypto_hash_alg hash_alg)
-{
- const struct cfs_crypto_hash_type *ht;
-
- ht = cfs_crypto_hash_type(hash_alg);
- if (ht)
- return ht->cht_size;
- return 0;
-}
-
-/**
- * Find hash algorithm ID for the specified algorithm name
- *
- * \retval hash algorithm ID for valid ID (CFS_HASH_ALG_*)
- * \retval CFS_HASH_ALG_UNKNOWN for unknown algorithm name
- */
-static inline unsigned char cfs_crypto_hash_alg(const char *algname)
-{
- enum cfs_crypto_hash_alg hash_alg;
-
- for (hash_alg = 0; hash_alg < CFS_HASH_ALG_MAX; hash_alg++)
- if (!strcmp(hash_types[hash_alg].cht_name, algname))
- return hash_alg;
-
- return CFS_HASH_ALG_UNKNOWN;
-}
-
-int cfs_crypto_hash_digest(enum cfs_crypto_hash_alg hash_alg,
- const void *buf, unsigned int buf_len,
- unsigned char *key, unsigned int key_len,
- unsigned char *hash, unsigned int *hash_len);
-
-struct ahash_request *
-cfs_crypto_hash_init(enum cfs_crypto_hash_alg hash_alg,
- unsigned char *key, unsigned int key_len);
-int cfs_crypto_hash_update_page(struct ahash_request *desc,
- struct page *page, unsigned int offset,
- unsigned int len);
-int cfs_crypto_hash_update(struct ahash_request *desc, const void *buf,
- unsigned int buf_len);
-int cfs_crypto_hash_final(struct ahash_request *desc,
- unsigned char *hash, unsigned int *hash_len);
-int cfs_crypto_register(void);
-void cfs_crypto_unregister(void);
-int cfs_crypto_hash_speed(enum cfs_crypto_hash_alg hash_alg);
-#endif
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_debug.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_debug.h
deleted file mode 100644
index 17534a76362a..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_debug.h
+++ /dev/null
@@ -1,207 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_debug.h
- *
- * Debug messages and assertions
- *
- */
-
-#ifndef __LIBCFS_DEBUG_H__
-#define __LIBCFS_DEBUG_H__
-
-#include <linux/limits.h>
-#include <uapi/linux/lnet/libcfs_debug.h>
-
-/*
- * Debugging
- */
-extern unsigned int libcfs_subsystem_debug;
-extern unsigned int libcfs_stack;
-extern unsigned int libcfs_debug;
-extern unsigned int libcfs_printk;
-extern unsigned int libcfs_console_ratelimit;
-extern unsigned int libcfs_console_max_delay;
-extern unsigned int libcfs_console_min_delay;
-extern unsigned int libcfs_console_backoff;
-extern unsigned int libcfs_debug_binary;
-extern char libcfs_debug_file_path_arr[PATH_MAX];
-
-int libcfs_debug_mask2str(char *str, int size, int mask, int is_subsys);
-int libcfs_debug_str2mask(int *mask, const char *str, int is_subsys);
-
-/* Has there been an LBUG? */
-extern unsigned int libcfs_catastrophe;
-extern unsigned int libcfs_panic_on_lbug;
-
-/* Enable debug-checks on stack size - except on x86_64 */
-#if !defined(__x86_64__)
-# ifdef __ia64__
-# define CDEBUG_STACK() (THREAD_SIZE - \
- ((unsigned long)__builtin_dwarf_cfa() & \
- (THREAD_SIZE - 1)))
-# else
-# define CDEBUG_STACK() (THREAD_SIZE - \
- ((unsigned long)__builtin_frame_address(0) & \
- (THREAD_SIZE - 1)))
-# endif /* __ia64__ */
-
-#define __CHECK_STACK(msgdata, mask, cdls) \
-do { \
- if (unlikely(CDEBUG_STACK() > libcfs_stack)) { \
- LIBCFS_DEBUG_MSG_DATA_INIT(msgdata, D_WARNING, NULL); \
- libcfs_stack = CDEBUG_STACK(); \
- libcfs_debug_msg(msgdata, \
- "maximum lustre stack %lu\n", \
- CDEBUG_STACK()); \
- (msgdata)->msg_mask = mask; \
- (msgdata)->msg_cdls = cdls; \
- dump_stack(); \
- /*panic("LBUG");*/ \
- } \
-} while (0)
-#define CFS_CHECK_STACK(msgdata, mask, cdls) __CHECK_STACK(msgdata, mask, cdls)
-#else /* __x86_64__ */
-#define CFS_CHECK_STACK(msgdata, mask, cdls) do {} while (0)
-#define CDEBUG_STACK() (0L)
-#endif /* __x86_64__ */
-
-#ifndef DEBUG_SUBSYSTEM
-# define DEBUG_SUBSYSTEM S_UNDEFINED
-#endif
-
-#define CDEBUG_DEFAULT_MAX_DELAY (600 * HZ) /* jiffies */
-#define CDEBUG_DEFAULT_MIN_DELAY ((HZ + 1) / 2) /* jiffies */
-#define CDEBUG_DEFAULT_BACKOFF 2
-struct cfs_debug_limit_state {
- unsigned long cdls_next;
- unsigned int cdls_delay;
- int cdls_count;
-};
-
-struct libcfs_debug_msg_data {
- const char *msg_file;
- const char *msg_fn;
- int msg_subsys;
- int msg_line;
- int msg_mask;
- struct cfs_debug_limit_state *msg_cdls;
-};
-
-#define LIBCFS_DEBUG_MSG_DATA_INIT(data, mask, cdls) \
-do { \
- (data)->msg_subsys = DEBUG_SUBSYSTEM; \
- (data)->msg_file = __FILE__; \
- (data)->msg_fn = __func__; \
- (data)->msg_line = __LINE__; \
- (data)->msg_cdls = (cdls); \
- (data)->msg_mask = (mask); \
-} while (0)
-
-#define LIBCFS_DEBUG_MSG_DATA_DECL(dataname, mask, cdls) \
- static struct libcfs_debug_msg_data dataname = { \
- .msg_subsys = DEBUG_SUBSYSTEM, \
- .msg_file = __FILE__, \
- .msg_fn = __func__, \
- .msg_line = __LINE__, \
- .msg_cdls = (cdls) }; \
- dataname.msg_mask = (mask)
-
-/**
- * Filters out logging messages based on mask and subsystem.
- */
-static inline int cfs_cdebug_show(unsigned int mask, unsigned int subsystem)
-{
- return mask & D_CANTMASK ||
- ((libcfs_debug & mask) && (libcfs_subsystem_debug & subsystem));
-}
-
-#define __CDEBUG(cdls, mask, format, ...) \
-do { \
- static struct libcfs_debug_msg_data msgdata; \
- \
- CFS_CHECK_STACK(&msgdata, mask, cdls); \
- \
- if (cfs_cdebug_show(mask, DEBUG_SUBSYSTEM)) { \
- LIBCFS_DEBUG_MSG_DATA_INIT(&msgdata, mask, cdls); \
- libcfs_debug_msg(&msgdata, format, ## __VA_ARGS__); \
- } \
-} while (0)
-
-#define CDEBUG(mask, format, ...) __CDEBUG(NULL, mask, format, ## __VA_ARGS__)
-
-#define CDEBUG_LIMIT(mask, format, ...) \
-do { \
- static struct cfs_debug_limit_state cdls; \
- \
- __CDEBUG(&cdls, mask, format, ## __VA_ARGS__); \
-} while (0)
-
-/*
- * Lustre Error Checksum: calculates checksum
- * of Hex number by XORing the nybbles.
- */
-#define LERRCHKSUM(hexnum) (((hexnum) & 0xf) ^ ((hexnum) >> 4 & 0xf) ^ \
- ((hexnum) >> 8 & 0xf))
-
-#define CWARN(format, ...) CDEBUG_LIMIT(D_WARNING, format, ## __VA_ARGS__)
-#define CERROR(format, ...) CDEBUG_LIMIT(D_ERROR, format, ## __VA_ARGS__)
-#define CNETERR(format, a...) CDEBUG_LIMIT(D_NETERROR, format, ## a)
-#define CEMERG(format, ...) CDEBUG_LIMIT(D_EMERG, format, ## __VA_ARGS__)
-
-#define LCONSOLE(mask, format, ...) CDEBUG(D_CONSOLE | (mask), format, ## __VA_ARGS__)
-#define LCONSOLE_INFO(format, ...) CDEBUG_LIMIT(D_CONSOLE, format, ## __VA_ARGS__)
-#define LCONSOLE_WARN(format, ...) CDEBUG_LIMIT(D_CONSOLE | D_WARNING, format, ## __VA_ARGS__)
-#define LCONSOLE_ERROR_MSG(errnum, format, ...) CDEBUG_LIMIT(D_CONSOLE | D_ERROR, \
- "%x-%x: " format, errnum, LERRCHKSUM(errnum), ## __VA_ARGS__)
-#define LCONSOLE_ERROR(format, ...) LCONSOLE_ERROR_MSG(0x00, format, ## __VA_ARGS__)
-
-#define LCONSOLE_EMERG(format, ...) CDEBUG(D_CONSOLE | D_EMERG, format, ## __VA_ARGS__)
-
-int libcfs_debug_msg(struct libcfs_debug_msg_data *msgdata,
- const char *format1, ...)
- __printf(2, 3);
-
-int libcfs_debug_vmsg2(struct libcfs_debug_msg_data *msgdata,
- const char *format1,
- va_list args, const char *format2, ...)
- __printf(4, 5);
-
-/* other external symbols that tracefile provides: */
-int cfs_trace_copyin_string(char *knl_buffer, int knl_buffer_nob,
- const char __user *usr_buffer, int usr_buffer_nob);
-int cfs_trace_copyout_string(char __user *usr_buffer, int usr_buffer_nob,
- const char *knl_buffer, char *append);
-
-#define LIBCFS_DEBUG_FILE_PATH_DEFAULT "/tmp/lustre-log"
-
-#endif /* __LIBCFS_DEBUG_H__ */
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h
deleted file mode 100644
index 8074e390b4d1..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_fail.h
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see http://www.gnu.org/licenses
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2012, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Oracle Corporation, Inc.
- */
-
-#ifndef _LIBCFS_FAIL_H
-#define _LIBCFS_FAIL_H
-
-#include <linux/sched.h>
-#include <linux/wait.h>
-
-extern unsigned long cfs_fail_loc;
-extern unsigned int cfs_fail_val;
-extern int cfs_fail_err;
-
-extern wait_queue_head_t cfs_race_waitq;
-extern int cfs_race_state;
-
-int __cfs_fail_check_set(u32 id, u32 value, int set);
-int __cfs_fail_timeout_set(u32 id, u32 value, int ms, int set);
-
-enum {
- CFS_FAIL_LOC_NOSET = 0,
- CFS_FAIL_LOC_ORSET = 1,
- CFS_FAIL_LOC_RESET = 2,
- CFS_FAIL_LOC_VALUE = 3
-};
-
-/* Failure injection control */
-#define CFS_FAIL_MASK_SYS 0x0000FF00
-#define CFS_FAIL_MASK_LOC (0x000000FF | CFS_FAIL_MASK_SYS)
-
-#define CFS_FAILED_BIT 30
-/* CFS_FAILED is 0x40000000 */
-#define CFS_FAILED BIT(CFS_FAILED_BIT)
-
-#define CFS_FAIL_ONCE_BIT 31
-/* CFS_FAIL_ONCE is 0x80000000 */
-#define CFS_FAIL_ONCE BIT(CFS_FAIL_ONCE_BIT)
-
-/* The following flags aren't made to be combined */
-#define CFS_FAIL_SKIP 0x20000000 /* skip N times then fail */
-#define CFS_FAIL_SOME 0x10000000 /* only fail N times */
-#define CFS_FAIL_RAND 0x08000000 /* fail 1/N of the times */
-#define CFS_FAIL_USR1 0x04000000 /* user flag */
-
-#define CFS_FAULT 0x02000000 /* match any CFS_FAULT_CHECK */
-
-static inline bool CFS_FAIL_PRECHECK(u32 id)
-{
- return cfs_fail_loc &&
- ((cfs_fail_loc & CFS_FAIL_MASK_LOC) == (id & CFS_FAIL_MASK_LOC) ||
- (cfs_fail_loc & id & CFS_FAULT));
-}
-
-static inline int cfs_fail_check_set(u32 id, u32 value,
- int set, int quiet)
-{
- int ret = 0;
-
- if (unlikely(CFS_FAIL_PRECHECK(id))) {
- ret = __cfs_fail_check_set(id, value, set);
- if (ret) {
- if (quiet) {
- CDEBUG(D_INFO, "*** cfs_fail_loc=%x, val=%u***\n",
- id, value);
- } else {
- LCONSOLE_INFO("*** cfs_fail_loc=%x, val=%u***\n",
- id, value);
- }
- }
- }
-
- return ret;
-}
-
-/* If id hit cfs_fail_loc, return 1, otherwise return 0 */
-#define CFS_FAIL_CHECK(id) \
- cfs_fail_check_set(id, 0, CFS_FAIL_LOC_NOSET, 0)
-#define CFS_FAIL_CHECK_QUIET(id) \
- cfs_fail_check_set(id, 0, CFS_FAIL_LOC_NOSET, 1)
-
-/*
- * If id hit cfs_fail_loc and cfs_fail_val == (-1 or value) return 1,
- * otherwise return 0
- */
-#define CFS_FAIL_CHECK_VALUE(id, value) \
- cfs_fail_check_set(id, value, CFS_FAIL_LOC_VALUE, 0)
-#define CFS_FAIL_CHECK_VALUE_QUIET(id, value) \
- cfs_fail_check_set(id, value, CFS_FAIL_LOC_VALUE, 1)
-
-/*
- * If id hit cfs_fail_loc, cfs_fail_loc |= value and return 1,
- * otherwise return 0
- */
-#define CFS_FAIL_CHECK_ORSET(id, value) \
- cfs_fail_check_set(id, value, CFS_FAIL_LOC_ORSET, 0)
-#define CFS_FAIL_CHECK_ORSET_QUIET(id, value) \
- cfs_fail_check_set(id, value, CFS_FAIL_LOC_ORSET, 1)
-
-/*
- * If id hit cfs_fail_loc, cfs_fail_loc = value and return 1,
- * otherwise return 0
- */
-#define CFS_FAIL_CHECK_RESET(id, value) \
- cfs_fail_check_set(id, value, CFS_FAIL_LOC_RESET, 0)
-#define CFS_FAIL_CHECK_RESET_QUIET(id, value) \
- cfs_fail_check_set(id, value, CFS_FAIL_LOC_RESET, 1)
-
-static inline int cfs_fail_timeout_set(u32 id, u32 value, int ms, int set)
-{
- if (unlikely(CFS_FAIL_PRECHECK(id)))
- return __cfs_fail_timeout_set(id, value, ms, set);
- return 0;
-}
-
-/* If id hit cfs_fail_loc, sleep for seconds or milliseconds */
-#define CFS_FAIL_TIMEOUT(id, secs) \
- cfs_fail_timeout_set(id, 0, (secs) * 1000, CFS_FAIL_LOC_NOSET)
-
-#define CFS_FAIL_TIMEOUT_MS(id, ms) \
- cfs_fail_timeout_set(id, 0, ms, CFS_FAIL_LOC_NOSET)
-
-/*
- * If id hit cfs_fail_loc, cfs_fail_loc |= value and
- * sleep seconds or milliseconds
- */
-#define CFS_FAIL_TIMEOUT_ORSET(id, value, secs) \
- cfs_fail_timeout_set(id, value, (secs) * 1000, CFS_FAIL_LOC_ORSET)
-
-#define CFS_FAIL_TIMEOUT_RESET(id, value, secs) \
- cfs_fail_timeout_set(id, value, (secs) * 1000, CFS_FAIL_LOC_RESET)
-
-#define CFS_FAIL_TIMEOUT_MS_ORSET(id, value, ms) \
- cfs_fail_timeout_set(id, value, ms, CFS_FAIL_LOC_ORSET)
-
-#define CFS_FAULT_CHECK(id) \
- CFS_FAIL_CHECK(CFS_FAULT | (id))
-
-/*
- * The idea here is to synchronise two threads to force a race. The
- * first thread that calls this with a matching fail_loc is put to
- * sleep. The next thread that calls with the same fail_loc wakes up
- * the first and continues.
- */
-static inline void cfs_race(u32 id)
-{
- if (CFS_FAIL_PRECHECK(id)) {
- if (unlikely(__cfs_fail_check_set(id, 0, CFS_FAIL_LOC_NOSET))) {
- int rc;
-
- cfs_race_state = 0;
- CERROR("cfs_race id %x sleeping\n", id);
- rc = wait_event_interruptible(cfs_race_waitq,
- !!cfs_race_state);
- CERROR("cfs_fail_race id %x awake, rc=%d\n", id, rc);
- } else {
- CERROR("cfs_fail_race id %x waking\n", id);
- cfs_race_state = 1;
- wake_up(&cfs_race_waitq);
- }
- }
-}
-
-#define CFS_RACE(id) cfs_race(id)
-
-#endif /* _LIBCFS_FAIL_H */
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_hash.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_hash.h
deleted file mode 100644
index be315958a4b3..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_hash.h
+++ /dev/null
@@ -1,869 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, 2015 Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_hash.h
- *
- * Hashing routines
- *
- */
-
-#ifndef __LIBCFS_HASH_H__
-#define __LIBCFS_HASH_H__
-
-#include <linux/hash.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
-#include <linux/libcfs/libcfs.h>
-
-/*
- * Knuth recommends primes in approximately golden ratio to the maximum
- * integer representable by a machine word for multiplicative hashing.
- * Chuck Lever verified the effectiveness of this technique:
- * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
- *
- * These primes are chosen to be bit-sparse, that is operations on
- * them can use shifts and additions instead of multiplications for
- * machines where multiplications are slow.
- */
-/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
-#define CFS_GOLDEN_RATIO_PRIME_32 0x9e370001UL
-/* 2^63 + 2^61 - 2^57 + 2^54 - 2^51 - 2^18 + 1 */
-#define CFS_GOLDEN_RATIO_PRIME_64 0x9e37fffffffc0001ULL
-
-/** disable debug */
-#define CFS_HASH_DEBUG_NONE 0
-/*
- * record hash depth and output to console when it's too deep,
- * computing overhead is low but consume more memory
- */
-#define CFS_HASH_DEBUG_1 1
-/** expensive, check key validation */
-#define CFS_HASH_DEBUG_2 2
-
-#define CFS_HASH_DEBUG_LEVEL CFS_HASH_DEBUG_NONE
-
-struct cfs_hash_ops;
-struct cfs_hash_lock_ops;
-struct cfs_hash_hlist_ops;
-
-union cfs_hash_lock {
- rwlock_t rw; /**< rwlock */
- spinlock_t spin; /**< spinlock */
-};
-
-/**
- * cfs_hash_bucket is a container of:
- * - lock, counter ...
- * - array of hash-head starting from hsb_head[0], hash-head can be one of
- * . struct cfs_hash_head
- * . struct cfs_hash_head_dep
- * . struct cfs_hash_dhead
- * . struct cfs_hash_dhead_dep
- * which depends on requirement of user
- * - some extra bytes (caller can require it while creating hash)
- */
-struct cfs_hash_bucket {
- union cfs_hash_lock hsb_lock; /**< bucket lock */
- u32 hsb_count; /**< current entries */
- u32 hsb_version; /**< change version */
- unsigned int hsb_index; /**< index of bucket */
- int hsb_depmax; /**< max depth on bucket */
- long hsb_head[0]; /**< hash-head array */
-};
-
-/**
- * cfs_hash bucket descriptor, it's normally in stack of caller
- */
-struct cfs_hash_bd {
- /* address of bucket */
- struct cfs_hash_bucket *bd_bucket;
- /* offset in bucket */
- unsigned int bd_offset;
-};
-
-#define CFS_HASH_NAME_LEN 16 /**< default name length */
-#define CFS_HASH_BIGNAME_LEN 64 /**< bigname for param tree */
-
-#define CFS_HASH_BKT_BITS 3 /**< default bits of bucket */
-#define CFS_HASH_BITS_MAX 30 /**< max bits of bucket */
-#define CFS_HASH_BITS_MIN CFS_HASH_BKT_BITS
-
-/**
- * common hash attributes.
- */
-enum cfs_hash_tag {
- /**
- * don't need any lock, caller will protect operations with it's
- * own lock. With this flag:
- * . CFS_HASH_NO_BKTLOCK, CFS_HASH_RW_BKTLOCK, CFS_HASH_SPIN_BKTLOCK
- * will be ignored.
- * . Some functions will be disabled with this flag, i.e:
- * cfs_hash_for_each_empty, cfs_hash_rehash
- */
- CFS_HASH_NO_LOCK = BIT(0),
- /** no bucket lock, use one spinlock to protect the whole hash */
- CFS_HASH_NO_BKTLOCK = BIT(1),
- /** rwlock to protect bucket */
- CFS_HASH_RW_BKTLOCK = BIT(2),
- /** spinlock to protect bucket */
- CFS_HASH_SPIN_BKTLOCK = BIT(3),
- /** always add new item to tail */
- CFS_HASH_ADD_TAIL = BIT(4),
- /** hash-table doesn't have refcount on item */
- CFS_HASH_NO_ITEMREF = BIT(5),
- /** big name for param-tree */
- CFS_HASH_BIGNAME = BIT(6),
- /** track global count */
- CFS_HASH_COUNTER = BIT(7),
- /** rehash item by new key */
- CFS_HASH_REHASH_KEY = BIT(8),
- /** Enable dynamic hash resizing */
- CFS_HASH_REHASH = BIT(9),
- /** can shrink hash-size */
- CFS_HASH_SHRINK = BIT(10),
- /** assert hash is empty on exit */
- CFS_HASH_ASSERT_EMPTY = BIT(11),
- /** record hlist depth */
- CFS_HASH_DEPTH = BIT(12),
- /**
- * rehash is always scheduled in a different thread, so current
- * change on hash table is non-blocking
- */
- CFS_HASH_NBLK_CHANGE = BIT(13),
- /**
- * NB, we typed hs_flags as u16, please change it
- * if you need to extend >=16 flags
- */
-};
-
-/** most used attributes */
-#define CFS_HASH_DEFAULT (CFS_HASH_RW_BKTLOCK | \
- CFS_HASH_COUNTER | CFS_HASH_REHASH)
-
-/**
- * cfs_hash is a hash-table implementation for general purpose, it can support:
- * . two refcount modes
- * hash-table with & without refcount
- * . four lock modes
- * nolock, one-spinlock, rw-bucket-lock, spin-bucket-lock
- * . general operations
- * lookup, add(add_tail or add_head), delete
- * . rehash
- * grows or shrink
- * . iteration
- * locked iteration and unlocked iteration
- * . bigname
- * support long name hash
- * . debug
- * trace max searching depth
- *
- * Rehash:
- * When the htable grows or shrinks, a separate task (cfs_hash_rehash_worker)
- * is spawned to handle the rehash in the background, it's possible that other
- * processes can concurrently perform additions, deletions, and lookups
- * without being blocked on rehash completion, because rehash will release
- * the global wrlock for each bucket.
- *
- * rehash and iteration can't run at the same time because it's too tricky
- * to keep both of them safe and correct.
- * As they are relatively rare operations, so:
- * . if iteration is in progress while we try to launch rehash, then
- * it just giveup, iterator will launch rehash at the end.
- * . if rehash is in progress while we try to iterate the hash table,
- * then we just wait (shouldn't be very long time), anyway, nobody
- * should expect iteration of whole hash-table to be non-blocking.
- *
- * During rehashing, a (key,object) pair may be in one of two buckets,
- * depending on whether the worker task has yet to transfer the object
- * to its new location in the table. Lookups and deletions need to search both
- * locations; additions must take care to only insert into the new bucket.
- */
-
-struct cfs_hash {
- /**
- * serialize with rehash, or serialize all operations if
- * the hash-table has CFS_HASH_NO_BKTLOCK
- */
- union cfs_hash_lock hs_lock;
- /** hash operations */
- struct cfs_hash_ops *hs_ops;
- /** hash lock operations */
- struct cfs_hash_lock_ops *hs_lops;
- /** hash list operations */
- struct cfs_hash_hlist_ops *hs_hops;
- /** hash buckets-table */
- struct cfs_hash_bucket **hs_buckets;
- /** total number of items on this hash-table */
- atomic_t hs_count;
- /** hash flags, see cfs_hash_tag for detail */
- u16 hs_flags;
- /** # of extra-bytes for bucket, for user saving extended attributes */
- u16 hs_extra_bytes;
- /** wants to iterate */
- u8 hs_iterating;
- /** hash-table is dying */
- u8 hs_exiting;
- /** current hash bits */
- u8 hs_cur_bits;
- /** min hash bits */
- u8 hs_min_bits;
- /** max hash bits */
- u8 hs_max_bits;
- /** bits for rehash */
- u8 hs_rehash_bits;
- /** bits for each bucket */
- u8 hs_bkt_bits;
- /** resize min threshold */
- u16 hs_min_theta;
- /** resize max threshold */
- u16 hs_max_theta;
- /** resize count */
- u32 hs_rehash_count;
- /** # of iterators (caller of cfs_hash_for_each_*) */
- u32 hs_iterators;
- /** rehash workitem */
- struct work_struct hs_rehash_work;
- /** refcount on this hash table */
- atomic_t hs_refcount;
- /** rehash buckets-table */
- struct cfs_hash_bucket **hs_rehash_buckets;
-#if CFS_HASH_DEBUG_LEVEL >= CFS_HASH_DEBUG_1
- /** serialize debug members */
- spinlock_t hs_dep_lock;
- /** max depth */
- unsigned int hs_dep_max;
- /** id of the deepest bucket */
- unsigned int hs_dep_bkt;
- /** offset in the deepest bucket */
- unsigned int hs_dep_off;
- /** bits when we found the max depth */
- unsigned int hs_dep_bits;
- /** workitem to output max depth */
- struct work_struct hs_dep_work;
-#endif
- /** name of htable */
- char hs_name[0];
-};
-
-struct cfs_hash_lock_ops {
- /** lock the hash table */
- void (*hs_lock)(union cfs_hash_lock *lock, int exclusive);
- /** unlock the hash table */
- void (*hs_unlock)(union cfs_hash_lock *lock, int exclusive);
- /** lock the hash bucket */
- void (*hs_bkt_lock)(union cfs_hash_lock *lock, int exclusive);
- /** unlock the hash bucket */
- void (*hs_bkt_unlock)(union cfs_hash_lock *lock, int exclusive);
-};
-
-struct cfs_hash_hlist_ops {
- /** return hlist_head of hash-head of @bd */
- struct hlist_head *(*hop_hhead)(struct cfs_hash *hs,
- struct cfs_hash_bd *bd);
- /** return hash-head size */
- int (*hop_hhead_size)(struct cfs_hash *hs);
- /** add @hnode to hash-head of @bd */
- int (*hop_hnode_add)(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- struct hlist_node *hnode);
- /** remove @hnode from hash-head of @bd */
- int (*hop_hnode_del)(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- struct hlist_node *hnode);
-};
-
-struct cfs_hash_ops {
- /** return hashed value from @key */
- unsigned int (*hs_hash)(struct cfs_hash *hs, const void *key,
- unsigned int mask);
- /** return key address of @hnode */
- void * (*hs_key)(struct hlist_node *hnode);
- /** copy key from @hnode to @key */
- void (*hs_keycpy)(struct hlist_node *hnode, void *key);
- /**
- * compare @key with key of @hnode
- * returns 1 on a match
- */
- int (*hs_keycmp)(const void *key, struct hlist_node *hnode);
- /** return object address of @hnode, i.e: container_of(...hnode) */
- void * (*hs_object)(struct hlist_node *hnode);
- /** get refcount of item, always called with holding bucket-lock */
- void (*hs_get)(struct cfs_hash *hs, struct hlist_node *hnode);
- /** release refcount of item */
- void (*hs_put)(struct cfs_hash *hs, struct hlist_node *hnode);
- /** release refcount of item, always called with holding bucket-lock */
- void (*hs_put_locked)(struct cfs_hash *hs,
- struct hlist_node *hnode);
- /** it's called before removing of @hnode */
- void (*hs_exit)(struct cfs_hash *hs, struct hlist_node *hnode);
-};
-
-/** total number of buckets in @hs */
-#define CFS_HASH_NBKT(hs) \
- BIT((hs)->hs_cur_bits - (hs)->hs_bkt_bits)
-
-/** total number of buckets in @hs while rehashing */
-#define CFS_HASH_RH_NBKT(hs) \
- BIT((hs)->hs_rehash_bits - (hs)->hs_bkt_bits)
-
-/** number of hlist for in bucket */
-#define CFS_HASH_BKT_NHLIST(hs) BIT((hs)->hs_bkt_bits)
-
-/** total number of hlist in @hs */
-#define CFS_HASH_NHLIST(hs) BIT((hs)->hs_cur_bits)
-
-/** total number of hlist in @hs while rehashing */
-#define CFS_HASH_RH_NHLIST(hs) BIT((hs)->hs_rehash_bits)
-
-static inline int
-cfs_hash_with_no_lock(struct cfs_hash *hs)
-{
- /* caller will serialize all operations for this hash-table */
- return hs->hs_flags & CFS_HASH_NO_LOCK;
-}
-
-static inline int
-cfs_hash_with_no_bktlock(struct cfs_hash *hs)
-{
- /* no bucket lock, one single lock to protect the hash-table */
- return hs->hs_flags & CFS_HASH_NO_BKTLOCK;
-}
-
-static inline int
-cfs_hash_with_rw_bktlock(struct cfs_hash *hs)
-{
- /* rwlock to protect hash bucket */
- return hs->hs_flags & CFS_HASH_RW_BKTLOCK;
-}
-
-static inline int
-cfs_hash_with_spin_bktlock(struct cfs_hash *hs)
-{
- /* spinlock to protect hash bucket */
- return hs->hs_flags & CFS_HASH_SPIN_BKTLOCK;
-}
-
-static inline int
-cfs_hash_with_add_tail(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_ADD_TAIL;
-}
-
-static inline int
-cfs_hash_with_no_itemref(struct cfs_hash *hs)
-{
- /*
- * hash-table doesn't keep refcount on item,
- * item can't be removed from hash unless it's
- * ZERO refcount
- */
- return hs->hs_flags & CFS_HASH_NO_ITEMREF;
-}
-
-static inline int
-cfs_hash_with_bigname(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_BIGNAME;
-}
-
-static inline int
-cfs_hash_with_counter(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_COUNTER;
-}
-
-static inline int
-cfs_hash_with_rehash(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_REHASH;
-}
-
-static inline int
-cfs_hash_with_rehash_key(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_REHASH_KEY;
-}
-
-static inline int
-cfs_hash_with_shrink(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_SHRINK;
-}
-
-static inline int
-cfs_hash_with_assert_empty(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_ASSERT_EMPTY;
-}
-
-static inline int
-cfs_hash_with_depth(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_DEPTH;
-}
-
-static inline int
-cfs_hash_with_nblk_change(struct cfs_hash *hs)
-{
- return hs->hs_flags & CFS_HASH_NBLK_CHANGE;
-}
-
-static inline int
-cfs_hash_is_exiting(struct cfs_hash *hs)
-{
- /* cfs_hash_destroy is called */
- return hs->hs_exiting;
-}
-
-static inline int
-cfs_hash_is_rehashing(struct cfs_hash *hs)
-{
- /* rehash is launched */
- return !!hs->hs_rehash_bits;
-}
-
-static inline int
-cfs_hash_is_iterating(struct cfs_hash *hs)
-{
- /* someone is calling cfs_hash_for_each_* */
- return hs->hs_iterating || hs->hs_iterators;
-}
-
-static inline int
-cfs_hash_bkt_size(struct cfs_hash *hs)
-{
- return offsetof(struct cfs_hash_bucket, hsb_head[0]) +
- hs->hs_hops->hop_hhead_size(hs) * CFS_HASH_BKT_NHLIST(hs) +
- hs->hs_extra_bytes;
-}
-
-static inline unsigned
-cfs_hash_id(struct cfs_hash *hs, const void *key, unsigned int mask)
-{
- return hs->hs_ops->hs_hash(hs, key, mask);
-}
-
-static inline void *
-cfs_hash_key(struct cfs_hash *hs, struct hlist_node *hnode)
-{
- return hs->hs_ops->hs_key(hnode);
-}
-
-static inline void
-cfs_hash_keycpy(struct cfs_hash *hs, struct hlist_node *hnode, void *key)
-{
- if (hs->hs_ops->hs_keycpy)
- hs->hs_ops->hs_keycpy(hnode, key);
-}
-
-/**
- * Returns 1 on a match,
- */
-static inline int
-cfs_hash_keycmp(struct cfs_hash *hs, const void *key, struct hlist_node *hnode)
-{
- return hs->hs_ops->hs_keycmp(key, hnode);
-}
-
-static inline void *
-cfs_hash_object(struct cfs_hash *hs, struct hlist_node *hnode)
-{
- return hs->hs_ops->hs_object(hnode);
-}
-
-static inline void
-cfs_hash_get(struct cfs_hash *hs, struct hlist_node *hnode)
-{
- return hs->hs_ops->hs_get(hs, hnode);
-}
-
-static inline void
-cfs_hash_put_locked(struct cfs_hash *hs, struct hlist_node *hnode)
-{
- return hs->hs_ops->hs_put_locked(hs, hnode);
-}
-
-static inline void
-cfs_hash_put(struct cfs_hash *hs, struct hlist_node *hnode)
-{
- return hs->hs_ops->hs_put(hs, hnode);
-}
-
-static inline void
-cfs_hash_exit(struct cfs_hash *hs, struct hlist_node *hnode)
-{
- if (hs->hs_ops->hs_exit)
- hs->hs_ops->hs_exit(hs, hnode);
-}
-
-static inline void cfs_hash_lock(struct cfs_hash *hs, int excl)
-{
- hs->hs_lops->hs_lock(&hs->hs_lock, excl);
-}
-
-static inline void cfs_hash_unlock(struct cfs_hash *hs, int excl)
-{
- hs->hs_lops->hs_unlock(&hs->hs_lock, excl);
-}
-
-static inline int cfs_hash_dec_and_lock(struct cfs_hash *hs,
- atomic_t *condition)
-{
- LASSERT(cfs_hash_with_no_bktlock(hs));
- return atomic_dec_and_lock(condition, &hs->hs_lock.spin);
-}
-
-static inline void cfs_hash_bd_lock(struct cfs_hash *hs,
- struct cfs_hash_bd *bd, int excl)
-{
- hs->hs_lops->hs_bkt_lock(&bd->bd_bucket->hsb_lock, excl);
-}
-
-static inline void cfs_hash_bd_unlock(struct cfs_hash *hs,
- struct cfs_hash_bd *bd, int excl)
-{
- hs->hs_lops->hs_bkt_unlock(&bd->bd_bucket->hsb_lock, excl);
-}
-
-/**
- * operations on cfs_hash bucket (bd: bucket descriptor),
- * they are normally for hash-table without rehash
- */
-void cfs_hash_bd_get(struct cfs_hash *hs, const void *key,
- struct cfs_hash_bd *bd);
-
-static inline void
-cfs_hash_bd_get_and_lock(struct cfs_hash *hs, const void *key,
- struct cfs_hash_bd *bd, int excl)
-{
- cfs_hash_bd_get(hs, key, bd);
- cfs_hash_bd_lock(hs, bd, excl);
-}
-
-static inline unsigned
-cfs_hash_bd_index_get(struct cfs_hash *hs, struct cfs_hash_bd *bd)
-{
- return bd->bd_offset | (bd->bd_bucket->hsb_index << hs->hs_bkt_bits);
-}
-
-static inline void
-cfs_hash_bd_index_set(struct cfs_hash *hs, unsigned int index,
- struct cfs_hash_bd *bd)
-{
- bd->bd_bucket = hs->hs_buckets[index >> hs->hs_bkt_bits];
- bd->bd_offset = index & (CFS_HASH_BKT_NHLIST(hs) - 1U);
-}
-
-static inline void *
-cfs_hash_bd_extra_get(struct cfs_hash *hs, struct cfs_hash_bd *bd)
-{
- return (void *)bd->bd_bucket +
- cfs_hash_bkt_size(hs) - hs->hs_extra_bytes;
-}
-
-static inline u32
-cfs_hash_bd_version_get(struct cfs_hash_bd *bd)
-{
- /* need hold cfs_hash_bd_lock */
- return bd->bd_bucket->hsb_version;
-}
-
-static inline u32
-cfs_hash_bd_count_get(struct cfs_hash_bd *bd)
-{
- /* need hold cfs_hash_bd_lock */
- return bd->bd_bucket->hsb_count;
-}
-
-static inline int
-cfs_hash_bd_depmax_get(struct cfs_hash_bd *bd)
-{
- return bd->bd_bucket->hsb_depmax;
-}
-
-static inline int
-cfs_hash_bd_compare(struct cfs_hash_bd *bd1, struct cfs_hash_bd *bd2)
-{
- if (bd1->bd_bucket->hsb_index != bd2->bd_bucket->hsb_index)
- return bd1->bd_bucket->hsb_index - bd2->bd_bucket->hsb_index;
-
- if (bd1->bd_offset != bd2->bd_offset)
- return bd1->bd_offset - bd2->bd_offset;
-
- return 0;
-}
-
-void cfs_hash_bd_add_locked(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- struct hlist_node *hnode);
-void cfs_hash_bd_del_locked(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- struct hlist_node *hnode);
-void cfs_hash_bd_move_locked(struct cfs_hash *hs, struct cfs_hash_bd *bd_old,
- struct cfs_hash_bd *bd_new,
- struct hlist_node *hnode);
-
-static inline int
-cfs_hash_bd_dec_and_lock(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- atomic_t *condition)
-{
- LASSERT(cfs_hash_with_spin_bktlock(hs));
- return atomic_dec_and_lock(condition, &bd->bd_bucket->hsb_lock.spin);
-}
-
-static inline struct hlist_head *
-cfs_hash_bd_hhead(struct cfs_hash *hs, struct cfs_hash_bd *bd)
-{
- return hs->hs_hops->hop_hhead(hs, bd);
-}
-
-struct hlist_node *
-cfs_hash_bd_lookup_locked(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- const void *key);
-struct hlist_node *
-cfs_hash_bd_peek_locked(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- const void *key);
-
-/**
- * operations on cfs_hash bucket (bd: bucket descriptor),
- * they are safe for hash-table with rehash
- */
-void cfs_hash_dual_bd_get(struct cfs_hash *hs, const void *key,
- struct cfs_hash_bd *bds);
-void cfs_hash_dual_bd_lock(struct cfs_hash *hs, struct cfs_hash_bd *bds,
- int excl);
-void cfs_hash_dual_bd_unlock(struct cfs_hash *hs, struct cfs_hash_bd *bds,
- int excl);
-
-static inline void
-cfs_hash_dual_bd_get_and_lock(struct cfs_hash *hs, const void *key,
- struct cfs_hash_bd *bds, int excl)
-{
- cfs_hash_dual_bd_get(hs, key, bds);
- cfs_hash_dual_bd_lock(hs, bds, excl);
-}
-
-struct hlist_node *
-cfs_hash_dual_bd_lookup_locked(struct cfs_hash *hs, struct cfs_hash_bd *bds,
- const void *key);
-struct hlist_node *
-cfs_hash_dual_bd_findadd_locked(struct cfs_hash *hs, struct cfs_hash_bd *bds,
- const void *key, struct hlist_node *hnode,
- int insist_add);
-struct hlist_node *
-cfs_hash_dual_bd_finddel_locked(struct cfs_hash *hs, struct cfs_hash_bd *bds,
- const void *key, struct hlist_node *hnode);
-
-/* Hash init/cleanup functions */
-struct cfs_hash *
-cfs_hash_create(char *name, unsigned int cur_bits, unsigned int max_bits,
- unsigned int bkt_bits, unsigned int extra_bytes,
- unsigned int min_theta, unsigned int max_theta,
- struct cfs_hash_ops *ops, unsigned int flags);
-
-struct cfs_hash *cfs_hash_getref(struct cfs_hash *hs);
-void cfs_hash_putref(struct cfs_hash *hs);
-
-/* Hash addition functions */
-void cfs_hash_add(struct cfs_hash *hs, const void *key,
- struct hlist_node *hnode);
-int cfs_hash_add_unique(struct cfs_hash *hs, const void *key,
- struct hlist_node *hnode);
-void *cfs_hash_findadd_unique(struct cfs_hash *hs, const void *key,
- struct hlist_node *hnode);
-
-/* Hash deletion functions */
-void *cfs_hash_del(struct cfs_hash *hs, const void *key,
- struct hlist_node *hnode);
-void *cfs_hash_del_key(struct cfs_hash *hs, const void *key);
-
-/* Hash lookup/for_each functions */
-#define CFS_HASH_LOOP_HOG 1024
-
-typedef int (*cfs_hash_for_each_cb_t)(struct cfs_hash *hs,
- struct cfs_hash_bd *bd,
- struct hlist_node *node,
- void *data);
-void *
-cfs_hash_lookup(struct cfs_hash *hs, const void *key);
-void
-cfs_hash_for_each(struct cfs_hash *hs, cfs_hash_for_each_cb_t cb, void *data);
-void
-cfs_hash_for_each_safe(struct cfs_hash *hs, cfs_hash_for_each_cb_t cb,
- void *data);
-int
-cfs_hash_for_each_nolock(struct cfs_hash *hs, cfs_hash_for_each_cb_t cb,
- void *data, int start);
-int
-cfs_hash_for_each_empty(struct cfs_hash *hs, cfs_hash_for_each_cb_t cb,
- void *data);
-void
-cfs_hash_for_each_key(struct cfs_hash *hs, const void *key,
- cfs_hash_for_each_cb_t cb, void *data);
-typedef int (*cfs_hash_cond_opt_cb_t)(void *obj, void *data);
-void
-cfs_hash_cond_del(struct cfs_hash *hs, cfs_hash_cond_opt_cb_t cb, void *data);
-
-void
-cfs_hash_hlist_for_each(struct cfs_hash *hs, unsigned int hindex,
- cfs_hash_for_each_cb_t cb, void *data);
-int cfs_hash_is_empty(struct cfs_hash *hs);
-u64 cfs_hash_size_get(struct cfs_hash *hs);
-
-/*
- * Rehash - Theta is calculated to be the average chained
- * hash depth assuming a perfectly uniform hash function.
- */
-void cfs_hash_rehash_cancel_locked(struct cfs_hash *hs);
-void cfs_hash_rehash_cancel(struct cfs_hash *hs);
-void cfs_hash_rehash(struct cfs_hash *hs, int do_rehash);
-void cfs_hash_rehash_key(struct cfs_hash *hs, const void *old_key,
- void *new_key, struct hlist_node *hnode);
-
-#if CFS_HASH_DEBUG_LEVEL > CFS_HASH_DEBUG_1
-/* Validate hnode references the correct key */
-static inline void
-cfs_hash_key_validate(struct cfs_hash *hs, const void *key,
- struct hlist_node *hnode)
-{
- LASSERT(cfs_hash_keycmp(hs, key, hnode));
-}
-
-/* Validate hnode is in the correct bucket */
-static inline void
-cfs_hash_bucket_validate(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- struct hlist_node *hnode)
-{
- struct cfs_hash_bd bds[2];
-
- cfs_hash_dual_bd_get(hs, cfs_hash_key(hs, hnode), bds);
- LASSERT(bds[0].bd_bucket == bd->bd_bucket ||
- bds[1].bd_bucket == bd->bd_bucket);
-}
-
-#else /* CFS_HASH_DEBUG_LEVEL > CFS_HASH_DEBUG_1 */
-
-static inline void
-cfs_hash_key_validate(struct cfs_hash *hs, const void *key,
- struct hlist_node *hnode) {}
-
-static inline void
-cfs_hash_bucket_validate(struct cfs_hash *hs, struct cfs_hash_bd *bd,
- struct hlist_node *hnode) {}
-
-#endif /* CFS_HASH_DEBUG_LEVEL */
-
-#define CFS_HASH_THETA_BITS 10
-#define CFS_HASH_MIN_THETA BIT(CFS_HASH_THETA_BITS - 1)
-#define CFS_HASH_MAX_THETA BIT(CFS_HASH_THETA_BITS + 1)
-
-/* Return integer component of theta */
-static inline int __cfs_hash_theta_int(int theta)
-{
- return (theta >> CFS_HASH_THETA_BITS);
-}
-
-/* Return a fractional value between 0 and 999 */
-static inline int __cfs_hash_theta_frac(int theta)
-{
- return ((theta * 1000) >> CFS_HASH_THETA_BITS) -
- (__cfs_hash_theta_int(theta) * 1000);
-}
-
-static inline int __cfs_hash_theta(struct cfs_hash *hs)
-{
- return (atomic_read(&hs->hs_count) <<
- CFS_HASH_THETA_BITS) >> hs->hs_cur_bits;
-}
-
-static inline void
-__cfs_hash_set_theta(struct cfs_hash *hs, int min, int max)
-{
- LASSERT(min < max);
- hs->hs_min_theta = (u16)min;
- hs->hs_max_theta = (u16)max;
-}
-
-/* Generic debug formatting routines mainly for proc handler */
-struct seq_file;
-void cfs_hash_debug_header(struct seq_file *m);
-void cfs_hash_debug_str(struct cfs_hash *hs, struct seq_file *m);
-
-/*
- * Generic djb2 hash algorithm for character arrays.
- */
-static inline unsigned
-cfs_hash_djb2_hash(const void *key, size_t size, unsigned int mask)
-{
- unsigned int i, hash = 5381;
-
- LASSERT(key);
-
- for (i = 0; i < size; i++)
- hash = hash * 33 + ((char *)key)[i];
-
- return (hash & mask);
-}
-
-/*
- * Generic u32 hash algorithm.
- */
-static inline unsigned
-cfs_hash_u32_hash(const u32 key, unsigned int mask)
-{
- return ((key * CFS_GOLDEN_RATIO_PRIME_32) & mask);
-}
-
-/*
- * Generic u64 hash algorithm.
- */
-static inline unsigned
-cfs_hash_u64_hash(const u64 key, unsigned int mask)
-{
- return ((unsigned int)(key * CFS_GOLDEN_RATIO_PRIME_64) & mask);
-}
-
-/** iterate over all buckets in @bds (array of struct cfs_hash_bd) */
-#define cfs_hash_for_each_bd(bds, n, i) \
- for (i = 0; i < n && (bds)[i].bd_bucket != NULL; i++)
-
-/** iterate over all buckets of @hs */
-#define cfs_hash_for_each_bucket(hs, bd, pos) \
- for (pos = 0; \
- pos < CFS_HASH_NBKT(hs) && \
- ((bd)->bd_bucket = (hs)->hs_buckets[pos]) != NULL; pos++)
-
-/** iterate over all hlist of bucket @bd */
-#define cfs_hash_bd_for_each_hlist(hs, bd, hlist) \
- for ((bd)->bd_offset = 0; \
- (bd)->bd_offset < CFS_HASH_BKT_NHLIST(hs) && \
- (hlist = cfs_hash_bd_hhead(hs, bd)) != NULL; \
- (bd)->bd_offset++)
-
-/* !__LIBCFS__HASH_H__ */
-#endif
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
deleted file mode 100644
index 491d5971d199..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
+++ /dev/null
@@ -1,200 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2012, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_private.h
- *
- * Various defines for libcfs.
- *
- */
-
-#ifndef __LIBCFS_PRIVATE_H__
-#define __LIBCFS_PRIVATE_H__
-
-#ifndef DEBUG_SUBSYSTEM
-# define DEBUG_SUBSYSTEM S_UNDEFINED
-#endif
-
-#define LASSERTF(cond, fmt, ...) \
-do { \
- if (unlikely(!(cond))) { \
- LIBCFS_DEBUG_MSG_DATA_DECL(__msg_data, D_EMERG, NULL); \
- libcfs_debug_msg(&__msg_data, \
- "ASSERTION( %s ) failed: " fmt, #cond, \
- ## __VA_ARGS__); \
- lbug_with_loc(&__msg_data); \
- } \
-} while (0)
-
-#define LASSERT(cond) LASSERTF(cond, "\n")
-
-#ifdef CONFIG_LUSTRE_DEBUG_EXPENSIVE_CHECK
-/**
- * This is for more expensive checks that one doesn't want to be enabled all
- * the time. LINVRNT() has to be explicitly enabled by
- * CONFIG_LUSTRE_DEBUG_EXPENSIVE_CHECK option.
- */
-# define LINVRNT(exp) LASSERT(exp)
-#else
-# define LINVRNT(exp) ((void)sizeof !!(exp))
-#endif
-
-void __noreturn lbug_with_loc(struct libcfs_debug_msg_data *msg);
-
-#define LBUG() \
-do { \
- LIBCFS_DEBUG_MSG_DATA_DECL(msgdata, D_EMERG, NULL); \
- lbug_with_loc(&msgdata); \
-} while (0)
-
-/*
- * Use #define rather than inline, as lnet_cpt_table() might
- * not be defined yet
- */
-#define kmalloc_cpt(size, flags, cpt) \
- kmalloc_node(size, flags, cfs_cpt_spread_node(lnet_cpt_table(), cpt))
-
-#define kzalloc_cpt(size, flags, cpt) \
- kmalloc_node(size, flags | __GFP_ZERO, \
- cfs_cpt_spread_node(lnet_cpt_table(), cpt))
-
-#define kvmalloc_cpt(size, flags, cpt) \
- kvmalloc_node(size, flags, \
- cfs_cpt_spread_node(lnet_cpt_table(), cpt))
-
-#define kvzalloc_cpt(size, flags, cpt) \
- kvmalloc_node(size, flags | __GFP_ZERO, \
- cfs_cpt_spread_node(lnet_cpt_table(), cpt))
-
-/******************************************************************************/
-
-void libcfs_debug_dumplog(void);
-int libcfs_debug_init(unsigned long bufsize);
-int libcfs_debug_cleanup(void);
-int libcfs_debug_clear_buffer(void);
-int libcfs_debug_mark_buffer(const char *text);
-
-/*
- * allocate a variable array, returned value is an array of pointers.
- * Caller can specify length of array by count.
- */
-void *cfs_array_alloc(int count, unsigned int size);
-void cfs_array_free(void *vars);
-
-#define LASSERT_ATOMIC_ENABLED (1)
-
-#if LASSERT_ATOMIC_ENABLED
-
-/** assert value of @a is equal to @v */
-#define LASSERT_ATOMIC_EQ(a, v) \
- LASSERTF(atomic_read(a) == v, "value: %d\n", atomic_read((a)))
-
-/** assert value of @a is unequal to @v */
-#define LASSERT_ATOMIC_NE(a, v) \
- LASSERTF(atomic_read(a) != v, "value: %d\n", atomic_read((a)))
-
-/** assert value of @a is little than @v */
-#define LASSERT_ATOMIC_LT(a, v) \
- LASSERTF(atomic_read(a) < v, "value: %d\n", atomic_read((a)))
-
-/** assert value of @a is little/equal to @v */
-#define LASSERT_ATOMIC_LE(a, v) \
- LASSERTF(atomic_read(a) <= v, "value: %d\n", atomic_read((a)))
-
-/** assert value of @a is great than @v */
-#define LASSERT_ATOMIC_GT(a, v) \
- LASSERTF(atomic_read(a) > v, "value: %d\n", atomic_read((a)))
-
-/** assert value of @a is great/equal to @v */
-#define LASSERT_ATOMIC_GE(a, v) \
- LASSERTF(atomic_read(a) >= v, "value: %d\n", atomic_read((a)))
-
-/** assert value of @a is great than @v1 and little than @v2 */
-#define LASSERT_ATOMIC_GT_LT(a, v1, v2) \
-do { \
- int __v = atomic_read(a); \
- LASSERTF(__v > v1 && __v < v2, "value: %d\n", __v); \
-} while (0)
-
-/** assert value of @a is great than @v1 and little/equal to @v2 */
-#define LASSERT_ATOMIC_GT_LE(a, v1, v2) \
-do { \
- int __v = atomic_read(a); \
- LASSERTF(__v > v1 && __v <= v2, "value: %d\n", __v); \
-} while (0)
-
-/** assert value of @a is great/equal to @v1 and little than @v2 */
-#define LASSERT_ATOMIC_GE_LT(a, v1, v2) \
-do { \
- int __v = atomic_read(a); \
- LASSERTF(__v >= v1 && __v < v2, "value: %d\n", __v); \
-} while (0)
-
-/** assert value of @a is great/equal to @v1 and little/equal to @v2 */
-#define LASSERT_ATOMIC_GE_LE(a, v1, v2) \
-do { \
- int __v = atomic_read(a); \
- LASSERTF(__v >= v1 && __v <= v2, "value: %d\n", __v); \
-} while (0)
-
-#else /* !LASSERT_ATOMIC_ENABLED */
-
-#define LASSERT_ATOMIC_EQ(a, v) do {} while (0)
-#define LASSERT_ATOMIC_NE(a, v) do {} while (0)
-#define LASSERT_ATOMIC_LT(a, v) do {} while (0)
-#define LASSERT_ATOMIC_LE(a, v) do {} while (0)
-#define LASSERT_ATOMIC_GT(a, v) do {} while (0)
-#define LASSERT_ATOMIC_GE(a, v) do {} while (0)
-#define LASSERT_ATOMIC_GT_LT(a, v1, v2) do {} while (0)
-#define LASSERT_ATOMIC_GT_LE(a, v1, v2) do {} while (0)
-#define LASSERT_ATOMIC_GE_LT(a, v1, v2) do {} while (0)
-#define LASSERT_ATOMIC_GE_LE(a, v1, v2) do {} while (0)
-
-#endif /* LASSERT_ATOMIC_ENABLED */
-
-#define LASSERT_ATOMIC_ZERO(a) LASSERT_ATOMIC_EQ(a, 0)
-#define LASSERT_ATOMIC_POS(a) LASSERT_ATOMIC_GT(a, 0)
-
-/* implication */
-#define ergo(a, b) (!(a) || (b))
-/* logical equivalence */
-#define equi(a, b) (!!(a) == !!(b))
-
-#ifndef HAVE_CFS_SIZE_ROUND
-static inline size_t cfs_size_round(int val)
-{
- return round_up(val, 8);
-}
-
-#define HAVE_CFS_SIZE_ROUND
-#endif
-
-#endif
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_string.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_string.h
deleted file mode 100644
index cd7c3ccb2dc0..000000000000
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_string.h
+++ /dev/null
@@ -1,102 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_string.h
- *
- * Generic string manipulation functions.
- *
- * Author: Nathan Rutman <nathan.rutman@sun.com>
- */
-
-#ifndef __LIBCFS_STRING_H__
-#define __LIBCFS_STRING_H__
-
-#include <linux/mm.h>
-
-/* libcfs_string.c */
-/* Convert a text string to a bitmask */
-int cfs_str2mask(const char *str, const char *(*bit2str)(int bit),
- int *oldmask, int minmask, int allmask);
-/* trim leading and trailing space characters */
-char *cfs_firststr(char *str, size_t size);
-
-/**
- * Structure to represent NULL-less strings.
- */
-struct cfs_lstr {
- char *ls_str;
- int ls_len;
-};
-
-/*
- * Structure to represent \<range_expr\> token of the syntax.
- */
-struct cfs_range_expr {
- /*
- * Link to cfs_expr_list::el_exprs.
- */
- struct list_head re_link;
- u32 re_lo;
- u32 re_hi;
- u32 re_stride;
-};
-
-struct cfs_expr_list {
- struct list_head el_link;
- struct list_head el_exprs;
-};
-
-int cfs_gettok(struct cfs_lstr *next, char delim, struct cfs_lstr *res);
-int cfs_str2num_check(char *str, int nob, unsigned int *num,
- unsigned int min, unsigned int max);
-int cfs_expr_list_match(u32 value, struct cfs_expr_list *expr_list);
-int cfs_expr_list_print(char *buffer, int count,
- struct cfs_expr_list *expr_list);
-int cfs_expr_list_values(struct cfs_expr_list *expr_list,
- int max, u32 **values);
-static inline void
-cfs_expr_list_values_free(u32 *values, int num)
-{
- /*
- * This array is allocated by kvalloc(), so it shouldn't be freed
- * by OBD_FREE() if it's called by module other than libcfs & LNet,
- * otherwise we will see fake memory leak
- */
- kvfree(values);
-}
-
-void cfs_expr_list_free(struct cfs_expr_list *expr_list);
-int cfs_expr_list_parse(char *str, int len, unsigned int min, unsigned int max,
- struct cfs_expr_list **elpp);
-void cfs_expr_list_free_list(struct list_head *list);
-
-#endif
diff --git a/drivers/staging/lustre/include/linux/lnet/api.h b/drivers/staging/lustre/include/linux/lnet/api.h
deleted file mode 100644
index dae2e4f0056c..000000000000
--- a/drivers/staging/lustre/include/linux/lnet/api.h
+++ /dev/null
@@ -1,212 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011 - 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Seagate, Inc.
- */
-
-#ifndef __LNET_API_H__
-#define __LNET_API_H__
-
-/** \defgroup lnet LNet
- *
- * The Lustre Networking subsystem.
- *
- * LNet is an asynchronous message-passing API, which provides an unreliable
- * connectionless service that can't guarantee any order. It supports OFA IB,
- * TCP/IP, and Cray Interconnects, and routes between heterogeneous networks.
- *
- * @{
- */
-
-#include <uapi/linux/lnet/lnet-types.h>
-
-/** \defgroup lnet_init_fini Initialization and cleanup
- * The LNet must be properly initialized before any LNet calls can be made.
- * @{
- */
-int LNetNIInit(lnet_pid_t requested_pid);
-int LNetNIFini(void);
-/** @} lnet_init_fini */
-
-/** \defgroup lnet_addr LNet addressing and basic types
- *
- * Addressing scheme and basic data types of LNet.
- *
- * The LNet API is memory-oriented, so LNet must be able to address not only
- * end-points but also memory region within a process address space.
- * An ::lnet_nid_t addresses an end-point. An ::lnet_pid_t identifies a process
- * in a node. A portal represents an opening in the address space of a
- * process. Match bits is criteria to identify a region of memory inside a
- * portal, and offset specifies an offset within the memory region.
- *
- * LNet creates a table of portals for each process during initialization.
- * This table has MAX_PORTALS entries and its size can't be dynamically
- * changed. A portal stays empty until the owning process starts to add
- * memory regions to it. A portal is sometimes called an index because
- * it's an entry in the portals table of a process.
- *
- * \see LNetMEAttach
- * @{
- */
-int LNetGetId(unsigned int index, struct lnet_process_id *id);
-int LNetDist(lnet_nid_t nid, lnet_nid_t *srcnid, __u32 *order);
-
-/** @} lnet_addr */
-
-/** \defgroup lnet_me Match entries
- *
- * A match entry (abbreviated as ME) describes a set of criteria to accept
- * incoming requests.
- *
- * A portal is essentially a match list plus a set of attributes. A match
- * list is a chain of MEs. Each ME includes a pointer to a memory descriptor
- * and a set of match criteria. The match criteria can be used to reject
- * incoming requests based on process ID or the match bits provided in the
- * request. MEs can be dynamically inserted into a match list by LNetMEAttach()
- * and LNetMEInsert(), and removed from its list by LNetMEUnlink().
- * @{
- */
-int LNetMEAttach(unsigned int portal,
- struct lnet_process_id match_id_in,
- __u64 match_bits_in,
- __u64 ignore_bits_in,
- enum lnet_unlink unlink_in,
- enum lnet_ins_pos pos_in,
- struct lnet_handle_me *handle_out);
-
-int LNetMEInsert(struct lnet_handle_me current_in,
- struct lnet_process_id match_id_in,
- __u64 match_bits_in,
- __u64 ignore_bits_in,
- enum lnet_unlink unlink_in,
- enum lnet_ins_pos position_in,
- struct lnet_handle_me *handle_out);
-
-int LNetMEUnlink(struct lnet_handle_me current_in);
-/** @} lnet_me */
-
-/** \defgroup lnet_md Memory descriptors
- *
- * A memory descriptor contains information about a region of a user's
- * memory (either in kernel or user space) and optionally points to an
- * event queue where information about the operations performed on the
- * memory descriptor are recorded. Memory descriptor is abbreviated as
- * MD and can be used interchangeably with the memory region it describes.
- *
- * The LNet API provides two operations to create MDs: LNetMDAttach()
- * and LNetMDBind(); one operation to unlink and release the resources
- * associated with a MD: LNetMDUnlink().
- * @{
- */
-int LNetMDAttach(struct lnet_handle_me current_in,
- struct lnet_md md_in,
- enum lnet_unlink unlink_in,
- struct lnet_handle_md *md_handle_out);
-
-int LNetMDBind(struct lnet_md md_in,
- enum lnet_unlink unlink_in,
- struct lnet_handle_md *md_handle_out);
-
-int LNetMDUnlink(struct lnet_handle_md md_in);
-/** @} lnet_md */
-
-/** \defgroup lnet_eq Events and event queues
- *
- * Event queues (abbreviated as EQ) are used to log operations performed on
- * local MDs. In particular, they signal the completion of a data transmission
- * into or out of a MD. They can also be used to hold acknowledgments for
- * completed PUT operations and indicate when a MD has been unlinked. Multiple
- * MDs can share a single EQ. An EQ may have an optional event handler
- * associated with it. If an event handler exists, it will be run for each
- * event that is deposited into the EQ.
- *
- * In addition to the lnet_handle_eq, the LNet API defines two types
- * associated with events: The ::lnet_event_kind defines the kinds of events
- * that can be stored in an EQ. The lnet_event defines a structure that
- * holds the information about with an event.
- *
- * There are five functions for dealing with EQs: LNetEQAlloc() is used to
- * create an EQ and allocate the resources needed, while LNetEQFree()
- * releases these resources and free the EQ. LNetEQGet() retrieves the next
- * event from an EQ, and LNetEQWait() can be used to block a process until
- * an EQ has at least one event. LNetEQPoll() can be used to test or wait
- * on multiple EQs.
- * @{
- */
-int LNetEQAlloc(unsigned int count_in,
- lnet_eq_handler_t handler,
- struct lnet_handle_eq *handle_out);
-
-int LNetEQFree(struct lnet_handle_eq eventq_in);
-
-int LNetEQPoll(struct lnet_handle_eq *eventqs_in,
- int neq_in,
- int timeout_ms,
- int interruptible,
- struct lnet_event *event_out,
- int *which_eq_out);
-/** @} lnet_eq */
-
-/** \defgroup lnet_data Data movement operations
- *
- * The LNet API provides two data movement operations: LNetPut()
- * and LNetGet().
- * @{
- */
-int LNetPut(lnet_nid_t self,
- struct lnet_handle_md md_in,
- enum lnet_ack_req ack_req_in,
- struct lnet_process_id target_in,
- unsigned int portal_in,
- __u64 match_bits_in,
- unsigned int offset_in,
- __u64 hdr_data_in);
-
-int LNetGet(lnet_nid_t self,
- struct lnet_handle_md md_in,
- struct lnet_process_id target_in,
- unsigned int portal_in,
- __u64 match_bits_in,
- unsigned int offset_in);
-/** @} lnet_data */
-
-/** \defgroup lnet_misc Miscellaneous operations.
- * Miscellaneous operations.
- * @{
- */
-int LNetSetLazyPortal(int portal);
-int LNetClearLazyPortal(int portal);
-int LNetCtl(unsigned int cmd, void *arg);
-void LNetDebugPeer(struct lnet_process_id id);
-
-/** @} lnet_misc */
-
-/** @} lnet */
-#endif
diff --git a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
deleted file mode 100644
index 973c17a1c4a1..000000000000
--- a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
+++ /dev/null
@@ -1,652 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Seagate, Inc.
- *
- * lnet/include/lnet/lib-lnet.h
- */
-
-#ifndef __LNET_LIB_LNET_H__
-#define __LNET_LIB_LNET_H__
-
-#include <linux/libcfs/libcfs.h>
-#include <linux/libcfs/libcfs_cpu.h>
-#include <linux/libcfs/libcfs_string.h>
-#include <net/sock.h>
-
-#include <linux/lnet/api.h>
-#include <linux/lnet/lib-types.h>
-#include <uapi/linux/lnet/lnet-dlc.h>
-#include <uapi/linux/lnet/lnet-types.h>
-#include <uapi/linux/lnet/lnetctl.h>
-#include <uapi/linux/lnet/nidstr.h>
-
-extern struct lnet the_lnet; /* THE network */
-
-#if (BITS_PER_LONG == 32)
-/* 2 CPTs, allowing more CPTs might make us under memory pressure */
-#define LNET_CPT_MAX_BITS 1
-
-#else /* 64-bit system */
-/*
- * 256 CPTs for thousands of CPUs, allowing more CPTs might make us
- * under risk of consuming all lh_cookie.
- */
-#define LNET_CPT_MAX_BITS 8
-#endif /* BITS_PER_LONG == 32 */
-
-/* max allowed CPT number */
-#define LNET_CPT_MAX (1 << LNET_CPT_MAX_BITS)
-
-#define LNET_CPT_NUMBER (the_lnet.ln_cpt_number)
-#define LNET_CPT_BITS (the_lnet.ln_cpt_bits)
-#define LNET_CPT_MASK ((1ULL << LNET_CPT_BITS) - 1)
-
-/** exclusive lock */
-#define LNET_LOCK_EX CFS_PERCPT_LOCK_EX
-
-/* need both kernel and user-land acceptor */
-#define LNET_ACCEPTOR_MIN_RESERVED_PORT 512
-#define LNET_ACCEPTOR_MAX_RESERVED_PORT 1023
-
-static inline int lnet_is_route_alive(struct lnet_route *route)
-{
- /* gateway is down */
- if (!route->lr_gateway->lp_alive)
- return 0;
- /* no NI status, assume it's alive */
- if ((route->lr_gateway->lp_ping_feats &
- LNET_PING_FEAT_NI_STATUS) == 0)
- return 1;
- /* has NI status, check # down NIs */
- return route->lr_downis == 0;
-}
-
-static inline int lnet_is_wire_handle_none(struct lnet_handle_wire *wh)
-{
- return (wh->wh_interface_cookie == LNET_WIRE_HANDLE_COOKIE_NONE &&
- wh->wh_object_cookie == LNET_WIRE_HANDLE_COOKIE_NONE);
-}
-
-static inline int lnet_md_exhausted(struct lnet_libmd *md)
-{
- return (!md->md_threshold ||
- ((md->md_options & LNET_MD_MAX_SIZE) &&
- md->md_offset + md->md_max_size > md->md_length));
-}
-
-static inline int lnet_md_unlinkable(struct lnet_libmd *md)
-{
- /*
- * Should unlink md when its refcount is 0 and either:
- * - md has been flagged for deletion (by auto unlink or
- * LNetM[DE]Unlink, in the latter case md may not be exhausted).
- * - auto unlink is on and md is exhausted.
- */
- if (md->md_refcount)
- return 0;
-
- if (md->md_flags & LNET_MD_FLAG_ZOMBIE)
- return 1;
-
- return ((md->md_flags & LNET_MD_FLAG_AUTO_UNLINK) &&
- lnet_md_exhausted(md));
-}
-
-#define lnet_cpt_table() (the_lnet.ln_cpt_table)
-#define lnet_cpt_current() cfs_cpt_current(the_lnet.ln_cpt_table, 1)
-
-static inline int
-lnet_cpt_of_cookie(__u64 cookie)
-{
- unsigned int cpt = (cookie >> LNET_COOKIE_TYPE_BITS) & LNET_CPT_MASK;
-
- /*
- * LNET_CPT_NUMBER doesn't have to be power2, which means we can
- * get illegal cpt from it's invalid cookie
- */
- return cpt < LNET_CPT_NUMBER ? cpt : cpt % LNET_CPT_NUMBER;
-}
-
-static inline void
-lnet_res_lock(int cpt)
-{
- cfs_percpt_lock(the_lnet.ln_res_lock, cpt);
-}
-
-static inline void
-lnet_res_unlock(int cpt)
-{
- cfs_percpt_unlock(the_lnet.ln_res_lock, cpt);
-}
-
-static inline int
-lnet_res_lock_current(void)
-{
- int cpt = lnet_cpt_current();
-
- lnet_res_lock(cpt);
- return cpt;
-}
-
-static inline void
-lnet_net_lock(int cpt)
-{
- cfs_percpt_lock(the_lnet.ln_net_lock, cpt);
-}
-
-static inline void
-lnet_net_unlock(int cpt)
-{
- cfs_percpt_unlock(the_lnet.ln_net_lock, cpt);
-}
-
-static inline int
-lnet_net_lock_current(void)
-{
- int cpt = lnet_cpt_current();
-
- lnet_net_lock(cpt);
- return cpt;
-}
-
-#define LNET_LOCK() lnet_net_lock(LNET_LOCK_EX)
-#define LNET_UNLOCK() lnet_net_unlock(LNET_LOCK_EX)
-
-#define lnet_ptl_lock(ptl) spin_lock(&(ptl)->ptl_lock)
-#define lnet_ptl_unlock(ptl) spin_unlock(&(ptl)->ptl_lock)
-#define lnet_eq_wait_lock() spin_lock(&the_lnet.ln_eq_wait_lock)
-#define lnet_eq_wait_unlock() spin_unlock(&the_lnet.ln_eq_wait_lock)
-#define lnet_ni_lock(ni) spin_lock(&(ni)->ni_lock)
-#define lnet_ni_unlock(ni) spin_unlock(&(ni)->ni_lock)
-
-#define MAX_PORTALS 64
-
-static inline struct lnet_libmd *
-lnet_md_alloc(struct lnet_md *umd)
-{
- struct lnet_libmd *md;
- unsigned int size;
- unsigned int niov;
-
- if (umd->options & LNET_MD_KIOV) {
- niov = umd->length;
- size = offsetof(struct lnet_libmd, md_iov.kiov[niov]);
- } else {
- niov = umd->options & LNET_MD_IOVEC ? umd->length : 1;
- size = offsetof(struct lnet_libmd, md_iov.iov[niov]);
- }
-
- md = kzalloc(size, GFP_NOFS);
-
- if (md) {
- /* Set here in case of early free */
- md->md_options = umd->options;
- md->md_niov = niov;
- INIT_LIST_HEAD(&md->md_list);
- }
-
- return md;
-}
-
-struct lnet_libhandle *lnet_res_lh_lookup(struct lnet_res_container *rec,
- __u64 cookie);
-void lnet_res_lh_initialize(struct lnet_res_container *rec,
- struct lnet_libhandle *lh);
-static inline void
-lnet_res_lh_invalidate(struct lnet_libhandle *lh)
-{
- /* NB: cookie is still useful, don't reset it */
- list_del(&lh->lh_hash_chain);
-}
-
-static inline void
-lnet_eq2handle(struct lnet_handle_eq *handle, struct lnet_eq *eq)
-{
- if (!eq) {
- LNetInvalidateEQHandle(handle);
- return;
- }
-
- handle->cookie = eq->eq_lh.lh_cookie;
-}
-
-static inline struct lnet_eq *
-lnet_handle2eq(struct lnet_handle_eq *handle)
-{
- struct lnet_libhandle *lh;
-
- lh = lnet_res_lh_lookup(&the_lnet.ln_eq_container, handle->cookie);
- if (!lh)
- return NULL;
-
- return lh_entry(lh, struct lnet_eq, eq_lh);
-}
-
-static inline void
-lnet_md2handle(struct lnet_handle_md *handle, struct lnet_libmd *md)
-{
- handle->cookie = md->md_lh.lh_cookie;
-}
-
-static inline struct lnet_libmd *
-lnet_handle2md(struct lnet_handle_md *handle)
-{
- /* ALWAYS called with resource lock held */
- struct lnet_libhandle *lh;
- int cpt;
-
- cpt = lnet_cpt_of_cookie(handle->cookie);
- lh = lnet_res_lh_lookup(the_lnet.ln_md_containers[cpt],
- handle->cookie);
- if (!lh)
- return NULL;
-
- return lh_entry(lh, struct lnet_libmd, md_lh);
-}
-
-static inline struct lnet_libmd *
-lnet_wire_handle2md(struct lnet_handle_wire *wh)
-{
- /* ALWAYS called with resource lock held */
- struct lnet_libhandle *lh;
- int cpt;
-
- if (wh->wh_interface_cookie != the_lnet.ln_interface_cookie)
- return NULL;
-
- cpt = lnet_cpt_of_cookie(wh->wh_object_cookie);
- lh = lnet_res_lh_lookup(the_lnet.ln_md_containers[cpt],
- wh->wh_object_cookie);
- if (!lh)
- return NULL;
-
- return lh_entry(lh, struct lnet_libmd, md_lh);
-}
-
-static inline void
-lnet_me2handle(struct lnet_handle_me *handle, struct lnet_me *me)
-{
- handle->cookie = me->me_lh.lh_cookie;
-}
-
-static inline struct lnet_me *
-lnet_handle2me(struct lnet_handle_me *handle)
-{
- /* ALWAYS called with resource lock held */
- struct lnet_libhandle *lh;
- int cpt;
-
- cpt = lnet_cpt_of_cookie(handle->cookie);
- lh = lnet_res_lh_lookup(the_lnet.ln_me_containers[cpt],
- handle->cookie);
- if (!lh)
- return NULL;
-
- return lh_entry(lh, struct lnet_me, me_lh);
-}
-
-static inline void
-lnet_peer_addref_locked(struct lnet_peer *lp)
-{
- LASSERT(lp->lp_refcount > 0);
- lp->lp_refcount++;
-}
-
-void lnet_destroy_peer_locked(struct lnet_peer *lp);
-
-static inline void
-lnet_peer_decref_locked(struct lnet_peer *lp)
-{
- LASSERT(lp->lp_refcount > 0);
- lp->lp_refcount--;
- if (!lp->lp_refcount)
- lnet_destroy_peer_locked(lp);
-}
-
-static inline int
-lnet_isrouter(struct lnet_peer *lp)
-{
- return lp->lp_rtr_refcount ? 1 : 0;
-}
-
-static inline void
-lnet_ni_addref_locked(struct lnet_ni *ni, int cpt)
-{
- LASSERT(cpt >= 0 && cpt < LNET_CPT_NUMBER);
- LASSERT(*ni->ni_refs[cpt] >= 0);
-
- (*ni->ni_refs[cpt])++;
-}
-
-static inline void
-lnet_ni_addref(struct lnet_ni *ni)
-{
- lnet_net_lock(0);
- lnet_ni_addref_locked(ni, 0);
- lnet_net_unlock(0);
-}
-
-static inline void
-lnet_ni_decref_locked(struct lnet_ni *ni, int cpt)
-{
- LASSERT(cpt >= 0 && cpt < LNET_CPT_NUMBER);
- LASSERT(*ni->ni_refs[cpt] > 0);
-
- (*ni->ni_refs[cpt])--;
-}
-
-static inline void
-lnet_ni_decref(struct lnet_ni *ni)
-{
- lnet_net_lock(0);
- lnet_ni_decref_locked(ni, 0);
- lnet_net_unlock(0);
-}
-
-void lnet_ni_free(struct lnet_ni *ni);
-struct lnet_ni *
-lnet_ni_alloc(__u32 net, struct cfs_expr_list *el, struct list_head *nilist);
-
-static inline int
-lnet_nid2peerhash(lnet_nid_t nid)
-{
- return hash_long(nid, LNET_PEER_HASH_BITS);
-}
-
-static inline struct list_head *
-lnet_net2rnethash(__u32 net)
-{
- return &the_lnet.ln_remote_nets_hash[(LNET_NETNUM(net) +
- LNET_NETTYP(net)) &
- ((1U << the_lnet.ln_remote_nets_hbits) - 1)];
-}
-
-extern struct lnet_lnd the_lolnd;
-extern int avoid_asym_router_failure;
-
-int lnet_cpt_of_nid_locked(lnet_nid_t nid);
-int lnet_cpt_of_nid(lnet_nid_t nid);
-struct lnet_ni *lnet_nid2ni_locked(lnet_nid_t nid, int cpt);
-struct lnet_ni *lnet_net2ni_locked(__u32 net, int cpt);
-struct lnet_ni *lnet_net2ni(__u32 net);
-
-extern int portal_rotor;
-
-int lnet_lib_init(void);
-void lnet_lib_exit(void);
-
-int lnet_notify(struct lnet_ni *ni, lnet_nid_t peer, int alive,
- unsigned long when);
-void lnet_notify_locked(struct lnet_peer *lp, int notifylnd, int alive,
- unsigned long when);
-int lnet_add_route(__u32 net, __u32 hops, lnet_nid_t gateway_nid,
- unsigned int priority);
-int lnet_check_routes(void);
-int lnet_del_route(__u32 net, lnet_nid_t gw_nid);
-void lnet_destroy_routes(void);
-int lnet_get_route(int idx, __u32 *net, __u32 *hops,
- lnet_nid_t *gateway, __u32 *alive, __u32 *priority);
-int lnet_get_rtr_pool_cfg(int idx, struct lnet_ioctl_pool_cfg *pool_cfg);
-
-void lnet_router_debugfs_init(void);
-void lnet_router_debugfs_fini(void);
-int lnet_rtrpools_alloc(int im_a_router);
-void lnet_destroy_rtrbuf(struct lnet_rtrbuf *rb, int npages);
-int lnet_rtrpools_adjust(int tiny, int small, int large);
-int lnet_rtrpools_enable(void);
-void lnet_rtrpools_disable(void);
-void lnet_rtrpools_free(int keep_pools);
-struct lnet_remotenet *lnet_find_net_locked(__u32 net);
-int lnet_dyn_add_ni(lnet_pid_t requested_pid,
- struct lnet_ioctl_config_data *conf);
-int lnet_dyn_del_ni(__u32 net);
-int lnet_clear_lazy_portal(struct lnet_ni *ni, int portal, char *reason);
-
-int lnet_islocalnid(lnet_nid_t nid);
-int lnet_islocalnet(__u32 net);
-
-void lnet_msg_attach_md(struct lnet_msg *msg, struct lnet_libmd *md,
- unsigned int offset, unsigned int mlen);
-void lnet_msg_detach_md(struct lnet_msg *msg, int status);
-void lnet_build_unlink_event(struct lnet_libmd *md, struct lnet_event *ev);
-void lnet_build_msg_event(struct lnet_msg *msg, enum lnet_event_kind ev_type);
-void lnet_msg_commit(struct lnet_msg *msg, int cpt);
-void lnet_msg_decommit(struct lnet_msg *msg, int cpt, int status);
-
-void lnet_eq_enqueue_event(struct lnet_eq *eq, struct lnet_event *ev);
-void lnet_prep_send(struct lnet_msg *msg, int type,
- struct lnet_process_id target, unsigned int offset,
- unsigned int len);
-int lnet_send(lnet_nid_t nid, struct lnet_msg *msg, lnet_nid_t rtr_nid);
-void lnet_return_tx_credits_locked(struct lnet_msg *msg);
-void lnet_return_rx_credits_locked(struct lnet_msg *msg);
-void lnet_schedule_blocked_locked(struct lnet_rtrbufpool *rbp);
-void lnet_drop_routed_msgs_locked(struct list_head *list, int cpt);
-
-/* portals functions */
-/* portals attributes */
-static inline int
-lnet_ptl_is_lazy(struct lnet_portal *ptl)
-{
- return !!(ptl->ptl_options & LNET_PTL_LAZY);
-}
-
-static inline int
-lnet_ptl_is_unique(struct lnet_portal *ptl)
-{
- return !!(ptl->ptl_options & LNET_PTL_MATCH_UNIQUE);
-}
-
-static inline int
-lnet_ptl_is_wildcard(struct lnet_portal *ptl)
-{
- return !!(ptl->ptl_options & LNET_PTL_MATCH_WILDCARD);
-}
-
-static inline void
-lnet_ptl_setopt(struct lnet_portal *ptl, int opt)
-{
- ptl->ptl_options |= opt;
-}
-
-static inline void
-lnet_ptl_unsetopt(struct lnet_portal *ptl, int opt)
-{
- ptl->ptl_options &= ~opt;
-}
-
-/* match-table functions */
-struct list_head *lnet_mt_match_head(struct lnet_match_table *mtable,
- struct lnet_process_id id, __u64 mbits);
-struct lnet_match_table *lnet_mt_of_attach(unsigned int index,
- struct lnet_process_id id,
- __u64 mbits, __u64 ignore_bits,
- enum lnet_ins_pos pos);
-int lnet_mt_match_md(struct lnet_match_table *mtable,
- struct lnet_match_info *info, struct lnet_msg *msg);
-
-/* portals match/attach functions */
-void lnet_ptl_attach_md(struct lnet_me *me, struct lnet_libmd *md,
- struct list_head *matches, struct list_head *drops);
-void lnet_ptl_detach_md(struct lnet_me *me, struct lnet_libmd *md);
-int lnet_ptl_match_md(struct lnet_match_info *info, struct lnet_msg *msg);
-
-/* initialized and finalize portals */
-int lnet_portals_create(void);
-void lnet_portals_destroy(void);
-
-/* message functions */
-int lnet_parse(struct lnet_ni *ni, struct lnet_hdr *hdr,
- lnet_nid_t fromnid, void *private, int rdma_req);
-int lnet_parse_local(struct lnet_ni *ni, struct lnet_msg *msg);
-int lnet_parse_forward_locked(struct lnet_ni *ni, struct lnet_msg *msg);
-
-void lnet_recv(struct lnet_ni *ni, void *private, struct lnet_msg *msg,
- int delayed, unsigned int offset, unsigned int mlen,
- unsigned int rlen);
-void lnet_ni_recv(struct lnet_ni *ni, void *private, struct lnet_msg *msg,
- int delayed, unsigned int offset,
- unsigned int mlen, unsigned int rlen);
-
-struct lnet_msg *lnet_create_reply_msg(struct lnet_ni *ni,
- struct lnet_msg *get_msg);
-void lnet_set_reply_msg_len(struct lnet_ni *ni, struct lnet_msg *msg,
- unsigned int len);
-
-void lnet_finalize(struct lnet_ni *ni, struct lnet_msg *msg, int rc);
-
-void lnet_drop_message(struct lnet_ni *ni, int cpt, void *private,
- unsigned int nob);
-void lnet_drop_delayed_msg_list(struct list_head *head, char *reason);
-void lnet_recv_delayed_msg_list(struct list_head *head);
-
-int lnet_msg_container_setup(struct lnet_msg_container *container, int cpt);
-void lnet_msg_container_cleanup(struct lnet_msg_container *container);
-void lnet_msg_containers_destroy(void);
-int lnet_msg_containers_create(void);
-
-char *lnet_msgtyp2str(int type);
-void lnet_print_hdr(struct lnet_hdr *hdr);
-int lnet_fail_nid(lnet_nid_t nid, unsigned int threshold);
-
-/** \addtogroup lnet_fault_simulation @{ */
-
-int lnet_fault_ctl(int cmd, struct libcfs_ioctl_data *data);
-int lnet_fault_init(void);
-void lnet_fault_fini(void);
-
-bool lnet_drop_rule_match(struct lnet_hdr *hdr);
-
-int lnet_delay_rule_add(struct lnet_fault_attr *attr);
-int lnet_delay_rule_del(lnet_nid_t src, lnet_nid_t dst, bool shutdown);
-int lnet_delay_rule_list(int pos, struct lnet_fault_attr *attr,
- struct lnet_fault_stat *stat);
-void lnet_delay_rule_reset(void);
-void lnet_delay_rule_check(void);
-bool lnet_delay_rule_match_locked(struct lnet_hdr *hdr, struct lnet_msg *msg);
-
-/** @} lnet_fault_simulation */
-
-void lnet_counters_get(struct lnet_counters *counters);
-void lnet_counters_reset(void);
-
-unsigned int lnet_iov_nob(unsigned int niov, struct kvec *iov);
-int lnet_extract_iov(int dst_niov, struct kvec *dst,
- int src_niov, const struct kvec *src,
- unsigned int offset, unsigned int len);
-
-unsigned int lnet_kiov_nob(unsigned int niov, struct bio_vec *iov);
-int lnet_extract_kiov(int dst_niov, struct bio_vec *dst,
- int src_niov, const struct bio_vec *src,
- unsigned int offset, unsigned int len);
-
-void lnet_copy_iov2iter(struct iov_iter *to,
- unsigned int nsiov, const struct kvec *siov,
- unsigned int soffset, unsigned int nob);
-void lnet_copy_kiov2iter(struct iov_iter *to,
- unsigned int nkiov, const struct bio_vec *kiov,
- unsigned int kiovoffset, unsigned int nob);
-
-void lnet_me_unlink(struct lnet_me *me);
-
-void lnet_md_unlink(struct lnet_libmd *md);
-void lnet_md_deconstruct(struct lnet_libmd *lmd, struct lnet_md *umd);
-
-void lnet_register_lnd(struct lnet_lnd *lnd);
-void lnet_unregister_lnd(struct lnet_lnd *lnd);
-
-int lnet_connect(struct socket **sockp, lnet_nid_t peer_nid,
- __u32 local_ip, __u32 peer_ip, int peer_port);
-void lnet_connect_console_error(int rc, lnet_nid_t peer_nid,
- __u32 peer_ip, int port);
-int lnet_count_acceptor_nis(void);
-int lnet_acceptor_timeout(void);
-int lnet_acceptor_port(void);
-
-int lnet_count_acceptor_nis(void);
-int lnet_acceptor_port(void);
-
-int lnet_acceptor_start(void);
-void lnet_acceptor_stop(void);
-
-int lnet_ipif_query(char *name, int *up, __u32 *ip, __u32 *mask);
-int lnet_ipif_enumerate(char ***names);
-void lnet_ipif_free_enumeration(char **names, int n);
-int lnet_sock_setbuf(struct socket *socket, int txbufsize, int rxbufsize);
-int lnet_sock_getbuf(struct socket *socket, int *txbufsize, int *rxbufsize);
-int lnet_sock_getaddr(struct socket *socket, bool remote, __u32 *ip, int *port);
-int lnet_sock_write(struct socket *sock, void *buffer, int nob, int timeout);
-int lnet_sock_read(struct socket *sock, void *buffer, int nob, int timeout);
-
-int lnet_sock_listen(struct socket **sockp, __u32 ip, int port, int backlog);
-int lnet_sock_accept(struct socket **newsockp, struct socket *sock);
-int lnet_sock_connect(struct socket **sockp, int *fatal,
- __u32 local_ip, int local_port,
- __u32 peer_ip, int peer_port);
-void libcfs_sock_release(struct socket *sock);
-
-int lnet_peers_start_down(void);
-int lnet_peer_buffer_credits(struct lnet_ni *ni);
-
-int lnet_router_checker_start(void);
-void lnet_router_checker_stop(void);
-void lnet_router_ni_update_locked(struct lnet_peer *gw, __u32 net);
-void lnet_swap_pinginfo(struct lnet_ping_info *info);
-
-int lnet_parse_ip2nets(char **networksp, char *ip2nets);
-int lnet_parse_routes(char *route_str, int *im_a_router);
-int lnet_parse_networks(struct list_head *nilist, char *networks);
-int lnet_net_unique(__u32 net, struct list_head *nilist);
-
-int lnet_nid2peer_locked(struct lnet_peer **lpp, lnet_nid_t nid, int cpt);
-struct lnet_peer *lnet_find_peer_locked(struct lnet_peer_table *ptable,
- lnet_nid_t nid);
-void lnet_peer_tables_cleanup(struct lnet_ni *ni);
-void lnet_peer_tables_destroy(void);
-int lnet_peer_tables_create(void);
-void lnet_debug_peer(lnet_nid_t nid);
-int lnet_get_peer_info(__u32 peer_index, __u64 *nid,
- char alivness[LNET_MAX_STR_LEN],
- __u32 *cpt_iter, __u32 *refcount,
- __u32 *ni_peer_tx_credits, __u32 *peer_tx_credits,
- __u32 *peer_rtr_credits, __u32 *peer_min_rtr_credtis,
- __u32 *peer_tx_qnob);
-
-static inline void
-lnet_peer_set_alive(struct lnet_peer *lp)
-{
- lp->lp_last_query = jiffies;
- lp->lp_last_alive = jiffies;
- if (!lp->lp_alive)
- lnet_notify_locked(lp, 0, 1, lp->lp_last_alive);
-}
-
-#endif
diff --git a/drivers/staging/lustre/include/linux/lnet/lib-types.h b/drivers/staging/lustre/include/linux/lnet/lib-types.h
deleted file mode 100644
index cfe8ee424e94..000000000000
--- a/drivers/staging/lustre/include/linux/lnet/lib-types.h
+++ /dev/null
@@ -1,666 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Seagate, Inc.
- *
- * lnet/include/lnet/lib-types.h
- */
-
-#ifndef __LNET_LIB_TYPES_H__
-#define __LNET_LIB_TYPES_H__
-
-#include <linux/kthread.h>
-#include <linux/uio.h>
-#include <linux/types.h>
-#include <linux/completion.h>
-
-#include <uapi/linux/lnet/lnet-types.h>
-#include <uapi/linux/lnet/lnetctl.h>
-
-/* Max payload size */
-#define LNET_MAX_PAYLOAD CONFIG_LNET_MAX_PAYLOAD
-#if (LNET_MAX_PAYLOAD < LNET_MTU)
-# error "LNET_MAX_PAYLOAD too small - error in configure --with-max-payload-mb"
-#elif (LNET_MAX_PAYLOAD > (PAGE_SIZE * LNET_MAX_IOV))
-# error "LNET_MAX_PAYLOAD too large - error in configure --with-max-payload-mb"
-#endif
-
-/* forward refs */
-struct lnet_libmd;
-
-struct lnet_msg {
- struct list_head msg_activelist;
- struct list_head msg_list; /* Q for credits/MD */
-
- struct lnet_process_id msg_target;
- /* where is it from, it's only for building event */
- lnet_nid_t msg_from;
- __u32 msg_type;
-
- /* committed for sending */
- unsigned int msg_tx_committed:1;
- /* CPT # this message committed for sending */
- unsigned int msg_tx_cpt:15;
- /* committed for receiving */
- unsigned int msg_rx_committed:1;
- /* CPT # this message committed for receiving */
- unsigned int msg_rx_cpt:15;
- /* queued for tx credit */
- unsigned int msg_tx_delayed:1;
- /* queued for RX buffer */
- unsigned int msg_rx_delayed:1;
- /* ready for pending on RX delay list */
- unsigned int msg_rx_ready_delay:1;
-
- unsigned int msg_vmflush:1; /* VM trying to free memory */
- unsigned int msg_target_is_router:1; /* sending to a router */
- unsigned int msg_routing:1; /* being forwarded */
- unsigned int msg_ack:1; /* ack on finalize (PUT) */
- unsigned int msg_sending:1; /* outgoing message */
- unsigned int msg_receiving:1; /* being received */
- unsigned int msg_txcredit:1; /* taken an NI send credit */
- unsigned int msg_peertxcredit:1; /* taken a peer send credit */
- unsigned int msg_rtrcredit:1; /* taken a global router credit */
- unsigned int msg_peerrtrcredit:1; /* taken a peer router credit */
- unsigned int msg_onactivelist:1; /* on the activelist */
- unsigned int msg_rdma_get:1;
-
- struct lnet_peer *msg_txpeer; /* peer I'm sending to */
- struct lnet_peer *msg_rxpeer; /* peer I received from */
-
- void *msg_private;
- struct lnet_libmd *msg_md;
-
- unsigned int msg_len;
- unsigned int msg_wanted;
- unsigned int msg_offset;
- unsigned int msg_niov;
- struct kvec *msg_iov;
- struct bio_vec *msg_kiov;
-
- struct lnet_event msg_ev;
- struct lnet_hdr msg_hdr;
-};
-
-struct lnet_libhandle {
- struct list_head lh_hash_chain;
- __u64 lh_cookie;
-};
-
-#define lh_entry(ptr, type, member) \
- ((type *)((char *)(ptr) - (char *)(&((type *)0)->member)))
-
-struct lnet_eq {
- struct list_head eq_list;
- struct lnet_libhandle eq_lh;
- unsigned long eq_enq_seq;
- unsigned long eq_deq_seq;
- unsigned int eq_size;
- lnet_eq_handler_t eq_callback;
- struct lnet_event *eq_events;
- int **eq_refs; /* percpt refcount for EQ */
-};
-
-struct lnet_me {
- struct list_head me_list;
- struct lnet_libhandle me_lh;
- struct lnet_process_id me_match_id;
- unsigned int me_portal;
- unsigned int me_pos; /* hash offset in mt_hash */
- __u64 me_match_bits;
- __u64 me_ignore_bits;
- enum lnet_unlink me_unlink;
- struct lnet_libmd *me_md;
-};
-
-struct lnet_libmd {
- struct list_head md_list;
- struct lnet_libhandle md_lh;
- struct lnet_me *md_me;
- char *md_start;
- unsigned int md_offset;
- unsigned int md_length;
- unsigned int md_max_size;
- int md_threshold;
- int md_refcount;
- unsigned int md_options;
- unsigned int md_flags;
- void *md_user_ptr;
- struct lnet_eq *md_eq;
- unsigned int md_niov; /* # frags */
- union {
- struct kvec iov[LNET_MAX_IOV];
- struct bio_vec kiov[LNET_MAX_IOV];
- } md_iov;
-};
-
-#define LNET_MD_FLAG_ZOMBIE BIT(0)
-#define LNET_MD_FLAG_AUTO_UNLINK BIT(1)
-#define LNET_MD_FLAG_ABORTED BIT(2)
-
-struct lnet_test_peer {
- /* info about peers we are trying to fail */
- struct list_head tp_list; /* ln_test_peers */
- lnet_nid_t tp_nid; /* matching nid */
- unsigned int tp_threshold; /* # failures to simulate */
-};
-
-#define LNET_COOKIE_TYPE_MD 1
-#define LNET_COOKIE_TYPE_ME 2
-#define LNET_COOKIE_TYPE_EQ 3
-#define LNET_COOKIE_TYPE_BITS 2
-#define LNET_COOKIE_MASK ((1ULL << LNET_COOKIE_TYPE_BITS) - 1ULL)
-
-struct lnet_ni; /* forward ref */
-
-struct lnet_lnd {
- /* fields managed by portals */
- struct list_head lnd_list; /* stash in the LND table */
- int lnd_refcount; /* # active instances */
-
- /* fields initialised by the LND */
- __u32 lnd_type;
-
- int (*lnd_startup)(struct lnet_ni *ni);
- void (*lnd_shutdown)(struct lnet_ni *ni);
- int (*lnd_ctl)(struct lnet_ni *ni, unsigned int cmd, void *arg);
-
- /*
- * In data movement APIs below, payload buffers are described as a set
- * of 'niov' fragments which are...
- * EITHER
- * in virtual memory (struct iovec *iov != NULL)
- * OR
- * in pages (kernel only: plt_kiov_t *kiov != NULL).
- * The LND may NOT overwrite these fragment descriptors.
- * An 'offset' and may specify a byte offset within the set of
- * fragments to start from
- */
-
- /*
- * Start sending a preformatted message. 'private' is NULL for PUT and
- * GET messages; otherwise this is a response to an incoming message
- * and 'private' is the 'private' passed to lnet_parse(). Return
- * non-zero for immediate failure, otherwise complete later with
- * lnet_finalize()
- */
- int (*lnd_send)(struct lnet_ni *ni, void *private,
- struct lnet_msg *msg);
-
- /*
- * Start receiving 'mlen' bytes of payload data, skipping the following
- * 'rlen' - 'mlen' bytes. 'private' is the 'private' passed to
- * lnet_parse(). Return non-zero for immediate failure, otherwise
- * complete later with lnet_finalize(). This also gives back a receive
- * credit if the LND does flow control.
- */
- int (*lnd_recv)(struct lnet_ni *ni, void *private, struct lnet_msg *msg,
- int delayed, struct iov_iter *to, unsigned int rlen);
-
- /*
- * lnet_parse() has had to delay processing of this message
- * (e.g. waiting for a forwarding buffer or send credits). Give the
- * LND a chance to free urgently needed resources. If called, return 0
- * for success and do NOT give back a receive credit; that has to wait
- * until lnd_recv() gets called. On failure return < 0 and
- * release resources; lnd_recv() will not be called.
- */
- int (*lnd_eager_recv)(struct lnet_ni *ni, void *private,
- struct lnet_msg *msg, void **new_privatep);
-
- /* notification of peer health */
- void (*lnd_notify)(struct lnet_ni *ni, lnet_nid_t peer, int alive);
-
- /* query of peer aliveness */
- void (*lnd_query)(struct lnet_ni *ni, lnet_nid_t peer,
- unsigned long *when);
-
- /* accept a new connection */
- int (*lnd_accept)(struct lnet_ni *ni, struct socket *sock);
-};
-
-struct lnet_tx_queue {
- int tq_credits; /* # tx credits free */
- int tq_credits_min; /* lowest it's been */
- int tq_credits_max; /* total # tx credits */
- struct list_head tq_delayed; /* delayed TXs */
-};
-
-struct lnet_ni {
- spinlock_t ni_lock;
- struct list_head ni_list; /* chain on ln_nis */
- struct list_head ni_cptlist; /* chain on ln_nis_cpt */
- int ni_maxtxcredits; /* # tx credits */
- /* # per-peer send credits */
- int ni_peertxcredits;
- /* # per-peer router buffer credits */
- int ni_peerrtrcredits;
- /* seconds to consider peer dead */
- int ni_peertimeout;
- int ni_ncpts; /* number of CPTs */
- __u32 *ni_cpts; /* bond NI on some CPTs */
- lnet_nid_t ni_nid; /* interface's NID */
- void *ni_data; /* instance-specific data */
- struct lnet_lnd *ni_lnd; /* procedural interface */
- struct lnet_tx_queue **ni_tx_queues; /* percpt TX queues */
- int **ni_refs; /* percpt reference count */
- time64_t ni_last_alive;/* when I was last alive */
- struct lnet_ni_status *ni_status; /* my health status */
- /* per NI LND tunables */
- struct lnet_ioctl_config_lnd_tunables *ni_lnd_tunables;
- /* equivalent interfaces to use */
- char *ni_interfaces[LNET_MAX_INTERFACES];
- /* original net namespace */
- struct net *ni_net_ns;
-};
-
-#define LNET_PROTO_PING_MATCHBITS 0x8000000000000000LL
-
-/*
- * NB: value of these features equal to LNET_PROTO_PING_VERSION_x
- * of old LNet, so there shouldn't be any compatibility issue
- */
-#define LNET_PING_FEAT_INVAL (0) /* no feature */
-#define LNET_PING_FEAT_BASE BIT(0) /* just a ping */
-#define LNET_PING_FEAT_NI_STATUS BIT(1) /* return NI status */
-#define LNET_PING_FEAT_RTE_DISABLED BIT(2) /* Routing enabled */
-
-#define LNET_PING_FEAT_MASK (LNET_PING_FEAT_BASE | \
- LNET_PING_FEAT_NI_STATUS)
-
-/* router checker data, per router */
-#define LNET_MAX_RTR_NIS 16
-#define LNET_PINGINFO_SIZE offsetof(struct lnet_ping_info, pi_ni[LNET_MAX_RTR_NIS])
-struct lnet_rc_data {
- /* chain on the_lnet.ln_zombie_rcd or ln_deathrow_rcd */
- struct list_head rcd_list;
- struct lnet_handle_md rcd_mdh; /* ping buffer MD */
- struct lnet_peer *rcd_gateway; /* reference to gateway */
- struct lnet_ping_info *rcd_pinginfo; /* ping buffer */
-};
-
-struct lnet_peer {
- struct list_head lp_hashlist; /* chain on peer hash */
- struct list_head lp_txq; /* messages blocking for
- * tx credits
- */
- struct list_head lp_rtrq; /* messages blocking for
- * router credits
- */
- struct list_head lp_rtr_list; /* chain on router list */
- int lp_txcredits; /* # tx credits available */
- int lp_mintxcredits; /* low water mark */
- int lp_rtrcredits; /* # router credits */
- int lp_minrtrcredits; /* low water mark */
- unsigned int lp_alive:1; /* alive/dead? */
- unsigned int lp_notify:1; /* notification outstanding? */
- unsigned int lp_notifylnd:1;/* outstanding notification
- * for LND?
- */
- unsigned int lp_notifying:1; /* some thread is handling
- * notification
- */
- unsigned int lp_ping_notsent;/* SEND event outstanding
- * from ping
- */
- int lp_alive_count; /* # times router went
- * dead<->alive
- */
- long lp_txqnob; /* ytes queued for sending */
- unsigned long lp_timestamp; /* time of last aliveness
- * news
- */
- unsigned long lp_ping_timestamp;/* time of last ping
- * attempt
- */
- unsigned long lp_ping_deadline; /* != 0 if ping reply
- * expected
- */
- unsigned long lp_last_alive; /* when I was last alive */
- unsigned long lp_last_query; /* when lp_ni was queried
- * last time
- */
- struct lnet_ni *lp_ni; /* interface peer is on */
- lnet_nid_t lp_nid; /* peer's NID */
- int lp_refcount; /* # refs */
- int lp_cpt; /* CPT this peer attached on */
- /* # refs from lnet_route::lr_gateway */
- int lp_rtr_refcount;
- /* returned RC ping features */
- unsigned int lp_ping_feats;
- struct list_head lp_routes; /* routers on this peer */
- struct lnet_rc_data *lp_rcd; /* router checker state */
-};
-
-/* peer hash size */
-#define LNET_PEER_HASH_BITS 9
-#define LNET_PEER_HASH_SIZE (1 << LNET_PEER_HASH_BITS)
-
-/* peer hash table */
-struct lnet_peer_table {
- int pt_version; /* /proc validity stamp */
- int pt_number; /* # peers extant */
- /* # zombies to go to deathrow (and not there yet) */
- int pt_zombies;
- struct list_head pt_deathrow; /* zombie peers */
- struct list_head *pt_hash; /* NID->peer hash */
-};
-
-/*
- * peer aliveness is enabled only on routers for peers in a network where the
- * lnet_ni::ni_peertimeout has been set to a positive value
- */
-#define lnet_peer_aliveness_enabled(lp) (the_lnet.ln_routing && \
- (lp)->lp_ni->ni_peertimeout > 0)
-
-struct lnet_route {
- struct list_head lr_list; /* chain on net */
- struct list_head lr_gwlist; /* chain on gateway */
- struct lnet_peer *lr_gateway; /* router node */
- __u32 lr_net; /* remote network number */
- int lr_seq; /* sequence for round-robin */
- unsigned int lr_downis; /* number of down NIs */
- __u32 lr_hops; /* how far I am */
- unsigned int lr_priority; /* route priority */
-};
-
-#define LNET_REMOTE_NETS_HASH_DEFAULT (1U << 7)
-#define LNET_REMOTE_NETS_HASH_MAX (1U << 16)
-#define LNET_REMOTE_NETS_HASH_SIZE (1 << the_lnet.ln_remote_nets_hbits)
-
-struct lnet_remotenet {
- struct list_head lrn_list; /* chain on
- * ln_remote_nets_hash
- */
- struct list_head lrn_routes; /* routes to me */
- __u32 lrn_net; /* my net number */
-};
-
-/** lnet message has credit and can be submitted to lnd for send/receive */
-#define LNET_CREDIT_OK 0
-/** lnet message is waiting for credit */
-#define LNET_CREDIT_WAIT 1
-
-struct lnet_rtrbufpool {
- struct list_head rbp_bufs; /* my free buffer pool */
- struct list_head rbp_msgs; /* messages blocking
- * for a buffer
- */
- int rbp_npages; /* # pages in each buffer */
- /* requested number of buffers */
- int rbp_req_nbuffers;
- /* # buffers actually allocated */
- int rbp_nbuffers;
- int rbp_credits; /* # free buffers
- * blocked messages
- */
- int rbp_mincredits; /* low water mark */
-};
-
-struct lnet_rtrbuf {
- struct list_head rb_list; /* chain on rbp_bufs */
- struct lnet_rtrbufpool *rb_pool; /* owning pool */
- struct bio_vec rb_kiov[0]; /* the buffer space */
-};
-
-#define LNET_PEER_HASHSIZE 503 /* prime! */
-
-#define LNET_TINY_BUF_IDX 0
-#define LNET_SMALL_BUF_IDX 1
-#define LNET_LARGE_BUF_IDX 2
-
-/* # different router buffer pools */
-#define LNET_NRBPOOLS (LNET_LARGE_BUF_IDX + 1)
-
-enum lnet_match_flags {
- /* Didn't match anything */
- LNET_MATCHMD_NONE = BIT(0),
- /* Matched OK */
- LNET_MATCHMD_OK = BIT(1),
- /* Must be discarded */
- LNET_MATCHMD_DROP = BIT(2),
- /* match and buffer is exhausted */
- LNET_MATCHMD_EXHAUSTED = BIT(3),
- /* match or drop */
- LNET_MATCHMD_FINISH = (LNET_MATCHMD_OK | LNET_MATCHMD_DROP),
-};
-
-/* Options for lnet_portal::ptl_options */
-#define LNET_PTL_LAZY BIT(0)
-#define LNET_PTL_MATCH_UNIQUE BIT(1) /* unique match, for RDMA */
-#define LNET_PTL_MATCH_WILDCARD BIT(2) /* wildcard match, request portal */
-
-/* parameter for matching operations (GET, PUT) */
-struct lnet_match_info {
- __u64 mi_mbits;
- struct lnet_process_id mi_id;
- unsigned int mi_opc;
- unsigned int mi_portal;
- unsigned int mi_rlength;
- unsigned int mi_roffset;
-};
-
-/* ME hash of RDMA portal */
-#define LNET_MT_HASH_BITS 8
-#define LNET_MT_HASH_SIZE (1 << LNET_MT_HASH_BITS)
-#define LNET_MT_HASH_MASK (LNET_MT_HASH_SIZE - 1)
-/*
- * we allocate (LNET_MT_HASH_SIZE + 1) entries for lnet_match_table::mt_hash,
- * the last entry is reserved for MEs with ignore-bits
- */
-#define LNET_MT_HASH_IGNORE LNET_MT_HASH_SIZE
-/*
- * __u64 has 2^6 bits, so need 2^(LNET_MT_HASH_BITS - LNET_MT_BITS_U64) which
- * is 4 __u64s as bit-map, and add an extra __u64 (only use one bit) for the
- * ME-list with ignore-bits, which is mtable::mt_hash[LNET_MT_HASH_IGNORE]
- */
-#define LNET_MT_BITS_U64 6 /* 2^6 bits */
-#define LNET_MT_EXHAUSTED_BITS (LNET_MT_HASH_BITS - LNET_MT_BITS_U64)
-#define LNET_MT_EXHAUSTED_BMAP ((1 << LNET_MT_EXHAUSTED_BITS) + 1)
-
-/* portal match table */
-struct lnet_match_table {
- /* reserved for upcoming patches, CPU partition ID */
- unsigned int mt_cpt;
- unsigned int mt_portal; /* portal index */
- /*
- * match table is set as "enabled" if there's non-exhausted MD
- * attached on mt_mhash, it's only valid for wildcard portal
- */
- unsigned int mt_enabled;
- /* bitmap to flag whether MEs on mt_hash are exhausted or not */
- __u64 mt_exhausted[LNET_MT_EXHAUSTED_BMAP];
- struct list_head *mt_mhash; /* matching hash */
-};
-
-/* these are only useful for wildcard portal */
-/* Turn off message rotor for wildcard portals */
-#define LNET_PTL_ROTOR_OFF 0
-/* round-robin dispatch all PUT messages for wildcard portals */
-#define LNET_PTL_ROTOR_ON 1
-/* round-robin dispatch routed PUT message for wildcard portals */
-#define LNET_PTL_ROTOR_RR_RT 2
-/* dispatch routed PUT message by hashing source NID for wildcard portals */
-#define LNET_PTL_ROTOR_HASH_RT 3
-
-struct lnet_portal {
- spinlock_t ptl_lock;
- unsigned int ptl_index; /* portal ID, reserved */
- /* flags on this portal: lazy, unique... */
- unsigned int ptl_options;
- /* list of messages which are stealing buffer */
- struct list_head ptl_msg_stealing;
- /* messages blocking for MD */
- struct list_head ptl_msg_delayed;
- /* Match table for each CPT */
- struct lnet_match_table **ptl_mtables;
- /* spread rotor of incoming "PUT" */
- unsigned int ptl_rotor;
- /* # active entries for this portal */
- int ptl_mt_nmaps;
- /* array of active entries' cpu-partition-id */
- int ptl_mt_maps[0];
-};
-
-#define LNET_LH_HASH_BITS 12
-#define LNET_LH_HASH_SIZE (1ULL << LNET_LH_HASH_BITS)
-#define LNET_LH_HASH_MASK (LNET_LH_HASH_SIZE - 1)
-
-/* resource container (ME, MD, EQ) */
-struct lnet_res_container {
- unsigned int rec_type; /* container type */
- __u64 rec_lh_cookie; /* cookie generator */
- struct list_head rec_active; /* active resource list */
- struct list_head *rec_lh_hash; /* handle hash */
-};
-
-/* message container */
-struct lnet_msg_container {
- int msc_init; /* initialized or not */
- /* max # threads finalizing */
- int msc_nfinalizers;
- /* msgs waiting to complete finalizing */
- struct list_head msc_finalizing;
- struct list_head msc_active; /* active message list */
- /* threads doing finalization */
- void **msc_finalizers;
-};
-
-/* Router Checker states */
-#define LNET_RC_STATE_SHUTDOWN 0 /* not started */
-#define LNET_RC_STATE_RUNNING 1 /* started up OK */
-#define LNET_RC_STATE_STOPPING 2 /* telling thread to stop */
-
-struct lnet {
- /* CPU partition table of LNet */
- struct cfs_cpt_table *ln_cpt_table;
- /* number of CPTs in ln_cpt_table */
- unsigned int ln_cpt_number;
- unsigned int ln_cpt_bits;
-
- /* protect LNet resources (ME/MD/EQ) */
- struct cfs_percpt_lock *ln_res_lock;
- /* # portals */
- int ln_nportals;
- /* the vector of portals */
- struct lnet_portal **ln_portals;
- /* percpt ME containers */
- struct lnet_res_container **ln_me_containers;
- /* percpt MD container */
- struct lnet_res_container **ln_md_containers;
-
- /* Event Queue container */
- struct lnet_res_container ln_eq_container;
- wait_queue_head_t ln_eq_waitq;
- spinlock_t ln_eq_wait_lock;
- unsigned int ln_remote_nets_hbits;
-
- /* protect NI, peer table, credits, routers, rtrbuf... */
- struct cfs_percpt_lock *ln_net_lock;
- /* percpt message containers for active/finalizing/freed message */
- struct lnet_msg_container **ln_msg_containers;
- struct lnet_counters **ln_counters;
- struct lnet_peer_table **ln_peer_tables;
- /* failure simulation */
- struct list_head ln_test_peers;
- struct list_head ln_drop_rules;
- struct list_head ln_delay_rules;
-
- struct list_head ln_nis; /* LND instances */
- /* NIs bond on specific CPT(s) */
- struct list_head ln_nis_cpt;
- /* dying LND instances */
- struct list_head ln_nis_zombie;
- struct lnet_ni *ln_loni; /* the loopback NI */
-
- /* remote networks with routes to them */
- struct list_head *ln_remote_nets_hash;
- /* validity stamp */
- __u64 ln_remote_nets_version;
- /* list of all known routers */
- struct list_head ln_routers;
- /* validity stamp */
- __u64 ln_routers_version;
- /* percpt router buffer pools */
- struct lnet_rtrbufpool **ln_rtrpools;
-
- struct lnet_handle_md ln_ping_target_md;
- struct lnet_handle_eq ln_ping_target_eq;
- struct lnet_ping_info *ln_ping_info;
-
- /* router checker startup/shutdown state */
- int ln_rc_state;
- /* router checker's event queue */
- struct lnet_handle_eq ln_rc_eqh;
- /* rcd still pending on net */
- struct list_head ln_rcd_deathrow;
- /* rcd ready for free */
- struct list_head ln_rcd_zombie;
- /* serialise startup/shutdown */
- struct completion ln_rc_signal;
-
- struct mutex ln_api_mutex;
- struct mutex ln_lnd_mutex;
- struct mutex ln_delay_mutex;
- /* Have I called LNetNIInit myself? */
- int ln_niinit_self;
- /* LNetNIInit/LNetNIFini counter */
- int ln_refcount;
- /* shutdown in progress */
- int ln_shutdown;
-
- int ln_routing; /* am I a router? */
- lnet_pid_t ln_pid; /* requested pid */
- /* uniquely identifies this ni in this epoch */
- __u64 ln_interface_cookie;
- /* registered LNDs */
- struct list_head ln_lnds;
-
- /* test protocol compatibility flags */
- int ln_testprotocompat;
-
- /*
- * 0 - load the NIs from the mod params
- * 1 - do not load the NIs from the mod params
- * Reverse logic to ensure that other calls to LNetNIInit
- * need no change
- */
- bool ln_nis_from_mod_params;
-
- /*
- * waitq for router checker. As long as there are no routes in
- * the list, the router checker will sleep on this queue. when
- * routes are added the thread will wake up
- */
- wait_queue_head_t ln_rc_waitq;
-
-};
-
-#endif
diff --git a/drivers/staging/lustre/include/linux/lnet/socklnd.h b/drivers/staging/lustre/include/linux/lnet/socklnd.h
deleted file mode 100644
index 6bd1bca190a3..000000000000
--- a/drivers/staging/lustre/include/linux/lnet/socklnd.h
+++ /dev/null
@@ -1,87 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012 - 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Seagate, Inc.
- *
- * lnet/include/lnet/socklnd.h
- */
-#ifndef __LNET_LNET_SOCKLND_H__
-#define __LNET_LNET_SOCKLND_H__
-
-#include <uapi/linux/lnet/lnet-types.h>
-#include <uapi/linux/lnet/socklnd.h>
-
-struct ksock_hello_msg {
- __u32 kshm_magic; /* magic number of socklnd message */
- __u32 kshm_version; /* version of socklnd message */
- lnet_nid_t kshm_src_nid; /* sender's nid */
- lnet_nid_t kshm_dst_nid; /* destination nid */
- lnet_pid_t kshm_src_pid; /* sender's pid */
- lnet_pid_t kshm_dst_pid; /* destination pid */
- __u64 kshm_src_incarnation; /* sender's incarnation */
- __u64 kshm_dst_incarnation; /* destination's incarnation */
- __u32 kshm_ctype; /* connection type */
- __u32 kshm_nips; /* # IP addrs */
- __u32 kshm_ips[0]; /* IP addrs */
-} WIRE_ATTR;
-
-struct ksock_lnet_msg {
- struct lnet_hdr ksnm_hdr; /* lnet hdr */
-
- /*
- * ksnm_payload is removed because of winnt compiler's limitation:
- * zero-sized array can only be placed at the tail of [nested]
- * structure definitions. lnet payload will be stored just after
- * the body of structure ksock_lnet_msg_t
- */
-} WIRE_ATTR;
-
-struct ksock_msg {
- __u32 ksm_type; /* type of socklnd message */
- __u32 ksm_csum; /* checksum if != 0 */
- __u64 ksm_zc_cookies[2]; /* Zero-Copy request/ACK cookie */
- union {
- struct ksock_lnet_msg lnetmsg; /* lnet message, it's empty if
- * it's NOOP
- */
- } WIRE_ATTR ksm_u;
-} WIRE_ATTR;
-
-#define KSOCK_MSG_NOOP 0xC0 /* ksm_u empty */
-#define KSOCK_MSG_LNET 0xC1 /* lnet msg */
-
-/*
- * We need to know this number to parse hello msg from ksocklnd in
- * other LND (usocklnd, for example)
- */
-#define KSOCK_PROTO_V2 2
-#define KSOCK_PROTO_V3 3
-
-#endif
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_debug.h b/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_debug.h
deleted file mode 100644
index c4d9472b374f..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_debug.h
+++ /dev/null
@@ -1,149 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, 2014, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_debug.h
- *
- * Debug messages and assertions
- *
- */
-
-#ifndef __UAPI_LIBCFS_DEBUG_H__
-#define __UAPI_LIBCFS_DEBUG_H__
-
-/**
- * Format for debug message headers
- */
-struct ptldebug_header {
- __u32 ph_len;
- __u32 ph_flags;
- __u32 ph_subsys;
- __u32 ph_mask;
- __u16 ph_cpu_id;
- __u16 ph_type;
- /* time_t overflow in 2106 */
- __u32 ph_sec;
- __u64 ph_usec;
- __u32 ph_stack;
- __u32 ph_pid;
- __u32 ph_extern_pid;
- __u32 ph_line_num;
-} __attribute__((packed));
-
-#define PH_FLAG_FIRST_RECORD 1
-
-/* Debugging subsystems (32 bits, non-overlapping) */
-#define S_UNDEFINED 0x00000001
-#define S_MDC 0x00000002
-#define S_MDS 0x00000004
-#define S_OSC 0x00000008
-#define S_OST 0x00000010
-#define S_CLASS 0x00000020
-#define S_LOG 0x00000040
-#define S_LLITE 0x00000080
-#define S_RPC 0x00000100
-#define S_MGMT 0x00000200
-#define S_LNET 0x00000400
-#define S_LND 0x00000800 /* ALL LNDs */
-#define S_PINGER 0x00001000
-#define S_FILTER 0x00002000
-#define S_LIBCFS 0x00004000
-#define S_ECHO 0x00008000
-#define S_LDLM 0x00010000
-#define S_LOV 0x00020000
-#define S_LQUOTA 0x00040000
-#define S_OSD 0x00080000
-#define S_LFSCK 0x00100000
-#define S_SNAPSHOT 0x00200000
-/* unused */
-#define S_LMV 0x00800000 /* b_new_cmd */
-/* unused */
-#define S_SEC 0x02000000 /* upcall cache */
-#define S_GSS 0x04000000 /* b_new_cmd */
-/* unused */
-#define S_MGC 0x10000000
-#define S_MGS 0x20000000
-#define S_FID 0x40000000 /* b_new_cmd */
-#define S_FLD 0x80000000 /* b_new_cmd */
-
-#define LIBCFS_DEBUG_SUBSYS_NAMES { \
- "undefined", "mdc", "mds", "osc", "ost", "class", "log", \
- "llite", "rpc", "mgmt", "lnet", "lnd", "pinger", "filter", \
- "libcfs", "echo", "ldlm", "lov", "lquota", "osd", "lfsck", \
- "snapshot", "", "lmv", "", "sec", "gss", "", "mgc", "mgs", \
- "fid", "fld", NULL }
-
-/* Debugging masks (32 bits, non-overlapping) */
-#define D_TRACE 0x00000001 /* ENTRY/EXIT markers */
-#define D_INODE 0x00000002
-#define D_SUPER 0x00000004
-#define D_EXT2 0x00000008 /* anything from ext2_debug */
-#define D_MALLOC 0x00000010 /* print malloc, free information */
-#define D_CACHE 0x00000020 /* cache-related items */
-#define D_INFO 0x00000040 /* general information */
-#define D_IOCTL 0x00000080 /* ioctl related information */
-#define D_NETERROR 0x00000100 /* network errors */
-#define D_NET 0x00000200 /* network communications */
-#define D_WARNING 0x00000400 /* CWARN(...) == CDEBUG (D_WARNING, ...) */
-#define D_BUFFS 0x00000800
-#define D_OTHER 0x00001000
-#define D_DENTRY 0x00002000
-#define D_NETTRACE 0x00004000
-#define D_PAGE 0x00008000 /* bulk page handling */
-#define D_DLMTRACE 0x00010000
-#define D_ERROR 0x00020000 /* CERROR(...) == CDEBUG (D_ERROR, ...) */
-#define D_EMERG 0x00040000 /* CEMERG(...) == CDEBUG (D_EMERG, ...) */
-#define D_HA 0x00080000 /* recovery and failover */
-#define D_RPCTRACE 0x00100000 /* for distributed debugging */
-#define D_VFSTRACE 0x00200000
-#define D_READA 0x00400000 /* read-ahead */
-#define D_MMAP 0x00800000
-#define D_CONFIG 0x01000000
-#define D_CONSOLE 0x02000000
-#define D_QUOTA 0x04000000
-#define D_SEC 0x08000000
-#define D_LFSCK 0x10000000 /* For both OI scrub and LFSCK */
-#define D_HSM 0x20000000
-#define D_SNAPSHOT 0x40000000 /* snapshot */
-#define D_LAYOUT 0x80000000
-
-#define LIBCFS_DEBUG_MASKS_NAMES { \
- "trace", "inode", "super", "ext2", "malloc", "cache", "info", \
- "ioctl", "neterror", "net", "warning", "buffs", "other", \
- "dentry", "nettrace", "page", "dlmtrace", "error", "emerg", \
- "ha", "rpctrace", "vfstrace", "reada", "mmap", "config", \
- "console", "quota", "sec", "lfsck", "hsm", "snapshot", "layout",\
- NULL }
-
-#define D_CANTMASK (D_ERROR | D_EMERG | D_WARNING | D_CONSOLE)
-
-#define LIBCFS_DEBUG_FILE_PATH_DEFAULT "/tmp/lustre-log"
-
-#endif /* __UAPI_LIBCFS_DEBUG_H__ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h b/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h
deleted file mode 100644
index cce6b58e3682..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/libcfs_ioctl.h
+++ /dev/null
@@ -1,141 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * libcfs/include/libcfs/libcfs_ioctl.h
- *
- * Low-level ioctl data structures. Kernel ioctl functions declared here,
- * and user space functions are in libcfs/util/ioctl.h.
- *
- */
-
-#ifndef __LIBCFS_IOCTL_H__
-#define __LIBCFS_IOCTL_H__
-
-#include <linux/types.h>
-#include <linux/ioctl.h>
-
-#define LIBCFS_IOCTL_VERSION 0x0001000a
-#define LIBCFS_IOCTL_VERSION2 0x0001000b
-
-struct libcfs_ioctl_hdr {
- __u32 ioc_len;
- __u32 ioc_version;
-};
-
-/** max size to copy from userspace */
-#define LIBCFS_IOC_DATA_MAX (128 * 1024)
-
-struct libcfs_ioctl_data {
- struct libcfs_ioctl_hdr ioc_hdr;
-
- __u64 ioc_nid;
- __u64 ioc_u64[1];
-
- __u32 ioc_flags;
- __u32 ioc_count;
- __u32 ioc_net;
- __u32 ioc_u32[7];
-
- __u32 ioc_inllen1;
- char *ioc_inlbuf1;
- __u32 ioc_inllen2;
- char *ioc_inlbuf2;
-
- __u32 ioc_plen1; /* buffers in userspace */
- void __user *ioc_pbuf1;
- __u32 ioc_plen2; /* buffers in userspace */
- void __user *ioc_pbuf2;
-
- char ioc_bulk[0];
-};
-
-struct libcfs_debug_ioctl_data {
- struct libcfs_ioctl_hdr hdr;
- unsigned int subs;
- unsigned int debug;
-};
-
-/* 'f' ioctls are defined in lustre_ioctl.h and lustre_user.h except for: */
-#define LIBCFS_IOC_DEBUG_MASK _IOWR('f', 250, long)
-#define IOCTL_LIBCFS_TYPE long
-
-#define IOC_LIBCFS_TYPE ('e')
-#define IOC_LIBCFS_MIN_NR 30
-/* libcfs ioctls */
-/* IOC_LIBCFS_PANIC obsolete in 2.8.0, was _IOWR('e', 30, IOCTL_LIBCFS_TYPE) */
-#define IOC_LIBCFS_CLEAR_DEBUG _IOWR('e', 31, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_MARK_DEBUG _IOWR('e', 32, IOCTL_LIBCFS_TYPE)
-/* IOC_LIBCFS_MEMHOG obsolete in 2.8.0, was _IOWR('e', 36, IOCTL_LIBCFS_TYPE) */
-/* lnet ioctls */
-#define IOC_LIBCFS_GET_NI _IOWR('e', 50, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_FAIL_NID _IOWR('e', 51, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_NOTIFY_ROUTER _IOWR('e', 55, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_UNCONFIGURE _IOWR('e', 56, IOCTL_LIBCFS_TYPE)
-/* IOC_LIBCFS_PORTALS_COMPATIBILITY _IOWR('e', 57, IOCTL_LIBCFS_TYPE) */
-#define IOC_LIBCFS_LNET_DIST _IOWR('e', 58, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_CONFIGURE _IOWR('e', 59, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_TESTPROTOCOMPAT _IOWR('e', 60, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_PING _IOWR('e', 61, IOCTL_LIBCFS_TYPE)
-/* IOC_LIBCFS_DEBUG_PEER _IOWR('e', 62, IOCTL_LIBCFS_TYPE) */
-#define IOC_LIBCFS_LNETST _IOWR('e', 63, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_LNET_FAULT _IOWR('e', 64, IOCTL_LIBCFS_TYPE)
-/* lnd ioctls */
-#define IOC_LIBCFS_REGISTER_MYNID _IOWR('e', 70, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_CLOSE_CONNECTION _IOWR('e', 71, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_PUSH_CONNECTION _IOWR('e', 72, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_GET_CONN _IOWR('e', 73, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_DEL_PEER _IOWR('e', 74, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_ADD_PEER _IOWR('e', 75, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_GET_PEER _IOWR('e', 76, IOCTL_LIBCFS_TYPE)
-/* ioctl 77 is free for use */
-#define IOC_LIBCFS_ADD_INTERFACE _IOWR('e', 78, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_DEL_INTERFACE _IOWR('e', 79, IOCTL_LIBCFS_TYPE)
-#define IOC_LIBCFS_GET_INTERFACE _IOWR('e', 80, IOCTL_LIBCFS_TYPE)
-
-/*
- * DLC Specific IOCTL numbers.
- * In order to maintain backward compatibility with any possible external
- * tools which might be accessing the IOCTL numbers, a new group of IOCTL
- * number have been allocated.
- */
-#define IOCTL_CONFIG_SIZE struct lnet_ioctl_config_data
-#define IOC_LIBCFS_ADD_ROUTE _IOWR(IOC_LIBCFS_TYPE, 81, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_DEL_ROUTE _IOWR(IOC_LIBCFS_TYPE, 82, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_GET_ROUTE _IOWR(IOC_LIBCFS_TYPE, 83, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_ADD_NET _IOWR(IOC_LIBCFS_TYPE, 84, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_DEL_NET _IOWR(IOC_LIBCFS_TYPE, 85, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_GET_NET _IOWR(IOC_LIBCFS_TYPE, 86, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_CONFIG_RTR _IOWR(IOC_LIBCFS_TYPE, 87, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_ADD_BUF _IOWR(IOC_LIBCFS_TYPE, 88, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_GET_BUF _IOWR(IOC_LIBCFS_TYPE, 89, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_GET_PEER_INFO _IOWR(IOC_LIBCFS_TYPE, 90, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_GET_LNET_STATS _IOWR(IOC_LIBCFS_TYPE, 91, IOCTL_CONFIG_SIZE)
-#define IOC_LIBCFS_MAX_NR 91
-
-#endif /* __LIBCFS_IOCTL_H__ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/lnet-dlc.h b/drivers/staging/lustre/include/uapi/linux/lnet/lnet-dlc.h
deleted file mode 100644
index c1619f411d81..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/lnet-dlc.h
+++ /dev/null
@@ -1,150 +0,0 @@
-/*
- * LGPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library.
- *
- * LGPL HEADER END
- *
- */
-/*
- * Copyright (c) 2014, Intel Corporation.
- */
-/*
- * Author: Amir Shehata <amir.shehata@intel.com>
- */
-
-#ifndef LNET_DLC_H
-#define LNET_DLC_H
-
-#include <uapi/linux/lnet/libcfs_ioctl.h>
-#include <uapi/linux/lnet/lnet-types.h>
-
-#define MAX_NUM_SHOW_ENTRIES 32
-#define LNET_MAX_STR_LEN 128
-#define LNET_MAX_SHOW_NUM_CPT 128
-#define LNET_UNDEFINED_HOPS ((__u32)(-1))
-
-struct lnet_ioctl_config_lnd_cmn_tunables {
- __u32 lct_version;
- __u32 lct_peer_timeout;
- __u32 lct_peer_tx_credits;
- __u32 lct_peer_rtr_credits;
- __u32 lct_max_tx_credits;
-};
-
-struct lnet_ioctl_config_o2iblnd_tunables {
- __u32 lnd_version;
- __u32 lnd_peercredits_hiw;
- __u32 lnd_map_on_demand;
- __u32 lnd_concurrent_sends;
- __u32 lnd_fmr_pool_size;
- __u32 lnd_fmr_flush_trigger;
- __u32 lnd_fmr_cache;
- __u16 lnd_conns_per_peer;
- __u16 pad;
-};
-
-struct lnet_ioctl_config_lnd_tunables {
- struct lnet_ioctl_config_lnd_cmn_tunables lt_cmn;
- union {
- struct lnet_ioctl_config_o2iblnd_tunables lt_o2ib;
- } lt_tun_u;
-};
-
-struct lnet_ioctl_net_config {
- char ni_interfaces[LNET_MAX_INTERFACES][LNET_MAX_STR_LEN];
- __u32 ni_status;
- __u32 ni_cpts[LNET_MAX_SHOW_NUM_CPT];
- char cfg_bulk[0];
-};
-
-#define LNET_TINY_BUF_IDX 0
-#define LNET_SMALL_BUF_IDX 1
-#define LNET_LARGE_BUF_IDX 2
-
-/* # different router buffer pools */
-#define LNET_NRBPOOLS (LNET_LARGE_BUF_IDX + 1)
-
-struct lnet_ioctl_pool_cfg {
- struct {
- __u32 pl_npages;
- __u32 pl_nbuffers;
- __u32 pl_credits;
- __u32 pl_mincredits;
- } pl_pools[LNET_NRBPOOLS];
- __u32 pl_routing;
-};
-
-struct lnet_ioctl_config_data {
- struct libcfs_ioctl_hdr cfg_hdr;
-
- __u32 cfg_net;
- __u32 cfg_count;
- __u64 cfg_nid;
- __u32 cfg_ncpts;
-
- union {
- struct {
- __u32 rtr_hop;
- __u32 rtr_priority;
- __u32 rtr_flags;
- } cfg_route;
- struct {
- char net_intf[LNET_MAX_STR_LEN];
- __s32 net_peer_timeout;
- __s32 net_peer_tx_credits;
- __s32 net_peer_rtr_credits;
- __s32 net_max_tx_credits;
- __u32 net_cksum_algo;
- __u32 net_interface_count;
- } cfg_net;
- struct {
- __u32 buf_enable;
- __s32 buf_tiny;
- __s32 buf_small;
- __s32 buf_large;
- } cfg_buffers;
- } cfg_config_u;
-
- char cfg_bulk[0];
-};
-
-struct lnet_ioctl_peer {
- struct libcfs_ioctl_hdr pr_hdr;
- __u32 pr_count;
- __u32 pr_pad;
- __u64 pr_nid;
-
- union {
- struct {
- char cr_aliveness[LNET_MAX_STR_LEN];
- __u32 cr_refcount;
- __u32 cr_ni_peer_tx_credits;
- __u32 cr_peer_tx_credits;
- __u32 cr_peer_rtr_credits;
- __u32 cr_peer_min_rtr_credits;
- __u32 cr_peer_tx_qnob;
- __u32 cr_ncpt;
- } pr_peer_credits;
- } pr_lnd_u;
-};
-
-struct lnet_ioctl_lnet_stats {
- struct libcfs_ioctl_hdr st_hdr;
- struct lnet_counters st_cntrs;
-};
-
-#endif /* LNET_DLC_H */
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/lnet-types.h b/drivers/staging/lustre/include/uapi/linux/lnet/lnet-types.h
deleted file mode 100644
index 1be9b7aa7326..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/lnet-types.h
+++ /dev/null
@@ -1,669 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012 - 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Seagate, Inc.
- */
-
-#ifndef __LNET_TYPES_H__
-#define __LNET_TYPES_H__
-
-#include <linux/types.h>
-#include <linux/bvec.h>
-
-/** \addtogroup lnet
- * @{
- */
-
-#define LNET_VERSION "0.6.0"
-
-/** \addtogroup lnet_addr
- * @{
- */
-
-/** Portal reserved for LNet's own use.
- * \see lustre/include/lustre/lustre_idl.h for Lustre portal assignments.
- */
-#define LNET_RESERVED_PORTAL 0
-
-/**
- * Address of an end-point in an LNet network.
- *
- * A node can have multiple end-points and hence multiple addresses.
- * An LNet network can be a simple network (e.g. tcp0) or a network of
- * LNet networks connected by LNet routers. Therefore an end-point address
- * has two parts: network ID, and address within a network.
- *
- * \see LNET_NIDNET, LNET_NIDADDR, and LNET_MKNID.
- */
-typedef __u64 lnet_nid_t;
-/**
- * ID of a process in a node. Shortened as PID to distinguish from
- * lnet_process_id, the global process ID.
- */
-typedef __u32 lnet_pid_t;
-
-/** wildcard NID that matches any end-point address */
-#define LNET_NID_ANY ((lnet_nid_t)(-1))
-/** wildcard PID that matches any lnet_pid_t */
-#define LNET_PID_ANY ((lnet_pid_t)(-1))
-
-#define LNET_PID_RESERVED 0xf0000000 /* reserved bits in PID */
-#define LNET_PID_USERFLAG 0x80000000 /* set in userspace peers */
-#define LNET_PID_LUSTRE 12345
-
-#define LNET_TIME_FOREVER (-1)
-
-/* how an LNET NID encodes net:address */
-/** extract the address part of an lnet_nid_t */
-
-static inline __u32 LNET_NIDADDR(lnet_nid_t nid)
-{
- return nid & 0xffffffff;
-}
-
-static inline __u32 LNET_NIDNET(lnet_nid_t nid)
-{
- return (nid >> 32) & 0xffffffff;
-}
-
-static inline lnet_nid_t LNET_MKNID(__u32 net, __u32 addr)
-{
- return (((__u64)net) << 32) | addr;
-}
-
-static inline __u32 LNET_NETNUM(__u32 net)
-{
- return net & 0xffff;
-}
-
-static inline __u32 LNET_NETTYP(__u32 net)
-{
- return (net >> 16) & 0xffff;
-}
-
-static inline __u32 LNET_MKNET(__u32 type, __u32 num)
-{
- return (type << 16) | num;
-}
-
-#define WIRE_ATTR __packed
-
-/* Packed version of lnet_process_id to transfer via network */
-struct lnet_process_id_packed {
- /* node id / process id */
- lnet_nid_t nid;
- lnet_pid_t pid;
-} WIRE_ATTR;
-
-/*
- * The wire handle's interface cookie only matches one network interface in
- * one epoch (i.e. new cookie when the interface restarts or the node
- * reboots). The object cookie only matches one object on that interface
- * during that object's lifetime (i.e. no cookie re-use).
- */
-struct lnet_handle_wire {
- __u64 wh_interface_cookie;
- __u64 wh_object_cookie;
-} WIRE_ATTR;
-
-enum lnet_msg_type {
- LNET_MSG_ACK = 0,
- LNET_MSG_PUT,
- LNET_MSG_GET,
- LNET_MSG_REPLY,
- LNET_MSG_HELLO,
-};
-
-/*
- * The variant fields of the portals message header are aligned on an 8
- * byte boundary in the message header. Note that all types used in these
- * wire structs MUST be fixed size and the smaller types are placed at the
- * end.
- */
-struct lnet_ack {
- struct lnet_handle_wire dst_wmd;
- __u64 match_bits;
- __u32 mlength;
-} WIRE_ATTR;
-
-struct lnet_put {
- struct lnet_handle_wire ack_wmd;
- __u64 match_bits;
- __u64 hdr_data;
- __u32 ptl_index;
- __u32 offset;
-} WIRE_ATTR;
-
-struct lnet_get {
- struct lnet_handle_wire return_wmd;
- __u64 match_bits;
- __u32 ptl_index;
- __u32 src_offset;
- __u32 sink_length;
-} WIRE_ATTR;
-
-struct lnet_reply {
- struct lnet_handle_wire dst_wmd;
-} WIRE_ATTR;
-
-struct lnet_hello {
- __u64 incarnation;
- __u32 type;
-} WIRE_ATTR;
-
-struct lnet_hdr {
- lnet_nid_t dest_nid;
- lnet_nid_t src_nid;
- lnet_pid_t dest_pid;
- lnet_pid_t src_pid;
- __u32 type; /* enum lnet_msg_type */
- __u32 payload_length; /* payload data to follow */
- /*<------__u64 aligned------->*/
- union {
- struct lnet_ack ack;
- struct lnet_put put;
- struct lnet_get get;
- struct lnet_reply reply;
- struct lnet_hello hello;
- } msg;
-} WIRE_ATTR;
-
-/*
- * A HELLO message contains a magic number and protocol version
- * code in the header's dest_nid, the peer's NID in the src_nid, and
- * LNET_MSG_HELLO in the type field. All other common fields are zero
- * (including payload_size; i.e. no payload).
- * This is for use by byte-stream LNDs (e.g. TCP/IP) to check the peer is
- * running the same protocol and to find out its NID. These LNDs should
- * exchange HELLO messages when a connection is first established. Individual
- * LNDs can put whatever else they fancy in struct lnet_hdr::msg.
- */
-struct lnet_magicversion {
- __u32 magic; /* LNET_PROTO_TCP_MAGIC */
- __u16 version_major; /* increment on incompatible change */
- __u16 version_minor; /* increment on compatible change */
-} WIRE_ATTR;
-
-/* PROTO MAGIC for LNDs */
-#define LNET_PROTO_IB_MAGIC 0x0be91b91
-#define LNET_PROTO_GNI_MAGIC 0xb00fbabe /* ask Kim */
-#define LNET_PROTO_TCP_MAGIC 0xeebc0ded
-#define LNET_PROTO_ACCEPTOR_MAGIC 0xacce7100
-#define LNET_PROTO_PING_MAGIC 0x70696E67 /* 'ping' */
-
-/* Placeholder for a future "unified" protocol across all LNDs */
-/*
- * Current LNDs that receive a request with this magic will respond with a
- * "stub" reply using their current protocol
- */
-#define LNET_PROTO_MAGIC 0x45726963 /* ! */
-
-#define LNET_PROTO_TCP_VERSION_MAJOR 1
-#define LNET_PROTO_TCP_VERSION_MINOR 0
-
-/* Acceptor connection request */
-struct lnet_acceptor_connreq {
- __u32 acr_magic; /* PTL_ACCEPTOR_PROTO_MAGIC */
- __u32 acr_version; /* protocol version */
- __u64 acr_nid; /* target NID */
-} WIRE_ATTR;
-
-#define LNET_PROTO_ACCEPTOR_VERSION 1
-
-struct lnet_ni_status {
- lnet_nid_t ns_nid;
- __u32 ns_status;
- __u32 ns_unused;
-} WIRE_ATTR;
-
-struct lnet_ping_info {
- __u32 pi_magic;
- __u32 pi_features;
- lnet_pid_t pi_pid;
- __u32 pi_nnis;
- struct lnet_ni_status pi_ni[0];
-} WIRE_ATTR;
-
-struct lnet_counters {
- __u32 msgs_alloc;
- __u32 msgs_max;
- __u32 errors;
- __u32 send_count;
- __u32 recv_count;
- __u32 route_count;
- __u32 drop_count;
- __u64 send_length;
- __u64 recv_length;
- __u64 route_length;
- __u64 drop_length;
-} WIRE_ATTR;
-
-#define LNET_NI_STATUS_UP 0x15aac0de
-#define LNET_NI_STATUS_DOWN 0xdeadface
-#define LNET_NI_STATUS_INVALID 0x00000000
-
-#define LNET_MAX_INTERFACES 16
-
-/**
- * Objects maintained by the LNet are accessed through handles. Handle types
- * have names of the form lnet_handle_xx, where xx is one of the two letter
- * object type codes ('eq' for event queue, 'md' for memory descriptor, and
- * 'me' for match entry). Each type of object is given a unique handle type
- * to enhance type checking.
- */
-#define LNET_WIRE_HANDLE_COOKIE_NONE (-1)
-
-struct lnet_handle_eq {
- u64 cookie;
-};
-
-/**
- * Invalidate eq handle @h.
- */
-static inline void LNetInvalidateEQHandle(struct lnet_handle_eq *h)
-{
- h->cookie = LNET_WIRE_HANDLE_COOKIE_NONE;
-}
-
-/**
- * Check whether eq handle @h is invalid.
- *
- * @return 1 if handle is invalid, 0 if valid.
- */
-static inline int LNetEQHandleIsInvalid(struct lnet_handle_eq h)
-{
- return (LNET_WIRE_HANDLE_COOKIE_NONE == h.cookie);
-}
-
-struct lnet_handle_md {
- u64 cookie;
-};
-
-/**
- * Invalidate md handle @h.
- */
-static inline void LNetInvalidateMDHandle(struct lnet_handle_md *h)
-{
- h->cookie = LNET_WIRE_HANDLE_COOKIE_NONE;
-}
-
-/**
- * Check whether eq handle @h is invalid.
- *
- * @return 1 if handle is invalid, 0 if valid.
- */
-static inline int LNetMDHandleIsInvalid(struct lnet_handle_md h)
-{
- return (LNET_WIRE_HANDLE_COOKIE_NONE == h.cookie);
-}
-
-struct lnet_handle_me {
- u64 cookie;
-};
-
-/**
- * Global process ID.
- */
-struct lnet_process_id {
- /** node id */
- lnet_nid_t nid;
- /** process id */
- lnet_pid_t pid;
-};
-/** @} lnet_addr */
-
-/** \addtogroup lnet_me
- * @{
- */
-
-/**
- * Specifies whether the match entry or memory descriptor should be unlinked
- * automatically (LNET_UNLINK) or not (LNET_RETAIN).
- */
-enum lnet_unlink {
- LNET_RETAIN = 0,
- LNET_UNLINK
-};
-
-/**
- * Values of the type lnet_ins_pos are used to control where a new match
- * entry is inserted. The value LNET_INS_BEFORE is used to insert the new
- * entry before the current entry or before the head of the list. The value
- * LNET_INS_AFTER is used to insert the new entry after the current entry
- * or after the last item in the list.
- */
-enum lnet_ins_pos {
- /** insert ME before current position or head of the list */
- LNET_INS_BEFORE,
- /** insert ME after current position or tail of the list */
- LNET_INS_AFTER,
- /** attach ME at tail of local CPU partition ME list */
- LNET_INS_LOCAL
-};
-
-/** @} lnet_me */
-
-/** \addtogroup lnet_md
- * @{
- */
-
-/**
- * Defines the visible parts of a memory descriptor. Values of this type
- * are used to initialize memory descriptors.
- */
-struct lnet_md {
- /**
- * Specify the memory region associated with the memory descriptor.
- * If the options field has:
- * - LNET_MD_KIOV bit set: The start field points to the starting
- * address of an array of struct bio_vec and the length field specifies
- * the number of entries in the array. The length can't be bigger
- * than LNET_MAX_IOV. The struct bio_vec is used to describe page-based
- * fragments that are not necessarily mapped in virtual memory.
- * - LNET_MD_IOVEC bit set: The start field points to the starting
- * address of an array of struct iovec and the length field specifies
- * the number of entries in the array. The length can't be bigger
- * than LNET_MAX_IOV. The struct iovec is used to describe fragments
- * that have virtual addresses.
- * - Otherwise: The memory region is contiguous. The start field
- * specifies the starting address for the memory region and the
- * length field specifies its length.
- *
- * When the memory region is fragmented, all fragments but the first
- * one must start on page boundary, and all but the last must end on
- * page boundary.
- */
- void *start;
- unsigned int length;
- /**
- * Specifies the maximum number of operations that can be performed
- * on the memory descriptor. An operation is any action that could
- * possibly generate an event. In the usual case, the threshold value
- * is decremented for each operation on the MD. When the threshold
- * drops to zero, the MD becomes inactive and does not respond to
- * operations. A threshold value of LNET_MD_THRESH_INF indicates that
- * there is no bound on the number of operations that may be applied
- * to a MD.
- */
- int threshold;
- /**
- * Specifies the largest incoming request that the memory descriptor
- * should respond to. When the unused portion of a MD (length -
- * local offset) falls below this value, the MD becomes inactive and
- * does not respond to further operations. This value is only used
- * if the LNET_MD_MAX_SIZE option is set.
- */
- int max_size;
- /**
- * Specifies the behavior of the memory descriptor. A bitwise OR
- * of the following values can be used:
- * - LNET_MD_OP_PUT: The LNet PUT operation is allowed on this MD.
- * - LNET_MD_OP_GET: The LNet GET operation is allowed on this MD.
- * - LNET_MD_MANAGE_REMOTE: The offset used in accessing the memory
- * region is provided by the incoming request. By default, the
- * offset is maintained locally. When maintained locally, the
- * offset is incremented by the length of the request so that
- * the next operation (PUT or GET) will access the next part of
- * the memory region. Note that only one offset variable exists
- * per memory descriptor. If both PUT and GET operations are
- * performed on a memory descriptor, the offset is updated each time.
- * - LNET_MD_TRUNCATE: The length provided in the incoming request can
- * be reduced to match the memory available in the region (determined
- * by subtracting the offset from the length of the memory region).
- * By default, if the length in the incoming operation is greater
- * than the amount of memory available, the operation is rejected.
- * - LNET_MD_ACK_DISABLE: An acknowledgment should not be sent for
- * incoming PUT operations, even if requested. By default,
- * acknowledgments are sent for PUT operations that request an
- * acknowledgment. Acknowledgments are never sent for GET operations.
- * The data sent in the REPLY serves as an implicit acknowledgment.
- * - LNET_MD_KIOV: The start and length fields specify an array of
- * struct bio_vec.
- * - LNET_MD_IOVEC: The start and length fields specify an array of
- * struct iovec.
- * - LNET_MD_MAX_SIZE: The max_size field is valid.
- *
- * Note:
- * - LNET_MD_KIOV or LNET_MD_IOVEC allows for a scatter/gather
- * capability for memory descriptors. They can't be both set.
- * - When LNET_MD_MAX_SIZE is set, the total length of the memory
- * region (i.e. sum of all fragment lengths) must not be less than
- * \a max_size.
- */
- unsigned int options;
- /**
- * A user-specified value that is associated with the memory
- * descriptor. The value does not need to be a pointer, but must fit
- * in the space used by a pointer. This value is recorded in events
- * associated with operations on this MD.
- */
- void *user_ptr;
- /**
- * A handle for the event queue used to log the operations performed on
- * the memory region. If this argument is a NULL handle (i.e. nullified
- * by LNetInvalidateHandle()), operations performed on this memory
- * descriptor are not logged.
- */
- struct lnet_handle_eq eq_handle;
-};
-
-/*
- * Max Transfer Unit (minimum supported everywhere).
- * CAVEAT EMPTOR, with multinet (i.e. routers forwarding between networks)
- * these limits are system wide and not interface-local.
- */
-#define LNET_MTU_BITS 20
-#define LNET_MTU (1 << LNET_MTU_BITS)
-
-/** limit on the number of fragments in discontiguous MDs */
-#define LNET_MAX_IOV 256
-
-/**
- * Options for the MD structure. See lnet_md::options.
- */
-#define LNET_MD_OP_PUT (1 << 0)
-/** See lnet_md::options. */
-#define LNET_MD_OP_GET (1 << 1)
-/** See lnet_md::options. */
-#define LNET_MD_MANAGE_REMOTE (1 << 2)
-/* unused (1 << 3) */
-/** See lnet_md::options. */
-#define LNET_MD_TRUNCATE (1 << 4)
-/** See lnet_md::options. */
-#define LNET_MD_ACK_DISABLE (1 << 5)
-/** See lnet_md::options. */
-#define LNET_MD_IOVEC (1 << 6)
-/** See lnet_md::options. */
-#define LNET_MD_MAX_SIZE (1 << 7)
-/** See lnet_md::options. */
-#define LNET_MD_KIOV (1 << 8)
-
-/* For compatibility with Cray Portals */
-#define LNET_MD_PHYS 0
-
-/** Infinite threshold on MD operations. See lnet_md::threshold */
-#define LNET_MD_THRESH_INF (-1)
-
-/** @} lnet_md */
-
-/** \addtogroup lnet_eq
- * @{
- */
-
-/**
- * Six types of events can be logged in an event queue.
- */
-enum lnet_event_kind {
- /** An incoming GET operation has completed on the MD. */
- LNET_EVENT_GET = 1,
- /**
- * An incoming PUT operation has completed on the MD. The
- * underlying layers will not alter the memory (on behalf of this
- * operation) once this event has been logged.
- */
- LNET_EVENT_PUT,
- /**
- * A REPLY operation has completed. This event is logged after the
- * data (if any) from the REPLY has been written into the MD.
- */
- LNET_EVENT_REPLY,
- /** An acknowledgment has been received. */
- LNET_EVENT_ACK,
- /**
- * An outgoing send (PUT or GET) operation has completed. This event
- * is logged after the entire buffer has been sent and it is safe for
- * the caller to reuse the buffer.
- *
- * Note:
- * - The LNET_EVENT_SEND doesn't guarantee message delivery. It can
- * happen even when the message has not yet been put out on wire.
- * - It's unsafe to assume that in an outgoing GET operation
- * the LNET_EVENT_SEND event would happen before the
- * LNET_EVENT_REPLY event. The same holds for LNET_EVENT_SEND and
- * LNET_EVENT_ACK events in an outgoing PUT operation.
- */
- LNET_EVENT_SEND,
- /**
- * A MD has been unlinked. Note that LNetMDUnlink() does not
- * necessarily trigger an LNET_EVENT_UNLINK event.
- * \see LNetMDUnlink
- */
- LNET_EVENT_UNLINK,
-};
-
-#define LNET_SEQ_GT(a, b) (((signed long)((a) - (b))) > 0)
-
-/**
- * Information about an event on a MD.
- */
-struct lnet_event {
- /** The identifier (nid, pid) of the target. */
- struct lnet_process_id target;
- /** The identifier (nid, pid) of the initiator. */
- struct lnet_process_id initiator;
- /**
- * The NID of the immediate sender. If the request has been forwarded
- * by routers, this is the NID of the last hop; otherwise it's the
- * same as the initiator.
- */
- lnet_nid_t sender;
- /** Indicates the type of the event. */
- enum lnet_event_kind type;
- /** The portal table index specified in the request */
- unsigned int pt_index;
- /** A copy of the match bits specified in the request. */
- __u64 match_bits;
- /** The length (in bytes) specified in the request. */
- unsigned int rlength;
- /**
- * The length (in bytes) of the data that was manipulated by the
- * operation. For truncated operations, the manipulated length will be
- * the number of bytes specified by the MD (possibly with an offset,
- * see lnet_md). For all other operations, the manipulated length
- * will be the length of the requested operation, i.e. rlength.
- */
- unsigned int mlength;
- /**
- * The handle to the MD associated with the event. The handle may be
- * invalid if the MD has been unlinked.
- */
- struct lnet_handle_md md_handle;
- /**
- * A snapshot of the state of the MD immediately after the event has
- * been processed. In particular, the threshold field in md will
- * reflect the value of the threshold after the operation occurred.
- */
- struct lnet_md md;
- /**
- * 64 bits of out-of-band user data. Only valid for LNET_EVENT_PUT.
- * \see LNetPut
- */
- __u64 hdr_data;
- /**
- * Indicates the completion status of the operation. It's 0 for
- * successful operations, otherwise it's an error code.
- */
- int status;
- /**
- * Indicates whether the MD has been unlinked. Note that:
- * - An event with unlinked set is the last event on the MD.
- * - This field is also set for an explicit LNET_EVENT_UNLINK event.
- * \see LNetMDUnlink
- */
- int unlinked;
- /**
- * The displacement (in bytes) into the memory region that the
- * operation used. The offset can be determined by the operation for
- * a remote managed MD or by the local MD.
- * \see lnet_md::options
- */
- unsigned int offset;
- /**
- * The sequence number for this event. Sequence numbers are unique
- * to each event.
- */
- volatile unsigned long sequence;
-};
-
-/**
- * Event queue handler function type.
- *
- * The EQ handler runs for each event that is deposited into the EQ. The
- * handler is supplied with a pointer to the event that triggered the
- * handler invocation.
- *
- * The handler must not block, must be reentrant, and must not call any LNet
- * API functions. It should return as quickly as possible.
- */
-typedef void (*lnet_eq_handler_t)(struct lnet_event *event);
-#define LNET_EQ_HANDLER_NONE NULL
-/** @} lnet_eq */
-
-/** \addtogroup lnet_data
- * @{
- */
-
-/**
- * Specify whether an acknowledgment should be sent by target when the PUT
- * operation completes (i.e., when the data has been written to a MD of the
- * target process).
- *
- * \see lnet_md::options for the discussion on LNET_MD_ACK_DISABLE by which
- * acknowledgments can be disabled for a MD.
- */
-enum lnet_ack_req {
- /** Request an acknowledgment */
- LNET_ACK_REQ,
- /** Request that no acknowledgment should be generated. */
- LNET_NOACK_REQ
-};
-/** @} lnet_data */
-
-/** @} lnet */
-#endif
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/lnetctl.h b/drivers/staging/lustre/include/uapi/linux/lnet/lnetctl.h
deleted file mode 100644
index cccb32dd28f2..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/lnetctl.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * This file is part of Portals, http://www.sf.net/projects/lustre/
- *
- * Portals is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * Portals is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * header for lnet ioctl
- */
-#ifndef _LNETCTL_H_
-#define _LNETCTL_H_
-
-#include <uapi/linux/lnet/lnet-types.h>
-
-/** \addtogroup lnet_fault_simulation
- * @{
- */
-
-enum {
- LNET_CTL_DROP_ADD,
- LNET_CTL_DROP_DEL,
- LNET_CTL_DROP_RESET,
- LNET_CTL_DROP_LIST,
- LNET_CTL_DELAY_ADD,
- LNET_CTL_DELAY_DEL,
- LNET_CTL_DELAY_RESET,
- LNET_CTL_DELAY_LIST,
-};
-
-#define LNET_ACK_BIT (1 << 0)
-#define LNET_PUT_BIT (1 << 1)
-#define LNET_GET_BIT (1 << 2)
-#define LNET_REPLY_BIT (1 << 3)
-
-/** ioctl parameter for LNet fault simulation */
-struct lnet_fault_attr {
- /**
- * source NID of drop rule
- * LNET_NID_ANY is wildcard for all sources
- * 255.255.255.255@net is wildcard for all addresses from @net
- */
- lnet_nid_t fa_src;
- /** destination NID of drop rule, see \a dr_src for details */
- lnet_nid_t fa_dst;
- /**
- * Portal mask to drop, -1 means all portals, for example:
- * fa_ptl_mask = (1 << _LDLM_CB_REQUEST_PORTAL ) |
- * (1 << LDLM_CANCEL_REQUEST_PORTAL)
- *
- * If it is non-zero then only PUT and GET will be filtered, otherwise
- * there is no portal filter, all matched messages will be checked.
- */
- __u64 fa_ptl_mask;
- /**
- * message types to drop, for example:
- * dra_type = LNET_DROP_ACK_BIT | LNET_DROP_PUT_BIT
- *
- * If it is non-zero then only specified message types are filtered,
- * otherwise all message types will be checked.
- */
- __u32 fa_msg_mask;
- union {
- /** message drop simulation */
- struct {
- /** drop rate of this rule */
- __u32 da_rate;
- /**
- * time interval of message drop, it is exclusive
- * with da_rate
- */
- __u32 da_interval;
- } drop;
- /** message latency simulation */
- struct {
- __u32 la_rate;
- /**
- * time interval of message delay, it is exclusive
- * with la_rate
- */
- __u32 la_interval;
- /** latency to delay */
- __u32 la_latency;
- } delay;
- __u64 space[8];
- } u;
-};
-
-/** fault simluation stats */
-struct lnet_fault_stat {
- /** total # matched messages */
- __u64 fs_count;
- /** # dropped LNET_MSG_PUT by this rule */
- __u64 fs_put;
- /** # dropped LNET_MSG_ACK by this rule */
- __u64 fs_ack;
- /** # dropped LNET_MSG_GET by this rule */
- __u64 fs_get;
- /** # dropped LNET_MSG_REPLY by this rule */
- __u64 fs_reply;
- union {
- struct {
- /** total # dropped messages */
- __u64 ds_dropped;
- } drop;
- struct {
- /** total # delayed messages */
- __u64 ls_delayed;
- } delay;
- __u64 space[8];
- } u;
-};
-
-/** @} lnet_fault_simulation */
-
-#define LNET_DEV_ID 0
-#define LNET_DEV_PATH "/dev/lnet"
-
-#endif
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/lnetst.h b/drivers/staging/lustre/include/uapi/linux/lnet/lnetst.h
deleted file mode 100644
index a4f9ff01d458..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/lnetst.h
+++ /dev/null
@@ -1,556 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011 - 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Seagate, Inc.
- *
- * lnet/include/lnet/lnetst.h
- *
- * Author: Liang Zhen <liang.zhen@intel.com>
- */
-
-#ifndef __LNET_ST_H__
-#define __LNET_ST_H__
-
-#include <linux/types.h>
-
-#define LST_FEAT_NONE (0)
-#define LST_FEAT_BULK_LEN (1 << 0) /* enable variable page size */
-
-#define LST_FEATS_EMPTY (LST_FEAT_NONE)
-#define LST_FEATS_MASK (LST_FEAT_NONE | LST_FEAT_BULK_LEN)
-
-#define LST_NAME_SIZE 32 /* max name buffer length */
-
-#define LSTIO_DEBUG 0xC00 /* debug */
-#define LSTIO_SESSION_NEW 0xC01 /* create session */
-#define LSTIO_SESSION_END 0xC02 /* end session */
-#define LSTIO_SESSION_INFO 0xC03 /* query session */
-#define LSTIO_GROUP_ADD 0xC10 /* add group */
-#define LSTIO_GROUP_LIST 0xC11 /* list all groups in session */
-#define LSTIO_GROUP_INFO 0xC12 /* query default information of
- * specified group
- */
-#define LSTIO_GROUP_DEL 0xC13 /* delete group */
-#define LSTIO_NODES_ADD 0xC14 /* add nodes to specified group */
-#define LSTIO_GROUP_UPDATE 0xC15 /* update group */
-#define LSTIO_BATCH_ADD 0xC20 /* add batch */
-#define LSTIO_BATCH_START 0xC21 /* start batch */
-#define LSTIO_BATCH_STOP 0xC22 /* stop batch */
-#define LSTIO_BATCH_DEL 0xC23 /* delete batch */
-#define LSTIO_BATCH_LIST 0xC24 /* show all batches in the session */
-#define LSTIO_BATCH_INFO 0xC25 /* show defail of specified batch */
-#define LSTIO_TEST_ADD 0xC26 /* add test (to batch) */
-#define LSTIO_BATCH_QUERY 0xC27 /* query batch status */
-#define LSTIO_STAT_QUERY 0xC30 /* get stats */
-
-struct lst_sid {
- lnet_nid_t ses_nid; /* nid of console node */
- __u64 ses_stamp; /* time stamp */
-}; /*** session id */
-
-extern struct lst_sid LST_INVALID_SID;
-
-struct lst_bid {
- __u64 bat_id; /* unique id in session */
-}; /*** batch id (group of tests) */
-
-/* Status of test node */
-#define LST_NODE_ACTIVE 0x1 /* node in this session */
-#define LST_NODE_BUSY 0x2 /* node is taken by other session */
-#define LST_NODE_DOWN 0x4 /* node is down */
-#define LST_NODE_UNKNOWN 0x8 /* node not in session */
-
-struct lstcon_node_ent {
- struct lnet_process_id nde_id; /* id of node */
- int nde_state; /* state of node */
-}; /*** node entry, for list_group command */
-
-struct lstcon_ndlist_ent {
- int nle_nnode; /* # of nodes */
- int nle_nactive; /* # of active nodes */
- int nle_nbusy; /* # of busy nodes */
- int nle_ndown; /* # of down nodes */
- int nle_nunknown; /* # of unknown nodes */
-}; /*** node_list entry, for list_batch command */
-
-struct lstcon_test_ent {
- int tse_type; /* test type */
- int tse_loop; /* loop count */
- int tse_concur; /* concurrency of test */
-}; /* test summary entry, for
- * list_batch command
- */
-
-struct lstcon_batch_ent {
- int bae_state; /* batch status */
- int bae_timeout; /* batch timeout */
- int bae_ntest; /* # of tests in the batch */
-}; /* batch summary entry, for
- * list_batch command
- */
-
-struct lstcon_test_batch_ent {
- struct lstcon_ndlist_ent tbe_cli_nle; /* client (group) node_list
- * entry
- */
- struct lstcon_ndlist_ent tbe_srv_nle; /* server (group) node_list
- * entry
- */
- union {
- struct lstcon_test_ent tbe_test; /* test entry */
- struct lstcon_batch_ent tbe_batch;/* batch entry */
- } u;
-}; /* test/batch verbose information entry,
- * for list_batch command
- */
-
-struct lstcon_rpc_ent {
- struct list_head rpe_link; /* link chain */
- struct lnet_process_id rpe_peer; /* peer's id */
- struct timeval rpe_stamp; /* time stamp of RPC */
- int rpe_state; /* peer's state */
- int rpe_rpc_errno; /* RPC errno */
-
- struct lst_sid rpe_sid; /* peer's session id */
- int rpe_fwk_errno; /* framework errno */
- int rpe_priv[4]; /* private data */
- char rpe_payload[0]; /* private reply payload */
-};
-
-struct lstcon_trans_stat {
- int trs_rpc_stat[4]; /* RPCs stat (0: total 1: failed
- * 2: finished
- * 4: reserved
- */
- int trs_rpc_errno; /* RPC errno */
- int trs_fwk_stat[8]; /* framework stat */
- int trs_fwk_errno; /* errno of the first remote error */
- void *trs_fwk_private; /* private framework stat */
-};
-
-static inline int
-lstcon_rpc_stat_total(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_rpc_stat[0] : stat->trs_rpc_stat[0];
-}
-
-static inline int
-lstcon_rpc_stat_success(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_rpc_stat[1] : stat->trs_rpc_stat[1];
-}
-
-static inline int
-lstcon_rpc_stat_failure(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_rpc_stat[2] : stat->trs_rpc_stat[2];
-}
-
-static inline int
-lstcon_sesop_stat_success(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[0] : stat->trs_fwk_stat[0];
-}
-
-static inline int
-lstcon_sesop_stat_failure(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[1] : stat->trs_fwk_stat[1];
-}
-
-static inline int
-lstcon_sesqry_stat_active(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[0] : stat->trs_fwk_stat[0];
-}
-
-static inline int
-lstcon_sesqry_stat_busy(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[1] : stat->trs_fwk_stat[1];
-}
-
-static inline int
-lstcon_sesqry_stat_unknown(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[2] : stat->trs_fwk_stat[2];
-}
-
-static inline int
-lstcon_tsbop_stat_success(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[0] : stat->trs_fwk_stat[0];
-}
-
-static inline int
-lstcon_tsbop_stat_failure(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[1] : stat->trs_fwk_stat[1];
-}
-
-static inline int
-lstcon_tsbqry_stat_idle(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[0] : stat->trs_fwk_stat[0];
-}
-
-static inline int
-lstcon_tsbqry_stat_run(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[1] : stat->trs_fwk_stat[1];
-}
-
-static inline int
-lstcon_tsbqry_stat_failure(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[2] : stat->trs_fwk_stat[2];
-}
-
-static inline int
-lstcon_statqry_stat_success(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[0] : stat->trs_fwk_stat[0];
-}
-
-static inline int
-lstcon_statqry_stat_failure(struct lstcon_trans_stat *stat, int inc)
-{
- return inc ? ++stat->trs_fwk_stat[1] : stat->trs_fwk_stat[1];
-}
-
-/* create a session */
-struct lstio_session_new_args {
- int lstio_ses_key; /* IN: local key */
- int lstio_ses_timeout; /* IN: session timeout */
- int lstio_ses_force; /* IN: force create ? */
- /** IN: session features */
- unsigned int lstio_ses_feats;
- struct lst_sid __user *lstio_ses_idp; /* OUT: session id */
- int lstio_ses_nmlen; /* IN: name length */
- char __user *lstio_ses_namep; /* IN: session name */
-};
-
-/* query current session */
-struct lstio_session_info_args {
- struct lst_sid __user *lstio_ses_idp; /* OUT: session id */
- int __user *lstio_ses_keyp; /* OUT: local key */
- /** OUT: session features */
- unsigned int __user *lstio_ses_featp;
- struct lstcon_ndlist_ent __user *lstio_ses_ndinfo;/* OUT: */
- int lstio_ses_nmlen; /* IN: name length */
- char __user *lstio_ses_namep; /* OUT: session name */
-};
-
-/* delete a session */
-struct lstio_session_end_args {
- int lstio_ses_key; /* IN: session key */
-};
-
-#define LST_OPC_SESSION 1
-#define LST_OPC_GROUP 2
-#define LST_OPC_NODES 3
-#define LST_OPC_BATCHCLI 4
-#define LST_OPC_BATCHSRV 5
-
-struct lstio_debug_args {
- int lstio_dbg_key; /* IN: session key */
- int lstio_dbg_type; /* IN: debug
- * session|batch|
- * group|nodes list
- */
- int lstio_dbg_flags; /* IN: reserved debug
- * flags
- */
- int lstio_dbg_timeout; /* IN: timeout of
- * debug
- */
- int lstio_dbg_nmlen; /* IN: len of name */
- char __user *lstio_dbg_namep; /* IN: name of
- * group|batch
- */
- int lstio_dbg_count; /* IN: # of test nodes
- * to debug
- */
- struct lnet_process_id __user *lstio_dbg_idsp; /* IN: id of test
- * nodes
- */
- struct list_head __user *lstio_dbg_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-struct lstio_group_add_args {
- int lstio_grp_key; /* IN: session key */
- int lstio_grp_nmlen; /* IN: name length */
- char __user *lstio_grp_namep; /* IN: group name */
-};
-
-struct lstio_group_del_args {
- int lstio_grp_key; /* IN: session key */
- int lstio_grp_nmlen; /* IN: name length */
- char __user *lstio_grp_namep; /* IN: group name */
-};
-
-#define LST_GROUP_CLEAN 1 /* remove inactive nodes in the group */
-#define LST_GROUP_REFRESH 2 /* refresh inactive nodes
- * in the group
- */
-#define LST_GROUP_RMND 3 /* delete nodes from the group */
-
-struct lstio_group_update_args {
- int lstio_grp_key; /* IN: session key */
- int lstio_grp_opc; /* IN: OPC */
- int lstio_grp_args; /* IN: arguments */
- int lstio_grp_nmlen; /* IN: name length */
- char __user *lstio_grp_namep; /* IN: group name */
- int lstio_grp_count; /* IN: # of nodes id */
- struct lnet_process_id __user *lstio_grp_idsp; /* IN: array of nodes */
- struct list_head __user *lstio_grp_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-struct lstio_group_nodes_args {
- int lstio_grp_key; /* IN: session key */
- int lstio_grp_nmlen; /* IN: name length */
- char __user *lstio_grp_namep; /* IN: group name */
- int lstio_grp_count; /* IN: # of nodes */
- /** OUT: session features */
- unsigned int __user *lstio_grp_featp;
- struct lnet_process_id __user *lstio_grp_idsp; /* IN: nodes */
- struct list_head __user *lstio_grp_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-struct lstio_group_list_args {
- int lstio_grp_key; /* IN: session key */
- int lstio_grp_idx; /* IN: group idx */
- int lstio_grp_nmlen; /* IN: name len */
- char __user *lstio_grp_namep; /* OUT: name */
-};
-
-struct lstio_group_info_args {
- int lstio_grp_key; /* IN: session key */
- int lstio_grp_nmlen; /* IN: name len */
- char __user *lstio_grp_namep; /* IN: name */
- struct lstcon_ndlist_ent __user *lstio_grp_entp;/* OUT: description
- * of group
- */
- int __user *lstio_grp_idxp; /* IN/OUT: node index */
- int __user *lstio_grp_ndentp; /* IN/OUT: # of nodent */
- struct lstcon_node_ent __user *lstio_grp_dentsp;/* OUT: nodent array */
-};
-
-#define LST_DEFAULT_BATCH "batch" /* default batch name */
-
-struct lstio_batch_add_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: batch name */
-};
-
-struct lstio_batch_del_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: batch name */
-};
-
-struct lstio_batch_run_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_timeout; /* IN: timeout for
- * the batch
- */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: batch name */
- struct list_head __user *lstio_bat_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-struct lstio_batch_stop_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_force; /* IN: abort unfinished
- * test RPC
- */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: batch name */
- struct list_head __user *lstio_bat_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-struct lstio_batch_query_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_testidx; /* IN: test index */
- int lstio_bat_client; /* IN: we testing
- * client?
- */
- int lstio_bat_timeout; /* IN: timeout for
- * waiting
- */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: batch name */
- struct list_head __user *lstio_bat_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-struct lstio_batch_list_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_idx; /* IN: index */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: batch name */
-};
-
-struct lstio_batch_info_args {
- int lstio_bat_key; /* IN: session key */
- int lstio_bat_nmlen; /* IN: name length */
- char __user *lstio_bat_namep; /* IN: name */
- int lstio_bat_server; /* IN: query server
- * or not
- */
- int lstio_bat_testidx; /* IN: test index */
- struct lstcon_test_batch_ent __user *lstio_bat_entp;/* OUT: batch ent */
-
- int __user *lstio_bat_idxp; /* IN/OUT: index of node */
- int __user *lstio_bat_ndentp; /* IN/OUT: # of nodent */
- struct lstcon_node_ent __user *lstio_bat_dentsp;/* array of nodent */
-};
-
-/* add stat in session */
-struct lstio_stat_args {
- int lstio_sta_key; /* IN: session key */
- int lstio_sta_timeout; /* IN: timeout for
- * stat request
- */
- int lstio_sta_nmlen; /* IN: group name
- * length
- */
- char __user *lstio_sta_namep; /* IN: group name */
- int lstio_sta_count; /* IN: # of pid */
- struct lnet_process_id __user *lstio_sta_idsp; /* IN: pid */
- struct list_head __user *lstio_sta_resultp; /* OUT: list head of
- * result buffer
- */
-};
-
-enum lst_test_type {
- LST_TEST_BULK = 1,
- LST_TEST_PING = 2
-};
-
-/* create a test in a batch */
-#define LST_MAX_CONCUR 1024 /* Max concurrency of test */
-
-struct lstio_test_args {
- int lstio_tes_key; /* IN: session key */
- int lstio_tes_bat_nmlen; /* IN: batch name len */
- char __user *lstio_tes_bat_name; /* IN: batch name */
- int lstio_tes_type; /* IN: test type */
- int lstio_tes_oneside; /* IN: one sided test */
- int lstio_tes_loop; /* IN: loop count */
- int lstio_tes_concur; /* IN: concurrency */
-
- int lstio_tes_dist; /* IN: node distribution in
- * destination groups
- */
- int lstio_tes_span; /* IN: node span in
- * destination groups
- */
- int lstio_tes_sgrp_nmlen; /* IN: source group
- * name length
- */
- char __user *lstio_tes_sgrp_name; /* IN: group name */
- int lstio_tes_dgrp_nmlen; /* IN: destination group
- * name length
- */
- char __user *lstio_tes_dgrp_name; /* IN: group name */
-
- int lstio_tes_param_len; /* IN: param buffer len */
- void __user *lstio_tes_param; /* IN: parameter for specified
- * test: lstio_bulk_param_t,
- * lstio_ping_param_t,
- * ... more
- */
- int __user *lstio_tes_retp; /* OUT: private returned
- * value
- */
- struct list_head __user *lstio_tes_resultp;/* OUT: list head of
- * result buffer
- */
-};
-
-enum lst_brw_type {
- LST_BRW_READ = 1,
- LST_BRW_WRITE = 2
-};
-
-enum lst_brw_flags {
- LST_BRW_CHECK_NONE = 1,
- LST_BRW_CHECK_SIMPLE = 2,
- LST_BRW_CHECK_FULL = 3
-};
-
-struct lst_test_bulk_param {
- int blk_opc; /* bulk operation code */
- int blk_size; /* size (bytes) */
- int blk_time; /* time of running the test*/
- int blk_flags; /* reserved flags */
- int blk_cli_off; /* bulk offset on client */
- int blk_srv_off; /* reserved: bulk offset on server */
-};
-
-struct lst_test_ping_param {
- int png_size; /* size of ping message */
- int png_time; /* time */
- int png_loop; /* loop */
- int png_flags; /* reserved flags */
-};
-
-struct srpc_counters {
- __u32 errors;
- __u32 rpcs_sent;
- __u32 rpcs_rcvd;
- __u32 rpcs_dropped;
- __u32 rpcs_expired;
- __u64 bulk_get;
- __u64 bulk_put;
-} WIRE_ATTR;
-
-struct sfw_counters {
- /** milliseconds since current session started */
- __u32 running_ms;
- __u32 active_batches;
- __u32 zombie_sessions;
- __u32 brw_errors;
- __u32 ping_errors;
-} WIRE_ATTR;
-
-#endif
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/nidstr.h b/drivers/staging/lustre/include/uapi/linux/lnet/nidstr.h
deleted file mode 100644
index 882074ed6021..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/nidstr.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-#ifndef _LNET_NIDSTRINGS_H
-#define _LNET_NIDSTRINGS_H
-
-#include <uapi/linux/lnet/lnet-types.h>
-
-/**
- * Lustre Network Driver types.
- */
-enum {
- /*
- * Only add to these values (i.e. don't ever change or redefine them):
- * network addresses depend on them...
- */
- QSWLND = 1,
- SOCKLND = 2,
- GMLND = 3,
- PTLLND = 4,
- O2IBLND = 5,
- CIBLND = 6,
- OPENIBLND = 7,
- IIBLND = 8,
- LOLND = 9,
- RALND = 10,
- VIBLND = 11,
- MXLND = 12,
- GNILND = 13,
- GNIIPLND = 14,
-};
-
-struct list_head;
-
-#define LNET_NIDSTR_COUNT 1024 /* # of nidstrings */
-#define LNET_NIDSTR_SIZE 32 /* size of each one (see below for usage) */
-
-/* support decl needed by both kernel and user space */
-char *libcfs_next_nidstring(void);
-int libcfs_isknown_lnd(__u32 lnd);
-char *libcfs_lnd2modname(__u32 lnd);
-char *libcfs_lnd2str_r(__u32 lnd, char *buf, size_t buf_size);
-static inline char *libcfs_lnd2str(__u32 lnd)
-{
- return libcfs_lnd2str_r(lnd, libcfs_next_nidstring(),
- LNET_NIDSTR_SIZE);
-}
-
-int libcfs_str2lnd(const char *str);
-char *libcfs_net2str_r(__u32 net, char *buf, size_t buf_size);
-static inline char *libcfs_net2str(__u32 net)
-{
- return libcfs_net2str_r(net, libcfs_next_nidstring(),
- LNET_NIDSTR_SIZE);
-}
-
-char *libcfs_nid2str_r(lnet_nid_t nid, char *buf, size_t buf_size);
-static inline char *libcfs_nid2str(lnet_nid_t nid)
-{
- return libcfs_nid2str_r(nid, libcfs_next_nidstring(),
- LNET_NIDSTR_SIZE);
-}
-
-__u32 libcfs_str2net(const char *str);
-lnet_nid_t libcfs_str2nid(const char *str);
-int libcfs_str2anynid(lnet_nid_t *nid, const char *str);
-char *libcfs_id2str(struct lnet_process_id id);
-void cfs_free_nidlist(struct list_head *list);
-int cfs_parse_nidlist(char *str, int len, struct list_head *list);
-int cfs_print_nidlist(char *buffer, int count, struct list_head *list);
-int cfs_match_nid(lnet_nid_t nid, struct list_head *list);
-
-int cfs_ip_addr_parse(char *str, int len, struct list_head *list);
-int cfs_ip_addr_match(__u32 addr, struct list_head *list);
-bool cfs_nidrange_is_contiguous(struct list_head *nidlist);
-void cfs_nidrange_find_min_max(struct list_head *nidlist, char *min_nid,
- char *max_nid, size_t nidstr_length);
-
-struct netstrfns {
- __u32 nf_type;
- char *nf_name;
- char *nf_modname;
- void (*nf_addr2str)(__u32 addr, char *str, size_t size);
- int (*nf_str2addr)(const char *str, int nob, __u32 *addr);
- int (*nf_parse_addrlist)(char *str, int len,
- struct list_head *list);
- int (*nf_print_addrlist)(char *buffer, int count,
- struct list_head *list);
- int (*nf_match_addr)(__u32 addr, struct list_head *list);
- bool (*nf_is_contiguous)(struct list_head *nidlist);
- void (*nf_min_max)(struct list_head *nidlist, __u32 *min_nid,
- __u32 *max_nid);
-};
-
-#endif /* _LNET_NIDSTRINGS_H */
diff --git a/drivers/staging/lustre/include/uapi/linux/lnet/socklnd.h b/drivers/staging/lustre/include/uapi/linux/lnet/socklnd.h
deleted file mode 100644
index 6453e053fa99..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lnet/socklnd.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * #defines shared between socknal implementation and utilities
- */
-#ifndef __UAPI_LNET_SOCKLND_H__
-#define __UAPI_LNET_SOCKLND_H__
-
-#define SOCKLND_CONN_NONE (-1)
-#define SOCKLND_CONN_ANY 0
-#define SOCKLND_CONN_CONTROL 1
-#define SOCKLND_CONN_BULK_IN 2
-#define SOCKLND_CONN_BULK_OUT 3
-#define SOCKLND_CONN_NTYPES 4
-
-#define SOCKLND_CONN_ACK SOCKLND_CONN_BULK_IN
-
-#endif
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_cfg.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_cfg.h
deleted file mode 100644
index 11b51d93f64c..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_cfg.h
+++ /dev/null
@@ -1,261 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- */
-
-#ifndef _UAPI_LUSTRE_CFG_H_
-#define _UAPI_LUSTRE_CFG_H_
-
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <uapi/linux/lustre/lustre_user.h>
-
-/** \defgroup cfg cfg
- *
- * @{
- */
-
-/*
- * 1cf6
- * lcfG
- */
-#define LUSTRE_CFG_VERSION 0x1cf60001
-#define LUSTRE_CFG_MAX_BUFCOUNT 8
-
-#define LCFG_HDR_SIZE(count) \
- __ALIGN_KERNEL(offsetof(struct lustre_cfg, lcfg_buflens[(count)]), 8)
-
-/** If the LCFG_REQUIRED bit is set in a configuration command,
- * then the client is required to understand this parameter
- * in order to mount the filesystem. If it does not understand
- * a REQUIRED command the client mount will fail.
- */
-#define LCFG_REQUIRED 0x0001000
-
-enum lcfg_command_type {
- LCFG_ATTACH = 0x00cf001, /**< create a new obd instance */
- LCFG_DETACH = 0x00cf002, /**< destroy obd instance */
- LCFG_SETUP = 0x00cf003, /**< call type-specific setup */
- LCFG_CLEANUP = 0x00cf004, /**< call type-specific cleanup
- */
- LCFG_ADD_UUID = 0x00cf005, /**< add a nid to a niduuid */
- LCFG_DEL_UUID = 0x00cf006, /**< remove a nid from
- * a niduuid
- */
- LCFG_MOUNTOPT = 0x00cf007, /**< create a profile
- * (mdc, osc)
- */
- LCFG_DEL_MOUNTOPT = 0x00cf008, /**< destroy a profile */
- LCFG_SET_TIMEOUT = 0x00cf009, /**< set obd_timeout */
- LCFG_SET_UPCALL = 0x00cf00a, /**< deprecated */
- LCFG_ADD_CONN = 0x00cf00b, /**< add a failover niduuid to
- * an obd
- */
- LCFG_DEL_CONN = 0x00cf00c, /**< remove a failover niduuid */
- LCFG_LOV_ADD_OBD = 0x00cf00d, /**< add an osc to a lov */
- LCFG_LOV_DEL_OBD = 0x00cf00e, /**< remove an osc from a lov */
- LCFG_PARAM = 0x00cf00f, /**< set a proc parameter */
- LCFG_MARKER = 0x00cf010, /**< metadata about next
- * cfg rec
- */
- LCFG_LOG_START = 0x00ce011, /**< mgc only, process a
- * cfg log
- */
- LCFG_LOG_END = 0x00ce012, /**< stop processing updates */
- LCFG_LOV_ADD_INA = 0x00ce013, /**< like LOV_ADD_OBD,
- * inactive
- */
- LCFG_ADD_MDC = 0x00cf014, /**< add an mdc to a lmv */
- LCFG_DEL_MDC = 0x00cf015, /**< remove an mdc from a lmv */
- LCFG_SPTLRPC_CONF = 0x00ce016, /**< security */
- LCFG_POOL_NEW = 0x00ce020, /**< create an ost pool name */
- LCFG_POOL_ADD = 0x00ce021, /**< add an ost to a pool */
- LCFG_POOL_REM = 0x00ce022, /**< remove an ost from a pool */
- LCFG_POOL_DEL = 0x00ce023, /**< destroy an ost pool name */
- LCFG_SET_LDLM_TIMEOUT = 0x00ce030, /**< set ldlm_timeout */
- LCFG_PRE_CLEANUP = 0x00cf031, /**< call type-specific pre
- * cleanup cleanup
- */
- LCFG_SET_PARAM = 0x00ce032, /**< use set_param syntax to set
- * a proc parameters
- */
-};
-
-struct lustre_cfg_bufs {
- void *lcfg_buf[LUSTRE_CFG_MAX_BUFCOUNT];
- __u32 lcfg_buflen[LUSTRE_CFG_MAX_BUFCOUNT];
- __u32 lcfg_bufcount;
-};
-
-struct lustre_cfg {
- __u32 lcfg_version;
- __u32 lcfg_command;
-
- __u32 lcfg_num;
- __u32 lcfg_flags;
- __u64 lcfg_nid;
- __u32 lcfg_nal; /* not used any more */
-
- __u32 lcfg_bufcount;
- __u32 lcfg_buflens[0];
-};
-
-enum cfg_record_type {
- PORTALS_CFG_TYPE = 1,
- LUSTRE_CFG_TYPE = 123,
-};
-
-#define LUSTRE_CFG_BUFLEN(lcfg, idx) \
- ((lcfg)->lcfg_bufcount <= (idx) ? 0 : (lcfg)->lcfg_buflens[(idx)])
-
-static inline void lustre_cfg_bufs_set(struct lustre_cfg_bufs *bufs,
- __u32 index, void *buf, __u32 buflen)
-{
- if (index >= LUSTRE_CFG_MAX_BUFCOUNT)
- return;
-
- if (!bufs)
- return;
-
- if (bufs->lcfg_bufcount <= index)
- bufs->lcfg_bufcount = index + 1;
-
- bufs->lcfg_buf[index] = buf;
- bufs->lcfg_buflen[index] = buflen;
-}
-
-static inline void lustre_cfg_bufs_set_string(struct lustre_cfg_bufs *bufs,
- __u32 index, char *str)
-{
- lustre_cfg_bufs_set(bufs, index, str, str ? strlen(str) + 1 : 0);
-}
-
-static inline void lustre_cfg_bufs_reset(struct lustre_cfg_bufs *bufs,
- char *name)
-{
- memset((bufs), 0, sizeof(*bufs));
- if (name)
- lustre_cfg_bufs_set_string(bufs, 0, name);
-}
-
-static inline void *lustre_cfg_buf(struct lustre_cfg *lcfg, __u32 index)
-{
- __u32 i;
- size_t offset;
- __u32 bufcount;
-
- if (!lcfg)
- return NULL;
-
- bufcount = lcfg->lcfg_bufcount;
- if (index >= bufcount)
- return NULL;
-
- offset = LCFG_HDR_SIZE(lcfg->lcfg_bufcount);
- for (i = 0; i < index; i++)
- offset += __ALIGN_KERNEL(lcfg->lcfg_buflens[i], 8);
- return (char *)lcfg + offset;
-}
-
-static inline void lustre_cfg_bufs_init(struct lustre_cfg_bufs *bufs,
- struct lustre_cfg *lcfg)
-{
- __u32 i;
-
- bufs->lcfg_bufcount = lcfg->lcfg_bufcount;
- for (i = 0; i < bufs->lcfg_bufcount; i++) {
- bufs->lcfg_buflen[i] = lcfg->lcfg_buflens[i];
- bufs->lcfg_buf[i] = lustre_cfg_buf(lcfg, i);
- }
-}
-
-static inline __u32 lustre_cfg_len(__u32 bufcount, __u32 *buflens)
-{
- __u32 i;
- __u32 len;
-
- len = LCFG_HDR_SIZE(bufcount);
- for (i = 0; i < bufcount; i++)
- len += __ALIGN_KERNEL(buflens[i], 8);
-
- return __ALIGN_KERNEL(len, 8);
-}
-
-static inline void lustre_cfg_init(struct lustre_cfg *lcfg, int cmd,
- struct lustre_cfg_bufs *bufs)
-{
- char *ptr;
- __u32 i;
-
- lcfg->lcfg_version = LUSTRE_CFG_VERSION;
- lcfg->lcfg_command = cmd;
- lcfg->lcfg_bufcount = bufs->lcfg_bufcount;
-
- ptr = (char *)lcfg + LCFG_HDR_SIZE(lcfg->lcfg_bufcount);
- for (i = 0; i < lcfg->lcfg_bufcount; i++) {
- lcfg->lcfg_buflens[i] = bufs->lcfg_buflen[i];
- if (bufs->lcfg_buf[i]) {
- memcpy(ptr, bufs->lcfg_buf[i], bufs->lcfg_buflen[i]);
- ptr += __ALIGN_KERNEL(bufs->lcfg_buflen[i], 8);
- }
- }
-}
-
-static inline int lustre_cfg_sanity_check(void *buf, size_t len)
-{
- struct lustre_cfg *lcfg = (struct lustre_cfg *)buf;
-
- if (!lcfg)
- return -EINVAL;
-
- /* check that the first bits of the struct are valid */
- if (len < LCFG_HDR_SIZE(0))
- return -EINVAL;
-
- if (lcfg->lcfg_version != LUSTRE_CFG_VERSION)
- return -EINVAL;
-
- if (lcfg->lcfg_bufcount >= LUSTRE_CFG_MAX_BUFCOUNT)
- return -EINVAL;
-
- /* check that the buflens are valid */
- if (len < LCFG_HDR_SIZE(lcfg->lcfg_bufcount))
- return -EINVAL;
-
- /* make sure all the pointers point inside the data */
- if (len < lustre_cfg_len(lcfg->lcfg_bufcount, lcfg->lcfg_buflens))
- return -EINVAL;
-
- return 0;
-}
-
-/** @} cfg */
-
-#endif /* _UAPI_LUSTRE_CFG_H_ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_fid.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_fid.h
deleted file mode 100644
index 2e7a8d103777..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_fid.h
+++ /dev/null
@@ -1,293 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2014, Intel Corporation.
- *
- * Copyright 2016 Cray Inc, all rights reserved.
- * Author: Ben Evans.
- *
- * all fid manipulation functions go here
- *
- * FIDS are globally unique within a Lustre filessytem, and are made up
- * of three parts: sequence, Object ID, and version.
- *
- */
-#ifndef _UAPI_LUSTRE_FID_H_
-#define _UAPI_LUSTRE_FID_H_
-
-#include <uapi/linux/lustre/lustre_idl.h>
-
-/** returns fid object sequence */
-static inline __u64 fid_seq(const struct lu_fid *fid)
-{
- return fid->f_seq;
-}
-
-/** returns fid object id */
-static inline __u32 fid_oid(const struct lu_fid *fid)
-{
- return fid->f_oid;
-}
-
-/** returns fid object version */
-static inline __u32 fid_ver(const struct lu_fid *fid)
-{
- return fid->f_ver;
-}
-
-static inline void fid_zero(struct lu_fid *fid)
-{
- memset(fid, 0, sizeof(*fid));
-}
-
-static inline __u64 fid_ver_oid(const struct lu_fid *fid)
-{
- return (__u64)fid_ver(fid) << 32 | fid_oid(fid);
-}
-
-static inline bool fid_seq_is_mdt0(__u64 seq)
-{
- return seq == FID_SEQ_OST_MDT0;
-}
-
-static inline bool fid_seq_is_mdt(__u64 seq)
-{
- return seq == FID_SEQ_OST_MDT0 || seq >= FID_SEQ_NORMAL;
-};
-
-static inline bool fid_seq_is_echo(__u64 seq)
-{
- return seq == FID_SEQ_ECHO;
-}
-
-static inline bool fid_is_echo(const struct lu_fid *fid)
-{
- return fid_seq_is_echo(fid_seq(fid));
-}
-
-static inline bool fid_seq_is_llog(__u64 seq)
-{
- return seq == FID_SEQ_LLOG;
-}
-
-static inline bool fid_is_llog(const struct lu_fid *fid)
-{
- /* file with OID == 0 is not llog but contains last oid */
- return fid_seq_is_llog(fid_seq(fid)) && fid_oid(fid) > 0;
-}
-
-static inline bool fid_seq_is_rsvd(__u64 seq)
-{
- return seq > FID_SEQ_OST_MDT0 && seq <= FID_SEQ_RSVD;
-};
-
-static inline bool fid_seq_is_special(__u64 seq)
-{
- return seq == FID_SEQ_SPECIAL;
-};
-
-static inline bool fid_seq_is_local_file(__u64 seq)
-{
- return seq == FID_SEQ_LOCAL_FILE ||
- seq == FID_SEQ_LOCAL_NAME;
-};
-
-static inline bool fid_seq_is_root(__u64 seq)
-{
- return seq == FID_SEQ_ROOT;
-}
-
-static inline bool fid_seq_is_dot(__u64 seq)
-{
- return seq == FID_SEQ_DOT_LUSTRE;
-}
-
-static inline bool fid_seq_is_default(__u64 seq)
-{
- return seq == FID_SEQ_LOV_DEFAULT;
-}
-
-static inline bool fid_is_mdt0(const struct lu_fid *fid)
-{
- return fid_seq_is_mdt0(fid_seq(fid));
-}
-
-/**
- * Check if a fid is igif or not.
- * \param fid the fid to be tested.
- * \return true if the fid is an igif; otherwise false.
- */
-static inline bool fid_seq_is_igif(__u64 seq)
-{
- return seq >= FID_SEQ_IGIF && seq <= FID_SEQ_IGIF_MAX;
-}
-
-static inline bool fid_is_igif(const struct lu_fid *fid)
-{
- return fid_seq_is_igif(fid_seq(fid));
-}
-
-/**
- * Check if a fid is idif or not.
- * \param fid the fid to be tested.
- * \return true if the fid is an idif; otherwise false.
- */
-static inline bool fid_seq_is_idif(__u64 seq)
-{
- return seq >= FID_SEQ_IDIF && seq <= FID_SEQ_IDIF_MAX;
-}
-
-static inline bool fid_is_idif(const struct lu_fid *fid)
-{
- return fid_seq_is_idif(fid_seq(fid));
-}
-
-static inline bool fid_is_local_file(const struct lu_fid *fid)
-{
- return fid_seq_is_local_file(fid_seq(fid));
-}
-
-static inline bool fid_seq_is_norm(__u64 seq)
-{
- return (seq >= FID_SEQ_NORMAL);
-}
-
-static inline bool fid_is_norm(const struct lu_fid *fid)
-{
- return fid_seq_is_norm(fid_seq(fid));
-}
-
-/* convert an OST objid into an IDIF FID SEQ number */
-static inline __u64 fid_idif_seq(__u64 id, __u32 ost_idx)
-{
- return FID_SEQ_IDIF | (ost_idx << 16) | ((id >> 32) & 0xffff);
-}
-
-/* convert a packed IDIF FID into an OST objid */
-static inline __u64 fid_idif_id(__u64 seq, __u32 oid, __u32 ver)
-{
- return ((__u64)ver << 48) | ((seq & 0xffff) << 32) | oid;
-}
-
-static inline __u32 idif_ost_idx(__u64 seq)
-{
- return (seq >> 16) & 0xffff;
-}
-
-/* extract ost index from IDIF FID */
-static inline __u32 fid_idif_ost_idx(const struct lu_fid *fid)
-{
- return idif_ost_idx(fid_seq(fid));
-}
-
-/**
- * Get inode number from an igif.
- * \param fid an igif to get inode number from.
- * \return inode number for the igif.
- */
-static inline ino_t lu_igif_ino(const struct lu_fid *fid)
-{
- return fid_seq(fid);
-}
-
-/**
- * Get inode generation from an igif.
- * \param fid an igif to get inode generation from.
- * \return inode generation for the igif.
- */
-static inline __u32 lu_igif_gen(const struct lu_fid *fid)
-{
- return fid_oid(fid);
-}
-
-/**
- * Build igif from the inode number/generation.
- */
-static inline void lu_igif_build(struct lu_fid *fid, __u32 ino, __u32 gen)
-{
- fid->f_seq = ino;
- fid->f_oid = gen;
- fid->f_ver = 0;
-}
-
-/*
- * Fids are transmitted across network (in the sender byte-ordering),
- * and stored on disk in big-endian order.
- */
-static inline void fid_cpu_to_le(struct lu_fid *dst, const struct lu_fid *src)
-{
- dst->f_seq = __cpu_to_le64(fid_seq(src));
- dst->f_oid = __cpu_to_le32(fid_oid(src));
- dst->f_ver = __cpu_to_le32(fid_ver(src));
-}
-
-static inline void fid_le_to_cpu(struct lu_fid *dst, const struct lu_fid *src)
-{
- dst->f_seq = __le64_to_cpu(fid_seq(src));
- dst->f_oid = __le32_to_cpu(fid_oid(src));
- dst->f_ver = __le32_to_cpu(fid_ver(src));
-}
-
-static inline void fid_cpu_to_be(struct lu_fid *dst, const struct lu_fid *src)
-{
- dst->f_seq = __cpu_to_be64(fid_seq(src));
- dst->f_oid = __cpu_to_be32(fid_oid(src));
- dst->f_ver = __cpu_to_be32(fid_ver(src));
-}
-
-static inline void fid_be_to_cpu(struct lu_fid *dst, const struct lu_fid *src)
-{
- dst->f_seq = __be64_to_cpu(fid_seq(src));
- dst->f_oid = __be32_to_cpu(fid_oid(src));
- dst->f_ver = __be32_to_cpu(fid_ver(src));
-}
-
-static inline bool fid_is_sane(const struct lu_fid *fid)
-{
- return fid && ((fid_seq(fid) >= FID_SEQ_START && !fid_ver(fid)) ||
- fid_is_igif(fid) || fid_is_idif(fid) ||
- fid_seq_is_rsvd(fid_seq(fid)));
-}
-
-static inline bool lu_fid_eq(const struct lu_fid *f0, const struct lu_fid *f1)
-{
- return !memcmp(f0, f1, sizeof(*f0));
-}
-
-static inline int lu_fid_cmp(const struct lu_fid *f0,
- const struct lu_fid *f1)
-{
- if (fid_seq(f0) != fid_seq(f1))
- return fid_seq(f0) > fid_seq(f1) ? 1 : -1;
-
- if (fid_oid(f0) != fid_oid(f1))
- return fid_oid(f0) > fid_oid(f1) ? 1 : -1;
-
- if (fid_ver(f0) != fid_ver(f1))
- return fid_ver(f0) > fid_ver(f1) ? 1 : -1;
-
- return 0;
-}
-#endif
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_fiemap.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_fiemap.h
deleted file mode 100644
index d375a476f5ea..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_fiemap.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2014, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * FIEMAP data structures and flags. This header file will be used until
- * fiemap.h is available in the upstream kernel.
- *
- * Author: Kalpak Shah <kalpak.shah@sun.com>
- * Author: Andreas Dilger <adilger@sun.com>
- */
-
-#ifndef _LUSTRE_FIEMAP_H
-#define _LUSTRE_FIEMAP_H
-
-#include <stddef.h>
-#include <linux/fiemap.h>
-
-/* XXX: We use fiemap_extent::fe_reserved[0] */
-#define fe_device fe_reserved[0]
-
-static inline size_t fiemap_count_to_size(size_t extent_count)
-{
- return sizeof(struct fiemap) + extent_count *
- sizeof(struct fiemap_extent);
-}
-
-static inline unsigned int fiemap_size_to_count(size_t array_size)
-{
- return (array_size - sizeof(struct fiemap)) /
- sizeof(struct fiemap_extent);
-}
-
-#define FIEMAP_FLAG_DEVICE_ORDER 0x40000000 /* return device ordered mapping */
-
-#ifdef FIEMAP_FLAGS_COMPAT
-#undef FIEMAP_FLAGS_COMPAT
-#endif
-
-/* Lustre specific flags - use a high bit, don't conflict with upstream flag */
-#define FIEMAP_EXTENT_NO_DIRECT 0x40000000 /* Data mapping undefined */
-#define FIEMAP_EXTENT_NET 0x80000000 /* Data stored remotely.
- * Sets NO_DIRECT flag
- */
-
-#endif /* _LUSTRE_FIEMAP_H */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_idl.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_idl.h
deleted file mode 100644
index 6c7e3992d646..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_idl.h
+++ /dev/null
@@ -1,2690 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * Lustre wire protocol definitions.
- */
-
-/** \defgroup lustreidl lustreidl
- *
- * Lustre wire protocol definitions.
- *
- * ALL structs passing over the wire should be declared here. Structs
- * that are used in interfaces with userspace should go in lustre_user.h.
- *
- * All structs being declared here should be built from simple fixed-size
- * types (__u8, __u16, __u32, __u64) or be built from other types or
- * structs also declared in this file. Similarly, all flags and magic
- * values in those structs should also be declared here. This ensures
- * that the Lustre wire protocol is not influenced by external dependencies.
- *
- * The only other acceptable items in this file are VERY SIMPLE accessor
- * functions to avoid callers grubbing inside the structures. Nothing that
- * depends on external functions or definitions should be in here.
- *
- * Structs must be properly aligned to put 64-bit values on an 8-byte
- * boundary. Any structs being added here must also be added to
- * utils/wirecheck.c and "make newwiretest" run to regenerate the
- * utils/wiretest.c sources. This allows us to verify that wire structs
- * have the proper alignment/size on all architectures.
- *
- * DO NOT CHANGE any of the structs, flags, values declared here and used
- * in released Lustre versions. Some structs may have padding fields that
- * can be used. Some structs might allow addition at the end (verify this
- * in the code to ensure that new/old clients that see this larger struct
- * do not fail, otherwise you need to implement protocol compatibility).
- *
- * @{
- */
-
-#ifndef _LUSTRE_IDL_H_
-#define _LUSTRE_IDL_H_
-
-#include <asm/byteorder.h>
-#include <linux/types.h>
-
-#include <uapi/linux/lnet/lnet-types.h>
-/* Defn's shared with user-space. */
-#include <uapi/linux/lustre/lustre_user.h>
-#include <uapi/linux/lustre/lustre_ver.h>
-
-/*
- * GENERAL STUFF
- */
-/* FOO_REQUEST_PORTAL is for incoming requests on the FOO
- * FOO_REPLY_PORTAL is for incoming replies on the FOO
- * FOO_BULK_PORTAL is for incoming bulk on the FOO
- */
-
-/* Lustre service names are following the format
- * service name + MDT + seq name
- */
-#define LUSTRE_MDT_MAXNAMELEN 80
-
-#define CONNMGR_REQUEST_PORTAL 1
-#define CONNMGR_REPLY_PORTAL 2
-/*#define OSC_REQUEST_PORTAL 3 */
-#define OSC_REPLY_PORTAL 4
-/*#define OSC_BULK_PORTAL 5 */
-#define OST_IO_PORTAL 6
-#define OST_CREATE_PORTAL 7
-#define OST_BULK_PORTAL 8
-/*#define MDC_REQUEST_PORTAL 9 */
-#define MDC_REPLY_PORTAL 10
-/*#define MDC_BULK_PORTAL 11 */
-#define MDS_REQUEST_PORTAL 12
-/*#define MDS_REPLY_PORTAL 13 */
-#define MDS_BULK_PORTAL 14
-#define LDLM_CB_REQUEST_PORTAL 15
-#define LDLM_CB_REPLY_PORTAL 16
-#define LDLM_CANCEL_REQUEST_PORTAL 17
-#define LDLM_CANCEL_REPLY_PORTAL 18
-/*#define PTLBD_REQUEST_PORTAL 19 */
-/*#define PTLBD_REPLY_PORTAL 20 */
-/*#define PTLBD_BULK_PORTAL 21 */
-#define MDS_SETATTR_PORTAL 22
-#define MDS_READPAGE_PORTAL 23
-#define OUT_PORTAL 24
-
-#define MGC_REPLY_PORTAL 25
-#define MGS_REQUEST_PORTAL 26
-#define MGS_REPLY_PORTAL 27
-#define OST_REQUEST_PORTAL 28
-#define FLD_REQUEST_PORTAL 29
-#define SEQ_METADATA_PORTAL 30
-#define SEQ_DATA_PORTAL 31
-#define SEQ_CONTROLLER_PORTAL 32
-#define MGS_BULK_PORTAL 33
-
-/* Portal 63 is reserved for the Cray Inc DVS - nic@cray.com, roe@cray.com,
- * n8851@cray.com
- */
-
-/* packet types */
-#define PTL_RPC_MSG_REQUEST 4711
-#define PTL_RPC_MSG_ERR 4712
-#define PTL_RPC_MSG_REPLY 4713
-
-/* DON'T use swabbed values of MAGIC as magic! */
-#define LUSTRE_MSG_MAGIC_V2 0x0BD00BD3
-#define LUSTRE_MSG_MAGIC_V2_SWABBED 0xD30BD00B
-
-#define LUSTRE_MSG_MAGIC LUSTRE_MSG_MAGIC_V2
-
-#define PTLRPC_MSG_VERSION 0x00000003
-#define LUSTRE_VERSION_MASK 0xffff0000
-#define LUSTRE_OBD_VERSION 0x00010000
-#define LUSTRE_MDS_VERSION 0x00020000
-#define LUSTRE_OST_VERSION 0x00030000
-#define LUSTRE_DLM_VERSION 0x00040000
-#define LUSTRE_LOG_VERSION 0x00050000
-#define LUSTRE_MGS_VERSION 0x00060000
-
-/**
- * Describes a range of sequence, lsr_start is included but lsr_end is
- * not in the range.
- * Same structure is used in fld module where lsr_index field holds mdt id
- * of the home mdt.
- */
-struct lu_seq_range {
- __u64 lsr_start;
- __u64 lsr_end;
- __u32 lsr_index;
- __u32 lsr_flags;
-};
-
-struct lu_seq_range_array {
- __u32 lsra_count;
- __u32 lsra_padding;
- struct lu_seq_range lsra_lsr[0];
-};
-
-#define LU_SEQ_RANGE_MDT 0x0
-#define LU_SEQ_RANGE_OST 0x1
-#define LU_SEQ_RANGE_ANY 0x3
-
-#define LU_SEQ_RANGE_MASK 0x3
-
-/** \defgroup lu_fid lu_fid
- * @{
- */
-
-/**
- * Flags for lustre_mdt_attrs::lma_compat and lustre_mdt_attrs::lma_incompat.
- * Deprecated since HSM and SOM attributes are now stored in separate on-disk
- * xattr.
- */
-enum lma_compat {
- LMAC_HSM = 0x00000001,
-/* LMAC_SOM = 0x00000002, obsolete since 2.8.0 */
- LMAC_NOT_IN_OI = 0x00000004, /* the object does NOT need OI mapping */
- LMAC_FID_ON_OST = 0x00000008, /* For OST-object, its OI mapping is
- * under /O/<seq>/d<x>.
- */
-};
-
-/**
- * Masks for all features that should be supported by a Lustre version to
- * access a specific file.
- * This information is stored in lustre_mdt_attrs::lma_incompat.
- */
-enum lma_incompat {
- LMAI_RELEASED = 0x00000001, /* file is released */
- LMAI_AGENT = 0x00000002, /* agent inode */
- LMAI_REMOTE_PARENT = 0x00000004, /* the parent of the object
- * is on the remote MDT
- */
-};
-
-#define LMA_INCOMPAT_SUPP (LMAI_AGENT | LMAI_REMOTE_PARENT)
-
-/**
- * fid constants
- */
-enum {
- /** LASTID file has zero OID */
- LUSTRE_FID_LASTID_OID = 0UL,
- /** initial fid id value */
- LUSTRE_FID_INIT_OID = 1UL
-};
-
-/* copytool uses a 32b bitmask field to encode archive-Ids during register
- * with MDT thru kuc.
- * archive num = 0 => all
- * archive num from 1 to 32
- */
-#define LL_HSM_MAX_ARCHIVE (sizeof(__u32) * 8)
-
-/**
- * Note that reserved SEQ numbers below 12 will conflict with ldiskfs
- * inodes in the IGIF namespace, so these reserved SEQ numbers can be
- * used for other purposes and not risk collisions with existing inodes.
- *
- * Different FID Format
- * http://wiki.old.lustre.org/index.php/Architecture_-_Interoperability_fids_zfs
- */
-enum fid_seq {
- FID_SEQ_OST_MDT0 = 0,
- FID_SEQ_LLOG = 1, /* unnamed llogs */
- FID_SEQ_ECHO = 2,
- FID_SEQ_OST_MDT1 = 3,
- FID_SEQ_OST_MAX = 9, /* Max MDT count before OST_on_FID */
- FID_SEQ_LLOG_NAME = 10, /* named llogs */
- FID_SEQ_RSVD = 11,
- FID_SEQ_IGIF = 12,
- FID_SEQ_IGIF_MAX = 0x0ffffffffULL,
- FID_SEQ_IDIF = 0x100000000ULL,
- FID_SEQ_IDIF_MAX = 0x1ffffffffULL,
- /* Normal FID sequence starts from this value, i.e. 1<<33 */
- FID_SEQ_START = 0x200000000ULL,
- /* sequence for local pre-defined FIDs listed in local_oid */
- FID_SEQ_LOCAL_FILE = 0x200000001ULL,
- FID_SEQ_DOT_LUSTRE = 0x200000002ULL,
- /* sequence is used for local named objects FIDs generated
- * by local_object_storage library
- */
- FID_SEQ_LOCAL_NAME = 0x200000003ULL,
- /* Because current FLD will only cache the fid sequence, instead
- * of oid on the client side, if the FID needs to be exposed to
- * clients sides, it needs to make sure all of fids under one
- * sequence will be located in one MDT.
- */
- FID_SEQ_SPECIAL = 0x200000004ULL,
- FID_SEQ_QUOTA = 0x200000005ULL,
- FID_SEQ_QUOTA_GLB = 0x200000006ULL,
- FID_SEQ_ROOT = 0x200000007ULL, /* Located on MDT0 */
- FID_SEQ_NORMAL = 0x200000400ULL,
- FID_SEQ_LOV_DEFAULT = 0xffffffffffffffffULL
-};
-
-#define OBIF_OID_MAX_BITS 32
-#define OBIF_MAX_OID (1ULL << OBIF_OID_MAX_BITS)
-#define OBIF_OID_MASK ((1ULL << OBIF_OID_MAX_BITS) - 1)
-#define IDIF_OID_MAX_BITS 48
-#define IDIF_MAX_OID (1ULL << IDIF_OID_MAX_BITS)
-#define IDIF_OID_MASK ((1ULL << IDIF_OID_MAX_BITS) - 1)
-
-/** OID for FID_SEQ_SPECIAL */
-enum special_oid {
- /* Big Filesystem Lock to serialize rename operations */
- FID_OID_SPECIAL_BFL = 1UL,
-};
-
-/** OID for FID_SEQ_DOT_LUSTRE */
-enum dot_lustre_oid {
- FID_OID_DOT_LUSTRE = 1UL,
- FID_OID_DOT_LUSTRE_OBF = 2UL,
-};
-
-/** OID for FID_SEQ_ROOT */
-enum root_oid {
- FID_OID_ROOT = 1UL,
- FID_OID_ECHO_ROOT = 2UL,
-};
-
-/** @} lu_fid */
-
-/** \defgroup lu_dir lu_dir
- * @{
- */
-
-/**
- * Enumeration of possible directory entry attributes.
- *
- * Attributes follow directory entry header in the order they appear in this
- * enumeration.
- */
-enum lu_dirent_attrs {
- LUDA_FID = 0x0001,
- LUDA_TYPE = 0x0002,
- LUDA_64BITHASH = 0x0004,
-};
-
-/**
- * Layout of readdir pages, as transmitted on wire.
- */
-struct lu_dirent {
- /** valid if LUDA_FID is set. */
- struct lu_fid lde_fid;
- /** a unique entry identifier: a hash or an offset. */
- __u64 lde_hash;
- /** total record length, including all attributes. */
- __u16 lde_reclen;
- /** name length */
- __u16 lde_namelen;
- /** optional variable size attributes following this entry.
- * taken from enum lu_dirent_attrs.
- */
- __u32 lde_attrs;
- /** name is followed by the attributes indicated in ->ldp_attrs, in
- * their natural order. After the last attribute, padding bytes are
- * added to make ->lde_reclen a multiple of 8.
- */
- char lde_name[0];
-};
-
-/*
- * Definitions of optional directory entry attributes formats.
- *
- * Individual attributes do not have their length encoded in a generic way. It
- * is assumed that consumer of an attribute knows its format. This means that
- * it is impossible to skip over an unknown attribute, except by skipping over all
- * remaining attributes (by using ->lde_reclen), which is not too
- * constraining, because new server versions will append new attributes at
- * the end of an entry.
- */
-
-/**
- * Fid directory attribute: a fid of an object referenced by the entry. This
- * will be almost always requested by the client and supplied by the server.
- *
- * Aligned to 8 bytes.
- */
-/* To have compatibility with 1.8, lets have fid in lu_dirent struct. */
-
-/**
- * File type.
- *
- * Aligned to 2 bytes.
- */
-struct luda_type {
- __u16 lt_type;
-};
-
-#ifndef IFSHIFT
-#define IFSHIFT 12
-#endif
-
-#ifndef IFTODT
-#define IFTODT(type) (((type) & S_IFMT) >> IFSHIFT)
-#endif
-#ifndef DTTOIF
-#define DTTOIF(dirtype) ((dirtype) << IFSHIFT)
-#endif
-
-struct lu_dirpage {
- __le64 ldp_hash_start;
- __le64 ldp_hash_end;
- __le32 ldp_flags;
- __le32 ldp_pad0;
- struct lu_dirent ldp_entries[0];
-};
-
-enum lu_dirpage_flags {
- /**
- * dirpage contains no entry.
- */
- LDF_EMPTY = 1 << 0,
- /**
- * last entry's lde_hash equals ldp_hash_end.
- */
- LDF_COLLIDE = 1 << 1
-};
-
-static inline struct lu_dirent *lu_dirent_start(struct lu_dirpage *dp)
-{
- if (__le32_to_cpu(dp->ldp_flags) & LDF_EMPTY)
- return NULL;
- else
- return dp->ldp_entries;
-}
-
-static inline struct lu_dirent *lu_dirent_next(struct lu_dirent *ent)
-{
- struct lu_dirent *next;
-
- if (__le16_to_cpu(ent->lde_reclen) != 0)
- next = ((void *)ent) + __le16_to_cpu(ent->lde_reclen);
- else
- next = NULL;
-
- return next;
-}
-
-static inline size_t lu_dirent_calc_size(size_t namelen, __u16 attr)
-{
- size_t size;
-
- if (attr & LUDA_TYPE) {
- const size_t align = sizeof(struct luda_type) - 1;
-
- size = (sizeof(struct lu_dirent) + namelen + align) & ~align;
- size += sizeof(struct luda_type);
- } else {
- size = sizeof(struct lu_dirent) + namelen;
- }
-
- return (size + 7) & ~7;
-}
-
-#define MDS_DIR_END_OFF 0xfffffffffffffffeULL
-
-/**
- * MDS_READPAGE page size
- *
- * This is the directory page size packed in MDS_READPAGE RPC.
- * It's different than PAGE_SIZE because the client needs to
- * access the struct lu_dirpage header packed at the beginning of
- * the "page" and without this there isn't any way to know find the
- * lu_dirpage header is if client and server PAGE_SIZE differ.
- */
-#define LU_PAGE_SHIFT 12
-#define LU_PAGE_SIZE (1UL << LU_PAGE_SHIFT)
-#define LU_PAGE_MASK (~(LU_PAGE_SIZE - 1))
-
-#define LU_PAGE_COUNT (1 << (PAGE_SHIFT - LU_PAGE_SHIFT))
-
-/** @} lu_dir */
-
-struct lustre_handle {
- __u64 cookie;
-};
-
-#define DEAD_HANDLE_MAGIC 0xdeadbeefcafebabeULL
-
-static inline bool lustre_handle_is_used(const struct lustre_handle *lh)
-{
- return lh->cookie != 0ull;
-}
-
-static inline bool lustre_handle_equal(const struct lustre_handle *lh1,
- const struct lustre_handle *lh2)
-{
- return lh1->cookie == lh2->cookie;
-}
-
-static inline void lustre_handle_copy(struct lustre_handle *tgt,
- const struct lustre_handle *src)
-{
- tgt->cookie = src->cookie;
-}
-
-/* flags for lm_flags */
-#define MSGHDR_AT_SUPPORT 0x1
-#define MSGHDR_CKSUM_INCOMPAT18 0x2
-
-#define lustre_msg lustre_msg_v2
-/* we depend on this structure to be 8-byte aligned */
-/* this type is only endian-adjusted in lustre_unpack_msg() */
-struct lustre_msg_v2 {
- __u32 lm_bufcount;
- __u32 lm_secflvr;
- __u32 lm_magic;
- __u32 lm_repsize;
- __u32 lm_cksum;
- __u32 lm_flags;
- __u32 lm_padding_2;
- __u32 lm_padding_3;
- __u32 lm_buflens[0];
-};
-
-/* without gss, ptlrpc_body is put at the first buffer. */
-#define PTLRPC_NUM_VERSIONS 4
-
-struct ptlrpc_body_v3 {
- struct lustre_handle pb_handle;
- __u32 pb_type;
- __u32 pb_version;
- __u32 pb_opc;
- __u32 pb_status;
- __u64 pb_last_xid; /* highest replied XID without lower unreplied XID */
- __u16 pb_tag; /* virtual slot idx for multiple modifying RPCs */
- __u16 pb_padding0;
- __u32 pb_padding1;
- __u64 pb_last_committed;
- __u64 pb_transno;
- __u32 pb_flags;
- __u32 pb_op_flags;
- __u32 pb_conn_cnt;
- __u32 pb_timeout; /* for req, the deadline, for rep, the service est */
- __u32 pb_service_time; /* for rep, actual service time */
- __u32 pb_limit;
- __u64 pb_slv;
- /* VBR: pre-versions */
- __u64 pb_pre_versions[PTLRPC_NUM_VERSIONS];
- __u64 pb_mbits; /**< match bits for bulk request */
- /* padding for future needs */
- __u64 pb_padding64_0;
- __u64 pb_padding64_1;
- __u64 pb_padding64_2;
- char pb_jobid[LUSTRE_JOBID_SIZE];
-};
-
-#define ptlrpc_body ptlrpc_body_v3
-
-struct ptlrpc_body_v2 {
- struct lustre_handle pb_handle;
- __u32 pb_type;
- __u32 pb_version;
- __u32 pb_opc;
- __u32 pb_status;
- __u64 pb_last_xid; /* highest replied XID without lower unreplied XID */
- __u16 pb_tag; /* virtual slot idx for multiple modifying RPCs */
- __u16 pb_padding0;
- __u32 pb_padding1;
- __u64 pb_last_committed;
- __u64 pb_transno;
- __u32 pb_flags;
- __u32 pb_op_flags;
- __u32 pb_conn_cnt;
- __u32 pb_timeout; /* for req, the deadline, for rep, the service est */
- __u32 pb_service_time; /* for rep, actual service time, also used for
- * net_latency of req
- */
- __u32 pb_limit;
- __u64 pb_slv;
- /* VBR: pre-versions */
- __u64 pb_pre_versions[PTLRPC_NUM_VERSIONS];
- __u64 pb_mbits; /**< unused in V2 */
- /* padding for future needs */
- __u64 pb_padding64_0;
- __u64 pb_padding64_1;
- __u64 pb_padding64_2;
-};
-
-/* message body offset for lustre_msg_v2 */
-/* ptlrpc body offset in all request/reply messages */
-#define MSG_PTLRPC_BODY_OFF 0
-
-/* normal request/reply message record offset */
-#define REQ_REC_OFF 1
-#define REPLY_REC_OFF 1
-
-/* ldlm request message body offset */
-#define DLM_LOCKREQ_OFF 1 /* lockreq offset */
-#define DLM_REQ_REC_OFF 2 /* normal dlm request record offset */
-
-/* ldlm intent lock message body offset */
-#define DLM_INTENT_IT_OFF 2 /* intent lock it offset */
-#define DLM_INTENT_REC_OFF 3 /* intent lock record offset */
-
-/* ldlm reply message body offset */
-#define DLM_LOCKREPLY_OFF 1 /* lockrep offset */
-#define DLM_REPLY_REC_OFF 2 /* reply record offset */
-
-/** only use in req->rq_{req,rep}_swab_mask */
-#define MSG_PTLRPC_HEADER_OFF 31
-
-/* Flags that are operation-specific go in the top 16 bits. */
-#define MSG_OP_FLAG_MASK 0xffff0000
-#define MSG_OP_FLAG_SHIFT 16
-
-/* Flags that apply to all requests are in the bottom 16 bits */
-#define MSG_GEN_FLAG_MASK 0x0000ffff
-#define MSG_LAST_REPLAY 0x0001
-#define MSG_RESENT 0x0002
-#define MSG_REPLAY 0x0004
-/* #define MSG_AT_SUPPORT 0x0008
- * This was used in early prototypes of adaptive timeouts, and while there
- * shouldn't be any users of that code there also isn't a need for using this
- * bits. Defer usage until at least 1.10 to avoid potential conflict.
- */
-#define MSG_DELAY_REPLAY 0x0010
-#define MSG_VERSION_REPLAY 0x0020
-#define MSG_REQ_REPLAY_DONE 0x0040
-#define MSG_LOCK_REPLAY_DONE 0x0080
-
-/*
- * Flags for all connect opcodes (MDS_CONNECT, OST_CONNECT)
- */
-
-#define MSG_CONNECT_RECOVERING 0x00000001
-#define MSG_CONNECT_RECONNECT 0x00000002
-#define MSG_CONNECT_REPLAYABLE 0x00000004
-/*#define MSG_CONNECT_PEER 0x8 */
-#define MSG_CONNECT_LIBCLIENT 0x00000010
-#define MSG_CONNECT_INITIAL 0x00000020
-#define MSG_CONNECT_ASYNC 0x00000040
-#define MSG_CONNECT_NEXT_VER 0x00000080 /* use next version of lustre_msg */
-#define MSG_CONNECT_TRANSNO 0x00000100 /* report transno */
-
-/* Connect flags */
-#define OBD_CONNECT_RDONLY 0x1ULL /*client has read-only access*/
-#define OBD_CONNECT_INDEX 0x2ULL /*connect specific LOV idx */
-#define OBD_CONNECT_MDS 0x4ULL /*connect from MDT to OST */
-#define OBD_CONNECT_GRANT 0x8ULL /*OSC gets grant at connect */
-#define OBD_CONNECT_SRVLOCK 0x10ULL /*server takes locks for cli */
-#define OBD_CONNECT_VERSION 0x20ULL /*Lustre versions in ocd */
-#define OBD_CONNECT_REQPORTAL 0x40ULL /*Separate non-IO req portal */
-#define OBD_CONNECT_ACL 0x80ULL /*access control lists */
-#define OBD_CONNECT_XATTR 0x100ULL /*client use extended attr */
-#define OBD_CONNECT_LARGE_ACL 0x200ULL /* more than 32 ACL entries */
-#define OBD_CONNECT_TRUNCLOCK 0x400ULL /*locks on server for punch */
-#define OBD_CONNECT_TRANSNO 0x800ULL /*replay sends init transno */
-#define OBD_CONNECT_IBITS 0x1000ULL /*support for inodebits locks*/
-#define OBD_CONNECT_JOIN 0x2000ULL /*files can be concatenated.
- *We do not support JOIN FILE
- *anymore, reserve this flags
- *just for preventing such bit
- *to be reused.
- */
-#define OBD_CONNECT_ATTRFID 0x4000ULL /*Server can GetAttr By Fid*/
-#define OBD_CONNECT_NODEVOH 0x8000ULL /*No open hndl on specl nodes*/
-#define OBD_CONNECT_RMT_CLIENT 0x10000ULL /* Remote client, never used
- * in production. Removed in
- * 2.9. Keep this flag to
- * avoid reuse.
- */
-#define OBD_CONNECT_RMT_CLIENT_FORCE 0x20000ULL /* Remote client by force,
- * never used in production.
- * Removed in 2.9. Keep this
- * flag to avoid reuse
- */
-#define OBD_CONNECT_BRW_SIZE 0x40000ULL /*Max bytes per rpc */
-#define OBD_CONNECT_QUOTA64 0x80000ULL /*Not used since 2.4 */
-#define OBD_CONNECT_MDS_CAPA 0x100000ULL /*MDS capability */
-#define OBD_CONNECT_OSS_CAPA 0x200000ULL /*OSS capability */
-#define OBD_CONNECT_CANCELSET 0x400000ULL /*Early batched cancels. */
-#define OBD_CONNECT_SOM 0x800000ULL /*Size on MDS */
-#define OBD_CONNECT_AT 0x1000000ULL /*client uses AT */
-#define OBD_CONNECT_LRU_RESIZE 0x2000000ULL /*LRU resize feature. */
-#define OBD_CONNECT_MDS_MDS 0x4000000ULL /*MDS-MDS connection */
-#define OBD_CONNECT_REAL 0x8000000ULL /* obsolete since 2.8 */
-#define OBD_CONNECT_CHANGE_QS 0x10000000ULL /*Not used since 2.4 */
-#define OBD_CONNECT_CKSUM 0x20000000ULL /*support several cksum algos*/
-#define OBD_CONNECT_FID 0x40000000ULL /*FID is supported by server */
-#define OBD_CONNECT_VBR 0x80000000ULL /*version based recovery */
-#define OBD_CONNECT_LOV_V3 0x100000000ULL /*client supports LOV v3 EA */
-#define OBD_CONNECT_GRANT_SHRINK 0x200000000ULL /* support grant shrink */
-#define OBD_CONNECT_SKIP_ORPHAN 0x400000000ULL /* don't reuse orphan objids */
-#define OBD_CONNECT_MAX_EASIZE 0x800000000ULL /* preserved for large EA */
-#define OBD_CONNECT_FULL20 0x1000000000ULL /* it is 2.0 client */
-#define OBD_CONNECT_LAYOUTLOCK 0x2000000000ULL /* client uses layout lock */
-#define OBD_CONNECT_64BITHASH 0x4000000000ULL /* client supports 64-bits
- * directory hash
- */
-#define OBD_CONNECT_MAXBYTES 0x8000000000ULL /* max stripe size */
-#define OBD_CONNECT_IMP_RECOV 0x10000000000ULL /* imp recovery support */
-#define OBD_CONNECT_JOBSTATS 0x20000000000ULL /* jobid in ptlrpc_body */
-#define OBD_CONNECT_UMASK 0x40000000000ULL /* create uses client umask */
-#define OBD_CONNECT_EINPROGRESS 0x80000000000ULL /* client handles -EINPROGRESS
- * RPC error properly
- */
-#define OBD_CONNECT_GRANT_PARAM 0x100000000000ULL/* extra grant params used for
- * finer space reservation
- */
-#define OBD_CONNECT_FLOCK_OWNER 0x200000000000ULL /* for the fixed 1.8
- * policy and 2.x server
- */
-#define OBD_CONNECT_LVB_TYPE 0x400000000000ULL /* variable type of LVB */
-#define OBD_CONNECT_NANOSEC_TIME 0x800000000000ULL /* nanosecond timestamps */
-#define OBD_CONNECT_LIGHTWEIGHT 0x1000000000000ULL/* lightweight connection */
-#define OBD_CONNECT_SHORTIO 0x2000000000000ULL/* short io */
-#define OBD_CONNECT_PINGLESS 0x4000000000000ULL/* pings not required */
-#define OBD_CONNECT_FLOCK_DEAD 0x8000000000000ULL/* flock deadlock detection */
-#define OBD_CONNECT_DISP_STRIPE 0x10000000000000ULL/*create stripe disposition*/
-#define OBD_CONNECT_OPEN_BY_FID 0x20000000000000ULL /* open by fid won't pack
- * name in request
- */
-#define OBD_CONNECT_LFSCK 0x40000000000000ULL/* support online LFSCK */
-#define OBD_CONNECT_UNLINK_CLOSE 0x100000000000000ULL/* close file in unlink */
-#define OBD_CONNECT_MULTIMODRPCS 0x200000000000000ULL /* support multiple modify
- * RPCs in parallel
- */
-#define OBD_CONNECT_DIR_STRIPE 0x400000000000000ULL/* striped DNE dir */
-#define OBD_CONNECT_SUBTREE 0x800000000000000ULL /* fileset mount */
-#define OBD_CONNECT_LOCK_AHEAD 0x1000000000000000ULL /* lock ahead */
-/** bulk matchbits is sent within ptlrpc_body */
-#define OBD_CONNECT_BULK_MBITS 0x2000000000000000ULL
-#define OBD_CONNECT_OBDOPACK 0x4000000000000000ULL /* compact OUT obdo */
-#define OBD_CONNECT_FLAGS2 0x8000000000000000ULL /* second flags word */
-
-/* XXX README XXX:
- * Please DO NOT add flag values here before first ensuring that this same
- * flag value is not in use on some other branch. Please clear any such
- * changes with senior engineers before starting to use a new flag. Then,
- * submit a small patch against EVERY branch that ONLY adds the new flag,
- * updates obd_connect_names[] for lprocfs_rd_connect_flags(), adds the
- * flag to check_obd_connect_data(), and updates wiretests accordingly, so it
- * can be approved and landed easily to reserve the flag for future use.
- */
-
-/* The MNE_SWAB flag is overloading the MDS_MDS bit only for the MGS
- * connection. It is a temporary bug fix for Imperative Recovery interop
- * between 2.2 and 2.3 x86/ppc nodes, and can be removed when interop for
- * 2.2 clients/servers is no longer needed. LU-1252/LU-1644.
- */
-#define OBD_CONNECT_MNE_SWAB OBD_CONNECT_MDS_MDS
-
-#define OCD_HAS_FLAG(ocd, flg) \
- (!!((ocd)->ocd_connect_flags & OBD_CONNECT_##flg))
-
-/* Features required for this version of the client to work with server */
-#define CLIENT_CONNECT_MDT_REQD (OBD_CONNECT_IBITS | OBD_CONNECT_FID | \
- OBD_CONNECT_FULL20)
-
-/* This structure is used for both request and reply.
- *
- * If we eventually have separate connect data for different types, which we
- * almost certainly will, then perhaps we stick a union in here.
- */
-struct obd_connect_data {
- __u64 ocd_connect_flags; /* OBD_CONNECT_* per above */
- __u32 ocd_version; /* lustre release version number */
- __u32 ocd_grant; /* initial cache grant amount (bytes) */
- __u32 ocd_index; /* LOV index to connect to */
- __u32 ocd_brw_size; /* Maximum BRW size in bytes */
- __u64 ocd_ibits_known; /* inode bits this client understands */
- __u8 ocd_blocksize; /* log2 of the backend filesystem blocksize */
- __u8 ocd_inodespace; /* log2 of the per-inode space consumption */
- __u16 ocd_grant_extent; /* per-extent grant overhead, in 1K blocks */
- __u32 ocd_unused; /* also fix lustre_swab_connect */
- __u64 ocd_transno; /* first transno from client to be replayed */
- __u32 ocd_group; /* MDS group on OST */
- __u32 ocd_cksum_types; /* supported checksum algorithms */
- __u32 ocd_max_easize; /* How big LOV EA can be on MDS */
- __u32 ocd_instance; /* instance # of this target */
- __u64 ocd_maxbytes; /* Maximum stripe size in bytes */
- /* Fields after ocd_maxbytes are only accessible by the receiver
- * if the corresponding flag in ocd_connect_flags is set. Accessing
- * any field after ocd_maxbytes on the receiver without a valid flag
- * may result in out-of-bound memory access and kernel oops.
- */
- __u16 ocd_maxmodrpcs; /* Maximum modify RPCs in parallel */
- __u16 padding0; /* added 2.1.0. also fix lustre_swab_connect */
- __u32 padding1; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 ocd_connect_flags2;
- __u64 padding3; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 padding4; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 padding5; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 padding6; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 padding7; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 padding8; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 padding9; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 paddingA; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 paddingB; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 paddingC; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 paddingD; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 paddingE; /* added 2.1.0. also fix lustre_swab_connect */
- __u64 paddingF; /* added 2.1.0. also fix lustre_swab_connect */
-};
-
-/* XXX README XXX:
- * Please DO NOT use any fields here before first ensuring that this same
- * field is not in use on some other branch. Please clear any such changes
- * with senior engineers before starting to use a new field. Then, submit
- * a small patch against EVERY branch that ONLY adds the new field along with
- * the matching OBD_CONNECT flag, so that can be approved and landed easily to
- * reserve the flag for future use.
- */
-
-/*
- * Supported checksum algorithms. Up to 32 checksum types are supported.
- * (32-bit mask stored in obd_connect_data::ocd_cksum_types)
- * Please update DECLARE_CKSUM_NAME/OBD_CKSUM_ALL in obd.h when adding a new
- * algorithm and also the OBD_FL_CKSUM* flags.
- */
-enum cksum_type {
- OBD_CKSUM_CRC32 = 0x00000001,
- OBD_CKSUM_ADLER = 0x00000002,
- OBD_CKSUM_CRC32C = 0x00000004,
-};
-
-/*
- * OST requests: OBDO & OBD request records
- */
-
-/* opcodes */
-enum ost_cmd {
- OST_REPLY = 0, /* reply ? */
- OST_GETATTR = 1,
- OST_SETATTR = 2,
- OST_READ = 3,
- OST_WRITE = 4,
- OST_CREATE = 5,
- OST_DESTROY = 6,
- OST_GET_INFO = 7,
- OST_CONNECT = 8,
- OST_DISCONNECT = 9,
- OST_PUNCH = 10,
- OST_OPEN = 11,
- OST_CLOSE = 12,
- OST_STATFS = 13,
- OST_SYNC = 16,
- OST_SET_INFO = 17,
- OST_QUOTACHECK = 18, /* not used since 2.4 */
- OST_QUOTACTL = 19,
- OST_QUOTA_ADJUST_QUNIT = 20, /* not used since 2.4 */
- OST_LAST_OPC
-};
-#define OST_FIRST_OPC OST_REPLY
-
-enum obdo_flags {
- OBD_FL_INLINEDATA = 0x00000001,
- OBD_FL_OBDMDEXISTS = 0x00000002,
- OBD_FL_DELORPHAN = 0x00000004, /* if set in o_flags delete orphans */
- OBD_FL_NORPC = 0x00000008, /* set in o_flags do in OSC not OST */
- OBD_FL_IDONLY = 0x00000010, /* set in o_flags only adjust obj id*/
- OBD_FL_RECREATE_OBJS = 0x00000020, /* recreate missing obj */
- OBD_FL_DEBUG_CHECK = 0x00000040, /* echo client/server debug check */
- OBD_FL_NO_USRQUOTA = 0x00000100, /* the object's owner is over quota */
- OBD_FL_NO_GRPQUOTA = 0x00000200, /* the object's group is over quota */
- OBD_FL_CREATE_CROW = 0x00000400, /* object should be create on write */
- OBD_FL_SRVLOCK = 0x00000800, /* delegate DLM locking to server */
- OBD_FL_CKSUM_CRC32 = 0x00001000, /* CRC32 checksum type */
- OBD_FL_CKSUM_ADLER = 0x00002000, /* ADLER checksum type */
- OBD_FL_CKSUM_CRC32C = 0x00004000, /* CRC32C checksum type */
- OBD_FL_CKSUM_RSVD2 = 0x00008000, /* for future cksum types */
- OBD_FL_CKSUM_RSVD3 = 0x00010000, /* for future cksum types */
- OBD_FL_SHRINK_GRANT = 0x00020000, /* object shrink the grant */
- OBD_FL_MMAP = 0x00040000, /* object is mmapped on the client.
- * XXX: obsoleted - reserved for old
- * clients prior than 2.2
- */
- OBD_FL_RECOV_RESEND = 0x00080000, /* recoverable resent */
- OBD_FL_NOSPC_BLK = 0x00100000, /* no more block space on OST */
- OBD_FL_FLUSH = 0x00200000, /* flush pages on the OST */
- OBD_FL_SHORT_IO = 0x00400000, /* short io request */
-
- /* Note that while these checksum values are currently separate bits,
- * in 2.x we can actually allow all values from 1-31 if we wanted.
- */
- OBD_FL_CKSUM_ALL = OBD_FL_CKSUM_CRC32 | OBD_FL_CKSUM_ADLER |
- OBD_FL_CKSUM_CRC32C,
-
- /* mask for local-only flag, which won't be sent over network */
- OBD_FL_LOCAL_MASK = 0xF0000000,
-};
-
-/*
- * All LOV EA magics should have the same postfix, if some new version
- * Lustre instroduces new LOV EA magic, then when down-grade to an old
- * Lustre, even though the old version system does not recognizes such
- * new magic, it still can distinguish the corrupted cases by checking
- * the magic's postfix.
- */
-#define LOV_MAGIC_MAGIC 0x0BD0
-#define LOV_MAGIC_MASK 0xFFFF
-
-#define LOV_MAGIC_V1 (0x0BD10000 | LOV_MAGIC_MAGIC)
-#define LOV_MAGIC_JOIN_V1 (0x0BD20000 | LOV_MAGIC_MAGIC)
-#define LOV_MAGIC_V3 (0x0BD30000 | LOV_MAGIC_MAGIC)
-#define LOV_MAGIC_MIGRATE (0x0BD40000 | LOV_MAGIC_MAGIC)
-/* reserved for specifying OSTs */
-#define LOV_MAGIC_SPECIFIC (0x0BD50000 | LOV_MAGIC_MAGIC)
-#define LOV_MAGIC LOV_MAGIC_V1
-
-/*
- * magic for fully defined striping
- * the idea is that we should have different magics for striping "hints"
- * (struct lov_user_md_v[13]) and defined ready-to-use striping (struct
- * lov_mds_md_v[13]). at the moment the magics are used in wire protocol,
- * we can't just change it w/o long way preparation, but we still need a
- * mechanism to allow LOD to differentiate hint versus ready striping.
- * so, at the moment we do a trick: MDT knows what to expect from request
- * depending on the case (replay uses ready striping, non-replay req uses
- * hints), so MDT replaces magic with appropriate one and now LOD can
- * easily understand what's inside -bzzz
- */
-#define LOV_MAGIC_V1_DEF 0x0CD10BD0
-#define LOV_MAGIC_V3_DEF 0x0CD30BD0
-
-#define lov_pattern(pattern) (pattern & ~LOV_PATTERN_F_MASK)
-#define lov_pattern_flags(pattern) (pattern & LOV_PATTERN_F_MASK)
-
-#define lov_ost_data lov_ost_data_v1
-struct lov_ost_data_v1 { /* per-stripe data structure (little-endian)*/
- struct ost_id l_ost_oi; /* OST object ID */
- __u32 l_ost_gen; /* generation of this l_ost_idx */
- __u32 l_ost_idx; /* OST index in LOV (lov_tgt_desc->tgts) */
-};
-
-#define lov_mds_md lov_mds_md_v1
-struct lov_mds_md_v1 { /* LOV EA mds/wire data (little-endian) */
- __u32 lmm_magic; /* magic number = LOV_MAGIC_V1 */
- __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
- struct ost_id lmm_oi; /* LOV object ID */
- __u32 lmm_stripe_size; /* size of stripe in bytes */
- /* lmm_stripe_count used to be __u32 */
- __u16 lmm_stripe_count; /* num stripes in use for this object */
- __u16 lmm_layout_gen; /* layout generation number */
- struct lov_ost_data_v1 lmm_objects[0]; /* per-stripe data */
-};
-
-#define MAX_MD_SIZE \
- (sizeof(struct lov_mds_md) + 4 * sizeof(struct lov_ost_data))
-#define MIN_MD_SIZE \
- (sizeof(struct lov_mds_md) + 1 * sizeof(struct lov_ost_data))
-
-#define XATTR_NAME_ACL_ACCESS "system.posix_acl_access"
-#define XATTR_NAME_ACL_DEFAULT "system.posix_acl_default"
-#define XATTR_USER_PREFIX "user."
-#define XATTR_TRUSTED_PREFIX "trusted."
-#define XATTR_SECURITY_PREFIX "security."
-#define XATTR_LUSTRE_PREFIX "lustre."
-
-#define XATTR_NAME_LOV "trusted.lov"
-#define XATTR_NAME_LMA "trusted.lma"
-#define XATTR_NAME_LMV "trusted.lmv"
-#define XATTR_NAME_DEFAULT_LMV "trusted.dmv"
-#define XATTR_NAME_LINK "trusted.link"
-#define XATTR_NAME_FID "trusted.fid"
-#define XATTR_NAME_VERSION "trusted.version"
-#define XATTR_NAME_SOM "trusted.som"
-#define XATTR_NAME_HSM "trusted.hsm"
-#define XATTR_NAME_LFSCK_NAMESPACE "trusted.lfsck_namespace"
-
-struct lov_mds_md_v3 { /* LOV EA mds/wire data (little-endian) */
- __u32 lmm_magic; /* magic number = LOV_MAGIC_V3 */
- __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
- struct ost_id lmm_oi; /* LOV object ID */
- __u32 lmm_stripe_size; /* size of stripe in bytes */
- /* lmm_stripe_count used to be __u32 */
- __u16 lmm_stripe_count; /* num stripes in use for this object */
- __u16 lmm_layout_gen; /* layout generation number */
- char lmm_pool_name[LOV_MAXPOOLNAME + 1]; /* must be 32bit aligned */
- struct lov_ost_data_v1 lmm_objects[0]; /* per-stripe data */
-};
-
-static inline __u32 lov_mds_md_size(__u16 stripes, __u32 lmm_magic)
-{
- if (lmm_magic == LOV_MAGIC_V3)
- return sizeof(struct lov_mds_md_v3) +
- stripes * sizeof(struct lov_ost_data_v1);
- else
- return sizeof(struct lov_mds_md_v1) +
- stripes * sizeof(struct lov_ost_data_v1);
-}
-
-static inline __u32
-lov_mds_md_max_stripe_count(size_t buf_size, __u32 lmm_magic)
-{
- switch (lmm_magic) {
- case LOV_MAGIC_V1: {
- struct lov_mds_md_v1 lmm;
-
- if (buf_size < sizeof(lmm))
- return 0;
-
- return (buf_size - sizeof(lmm)) / sizeof(lmm.lmm_objects[0]);
- }
- case LOV_MAGIC_V3: {
- struct lov_mds_md_v3 lmm;
-
- if (buf_size < sizeof(lmm))
- return 0;
-
- return (buf_size - sizeof(lmm)) / sizeof(lmm.lmm_objects[0]);
- }
- default:
- return 0;
- }
-}
-
-#define OBD_MD_FLID (0x00000001ULL) /* object ID */
-#define OBD_MD_FLATIME (0x00000002ULL) /* access time */
-#define OBD_MD_FLMTIME (0x00000004ULL) /* data modification time */
-#define OBD_MD_FLCTIME (0x00000008ULL) /* change time */
-#define OBD_MD_FLSIZE (0x00000010ULL) /* size */
-#define OBD_MD_FLBLOCKS (0x00000020ULL) /* allocated blocks count */
-#define OBD_MD_FLBLKSZ (0x00000040ULL) /* block size */
-#define OBD_MD_FLMODE (0x00000080ULL) /* access bits (mode & ~S_IFMT) */
-#define OBD_MD_FLTYPE (0x00000100ULL) /* object type (mode & S_IFMT) */
-#define OBD_MD_FLUID (0x00000200ULL) /* user ID */
-#define OBD_MD_FLGID (0x00000400ULL) /* group ID */
-#define OBD_MD_FLFLAGS (0x00000800ULL) /* flags word */
-#define OBD_MD_FLNLINK (0x00002000ULL) /* link count */
-#define OBD_MD_FLGENER (0x00004000ULL) /* generation number */
-/*#define OBD_MD_FLINLINE (0x00008000ULL) inline data. used until 1.6.5 */
-#define OBD_MD_FLRDEV (0x00010000ULL) /* device number */
-#define OBD_MD_FLEASIZE (0x00020000ULL) /* extended attribute data */
-#define OBD_MD_LINKNAME (0x00040000ULL) /* symbolic link target */
-#define OBD_MD_FLHANDLE (0x00080000ULL) /* file/lock handle */
-#define OBD_MD_FLCKSUM (0x00100000ULL) /* bulk data checksum */
-#define OBD_MD_FLQOS (0x00200000ULL) /* quality of service stats */
-/*#define OBD_MD_FLOSCOPQ (0x00400000ULL) osc opaque data, never used */
-/* OBD_MD_FLCOOKIE (0x00800000ULL) obsolete in 2.8 */
-#define OBD_MD_FLGROUP (0x01000000ULL) /* group */
-#define OBD_MD_FLFID (0x02000000ULL) /* ->ost write inline fid */
-#define OBD_MD_FLEPOCH (0x04000000ULL) /* ->ost write with ioepoch */
- /* ->mds if epoch opens or closes
- */
-#define OBD_MD_FLGRANT (0x08000000ULL) /* ost preallocation space grant */
-#define OBD_MD_FLDIREA (0x10000000ULL) /* dir's extended attribute data */
-#define OBD_MD_FLUSRQUOTA (0x20000000ULL) /* over quota flags sent from ost */
-#define OBD_MD_FLGRPQUOTA (0x40000000ULL) /* over quota flags sent from ost */
-#define OBD_MD_FLMODEASIZE (0x80000000ULL) /* EA size will be changed */
-
-#define OBD_MD_MDS (0x0000000100000000ULL) /* where an inode lives on */
-#define OBD_MD_REINT (0x0000000200000000ULL) /* reintegrate oa */
-#define OBD_MD_MEA (0x0000000400000000ULL) /* CMD split EA */
-#define OBD_MD_TSTATE (0x0000000800000000ULL) /* transient state field */
-
-#define OBD_MD_FLXATTR (0x0000001000000000ULL) /* xattr */
-#define OBD_MD_FLXATTRLS (0x0000002000000000ULL) /* xattr list */
-#define OBD_MD_FLXATTRRM (0x0000004000000000ULL) /* xattr remove */
-#define OBD_MD_FLACL (0x0000008000000000ULL) /* ACL */
-/* OBD_MD_FLRMTPERM (0x0000010000000000ULL) remote perm, obsolete */
-#define OBD_MD_FLMDSCAPA (0x0000020000000000ULL) /* MDS capability */
-#define OBD_MD_FLOSSCAPA (0x0000040000000000ULL) /* OSS capability */
-#define OBD_MD_FLCKSPLIT (0x0000080000000000ULL) /* Check split on server */
-#define OBD_MD_FLCROSSREF (0x0000100000000000ULL) /* Cross-ref case */
-#define OBD_MD_FLGETATTRLOCK (0x0000200000000000ULL) /* Get IOEpoch attributes
- * under lock; for xattr
- * requests means the
- * client holds the lock
- */
-#define OBD_MD_FLOBJCOUNT (0x0000400000000000ULL) /* for multiple destroy */
-
-/* OBD_MD_FLRMTLSETFACL (0x0001000000000000ULL) lfs lsetfacl, obsolete */
-/* OBD_MD_FLRMTLGETFACL (0x0002000000000000ULL) lfs lgetfacl, obsolete */
-/* OBD_MD_FLRMTRSETFACL (0x0004000000000000ULL) lfs rsetfacl, obsolete */
-/* OBD_MD_FLRMTRGETFACL (0x0008000000000000ULL) lfs rgetfacl, obsolete */
-
-#define OBD_MD_FLDATAVERSION (0x0010000000000000ULL) /* iversion sum */
-#define OBD_MD_CLOSE_INTENT_EXECED (0x0020000000000000ULL) /* close intent
- * executed
- */
-
-#define OBD_MD_DEFAULT_MEA (0x0040000000000000ULL) /* default MEA */
-
-#define OBD_MD_FLGETATTR (OBD_MD_FLID | OBD_MD_FLATIME | OBD_MD_FLMTIME | \
- OBD_MD_FLCTIME | OBD_MD_FLSIZE | OBD_MD_FLBLKSZ | \
- OBD_MD_FLMODE | OBD_MD_FLTYPE | OBD_MD_FLUID | \
- OBD_MD_FLGID | OBD_MD_FLFLAGS | OBD_MD_FLNLINK | \
- OBD_MD_FLGENER | OBD_MD_FLRDEV | OBD_MD_FLGROUP)
-
-#define OBD_MD_FLXATTRALL (OBD_MD_FLXATTR | OBD_MD_FLXATTRLS)
-
-/* don't forget obdo_fid which is way down at the bottom so it can
- * come after the definition of llog_cookie
- */
-
-enum hss_valid {
- HSS_SETMASK = 0x01,
- HSS_CLEARMASK = 0x02,
- HSS_ARCHIVE_ID = 0x04,
-};
-
-struct hsm_state_set {
- __u32 hss_valid;
- __u32 hss_archive_id;
- __u64 hss_setmask;
- __u64 hss_clearmask;
-};
-
-/* ost_body.data values for OST_BRW */
-
-#define OBD_BRW_READ 0x01
-#define OBD_BRW_WRITE 0x02
-#define OBD_BRW_RWMASK (OBD_BRW_READ | OBD_BRW_WRITE)
-#define OBD_BRW_SYNC 0x08 /* this page is a part of synchronous
- * transfer and is not accounted in
- * the grant.
- */
-#define OBD_BRW_CHECK 0x10
-#define OBD_BRW_FROM_GRANT 0x20 /* the osc manages this under llite */
-#define OBD_BRW_GRANTED 0x40 /* the ost manages this */
-#define OBD_BRW_NOCACHE 0x80 /* this page is a part of non-cached IO */
-#define OBD_BRW_NOQUOTA 0x100
-#define OBD_BRW_SRVLOCK 0x200 /* Client holds no lock over this page */
-#define OBD_BRW_ASYNC 0x400 /* Server may delay commit to disk */
-#define OBD_BRW_MEMALLOC 0x800 /* Client runs in the "kswapd" context */
-#define OBD_BRW_OVER_USRQUOTA 0x1000 /* Running out of user quota */
-#define OBD_BRW_OVER_GRPQUOTA 0x2000 /* Running out of group quota */
-#define OBD_BRW_SOFT_SYNC 0x4000 /* This flag notifies the server
- * that the client is running low on
- * space for unstable pages; asking
- * it to sync quickly
- */
-
-#define OBD_OBJECT_EOF LUSTRE_EOF
-
-#define OST_MIN_PRECREATE 32
-#define OST_MAX_PRECREATE 20000
-
-struct obd_ioobj {
- struct ost_id ioo_oid; /* object ID, if multi-obj BRW */
- __u32 ioo_max_brw; /* low 16 bits were o_mode before 2.4,
- * now (PTLRPC_BULK_OPS_COUNT - 1) in
- * high 16 bits in 2.4 and later
- */
- __u32 ioo_bufcnt; /* number of niobufs for this object */
-};
-
-/*
- * NOTE: IOOBJ_MAX_BRW_BITS defines the _offset_ of the max_brw field in
- * ioo_max_brw, NOT the maximum number of bits in PTLRPC_BULK_OPS_BITS.
- * That said, ioo_max_brw is a 32-bit field so the limit is also 16 bits.
- */
-#define IOOBJ_MAX_BRW_BITS 16
-#define ioobj_max_brw_get(ioo) (((ioo)->ioo_max_brw >> IOOBJ_MAX_BRW_BITS) + 1)
-#define ioobj_max_brw_set(ioo, num) \
-do { (ioo)->ioo_max_brw = ((num) - 1) << IOOBJ_MAX_BRW_BITS; } while (0)
-
-/* multiple of 8 bytes => can array */
-struct niobuf_remote {
- __u64 rnb_offset;
- __u32 rnb_len;
- __u32 rnb_flags;
-};
-
-/* lock value block communicated between the filter and llite */
-
-/* OST_LVB_ERR_INIT is needed because the return code in rc is
- * negative, i.e. because ((MASK + rc) & MASK) != MASK.
- */
-#define OST_LVB_ERR_INIT 0xffbadbad80000000ULL
-#define OST_LVB_ERR_MASK 0xffbadbad00000000ULL
-#define OST_LVB_IS_ERR(blocks) \
- ((blocks & OST_LVB_ERR_MASK) == OST_LVB_ERR_MASK)
-#define OST_LVB_SET_ERR(blocks, rc) \
- do { blocks = OST_LVB_ERR_INIT + rc; } while (0)
-#define OST_LVB_GET_ERR(blocks) (int)(blocks - OST_LVB_ERR_INIT)
-
-struct ost_lvb_v1 {
- __u64 lvb_size;
- __s64 lvb_mtime;
- __s64 lvb_atime;
- __s64 lvb_ctime;
- __u64 lvb_blocks;
-};
-
-struct ost_lvb {
- __u64 lvb_size;
- __s64 lvb_mtime;
- __s64 lvb_atime;
- __s64 lvb_ctime;
- __u64 lvb_blocks;
- __u32 lvb_mtime_ns;
- __u32 lvb_atime_ns;
- __u32 lvb_ctime_ns;
- __u32 lvb_padding;
-};
-
-/*
- * lquota data structures
- */
-
-/* The lquota_id structure is a union of all the possible identifier types that
- * can be used with quota, this includes:
- * - 64-bit user ID
- * - 64-bit group ID
- * - a FID which can be used for per-directory quota in the future
- */
-union lquota_id {
- struct lu_fid qid_fid; /* FID for per-directory quota */
- __u64 qid_uid; /* user identifier */
- __u64 qid_gid; /* group identifier */
-};
-
-/* quotactl management */
-struct obd_quotactl {
- __u32 qc_cmd;
- __u32 qc_type; /* see Q_* flag below */
- __u32 qc_id;
- __u32 qc_stat;
- struct obd_dqinfo qc_dqinfo;
- struct obd_dqblk qc_dqblk;
-};
-
-#define Q_COPY(out, in, member) (out)->member = (in)->member
-
-#define QCTL_COPY(out, in) \
-do { \
- Q_COPY(out, in, qc_cmd); \
- Q_COPY(out, in, qc_type); \
- Q_COPY(out, in, qc_id); \
- Q_COPY(out, in, qc_stat); \
- Q_COPY(out, in, qc_dqinfo); \
- Q_COPY(out, in, qc_dqblk); \
-} while (0)
-
-/* Data structures associated with the quota locks */
-
-/* Glimpse descriptor used for the index & per-ID quota locks */
-struct ldlm_gl_lquota_desc {
- union lquota_id gl_id; /* quota ID subject to the glimpse */
- __u64 gl_flags; /* see LQUOTA_FL* below */
- __u64 gl_ver; /* new index version */
- __u64 gl_hardlimit; /* new hardlimit or qunit value */
- __u64 gl_softlimit; /* new softlimit */
- __u64 gl_time;
- __u64 gl_pad2;
-};
-
-/* quota glimpse flags */
-#define LQUOTA_FL_EDQUOT 0x1 /* user/group out of quota space on QMT */
-
-/* LVB used with quota (global and per-ID) locks */
-struct lquota_lvb {
- __u64 lvb_flags; /* see LQUOTA_FL* above */
- __u64 lvb_id_may_rel; /* space that might be released later */
- __u64 lvb_id_rel; /* space released by the slave for this ID */
- __u64 lvb_id_qunit; /* current qunit value */
- __u64 lvb_pad1;
-};
-
-/* op codes */
-enum quota_cmd {
- QUOTA_DQACQ = 601,
- QUOTA_DQREL = 602,
- QUOTA_LAST_OPC
-};
-#define QUOTA_FIRST_OPC QUOTA_DQACQ
-
-/*
- * MDS REQ RECORDS
- */
-
-/* opcodes */
-enum mds_cmd {
- MDS_GETATTR = 33,
- MDS_GETATTR_NAME = 34,
- MDS_CLOSE = 35,
- MDS_REINT = 36,
- MDS_READPAGE = 37,
- MDS_CONNECT = 38,
- MDS_DISCONNECT = 39,
- MDS_GETSTATUS = 40,
- MDS_STATFS = 41,
- MDS_PIN = 42, /* obsolete, never used in a release */
- MDS_UNPIN = 43, /* obsolete, never used in a release */
- MDS_SYNC = 44,
- MDS_DONE_WRITING = 45, /* obsolete since 2.8.0 */
- MDS_SET_INFO = 46,
- MDS_QUOTACHECK = 47, /* not used since 2.4 */
- MDS_QUOTACTL = 48,
- MDS_GETXATTR = 49,
- MDS_SETXATTR = 50, /* obsolete, now it's MDS_REINT op */
- MDS_WRITEPAGE = 51,
- MDS_IS_SUBDIR = 52, /* obsolete, never used in a release */
- MDS_GET_INFO = 53,
- MDS_HSM_STATE_GET = 54,
- MDS_HSM_STATE_SET = 55,
- MDS_HSM_ACTION = 56,
- MDS_HSM_PROGRESS = 57,
- MDS_HSM_REQUEST = 58,
- MDS_HSM_CT_REGISTER = 59,
- MDS_HSM_CT_UNREGISTER = 60,
- MDS_SWAP_LAYOUTS = 61,
- MDS_LAST_OPC
-};
-
-#define MDS_FIRST_OPC MDS_GETATTR
-
-/*
- * Do not exceed 63
- */
-
-enum mdt_reint_cmd {
- REINT_SETATTR = 1,
- REINT_CREATE = 2,
- REINT_LINK = 3,
- REINT_UNLINK = 4,
- REINT_RENAME = 5,
- REINT_OPEN = 6,
- REINT_SETXATTR = 7,
- REINT_RMENTRY = 8,
- REINT_MIGRATE = 9,
- REINT_MAX
-};
-
-/* the disposition of the intent outlines what was executed */
-#define DISP_IT_EXECD 0x00000001
-#define DISP_LOOKUP_EXECD 0x00000002
-#define DISP_LOOKUP_NEG 0x00000004
-#define DISP_LOOKUP_POS 0x00000008
-#define DISP_OPEN_CREATE 0x00000010
-#define DISP_OPEN_OPEN 0x00000020
-#define DISP_ENQ_COMPLETE 0x00400000 /* obsolete and unused */
-#define DISP_ENQ_OPEN_REF 0x00800000
-#define DISP_ENQ_CREATE_REF 0x01000000
-#define DISP_OPEN_LOCK 0x02000000
-#define DISP_OPEN_LEASE 0x04000000
-#define DISP_OPEN_STRIPE 0x08000000
-#define DISP_OPEN_DENY 0x10000000
-
-/* INODE LOCK PARTS */
-#define MDS_INODELOCK_LOOKUP 0x000001 /* For namespace, dentry etc, and also
- * was used to protect permission (mode,
- * owner, group etc) before 2.4.
- */
-#define MDS_INODELOCK_UPDATE 0x000002 /* size, links, timestamps */
-#define MDS_INODELOCK_OPEN 0x000004 /* For opened files */
-#define MDS_INODELOCK_LAYOUT 0x000008 /* for layout */
-
-/* The PERM bit is added int 2.4, and it is used to protect permission(mode,
- * owner, group, acl etc), so to separate the permission from LOOKUP lock.
- * Because for remote directories(in DNE), these locks will be granted by
- * different MDTs(different ldlm namespace).
- *
- * For local directory, MDT will always grant UPDATE_LOCK|PERM_LOCK together.
- * For Remote directory, the master MDT, where the remote directory is, will
- * grant UPDATE_LOCK|PERM_LOCK, and the remote MDT, where the name entry is,
- * will grant LOOKUP_LOCK.
- */
-#define MDS_INODELOCK_PERM 0x000010
-#define MDS_INODELOCK_XATTR 0x000020 /* extended attributes */
-
-#define MDS_INODELOCK_MAXSHIFT 5
-/* This FULL lock is useful to take on unlink sort of operations */
-#define MDS_INODELOCK_FULL ((1 << (MDS_INODELOCK_MAXSHIFT + 1)) - 1)
-
-/* NOTE: until Lustre 1.8.7/2.1.1 the fid_ver() was packed into name[2],
- * but was moved into name[1] along with the OID to avoid consuming the
- * name[2,3] fields that need to be used for the quota id (also a FID).
- */
-enum {
- LUSTRE_RES_ID_SEQ_OFF = 0,
- LUSTRE_RES_ID_VER_OID_OFF = 1,
- LUSTRE_RES_ID_WAS_VER_OFF = 2, /* see note above */
- LUSTRE_RES_ID_QUOTA_SEQ_OFF = 2,
- LUSTRE_RES_ID_QUOTA_VER_OID_OFF = 3,
- LUSTRE_RES_ID_HSH_OFF = 3
-};
-
-#define MDS_STATUS_CONN 1
-#define MDS_STATUS_LOV 2
-
-/* these should be identical to their EXT4_*_FL counterparts, they are
- * redefined here only to avoid dragging in fs/ext4/ext4.h
- */
-#define LUSTRE_SYNC_FL 0x00000008 /* Synchronous updates */
-#define LUSTRE_IMMUTABLE_FL 0x00000010 /* Immutable file */
-#define LUSTRE_APPEND_FL 0x00000020 /* writes to file may only append */
-#define LUSTRE_NODUMP_FL 0x00000040 /* do not dump file */
-#define LUSTRE_NOATIME_FL 0x00000080 /* do not update atime */
-#define LUSTRE_INDEX_FL 0x00001000 /* hash-indexed directory */
-#define LUSTRE_DIRSYNC_FL 0x00010000 /* dirsync behaviour (dir only) */
-#define LUSTRE_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
-#define LUSTRE_DIRECTIO_FL 0x00100000 /* Use direct i/o */
-#define LUSTRE_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
-
-/* Convert wire LUSTRE_*_FL to corresponding client local VFS S_* values
- * for the client inode i_flags. The LUSTRE_*_FL are the Lustre wire
- * protocol equivalents of LDISKFS_*_FL values stored on disk, while
- * the S_* flags are kernel-internal values that change between kernel
- * versions. These flags are set/cleared via FSFILT_IOC_{GET,SET}_FLAGS.
- * See b=16526 for a full history.
- */
-static inline int ll_ext_to_inode_flags(int flags)
-{
- return (((flags & LUSTRE_SYNC_FL) ? S_SYNC : 0) |
- ((flags & LUSTRE_NOATIME_FL) ? S_NOATIME : 0) |
- ((flags & LUSTRE_APPEND_FL) ? S_APPEND : 0) |
- ((flags & LUSTRE_DIRSYNC_FL) ? S_DIRSYNC : 0) |
- ((flags & LUSTRE_IMMUTABLE_FL) ? S_IMMUTABLE : 0));
-}
-
-static inline int ll_inode_to_ext_flags(int iflags)
-{
- return (((iflags & S_SYNC) ? LUSTRE_SYNC_FL : 0) |
- ((iflags & S_NOATIME) ? LUSTRE_NOATIME_FL : 0) |
- ((iflags & S_APPEND) ? LUSTRE_APPEND_FL : 0) |
- ((iflags & S_DIRSYNC) ? LUSTRE_DIRSYNC_FL : 0) |
- ((iflags & S_IMMUTABLE) ? LUSTRE_IMMUTABLE_FL : 0));
-}
-
-/* 64 possible states */
-enum md_transient_state {
- MS_RESTORE = (1 << 0), /* restore is running */
-};
-
-struct mdt_body {
- struct lu_fid mbo_fid1;
- struct lu_fid mbo_fid2;
- struct lustre_handle mbo_handle;
- __u64 mbo_valid;
- __u64 mbo_size; /* Offset, in the case of MDS_READPAGE */
- __s64 mbo_mtime;
- __s64 mbo_atime;
- __s64 mbo_ctime;
- __u64 mbo_blocks; /* XID, in the case of MDS_READPAGE */
- __u64 mbo_ioepoch;
- __u64 mbo_t_state; /* transient file state defined in
- * enum md_transient_state
- * was "ino" until 2.4.0
- */
- __u32 mbo_fsuid;
- __u32 mbo_fsgid;
- __u32 mbo_capability;
- __u32 mbo_mode;
- __u32 mbo_uid;
- __u32 mbo_gid;
- __u32 mbo_flags; /* LUSTRE_*_FL file attributes */
- __u32 mbo_rdev;
- __u32 mbo_nlink; /* #bytes to read in the case of MDS_READPAGE */
- __u32 mbo_unused2; /* was "generation" until 2.4.0 */
- __u32 mbo_suppgid;
- __u32 mbo_eadatasize;
- __u32 mbo_aclsize;
- __u32 mbo_max_mdsize;
- __u32 mbo_unused3; /* was max_cookiesize until 2.8 */
- __u32 mbo_uid_h; /* high 32-bits of uid, for FUID */
- __u32 mbo_gid_h; /* high 32-bits of gid, for FUID */
- __u32 mbo_padding_5; /* also fix lustre_swab_mdt_body */
- __u64 mbo_padding_6;
- __u64 mbo_padding_7;
- __u64 mbo_padding_8;
- __u64 mbo_padding_9;
- __u64 mbo_padding_10;
-}; /* 216 */
-
-struct mdt_ioepoch {
- struct lustre_handle mio_handle;
- __u64 mio_unused1; /* was ioepoch */
- __u32 mio_unused2; /* was flags */
- __u32 mio_padding;
-};
-
-/* permissions for md_perm.mp_perm */
-enum {
- CFS_SETUID_PERM = 0x01,
- CFS_SETGID_PERM = 0x02,
- CFS_SETGRP_PERM = 0x04,
-};
-
-struct mdt_rec_setattr {
- __u32 sa_opcode;
- __u32 sa_cap;
- __u32 sa_fsuid;
- __u32 sa_fsuid_h;
- __u32 sa_fsgid;
- __u32 sa_fsgid_h;
- __u32 sa_suppgid;
- __u32 sa_suppgid_h;
- __u32 sa_padding_1;
- __u32 sa_padding_1_h;
- struct lu_fid sa_fid;
- __u64 sa_valid;
- __u32 sa_uid;
- __u32 sa_gid;
- __u64 sa_size;
- __u64 sa_blocks;
- __s64 sa_mtime;
- __s64 sa_atime;
- __s64 sa_ctime;
- __u32 sa_attr_flags;
- __u32 sa_mode;
- __u32 sa_bias; /* some operation flags */
- __u32 sa_padding_3;
- __u32 sa_padding_4;
- __u32 sa_padding_5;
-};
-
-/*
- * Attribute flags used in mdt_rec_setattr::sa_valid.
- * The kernel's #defines for ATTR_* should not be used over the network
- * since the client and MDS may run different kernels (see bug 13828)
- * Therefore, we should only use MDS_ATTR_* attributes for sa_valid.
- */
-#define MDS_ATTR_MODE 0x1ULL /* = 1 */
-#define MDS_ATTR_UID 0x2ULL /* = 2 */
-#define MDS_ATTR_GID 0x4ULL /* = 4 */
-#define MDS_ATTR_SIZE 0x8ULL /* = 8 */
-#define MDS_ATTR_ATIME 0x10ULL /* = 16 */
-#define MDS_ATTR_MTIME 0x20ULL /* = 32 */
-#define MDS_ATTR_CTIME 0x40ULL /* = 64 */
-#define MDS_ATTR_ATIME_SET 0x80ULL /* = 128 */
-#define MDS_ATTR_MTIME_SET 0x100ULL /* = 256 */
-#define MDS_ATTR_FORCE 0x200ULL /* = 512, Not a change, but a change it */
-#define MDS_ATTR_ATTR_FLAG 0x400ULL /* = 1024 */
-#define MDS_ATTR_KILL_SUID 0x800ULL /* = 2048 */
-#define MDS_ATTR_KILL_SGID 0x1000ULL /* = 4096 */
-#define MDS_ATTR_CTIME_SET 0x2000ULL /* = 8192 */
-#define MDS_ATTR_FROM_OPEN 0x4000ULL /* = 16384, called from open path,
- * ie O_TRUNC
- */
-#define MDS_ATTR_BLOCKS 0x8000ULL /* = 32768 */
-
-#define MDS_FMODE_CLOSED 00000000
-#define MDS_FMODE_EXEC 00000004
-/* MDS_FMODE_EPOCH 01000000 obsolete since 2.8.0 */
-/* MDS_FMODE_TRUNC 02000000 obsolete since 2.8.0 */
-/* MDS_FMODE_SOM 04000000 obsolete since 2.8.0 */
-
-#define MDS_OPEN_CREATED 00000010
-#define MDS_OPEN_CROSS 00000020
-
-#define MDS_OPEN_CREAT 00000100
-#define MDS_OPEN_EXCL 00000200
-#define MDS_OPEN_TRUNC 00001000
-#define MDS_OPEN_APPEND 00002000
-#define MDS_OPEN_SYNC 00010000
-#define MDS_OPEN_DIRECTORY 00200000
-
-#define MDS_OPEN_BY_FID 040000000 /* open_by_fid for known object */
-#define MDS_OPEN_DELAY_CREATE 0100000000 /* delay initial object create */
-#define MDS_OPEN_OWNEROVERRIDE 0200000000 /* NFSD rw-reopen ro file for owner */
-#define MDS_OPEN_JOIN_FILE 0400000000 /* open for join file.
- * We do not support JOIN FILE
- * anymore, reserve this flags
- * just for preventing such bit
- * to be reused.
- */
-
-#define MDS_OPEN_LOCK 04000000000 /* This open requires open lock */
-#define MDS_OPEN_HAS_EA 010000000000 /* specify object create pattern */
-#define MDS_OPEN_HAS_OBJS 020000000000 /* Just set the EA the obj exist */
-#define MDS_OPEN_NORESTORE 0100000000000ULL /* Do not restore file at open */
-#define MDS_OPEN_NEWSTRIPE 0200000000000ULL /* New stripe needed (restripe or
- * hsm restore)
- */
-#define MDS_OPEN_VOLATILE 0400000000000ULL /* File is volatile = created
- * unlinked
- */
-#define MDS_OPEN_LEASE 01000000000000ULL /* Open the file and grant lease
- * delegation, succeed if it's not
- * being opened with conflict mode.
- */
-#define MDS_OPEN_RELEASE 02000000000000ULL /* Open the file for HSM release */
-
-#define MDS_OPEN_FL_INTERNAL (MDS_OPEN_HAS_EA | MDS_OPEN_HAS_OBJS | \
- MDS_OPEN_OWNEROVERRIDE | MDS_OPEN_LOCK | \
- MDS_OPEN_BY_FID | MDS_OPEN_LEASE | \
- MDS_OPEN_RELEASE)
-
-enum mds_op_bias {
- MDS_CHECK_SPLIT = 1 << 0,
- MDS_CROSS_REF = 1 << 1,
- MDS_VTX_BYPASS = 1 << 2,
- MDS_PERM_BYPASS = 1 << 3,
-/* MDS_SOM = 1 << 4, obsolete since 2.8.0 */
- MDS_QUOTA_IGNORE = 1 << 5,
- MDS_CLOSE_CLEANUP = 1 << 6,
- MDS_KEEP_ORPHAN = 1 << 7,
- MDS_RECOV_OPEN = 1 << 8,
- MDS_DATA_MODIFIED = 1 << 9,
- MDS_CREATE_VOLATILE = 1 << 10,
- MDS_OWNEROVERRIDE = 1 << 11,
- MDS_HSM_RELEASE = 1 << 12,
- MDS_RENAME_MIGRATE = 1 << 13,
- MDS_CLOSE_LAYOUT_SWAP = 1 << 14,
-};
-
-/* instance of mdt_reint_rec */
-struct mdt_rec_create {
- __u32 cr_opcode;
- __u32 cr_cap;
- __u32 cr_fsuid;
- __u32 cr_fsuid_h;
- __u32 cr_fsgid;
- __u32 cr_fsgid_h;
- __u32 cr_suppgid1;
- __u32 cr_suppgid1_h;
- __u32 cr_suppgid2;
- __u32 cr_suppgid2_h;
- struct lu_fid cr_fid1;
- struct lu_fid cr_fid2;
- struct lustre_handle cr_old_handle; /* handle in case of open replay */
- __s64 cr_time;
- __u64 cr_rdev;
- __u64 cr_ioepoch;
- __u64 cr_padding_1; /* rr_blocks */
- __u32 cr_mode;
- __u32 cr_bias;
- /* use of helpers set/get_mrc_cr_flags() is needed to access
- * 64 bits cr_flags [cr_flags_l, cr_flags_h], this is done to
- * extend cr_flags size without breaking 1.8 compat
- */
- __u32 cr_flags_l; /* for use with open, low 32 bits */
- __u32 cr_flags_h; /* for use with open, high 32 bits */
- __u32 cr_umask; /* umask for create */
- __u32 cr_padding_4; /* rr_padding_4 */
-};
-
-/* instance of mdt_reint_rec */
-struct mdt_rec_link {
- __u32 lk_opcode;
- __u32 lk_cap;
- __u32 lk_fsuid;
- __u32 lk_fsuid_h;
- __u32 lk_fsgid;
- __u32 lk_fsgid_h;
- __u32 lk_suppgid1;
- __u32 lk_suppgid1_h;
- __u32 lk_suppgid2;
- __u32 lk_suppgid2_h;
- struct lu_fid lk_fid1;
- struct lu_fid lk_fid2;
- __s64 lk_time;
- __u64 lk_padding_1; /* rr_atime */
- __u64 lk_padding_2; /* rr_ctime */
- __u64 lk_padding_3; /* rr_size */
- __u64 lk_padding_4; /* rr_blocks */
- __u32 lk_bias;
- __u32 lk_padding_5; /* rr_mode */
- __u32 lk_padding_6; /* rr_flags */
- __u32 lk_padding_7; /* rr_padding_2 */
- __u32 lk_padding_8; /* rr_padding_3 */
- __u32 lk_padding_9; /* rr_padding_4 */
-};
-
-/* instance of mdt_reint_rec */
-struct mdt_rec_unlink {
- __u32 ul_opcode;
- __u32 ul_cap;
- __u32 ul_fsuid;
- __u32 ul_fsuid_h;
- __u32 ul_fsgid;
- __u32 ul_fsgid_h;
- __u32 ul_suppgid1;
- __u32 ul_suppgid1_h;
- __u32 ul_suppgid2;
- __u32 ul_suppgid2_h;
- struct lu_fid ul_fid1;
- struct lu_fid ul_fid2;
- __s64 ul_time;
- __u64 ul_padding_2; /* rr_atime */
- __u64 ul_padding_3; /* rr_ctime */
- __u64 ul_padding_4; /* rr_size */
- __u64 ul_padding_5; /* rr_blocks */
- __u32 ul_bias;
- __u32 ul_mode;
- __u32 ul_padding_6; /* rr_flags */
- __u32 ul_padding_7; /* rr_padding_2 */
- __u32 ul_padding_8; /* rr_padding_3 */
- __u32 ul_padding_9; /* rr_padding_4 */
-};
-
-/* instance of mdt_reint_rec */
-struct mdt_rec_rename {
- __u32 rn_opcode;
- __u32 rn_cap;
- __u32 rn_fsuid;
- __u32 rn_fsuid_h;
- __u32 rn_fsgid;
- __u32 rn_fsgid_h;
- __u32 rn_suppgid1;
- __u32 rn_suppgid1_h;
- __u32 rn_suppgid2;
- __u32 rn_suppgid2_h;
- struct lu_fid rn_fid1;
- struct lu_fid rn_fid2;
- __s64 rn_time;
- __u64 rn_padding_1; /* rr_atime */
- __u64 rn_padding_2; /* rr_ctime */
- __u64 rn_padding_3; /* rr_size */
- __u64 rn_padding_4; /* rr_blocks */
- __u32 rn_bias; /* some operation flags */
- __u32 rn_mode; /* cross-ref rename has mode */
- __u32 rn_padding_5; /* rr_flags */
- __u32 rn_padding_6; /* rr_padding_2 */
- __u32 rn_padding_7; /* rr_padding_3 */
- __u32 rn_padding_8; /* rr_padding_4 */
-};
-
-/* instance of mdt_reint_rec */
-struct mdt_rec_setxattr {
- __u32 sx_opcode;
- __u32 sx_cap;
- __u32 sx_fsuid;
- __u32 sx_fsuid_h;
- __u32 sx_fsgid;
- __u32 sx_fsgid_h;
- __u32 sx_suppgid1;
- __u32 sx_suppgid1_h;
- __u32 sx_suppgid2;
- __u32 sx_suppgid2_h;
- struct lu_fid sx_fid;
- __u64 sx_padding_1; /* These three are rr_fid2 */
- __u32 sx_padding_2;
- __u32 sx_padding_3;
- __u64 sx_valid;
- __s64 sx_time;
- __u64 sx_padding_5; /* rr_ctime */
- __u64 sx_padding_6; /* rr_size */
- __u64 sx_padding_7; /* rr_blocks */
- __u32 sx_size;
- __u32 sx_flags;
- __u32 sx_padding_8; /* rr_flags */
- __u32 sx_padding_9; /* rr_padding_2 */
- __u32 sx_padding_10; /* rr_padding_3 */
- __u32 sx_padding_11; /* rr_padding_4 */
-};
-
-/*
- * mdt_rec_reint is the template for all mdt_reint_xxx structures.
- * Do NOT change the size of various members, otherwise the value
- * will be broken in lustre_swab_mdt_rec_reint().
- *
- * If you add new members in other mdt_reint_xxx structures and need to use the
- * rr_padding_x fields, then update lustre_swab_mdt_rec_reint() also.
- */
-struct mdt_rec_reint {
- __u32 rr_opcode;
- __u32 rr_cap;
- __u32 rr_fsuid;
- __u32 rr_fsuid_h;
- __u32 rr_fsgid;
- __u32 rr_fsgid_h;
- __u32 rr_suppgid1;
- __u32 rr_suppgid1_h;
- __u32 rr_suppgid2;
- __u32 rr_suppgid2_h;
- struct lu_fid rr_fid1;
- struct lu_fid rr_fid2;
- __s64 rr_mtime;
- __s64 rr_atime;
- __s64 rr_ctime;
- __u64 rr_size;
- __u64 rr_blocks;
- __u32 rr_bias;
- __u32 rr_mode;
- __u32 rr_flags;
- __u32 rr_flags_h;
- __u32 rr_umask;
- __u32 rr_padding_4; /* also fix lustre_swab_mdt_rec_reint */
-};
-
-/* lmv structures */
-struct lmv_desc {
- __u32 ld_tgt_count; /* how many MDS's */
- __u32 ld_active_tgt_count; /* how many active */
- __u32 ld_default_stripe_count; /* how many objects are used */
- __u32 ld_pattern; /* default hash pattern */
- __u64 ld_default_hash_size;
- __u64 ld_padding_1; /* also fix lustre_swab_lmv_desc */
- __u32 ld_padding_2; /* also fix lustre_swab_lmv_desc */
- __u32 ld_qos_maxage; /* in second */
- __u32 ld_padding_3; /* also fix lustre_swab_lmv_desc */
- __u32 ld_padding_4; /* also fix lustre_swab_lmv_desc */
- struct obd_uuid ld_uuid;
-};
-
-/* LMV layout EA, and it will be stored both in master and slave object */
-struct lmv_mds_md_v1 {
- __u32 lmv_magic;
- __u32 lmv_stripe_count;
- __u32 lmv_master_mdt_index; /* On master object, it is master
- * MDT index, on slave object, it
- * is stripe index of the slave obj
- */
- __u32 lmv_hash_type; /* dir stripe policy, i.e. indicate
- * which hash function to be used,
- * Note: only lower 16 bits is being
- * used for now. Higher 16 bits will
- * be used to mark the object status,
- * for example migrating or dead.
- */
- __u32 lmv_layout_version; /* Used for directory restriping */
- __u32 lmv_padding1;
- __u64 lmv_padding2;
- __u64 lmv_padding3;
- char lmv_pool_name[LOV_MAXPOOLNAME + 1];/* pool name */
- struct lu_fid lmv_stripe_fids[0]; /* FIDs for each stripe */
-};
-
-#define LMV_MAGIC_V1 0x0CD20CD0 /* normal stripe lmv magic */
-#define LMV_MAGIC LMV_MAGIC_V1
-
-/* #define LMV_USER_MAGIC 0x0CD30CD0 */
-#define LMV_MAGIC_STRIPE 0x0CD40CD0 /* magic for dir sub_stripe */
-
-/*
- *Right now only the lower part(0-16bits) of lmv_hash_type is being used,
- * and the higher part will be the flag to indicate the status of object,
- * for example the object is being migrated. And the hash function
- * might be interpreted differently with different flags.
- */
-#define LMV_HASH_TYPE_MASK 0x0000ffff
-
-#define LMV_HASH_FLAG_MIGRATION 0x80000000
-#define LMV_HASH_FLAG_DEAD 0x40000000
-
-/**
- * The FNV-1a hash algorithm is as follows:
- * hash = FNV_offset_basis
- * for each octet_of_data to be hashed
- * hash = hash XOR octet_of_data
- * hash = hash × FNV_prime
- * return hash
- * http://en.wikipedia.org/wiki/Fowler–Noll–Vo_hash_function#FNV-1a_hash
- *
- * http://www.isthe.com/chongo/tech/comp/fnv/index.html#FNV-reference-source
- * FNV_prime is 2^40 + 2^8 + 0xb3 = 0x100000001b3ULL
- **/
-#define LUSTRE_FNV_1A_64_PRIME 0x100000001b3ULL
-#define LUSTRE_FNV_1A_64_OFFSET_BIAS 0xcbf29ce484222325ULL
-static inline __u64 lustre_hash_fnv_1a_64(const void *buf, size_t size)
-{
- __u64 hash = LUSTRE_FNV_1A_64_OFFSET_BIAS;
- const unsigned char *p = buf;
- size_t i;
-
- for (i = 0; i < size; i++) {
- hash ^= p[i];
- hash *= LUSTRE_FNV_1A_64_PRIME;
- }
-
- return hash;
-}
-
-union lmv_mds_md {
- __u32 lmv_magic;
- struct lmv_mds_md_v1 lmv_md_v1;
- struct lmv_user_md lmv_user_md;
-};
-
-static inline ssize_t lmv_mds_md_size(int stripe_count, unsigned int lmm_magic)
-{
- ssize_t len = -EINVAL;
-
- switch (lmm_magic) {
- case LMV_MAGIC_V1: {
- struct lmv_mds_md_v1 *lmm1;
-
- len = sizeof(*lmm1);
- len += stripe_count * sizeof(lmm1->lmv_stripe_fids[0]);
- break; }
- default:
- break;
- }
- return len;
-}
-
-static inline int lmv_mds_md_stripe_count_get(const union lmv_mds_md *lmm)
-{
- switch (__le32_to_cpu(lmm->lmv_magic)) {
- case LMV_MAGIC_V1:
- return __le32_to_cpu(lmm->lmv_md_v1.lmv_stripe_count);
- case LMV_USER_MAGIC:
- return __le32_to_cpu(lmm->lmv_user_md.lum_stripe_count);
- default:
- return -EINVAL;
- }
-}
-
-enum fld_rpc_opc {
- FLD_QUERY = 900,
- FLD_READ = 901,
- FLD_LAST_OPC,
- FLD_FIRST_OPC = FLD_QUERY
-};
-
-enum seq_rpc_opc {
- SEQ_QUERY = 700,
- SEQ_LAST_OPC,
- SEQ_FIRST_OPC = SEQ_QUERY
-};
-
-enum seq_op {
- SEQ_ALLOC_SUPER = 0,
- SEQ_ALLOC_META = 1
-};
-
-enum fld_op {
- FLD_CREATE = 0,
- FLD_DELETE = 1,
- FLD_LOOKUP = 2,
-};
-
-/*
- * LOV data structures
- */
-
-#define LOV_MAX_UUID_BUFFER_SIZE 8192
-/* The size of the buffer the lov/mdc reserves for the
- * array of UUIDs returned by the MDS. With the current
- * protocol, this will limit the max number of OSTs per LOV
- */
-
-#define LOV_DESC_MAGIC 0xB0CCDE5C
-#define LOV_DESC_QOS_MAXAGE_DEFAULT 5 /* Seconds */
-#define LOV_DESC_STRIPE_SIZE_DEFAULT (1 << LNET_MTU_BITS)
-
-/* LOV settings descriptor (should only contain static info) */
-struct lov_desc {
- __u32 ld_tgt_count; /* how many OBD's */
- __u32 ld_active_tgt_count; /* how many active */
- __u32 ld_default_stripe_count; /* how many objects are used */
- __u32 ld_pattern; /* default PATTERN_RAID0 */
- __u64 ld_default_stripe_size; /* in bytes */
- __u64 ld_default_stripe_offset; /* in bytes */
- __u32 ld_padding_0; /* unused */
- __u32 ld_qos_maxage; /* in second */
- __u32 ld_padding_1; /* also fix lustre_swab_lov_desc */
- __u32 ld_padding_2; /* also fix lustre_swab_lov_desc */
- struct obd_uuid ld_uuid;
-};
-
-#define ld_magic ld_active_tgt_count /* for swabbing from llogs */
-
-/*
- * LDLM requests:
- */
-/* opcodes -- MUST be distinct from OST/MDS opcodes */
-enum ldlm_cmd {
- LDLM_ENQUEUE = 101,
- LDLM_CONVERT = 102,
- LDLM_CANCEL = 103,
- LDLM_BL_CALLBACK = 104,
- LDLM_CP_CALLBACK = 105,
- LDLM_GL_CALLBACK = 106,
- LDLM_SET_INFO = 107,
- LDLM_LAST_OPC
-};
-#define LDLM_FIRST_OPC LDLM_ENQUEUE
-
-#define RES_NAME_SIZE 4
-struct ldlm_res_id {
- __u64 name[RES_NAME_SIZE];
-};
-
-#define DLDLMRES "[%#llx:%#llx:%#llx].%llx"
-#define PLDLMRES(res) (res)->lr_name.name[0], (res)->lr_name.name[1], \
- (res)->lr_name.name[2], (res)->lr_name.name[3]
-
-/* lock types */
-enum ldlm_mode {
- LCK_MINMODE = 0,
- LCK_EX = 1,
- LCK_PW = 2,
- LCK_PR = 4,
- LCK_CW = 8,
- LCK_CR = 16,
- LCK_NL = 32,
- LCK_GROUP = 64,
- LCK_COS = 128,
- LCK_MAXMODE
-};
-
-#define LCK_MODE_NUM 8
-
-enum ldlm_type {
- LDLM_PLAIN = 10,
- LDLM_EXTENT = 11,
- LDLM_FLOCK = 12,
- LDLM_IBITS = 13,
- LDLM_MAX_TYPE
-};
-
-#define LDLM_MIN_TYPE LDLM_PLAIN
-
-struct ldlm_extent {
- __u64 start;
- __u64 end;
- __u64 gid;
-};
-
-struct ldlm_inodebits {
- __u64 bits;
-};
-
-struct ldlm_flock_wire {
- __u64 lfw_start;
- __u64 lfw_end;
- __u64 lfw_owner;
- __u32 lfw_padding;
- __u32 lfw_pid;
-};
-
-/* it's important that the fields of the ldlm_extent structure match
- * the first fields of the ldlm_flock structure because there is only
- * one ldlm_swab routine to process the ldlm_policy_data_t union. if
- * this ever changes we will need to swab the union differently based
- * on the resource type.
- */
-
-union ldlm_wire_policy_data {
- struct ldlm_extent l_extent;
- struct ldlm_flock_wire l_flock;
- struct ldlm_inodebits l_inodebits;
-};
-
-union ldlm_gl_desc {
- struct ldlm_gl_lquota_desc lquota_desc;
-};
-
-enum ldlm_intent_flags {
- IT_OPEN = 0x00000001,
- IT_CREAT = 0x00000002,
- IT_OPEN_CREAT = 0x00000003,
- IT_READDIR = 0x00000004,
- IT_GETATTR = 0x00000008,
- IT_LOOKUP = 0x00000010,
- IT_UNLINK = 0x00000020,
- IT_TRUNC = 0x00000040,
- IT_GETXATTR = 0x00000080,
- IT_EXEC = 0x00000100,
- IT_PIN = 0x00000200,
- IT_LAYOUT = 0x00000400,
- IT_QUOTA_DQACQ = 0x00000800,
- IT_QUOTA_CONN = 0x00001000,
- IT_SETXATTR = 0x00002000,
-};
-
-struct ldlm_intent {
- __u64 opc;
-};
-
-struct ldlm_resource_desc {
- enum ldlm_type lr_type;
- __u32 lr_padding; /* also fix lustre_swab_ldlm_resource_desc */
- struct ldlm_res_id lr_name;
-};
-
-struct ldlm_lock_desc {
- struct ldlm_resource_desc l_resource;
- enum ldlm_mode l_req_mode;
- enum ldlm_mode l_granted_mode;
- union ldlm_wire_policy_data l_policy_data;
-};
-
-#define LDLM_LOCKREQ_HANDLES 2
-#define LDLM_ENQUEUE_CANCEL_OFF 1
-
-struct ldlm_request {
- __u32 lock_flags;
- __u32 lock_count;
- struct ldlm_lock_desc lock_desc;
- struct lustre_handle lock_handle[LDLM_LOCKREQ_HANDLES];
-};
-
-struct ldlm_reply {
- __u32 lock_flags;
- __u32 lock_padding; /* also fix lustre_swab_ldlm_reply */
- struct ldlm_lock_desc lock_desc;
- struct lustre_handle lock_handle;
- __u64 lock_policy_res1;
- __u64 lock_policy_res2;
-};
-
-#define ldlm_flags_to_wire(flags) ((__u32)(flags))
-#define ldlm_flags_from_wire(flags) ((__u64)(flags))
-
-/*
- * Opcodes for mountconf (mgs and mgc)
- */
-enum mgs_cmd {
- MGS_CONNECT = 250,
- MGS_DISCONNECT,
- MGS_EXCEPTION, /* node died, etc. */
- MGS_TARGET_REG, /* whenever target starts up */
- MGS_TARGET_DEL,
- MGS_SET_INFO,
- MGS_CONFIG_READ,
- MGS_LAST_OPC
-};
-#define MGS_FIRST_OPC MGS_CONNECT
-
-#define MGS_PARAM_MAXLEN 1024
-#define KEY_SET_INFO "set_info"
-
-struct mgs_send_param {
- char mgs_param[MGS_PARAM_MAXLEN];
-};
-
-/* We pass this info to the MGS so it can write config logs */
-#define MTI_NAME_MAXLEN 64
-#define MTI_PARAM_MAXLEN 4096
-#define MTI_NIDS_MAX 32
-struct mgs_target_info {
- __u32 mti_lustre_ver;
- __u32 mti_stripe_index;
- __u32 mti_config_ver;
- __u32 mti_flags;
- __u32 mti_nid_count;
- __u32 mti_instance; /* Running instance of target */
- char mti_fsname[MTI_NAME_MAXLEN];
- char mti_svname[MTI_NAME_MAXLEN];
- char mti_uuid[sizeof(struct obd_uuid)];
- __u64 mti_nids[MTI_NIDS_MAX]; /* host nids (lnet_nid_t)*/
- char mti_params[MTI_PARAM_MAXLEN];
-};
-
-struct mgs_nidtbl_entry {
- __u64 mne_version; /* table version of this entry */
- __u32 mne_instance; /* target instance # */
- __u32 mne_index; /* target index */
- __u32 mne_length; /* length of this entry - by bytes */
- __u8 mne_type; /* target type LDD_F_SV_TYPE_OST/MDT */
- __u8 mne_nid_type; /* type of nid(mbz). for ipv6. */
- __u8 mne_nid_size; /* size of each NID, by bytes */
- __u8 mne_nid_count; /* # of NIDs in buffer */
- union {
- lnet_nid_t nids[0]; /* variable size buffer for NIDs. */
- } u;
-};
-
-struct mgs_config_body {
- char mcb_name[MTI_NAME_MAXLEN]; /* logname */
- __u64 mcb_offset; /* next index of config log to request */
- __u16 mcb_type; /* type of log: CONFIG_T_[CONFIG|RECOVER] */
- __u8 mcb_reserved;
- __u8 mcb_bits; /* bits unit size of config log */
- __u32 mcb_units; /* # of units for bulk transfer */
-};
-
-struct mgs_config_res {
- __u64 mcr_offset; /* index of last config log */
- __u64 mcr_size; /* size of the log */
-};
-
-/* Config marker flags (in config log) */
-#define CM_START 0x01
-#define CM_END 0x02
-#define CM_SKIP 0x04
-#define CM_UPGRADE146 0x08
-#define CM_EXCLUDE 0x10
-#define CM_START_SKIP (CM_START | CM_SKIP)
-
-struct cfg_marker {
- __u32 cm_step; /* aka config version */
- __u32 cm_flags;
- __u32 cm_vers; /* lustre release version number */
- __u32 cm_padding; /* 64 bit align */
- __s64 cm_createtime; /*when this record was first created */
- __s64 cm_canceltime; /*when this record is no longer valid*/
- char cm_tgtname[MTI_NAME_MAXLEN];
- char cm_comment[MTI_NAME_MAXLEN];
-};
-
-/*
- * Opcodes for multiple servers.
- */
-
-enum obd_cmd {
- OBD_PING = 400,
- OBD_LOG_CANCEL,
- OBD_QC_CALLBACK, /* not used since 2.4 */
- OBD_IDX_READ,
- OBD_LAST_OPC
-};
-#define OBD_FIRST_OPC OBD_PING
-
-/**
- * llog contexts indices.
- *
- * There is compatibility problem with indexes below, they are not
- * continuous and must keep their numbers for compatibility needs.
- * See LU-5218 for details.
- */
-enum llog_ctxt_id {
- LLOG_CONFIG_ORIG_CTXT = 0,
- LLOG_CONFIG_REPL_CTXT = 1,
- LLOG_MDS_OST_ORIG_CTXT = 2,
- LLOG_MDS_OST_REPL_CTXT = 3, /* kept just to avoid re-assignment */
- LLOG_SIZE_ORIG_CTXT = 4,
- LLOG_SIZE_REPL_CTXT = 5,
- LLOG_TEST_ORIG_CTXT = 8,
- LLOG_TEST_REPL_CTXT = 9, /* kept just to avoid re-assignment */
- LLOG_CHANGELOG_ORIG_CTXT = 12, /**< changelog generation on mdd */
- LLOG_CHANGELOG_REPL_CTXT = 13, /**< changelog access on clients */
- /* for multiple changelog consumers */
- LLOG_CHANGELOG_USER_ORIG_CTXT = 14,
- LLOG_AGENT_ORIG_CTXT = 15, /**< agent requests generation on cdt */
- LLOG_MAX_CTXTS
-};
-
-/** Identifier for a single log object */
-struct llog_logid {
- struct ost_id lgl_oi;
- __u32 lgl_ogen;
-} __packed;
-
-/** Records written to the CATALOGS list */
-#define CATLIST "CATALOGS"
-struct llog_catid {
- struct llog_logid lci_logid;
- __u32 lci_padding1;
- __u32 lci_padding2;
- __u32 lci_padding3;
-} __packed;
-
-/* Log data record types - there is no specific reason that these need to
- * be related to the RPC opcodes, but no reason not to (may be handy later?)
- */
-#define LLOG_OP_MAGIC 0x10600000
-#define LLOG_OP_MASK 0xfff00000
-
-enum llog_op_type {
- LLOG_PAD_MAGIC = LLOG_OP_MAGIC | 0x00000,
- OST_SZ_REC = LLOG_OP_MAGIC | 0x00f00,
- /* OST_RAID1_REC = LLOG_OP_MAGIC | 0x01000, never used */
- MDS_UNLINK_REC = LLOG_OP_MAGIC | 0x10000 | (MDS_REINT << 8) |
- REINT_UNLINK, /* obsolete after 2.5.0 */
- MDS_UNLINK64_REC = LLOG_OP_MAGIC | 0x90000 | (MDS_REINT << 8) |
- REINT_UNLINK,
- /* MDS_SETATTR_REC = LLOG_OP_MAGIC | 0x12401, obsolete 1.8.0 */
- MDS_SETATTR64_REC = LLOG_OP_MAGIC | 0x90000 | (MDS_REINT << 8) |
- REINT_SETATTR,
- OBD_CFG_REC = LLOG_OP_MAGIC | 0x20000,
- /* PTL_CFG_REC = LLOG_OP_MAGIC | 0x30000, obsolete 1.4.0 */
- LLOG_GEN_REC = LLOG_OP_MAGIC | 0x40000,
- /* LLOG_JOIN_REC = LLOG_OP_MAGIC | 0x50000, obsolete 1.8.0 */
- CHANGELOG_REC = LLOG_OP_MAGIC | 0x60000,
- CHANGELOG_USER_REC = LLOG_OP_MAGIC | 0x70000,
- HSM_AGENT_REC = LLOG_OP_MAGIC | 0x80000,
- LLOG_HDR_MAGIC = LLOG_OP_MAGIC | 0x45539,
- LLOG_LOGID_MAGIC = LLOG_OP_MAGIC | 0x4553b,
-};
-
-#define LLOG_REC_HDR_NEEDS_SWABBING(r) \
- (((r)->lrh_type & __swab32(LLOG_OP_MASK)) == __swab32(LLOG_OP_MAGIC))
-
-/** Log record header - stored in little endian order.
- * Each record must start with this struct, end with a llog_rec_tail,
- * and be a multiple of 256 bits in size.
- */
-struct llog_rec_hdr {
- __u32 lrh_len;
- __u32 lrh_index;
- __u32 lrh_type;
- __u32 lrh_id;
-};
-
-struct llog_rec_tail {
- __u32 lrt_len;
- __u32 lrt_index;
-};
-
-/* Where data follow just after header */
-#define REC_DATA(ptr) \
- ((void *)((char *)ptr + sizeof(struct llog_rec_hdr)))
-
-#define REC_DATA_LEN(rec) \
- (rec->lrh_len - sizeof(struct llog_rec_hdr) - \
- sizeof(struct llog_rec_tail))
-
-struct llog_logid_rec {
- struct llog_rec_hdr lid_hdr;
- struct llog_logid lid_id;
- __u32 lid_padding1;
- __u64 lid_padding2;
- __u64 lid_padding3;
- struct llog_rec_tail lid_tail;
-} __packed;
-
-struct llog_unlink_rec {
- struct llog_rec_hdr lur_hdr;
- __u64 lur_oid;
- __u32 lur_oseq;
- __u32 lur_count;
- struct llog_rec_tail lur_tail;
-} __packed;
-
-struct llog_unlink64_rec {
- struct llog_rec_hdr lur_hdr;
- struct lu_fid lur_fid;
- __u32 lur_count; /* to destroy the lost precreated */
- __u32 lur_padding1;
- __u64 lur_padding2;
- __u64 lur_padding3;
- struct llog_rec_tail lur_tail;
-} __packed;
-
-struct llog_setattr64_rec {
- struct llog_rec_hdr lsr_hdr;
- struct ost_id lsr_oi;
- __u32 lsr_uid;
- __u32 lsr_uid_h;
- __u32 lsr_gid;
- __u32 lsr_gid_h;
- __u64 lsr_valid;
- struct llog_rec_tail lsr_tail;
-} __packed;
-
-struct llog_size_change_rec {
- struct llog_rec_hdr lsc_hdr;
- struct ll_fid lsc_fid;
- __u32 lsc_ioepoch;
- __u32 lsc_padding1;
- __u64 lsc_padding2;
- __u64 lsc_padding3;
- struct llog_rec_tail lsc_tail;
-} __packed;
-
-/* changelog llog name, needed by client replicators */
-#define CHANGELOG_CATALOG "changelog_catalog"
-
-struct changelog_setinfo {
- __u64 cs_recno;
- __u32 cs_id;
-} __packed;
-
-/** changelog record */
-struct llog_changelog_rec {
- struct llog_rec_hdr cr_hdr;
- struct changelog_rec cr; /**< Variable length field */
- struct llog_rec_tail cr_do_not_use; /**< for_sizezof_only */
-} __packed;
-
-struct llog_changelog_user_rec {
- struct llog_rec_hdr cur_hdr;
- __u32 cur_id;
- __u32 cur_padding;
- __u64 cur_endrec;
- struct llog_rec_tail cur_tail;
-} __packed;
-
-enum agent_req_status {
- ARS_WAITING,
- ARS_STARTED,
- ARS_FAILED,
- ARS_CANCELED,
- ARS_SUCCEED,
-};
-
-static inline const char *agent_req_status2name(const enum agent_req_status ars)
-{
- switch (ars) {
- case ARS_WAITING:
- return "WAITING";
- case ARS_STARTED:
- return "STARTED";
- case ARS_FAILED:
- return "FAILED";
- case ARS_CANCELED:
- return "CANCELED";
- case ARS_SUCCEED:
- return "SUCCEED";
- default:
- return "UNKNOWN";
- }
-}
-
-struct llog_agent_req_rec {
- struct llog_rec_hdr arr_hdr; /**< record header */
- __u32 arr_status; /**< status of the request */
- /* must match enum
- * agent_req_status
- */
- __u32 arr_archive_id; /**< backend archive number */
- __u64 arr_flags; /**< req flags */
- __u64 arr_compound_id;/**< compound cookie */
- __u64 arr_req_create; /**< req. creation time */
- __u64 arr_req_change; /**< req. status change time */
- struct hsm_action_item arr_hai; /**< req. to the agent */
- struct llog_rec_tail arr_tail; /**< record tail for_sizezof_only */
-} __packed;
-
-/* Old llog gen for compatibility */
-struct llog_gen {
- __u64 mnt_cnt;
- __u64 conn_cnt;
-} __packed;
-
-struct llog_gen_rec {
- struct llog_rec_hdr lgr_hdr;
- struct llog_gen lgr_gen;
- __u64 padding1;
- __u64 padding2;
- __u64 padding3;
- struct llog_rec_tail lgr_tail;
-};
-
-/* flags for the logs */
-enum llog_flag {
- LLOG_F_ZAP_WHEN_EMPTY = 0x1,
- LLOG_F_IS_CAT = 0x2,
- LLOG_F_IS_PLAIN = 0x4,
- LLOG_F_EXT_JOBID = 0x8,
- LLOG_F_IS_FIXSIZE = 0x10,
-
- /*
- * Note: Flags covered by LLOG_F_EXT_MASK will be inherited from
- * catlog to plain log, so do not add LLOG_F_IS_FIXSIZE here,
- * because the catlog record is usually fixed size, but its plain
- * log record can be variable
- */
- LLOG_F_EXT_MASK = LLOG_F_EXT_JOBID,
-};
-
-/* On-disk header structure of each log object, stored in little endian order */
-#define LLOG_MIN_CHUNK_SIZE 8192
-#define LLOG_HEADER_SIZE (96) /* sizeof (llog_log_hdr) +
- * sizeof(llh_tail) - sizeof(llh_bitmap)
- */
-#define LLOG_BITMAP_BYTES (LLOG_MIN_CHUNK_SIZE - LLOG_HEADER_SIZE)
-#define LLOG_MIN_REC_SIZE (24) /* round(llog_rec_hdr + llog_rec_tail) */
-
-/* flags for the logs */
-struct llog_log_hdr {
- struct llog_rec_hdr llh_hdr;
- __s64 llh_timestamp;
- __u32 llh_count;
- __u32 llh_bitmap_offset;
- __u32 llh_size;
- __u32 llh_flags;
- __u32 llh_cat_idx;
- /* for a catalog the first plain slot is next to it */
- struct obd_uuid llh_tgtuuid;
- __u32 llh_reserved[LLOG_HEADER_SIZE / sizeof(__u32) - 23];
- /* These fields must always be at the end of the llog_log_hdr.
- * Note: llh_bitmap size is variable because llog chunk size could be
- * bigger than LLOG_MIN_CHUNK_SIZE, i.e. sizeof(llog_log_hdr) > 8192
- * bytes, and the real size is stored in llh_hdr.lrh_len, which means
- * llh_tail should only be referred by LLOG_HDR_TAIL().
- * But this structure is also used by client/server llog interface
- * (see llog_client.c), it will be kept in its original way to avoid
- * compatibility issue.
- */
- __u32 llh_bitmap[LLOG_BITMAP_BYTES / sizeof(__u32)];
- struct llog_rec_tail llh_tail;
-} __packed;
-
-#undef LLOG_HEADER_SIZE
-#undef LLOG_BITMAP_BYTES
-
-#define LLOG_HDR_BITMAP_SIZE(llh) (__u32)((llh->llh_hdr.lrh_len - \
- llh->llh_bitmap_offset - \
- sizeof(llh->llh_tail)) * 8)
-#define LLOG_HDR_BITMAP(llh) (__u32 *)((char *)(llh) + \
- (llh)->llh_bitmap_offset)
-#define LLOG_HDR_TAIL(llh) ((struct llog_rec_tail *)((char *)llh + \
- llh->llh_hdr.lrh_len - \
- sizeof(llh->llh_tail)))
-
-/** log cookies are used to reference a specific log file and a record
- * therein
- */
-struct llog_cookie {
- struct llog_logid lgc_lgl;
- __u32 lgc_subsys;
- __u32 lgc_index;
- __u32 lgc_padding;
-} __packed;
-
-/** llog protocol */
-enum llogd_rpc_ops {
- LLOG_ORIGIN_HANDLE_CREATE = 501,
- LLOG_ORIGIN_HANDLE_NEXT_BLOCK = 502,
- LLOG_ORIGIN_HANDLE_READ_HEADER = 503,
- LLOG_ORIGIN_HANDLE_WRITE_REC = 504,
- LLOG_ORIGIN_HANDLE_CLOSE = 505,
- LLOG_ORIGIN_CONNECT = 506,
- LLOG_CATINFO = 507, /* deprecated */
- LLOG_ORIGIN_HANDLE_PREV_BLOCK = 508,
- LLOG_ORIGIN_HANDLE_DESTROY = 509, /* for destroy llog object*/
- LLOG_LAST_OPC,
- LLOG_FIRST_OPC = LLOG_ORIGIN_HANDLE_CREATE
-};
-
-struct llogd_body {
- struct llog_logid lgd_logid;
- __u32 lgd_ctxt_idx;
- __u32 lgd_llh_flags;
- __u32 lgd_index;
- __u32 lgd_saved_index;
- __u32 lgd_len;
- __u64 lgd_cur_offset;
-} __packed;
-
-struct llogd_conn_body {
- struct llog_gen lgdc_gen;
- struct llog_logid lgdc_logid;
- __u32 lgdc_ctxt_idx;
-} __packed;
-
-/* Note: 64-bit types are 64-bit aligned in structure */
-struct obdo {
- __u64 o_valid; /* hot fields in this obdo */
- struct ost_id o_oi;
- __u64 o_parent_seq;
- __u64 o_size; /* o_size-o_blocks == ost_lvb */
- __s64 o_mtime;
- __s64 o_atime;
- __s64 o_ctime;
- __u64 o_blocks; /* brw: cli sent cached bytes */
- __u64 o_grant;
-
- /* 32-bit fields start here: keep an even number of them via padding */
- __u32 o_blksize; /* optimal IO blocksize */
- __u32 o_mode; /* brw: cli sent cache remain */
- __u32 o_uid;
- __u32 o_gid;
- __u32 o_flags;
- __u32 o_nlink; /* brw: checksum */
- __u32 o_parent_oid;
- __u32 o_misc; /* brw: o_dropped */
-
- __u64 o_ioepoch; /* epoch in ost writes */
- __u32 o_stripe_idx; /* holds stripe idx */
- __u32 o_parent_ver;
- struct lustre_handle o_handle; /* brw: lock handle to prolong locks
- */
- struct llog_cookie o_lcookie; /* destroy: unlink cookie from MDS,
- * obsolete in 2.8, reused in OSP
- */
- __u32 o_uid_h;
- __u32 o_gid_h;
-
- __u64 o_data_version; /* getattr: sum of iversion for
- * each stripe.
- * brw: grant space consumed on
- * the client for the write
- */
- __u64 o_padding_4;
- __u64 o_padding_5;
- __u64 o_padding_6;
-};
-
-#define o_dirty o_blocks
-#define o_undirty o_mode
-#define o_dropped o_misc
-#define o_cksum o_nlink
-#define o_grant_used o_data_version
-
-/* request structure for OST's */
-struct ost_body {
- struct obdo oa;
-};
-
-/* Key for FIEMAP to be used in get_info calls */
-struct ll_fiemap_info_key {
- char lfik_name[8];
- struct obdo lfik_oa;
- struct fiemap lfik_fiemap;
-};
-
-/* security opcodes */
-enum sec_cmd {
- SEC_CTX_INIT = 801,
- SEC_CTX_INIT_CONT = 802,
- SEC_CTX_FINI = 803,
- SEC_LAST_OPC,
- SEC_FIRST_OPC = SEC_CTX_INIT
-};
-
-/*
- * capa related definitions
- */
-#define CAPA_HMAC_MAX_LEN 64
-#define CAPA_HMAC_KEY_MAX_LEN 56
-
-/* NB take care when changing the sequence of elements this struct,
- * because the offset info is used in find_capa()
- */
-struct lustre_capa {
- struct lu_fid lc_fid; /** fid */
- __u64 lc_opc; /** operations allowed */
- __u64 lc_uid; /** file owner */
- __u64 lc_gid; /** file group */
- __u32 lc_flags; /** HMAC algorithm & flags */
- __u32 lc_keyid; /** key# used for the capability */
- __u32 lc_timeout; /** capa timeout value (sec) */
-/* FIXME: y2038 time_t overflow: */
- __u32 lc_expiry; /** expiry time (sec) */
- __u8 lc_hmac[CAPA_HMAC_MAX_LEN]; /** HMAC */
-} __packed;
-
-/** lustre_capa::lc_opc */
-enum {
- CAPA_OPC_BODY_WRITE = 1 << 0, /**< write object data */
- CAPA_OPC_BODY_READ = 1 << 1, /**< read object data */
- CAPA_OPC_INDEX_LOOKUP = 1 << 2, /**< lookup object fid */
- CAPA_OPC_INDEX_INSERT = 1 << 3, /**< insert object fid */
- CAPA_OPC_INDEX_DELETE = 1 << 4, /**< delete object fid */
- CAPA_OPC_OSS_WRITE = 1 << 5, /**< write oss object data */
- CAPA_OPC_OSS_READ = 1 << 6, /**< read oss object data */
- CAPA_OPC_OSS_TRUNC = 1 << 7, /**< truncate oss object */
- CAPA_OPC_OSS_DESTROY = 1 << 8, /**< destroy oss object */
- CAPA_OPC_META_WRITE = 1 << 9, /**< write object meta data */
- CAPA_OPC_META_READ = 1 << 10, /**< read object meta data */
-};
-
-#define CAPA_OPC_OSS_RW (CAPA_OPC_OSS_READ | CAPA_OPC_OSS_WRITE)
-#define CAPA_OPC_MDS_ONLY \
- (CAPA_OPC_BODY_WRITE | CAPA_OPC_BODY_READ | CAPA_OPC_INDEX_LOOKUP | \
- CAPA_OPC_INDEX_INSERT | CAPA_OPC_INDEX_DELETE)
-#define CAPA_OPC_OSS_ONLY \
- (CAPA_OPC_OSS_WRITE | CAPA_OPC_OSS_READ | CAPA_OPC_OSS_TRUNC | \
- CAPA_OPC_OSS_DESTROY)
-#define CAPA_OPC_MDS_DEFAULT ~CAPA_OPC_OSS_ONLY
-#define CAPA_OPC_OSS_DEFAULT ~(CAPA_OPC_MDS_ONLY | CAPA_OPC_OSS_ONLY)
-
-struct lustre_capa_key {
- __u64 lk_seq; /**< mds# */
- __u32 lk_keyid; /**< key# */
- __u32 lk_padding;
- __u8 lk_key[CAPA_HMAC_KEY_MAX_LEN]; /**< key */
-} __packed;
-
-/** The link ea holds 1 \a link_ea_entry for each hardlink */
-#define LINK_EA_MAGIC 0x11EAF1DFUL
-struct link_ea_header {
- __u32 leh_magic;
- __u32 leh_reccount;
- __u64 leh_len; /* total size */
- __u32 leh_overflow_time;
- __u32 leh_padding;
-};
-
-/** Hardlink data is name and parent fid.
- * Stored in this crazy struct for maximum packing and endian-neutrality
- */
-struct link_ea_entry {
- /** __u16 stored big-endian, unaligned */
- unsigned char lee_reclen[2];
- unsigned char lee_parent_fid[sizeof(struct lu_fid)];
- char lee_name[0];
-} __packed;
-
-/** fid2path request/reply structure */
-struct getinfo_fid2path {
- struct lu_fid gf_fid;
- __u64 gf_recno;
- __u32 gf_linkno;
- __u32 gf_pathlen;
- char gf_path[0];
-} __packed;
-
-/** path2parent request/reply structures */
-struct getparent {
- struct lu_fid gp_fid; /**< parent FID */
- __u32 gp_linkno; /**< hardlink number */
- __u32 gp_name_size; /**< size of the name field */
- char gp_name[0]; /**< zero-terminated link name */
-} __packed;
-
-enum {
- LAYOUT_INTENT_ACCESS = 0,
- LAYOUT_INTENT_READ = 1,
- LAYOUT_INTENT_WRITE = 2,
- LAYOUT_INTENT_GLIMPSE = 3,
- LAYOUT_INTENT_TRUNC = 4,
- LAYOUT_INTENT_RELEASE = 5,
- LAYOUT_INTENT_RESTORE = 6
-};
-
-/* enqueue layout lock with intent */
-struct layout_intent {
- __u32 li_opc; /* intent operation for enqueue, read, write etc */
- __u32 li_flags;
- __u64 li_start;
- __u64 li_end;
-};
-
-/**
- * On the wire version of hsm_progress structure.
- *
- * Contains the userspace hsm_progress and some internal fields.
- */
-struct hsm_progress_kernel {
- /* Field taken from struct hsm_progress */
- struct lu_fid hpk_fid;
- __u64 hpk_cookie;
- struct hsm_extent hpk_extent;
- __u16 hpk_flags;
- __u16 hpk_errval; /* positive val */
- __u32 hpk_padding1;
- /* Additional fields */
- __u64 hpk_data_version;
- __u64 hpk_padding2;
-} __packed;
-
-/** layout swap request structure
- * fid1 and fid2 are in mdt_body
- */
-struct mdc_swap_layouts {
- __u64 msl_flags;
-} __packed;
-
-struct close_data {
- struct lustre_handle cd_handle;
- struct lu_fid cd_fid;
- __u64 cd_data_version;
- __u64 cd_reserved[8];
-};
-
-#endif
-/** @} lustreidl */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ioctl.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ioctl.h
deleted file mode 100644
index 6e4e109fb874..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ioctl.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-#ifndef _UAPI_LUSTRE_IOCTL_H_
-#define _UAPI_LUSTRE_IOCTL_H_
-
-#include <linux/ioctl.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <uapi/linux/lustre/lustre_idl.h>
-
-#if !defined(__KERNEL__) && !defined(LUSTRE_UTILS)
-# error This file is for Lustre internal use only.
-#endif
-
-enum md_echo_cmd {
- ECHO_MD_CREATE = 1, /* Open/Create file on MDT */
- ECHO_MD_MKDIR = 2, /* Mkdir on MDT */
- ECHO_MD_DESTROY = 3, /* Unlink file on MDT */
- ECHO_MD_RMDIR = 4, /* Rmdir on MDT */
- ECHO_MD_LOOKUP = 5, /* Lookup on MDT */
- ECHO_MD_GETATTR = 6, /* Getattr on MDT */
- ECHO_MD_SETATTR = 7, /* Setattr on MDT */
- ECHO_MD_ALLOC_FID = 8, /* Get FIDs from MDT */
-};
-
-#define OBD_DEV_ID 1
-#define OBD_DEV_NAME "obd"
-#define OBD_DEV_PATH "/dev/" OBD_DEV_NAME
-
-#define OBD_IOCTL_VERSION 0x00010004
-#define OBD_DEV_BY_DEVNAME 0xffffd0de
-
-struct obd_ioctl_data {
- __u32 ioc_len;
- __u32 ioc_version;
-
- union {
- __u64 ioc_cookie;
- __u64 ioc_u64_1;
- };
- union {
- __u32 ioc_conn1;
- __u32 ioc_u32_1;
- };
- union {
- __u32 ioc_conn2;
- __u32 ioc_u32_2;
- };
-
- struct obdo ioc_obdo1;
- struct obdo ioc_obdo2;
-
- __u64 ioc_count;
- __u64 ioc_offset;
- __u32 ioc_dev;
- __u32 ioc_command;
-
- __u64 ioc_nid;
- __u32 ioc_nal;
- __u32 ioc_type;
-
- /* buffers the kernel will treat as user pointers */
- __u32 ioc_plen1;
- char __user *ioc_pbuf1;
- __u32 ioc_plen2;
- char __user *ioc_pbuf2;
-
- /* inline buffers for various arguments */
- __u32 ioc_inllen1;
- char *ioc_inlbuf1;
- __u32 ioc_inllen2;
- char *ioc_inlbuf2;
- __u32 ioc_inllen3;
- char *ioc_inlbuf3;
- __u32 ioc_inllen4;
- char *ioc_inlbuf4;
-
- char ioc_bulk[0];
-};
-
-struct obd_ioctl_hdr {
- __u32 ioc_len;
- __u32 ioc_version;
-};
-
-static inline __u32 obd_ioctl_packlen(struct obd_ioctl_data *data)
-{
- __u32 len = __ALIGN_KERNEL(sizeof(*data), 8);
-
- len += __ALIGN_KERNEL(data->ioc_inllen1, 8);
- len += __ALIGN_KERNEL(data->ioc_inllen2, 8);
- len += __ALIGN_KERNEL(data->ioc_inllen3, 8);
- len += __ALIGN_KERNEL(data->ioc_inllen4, 8);
-
- return len;
-}
-
-/*
- * OBD_IOC_DATA_TYPE is only for compatibility reasons with older
- * Linux Lustre user tools. New ioctls should NOT use this macro as
- * the ioctl "size". Instead the ioctl should get a "size" argument
- * which is the actual data type used by the ioctl, to ensure the
- * ioctl interface is versioned correctly.
- */
-#define OBD_IOC_DATA_TYPE long
-
-/* IOC_LDLM_TEST _IOWR('f', 40, long) */
-/* IOC_LDLM_DUMP _IOWR('f', 41, long) */
-/* IOC_LDLM_REGRESS_START _IOWR('f', 42, long) */
-/* IOC_LDLM_REGRESS_STOP _IOWR('f', 43, long) */
-
-#define OBD_IOC_CREATE _IOWR('f', 101, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_DESTROY _IOW('f', 104, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_PREALLOCATE _IOWR('f', 105, OBD_IOC_DATA_TYPE) */
-
-#define OBD_IOC_SETATTR _IOW('f', 107, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETATTR _IOWR('f', 108, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_READ _IOWR('f', 109, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_WRITE _IOWR('f', 110, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_STATFS _IOWR('f', 113, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_SYNC _IOW('f', 114, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_READ2 _IOWR('f', 115, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_FORMAT _IOWR('f', 116, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_PARTITION _IOWR('f', 117, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_COPY _IOWR('f', 120, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_MIGR _IOWR('f', 121, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_PUNCH _IOWR('f', 122, OBD_IOC_DATA_TYPE) */
-
-/* OBD_IOC_MODULE_DEBUG _IOWR('f', 124, OBD_IOC_DATA_TYPE) */
-#define OBD_IOC_BRW_READ _IOWR('f', 125, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_BRW_WRITE _IOWR('f', 126, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_NAME2DEV _IOWR('f', 127, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_UUID2DEV _IOWR('f', 130, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETNAME _IOWR('f', 131, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETMDNAME _IOR('f', 131, char[MAX_OBD_NAME])
-#define OBD_IOC_GETDTNAME OBD_IOC_GETNAME
-#define OBD_IOC_LOV_GET_CONFIG _IOWR('f', 132, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_CLIENT_RECOVER _IOW('f', 133, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_PING_TARGET _IOW('f', 136, OBD_IOC_DATA_TYPE)
-
-/* OBD_IOC_DEC_FS_USE_COUNT _IO('f', 139) */
-#define OBD_IOC_NO_TRANSNO _IOW('f', 140, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_SET_READONLY _IOW('f', 141, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_ABORT_RECOVERY _IOR('f', 142, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_ROOT_SQUASH _IOWR('f', 143, OBD_IOC_DATA_TYPE) */
-#define OBD_GET_VERSION _IOWR('f', 144, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_GSS_SUPPORT _IOWR('f', 145, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_CLOSE_UUID _IOWR('f', 147, OBD_IOC_DATA_TYPE) */
-#define OBD_IOC_CHANGELOG_SEND _IOW('f', 148, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_GETDEVICE _IOWR('f', 149, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_FID2PATH _IOWR('f', 150, OBD_IOC_DATA_TYPE)
-/* lustre/lustre_user.h 151-153 */
-/* OBD_IOC_LOV_SETSTRIPE 154 LL_IOC_LOV_SETSTRIPE */
-/* OBD_IOC_LOV_GETSTRIPE 155 LL_IOC_LOV_GETSTRIPE */
-/* OBD_IOC_LOV_SETEA 156 LL_IOC_LOV_SETEA */
-/* lustre/lustre_user.h 157-159 */
-/* OBD_IOC_QUOTACHECK _IOW('f', 160, int) */
-/* OBD_IOC_POLL_QUOTACHECK _IOR('f', 161, struct if_quotacheck *) */
-#define OBD_IOC_QUOTACTL _IOWR('f', 162, struct if_quotactl)
-/* lustre/lustre_user.h 163-176 */
-#define OBD_IOC_CHANGELOG_REG _IOW('f', 177, struct obd_ioctl_data)
-#define OBD_IOC_CHANGELOG_DEREG _IOW('f', 178, struct obd_ioctl_data)
-#define OBD_IOC_CHANGELOG_CLEAR _IOW('f', 179, struct obd_ioctl_data)
-/* OBD_IOC_RECORD _IOWR('f', 180, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_ENDRECORD _IOWR('f', 181, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_PARSE _IOWR('f', 182, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_DORECORD _IOWR('f', 183, OBD_IOC_DATA_TYPE) */
-#define OBD_IOC_PROCESS_CFG _IOWR('f', 184, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_DUMP_LOG _IOWR('f', 185, OBD_IOC_DATA_TYPE) */
-/* OBD_IOC_CLEAR_LOG _IOWR('f', 186, OBD_IOC_DATA_TYPE) */
-#define OBD_IOC_PARAM _IOW('f', 187, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_POOL _IOWR('f', 188, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_REPLACE_NIDS _IOWR('f', 189, OBD_IOC_DATA_TYPE)
-
-#define OBD_IOC_CATLOGLIST _IOWR('f', 190, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_INFO _IOWR('f', 191, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_PRINT _IOWR('f', 192, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_CANCEL _IOWR('f', 193, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_REMOVE _IOWR('f', 194, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_LLOG_CHECK _IOWR('f', 195, OBD_IOC_DATA_TYPE)
-/* OBD_IOC_LLOG_CATINFO _IOWR('f', 196, OBD_IOC_DATA_TYPE) */
-#define OBD_IOC_NODEMAP _IOWR('f', 197, OBD_IOC_DATA_TYPE)
-
-/* ECHO_IOC_GET_STRIPE _IOWR('f', 200, OBD_IOC_DATA_TYPE) */
-/* ECHO_IOC_SET_STRIPE _IOWR('f', 201, OBD_IOC_DATA_TYPE) */
-/* ECHO_IOC_ENQUEUE _IOWR('f', 202, OBD_IOC_DATA_TYPE) */
-/* ECHO_IOC_CANCEL _IOWR('f', 203, OBD_IOC_DATA_TYPE) */
-
-#define OBD_IOC_GET_OBJ_VERSION _IOR('f', 210, OBD_IOC_DATA_TYPE)
-
-/* lustre/lustre_user.h 212-217 */
-#define OBD_IOC_GET_MNTOPT _IOW('f', 220, mntopt_t)
-#define OBD_IOC_ECHO_MD _IOR('f', 221, struct obd_ioctl_data)
-#define OBD_IOC_ECHO_ALLOC_SEQ _IOWR('f', 222, struct obd_ioctl_data)
-#define OBD_IOC_START_LFSCK _IOWR('f', 230, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_STOP_LFSCK _IOW('f', 231, OBD_IOC_DATA_TYPE)
-#define OBD_IOC_QUERY_LFSCK _IOR('f', 232, struct obd_ioctl_data)
-/* lustre/lustre_user.h 240-249 */
-/* LIBCFS_IOC_DEBUG_MASK 250 */
-
-#define IOC_OSC_SET_ACTIVE _IOWR('h', 21, void *)
-
-#endif /* _UAPI_LUSTRE_IOCTL_H_ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_kernelcomm.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_kernelcomm.h
deleted file mode 100644
index 94dadbe8e069..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_kernelcomm.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2009, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2013, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- *
- * Author: Nathan Rutman <nathan.rutman@sun.com>
- *
- * Kernel <-> userspace communication routines.
- * The definitions below are used in the kernel and userspace.
- */
-
-#ifndef __UAPI_LUSTRE_KERNELCOMM_H__
-#define __UAPI_LUSTRE_KERNELCOMM_H__
-
-#include <linux/types.h>
-
-/* KUC message header.
- * All current and future KUC messages should use this header.
- * To avoid having to include Lustre headers from libcfs, define this here.
- */
-struct kuc_hdr {
- __u16 kuc_magic;
- /* Each new Lustre feature should use a different transport */
- __u8 kuc_transport;
- __u8 kuc_flags;
- /* Message type or opcode, transport-specific */
- __u16 kuc_msgtype;
- /* Including header */
- __u16 kuc_msglen;
-} __aligned(sizeof(__u64));
-
-#define KUC_CHANGELOG_MSG_MAXSIZE (sizeof(struct kuc_hdr) + CR_MAXSIZE)
-
-#define KUC_MAGIC 0x191C /*Lustre9etLinC */
-
-/* kuc_msgtype values are defined in each transport */
-enum kuc_transport_type {
- KUC_TRANSPORT_GENERIC = 1,
- KUC_TRANSPORT_HSM = 2,
- KUC_TRANSPORT_CHANGELOG = 3,
-};
-
-enum kuc_generic_message_type {
- KUC_MSG_SHUTDOWN = 1,
-};
-
-/* KUC Broadcast Groups. This determines which userspace process hears which
- * messages. Mutliple transports may be used within a group, or multiple
- * groups may use the same transport. Broadcast
- * groups need not be used if e.g. a UID is specified instead;
- * use group 0 to signify unicast.
- */
-#define KUC_GRP_HSM 0x02
-#define KUC_GRP_MAX KUC_GRP_HSM
-
-#define LK_FLG_STOP 0x01
-#define LK_NOFD -1U
-
-/* kernelcomm control structure, passed from userspace to kernel */
-struct lustre_kernelcomm {
- __u32 lk_wfd;
- __u32 lk_rfd;
- __u32 lk_uid;
- __u32 lk_group;
- __u32 lk_data;
- __u32 lk_flags;
-} __packed;
-
-#endif /* __UAPI_LUSTRE_KERNELCOMM_H__ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ostid.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ostid.h
deleted file mode 100644
index 3343b602219b..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ostid.h
+++ /dev/null
@@ -1,236 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2014, Intel Corporation.
- *
- * Copyright 2015 Cray Inc, all rights reserved.
- * Author: Ben Evans.
- *
- * Define ost_id associated functions
- */
-
-#ifndef _UAPI_LUSTRE_OSTID_H_
-#define _UAPI_LUSTRE_OSTID_H_
-
-#include <linux/errno.h>
-#include <uapi/linux/lustre/lustre_fid.h>
-
-static inline __u64 lmm_oi_id(const struct ost_id *oi)
-{
- return oi->oi.oi_id;
-}
-
-static inline __u64 lmm_oi_seq(const struct ost_id *oi)
-{
- return oi->oi.oi_seq;
-}
-
-static inline void lmm_oi_set_seq(struct ost_id *oi, __u64 seq)
-{
- oi->oi.oi_seq = seq;
-}
-
-static inline void lmm_oi_set_id(struct ost_id *oi, __u64 oid)
-{
- oi->oi.oi_id = oid;
-}
-
-static inline void lmm_oi_le_to_cpu(struct ost_id *dst_oi,
- const struct ost_id *src_oi)
-{
- dst_oi->oi.oi_id = __le64_to_cpu(src_oi->oi.oi_id);
- dst_oi->oi.oi_seq = __le64_to_cpu(src_oi->oi.oi_seq);
-}
-
-static inline void lmm_oi_cpu_to_le(struct ost_id *dst_oi,
- const struct ost_id *src_oi)
-{
- dst_oi->oi.oi_id = __cpu_to_le64(src_oi->oi.oi_id);
- dst_oi->oi.oi_seq = __cpu_to_le64(src_oi->oi.oi_seq);
-}
-
-/* extract OST sequence (group) from a wire ost_id (id/seq) pair */
-static inline __u64 ostid_seq(const struct ost_id *ostid)
-{
- if (fid_seq_is_mdt0(ostid->oi.oi_seq))
- return FID_SEQ_OST_MDT0;
-
- if (fid_seq_is_default(ostid->oi.oi_seq))
- return FID_SEQ_LOV_DEFAULT;
-
- if (fid_is_idif(&ostid->oi_fid))
- return FID_SEQ_OST_MDT0;
-
- return fid_seq(&ostid->oi_fid);
-}
-
-/* extract OST objid from a wire ost_id (id/seq) pair */
-static inline __u64 ostid_id(const struct ost_id *ostid)
-{
- if (fid_seq_is_mdt0(ostid->oi.oi_seq))
- return ostid->oi.oi_id & IDIF_OID_MASK;
-
- if (fid_seq_is_default(ostid->oi.oi_seq))
- return ostid->oi.oi_id;
-
- if (fid_is_idif(&ostid->oi_fid))
- return fid_idif_id(fid_seq(&ostid->oi_fid),
- fid_oid(&ostid->oi_fid), 0);
-
- return fid_oid(&ostid->oi_fid);
-}
-
-static inline void ostid_set_seq(struct ost_id *oi, __u64 seq)
-{
- if (fid_seq_is_mdt0(seq) || fid_seq_is_default(seq)) {
- oi->oi.oi_seq = seq;
- } else {
- oi->oi_fid.f_seq = seq;
- /*
- * Note: if f_oid + f_ver is zero, we need init it
- * to be 1, otherwise, ostid_seq will treat this
- * as old ostid (oi_seq == 0)
- */
- if (!oi->oi_fid.f_oid && !oi->oi_fid.f_ver)
- oi->oi_fid.f_oid = LUSTRE_FID_INIT_OID;
- }
-}
-
-static inline void ostid_set_seq_mdt0(struct ost_id *oi)
-{
- ostid_set_seq(oi, FID_SEQ_OST_MDT0);
-}
-
-static inline void ostid_set_seq_echo(struct ost_id *oi)
-{
- ostid_set_seq(oi, FID_SEQ_ECHO);
-}
-
-static inline void ostid_set_seq_llog(struct ost_id *oi)
-{
- ostid_set_seq(oi, FID_SEQ_LLOG);
-}
-
-static inline void ostid_cpu_to_le(const struct ost_id *src_oi,
- struct ost_id *dst_oi)
-{
- if (fid_seq_is_mdt0(src_oi->oi.oi_seq)) {
- dst_oi->oi.oi_id = __cpu_to_le64(src_oi->oi.oi_id);
- dst_oi->oi.oi_seq = __cpu_to_le64(src_oi->oi.oi_seq);
- } else {
- fid_cpu_to_le(&dst_oi->oi_fid, &src_oi->oi_fid);
- }
-}
-
-static inline void ostid_le_to_cpu(const struct ost_id *src_oi,
- struct ost_id *dst_oi)
-{
- if (fid_seq_is_mdt0(src_oi->oi.oi_seq)) {
- dst_oi->oi.oi_id = __le64_to_cpu(src_oi->oi.oi_id);
- dst_oi->oi.oi_seq = __le64_to_cpu(src_oi->oi.oi_seq);
- } else {
- fid_le_to_cpu(&dst_oi->oi_fid, &src_oi->oi_fid);
- }
-}
-
-/**
- * Sigh, because pre-2.4 uses
- * struct lov_mds_md_v1 {
- * ........
- * __u64 lmm_object_id;
- * __u64 lmm_object_seq;
- * ......
- * }
- * to identify the LOV(MDT) object, and lmm_object_seq will
- * be normal_fid, which make it hard to combine these conversion
- * to ostid_to FID. so we will do lmm_oi/fid conversion separately
- *
- * We can tell the lmm_oi by this way,
- * 1.8: lmm_object_id = {inode}, lmm_object_gr = 0
- * 2.1: lmm_object_id = {oid < 128k}, lmm_object_seq = FID_SEQ_NORMAL
- * 2.4: lmm_oi.f_seq = FID_SEQ_NORMAL, lmm_oi.f_oid = {oid < 128k},
- * lmm_oi.f_ver = 0
- *
- * But currently lmm_oi/lsm_oi does not have any "real" usages,
- * except for printing some information, and the user can always
- * get the real FID from LMA, besides this multiple case check might
- * make swab more complicate. So we will keep using id/seq for lmm_oi.
- */
-
-static inline void fid_to_lmm_oi(const struct lu_fid *fid,
- struct ost_id *oi)
-{
- oi->oi.oi_id = fid_oid(fid);
- oi->oi.oi_seq = fid_seq(fid);
-}
-
-/**
- * Unpack an OST object id/seq (group) into a FID. This is needed for
- * converting all obdo, lmm, lsm, etc. 64-bit id/seq pairs into proper
- * FIDs. Note that if an id/seq is already in FID/IDIF format it will
- * be passed through unchanged. Only legacy OST objects in "group 0"
- * will be mapped into the IDIF namespace so that they can fit into the
- * struct lu_fid fields without loss.
- */
-static inline int ostid_to_fid(struct lu_fid *fid, const struct ost_id *ostid,
- __u32 ost_idx)
-{
- __u64 seq = ostid_seq(ostid);
-
- if (ost_idx > 0xffff)
- return -EBADF;
-
- if (fid_seq_is_mdt0(seq)) {
- __u64 oid = ostid_id(ostid);
-
- /* This is a "legacy" (old 1.x/2.early) OST object in "group 0"
- * that we map into the IDIF namespace. It allows up to 2^48
- * objects per OST, as this is the object namespace that has
- * been in production for years. This can handle create rates
- * of 1M objects/s/OST for 9 years, or combinations thereof.
- */
- if (oid >= IDIF_MAX_OID)
- return -EBADF;
-
- fid->f_seq = fid_idif_seq(oid, ost_idx);
- /* truncate to 32 bits by assignment */
- fid->f_oid = oid;
- /* in theory, not currently used */
- fid->f_ver = oid >> 48;
- } else if (!fid_seq_is_default(seq)) {
- /* This is either an IDIF object, which identifies objects
- * across all OSTs, or a regular FID. The IDIF namespace
- * maps legacy OST objects into the FID namespace. In both
- * cases, we just pass the FID through, no conversion needed.
- */
- if (ostid->oi_fid.f_ver)
- return -EBADF;
-
- *fid = ostid->oi_fid;
- }
-
- return 0;
-}
-#endif /* _UAPI_LUSTRE_OSTID_H_ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_param.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_param.h
deleted file mode 100644
index 1eab2ceca338..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_param.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * User-settable parameter keys
- *
- * Author: Nathan Rutman <nathan@clusterfs.com>
- */
-
-#ifndef _UAPI_LUSTRE_PARAM_H_
-#define _UAPI_LUSTRE_PARAM_H_
-
-/** \defgroup param param
- *
- * @{
- */
-
-/****************** User-settable parameter keys *********************/
-/* e.g.
- * tunefs.lustre --param="failover.node=192.168.0.13@tcp0" /dev/sda
- * lctl conf_param testfs-OST0000 failover.node=3@elan,192.168.0.3@tcp0
- * ... testfs-MDT0000.lov.stripesize=4M
- * ... testfs-OST0000.ost.client_cache_seconds=15
- * ... testfs.sys.timeout=<secs>
- * ... testfs.llite.max_read_ahead_mb=16
- */
-
-/* System global or special params not handled in obd's proc
- * See mgs_write_log_sys()
- */
-#define PARAM_TIMEOUT "timeout=" /* global */
-#define PARAM_LDLM_TIMEOUT "ldlm_timeout=" /* global */
-#define PARAM_AT_MIN "at_min=" /* global */
-#define PARAM_AT_MAX "at_max=" /* global */
-#define PARAM_AT_EXTRA "at_extra=" /* global */
-#define PARAM_AT_EARLY_MARGIN "at_early_margin=" /* global */
-#define PARAM_AT_HISTORY "at_history=" /* global */
-#define PARAM_JOBID_VAR "jobid_var=" /* global */
-#define PARAM_MGSNODE "mgsnode=" /* only at mounttime */
-#define PARAM_FAILNODE "failover.node=" /* add failover nid */
-#define PARAM_FAILMODE "failover.mode=" /* initial mount only */
-#define PARAM_ACTIVE "active=" /* activate/deactivate */
-#define PARAM_NETWORK "network=" /* bind on nid */
-#define PARAM_ID_UPCALL "identity_upcall=" /* identity upcall */
-
-/* Prefixes for parameters handled by obd's proc methods (XXX_process_config) */
-#define PARAM_OST "ost."
-#define PARAM_OSD "osd."
-#define PARAM_OSC "osc."
-#define PARAM_MDT "mdt."
-#define PARAM_HSM "mdt.hsm."
-#define PARAM_MDD "mdd."
-#define PARAM_MDC "mdc."
-#define PARAM_LLITE "llite."
-#define PARAM_LOV "lov."
-#define PARAM_LOD "lod."
-#define PARAM_OSP "osp."
-#define PARAM_SYS "sys." /* global */
-#define PARAM_SRPC "srpc."
-#define PARAM_SRPC_FLVR "srpc.flavor."
-#define PARAM_SRPC_UDESC "srpc.udesc.cli2mdt"
-#define PARAM_SEC "security."
-#define PARAM_QUOTA "quota." /* global */
-
-/** @} param */
-
-#endif /* _UAPI_LUSTRE_PARAM_H_ */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_user.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_user.h
deleted file mode 100644
index 69387f36d1f1..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_user.h
+++ /dev/null
@@ -1,1327 +0,0 @@
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2003, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2010, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * lustre/include/lustre/lustre_user.h
- *
- * Lustre public user-space interface definitions.
- */
-
-#ifndef _LUSTRE_USER_H
-#define _LUSTRE_USER_H
-
-/** \defgroup lustreuser lustreuser
- *
- * @{
- */
-
-#ifdef __KERNEL__
-# include <linux/fs.h>
-# include <linux/quota.h>
-# include <linux/sched/signal.h>
-# include <linux/string.h> /* snprintf() */
-# include <linux/version.h>
-#else /* !__KERNEL__ */
-# define NEED_QUOTA_DEFS
-# include <stdio.h> /* snprintf() */
-# include <string.h>
-# include <sys/quota.h>
-# include <sys/stat.h>
-#endif /* __KERNEL__ */
-#include <uapi/linux/lustre/lustre_fiemap.h>
-
-/*
- * We need to always use 64bit version because the structure
- * is shared across entire cluster where 32bit and 64bit machines
- * are co-existing.
- */
-#if __BITS_PER_LONG != 64 || defined(__ARCH_WANT_STAT64)
-typedef struct stat64 lstat_t;
-#define lstat_f lstat64
-#define fstat_f fstat64
-#define fstatat_f fstatat64
-#else
-typedef struct stat lstat_t;
-#define lstat_f lstat
-#define fstat_f fstat
-#define fstatat_f fstatat
-#endif
-
-#define HAVE_LOV_USER_MDS_DATA
-
-#define LUSTRE_EOF 0xffffffffffffffffULL
-
-/* for statfs() */
-#define LL_SUPER_MAGIC 0x0BD00BD0
-
-#ifndef FSFILT_IOC_GETFLAGS
-#define FSFILT_IOC_GETFLAGS _IOR('f', 1, long)
-#define FSFILT_IOC_SETFLAGS _IOW('f', 2, long)
-#define FSFILT_IOC_GETVERSION _IOR('f', 3, long)
-#define FSFILT_IOC_SETVERSION _IOW('f', 4, long)
-#define FSFILT_IOC_GETVERSION_OLD _IOR('v', 1, long)
-#define FSFILT_IOC_SETVERSION_OLD _IOW('v', 2, long)
-#endif
-
-/* FIEMAP flags supported by Lustre */
-#define LUSTRE_FIEMAP_FLAGS_COMPAT (FIEMAP_FLAG_SYNC | FIEMAP_FLAG_DEVICE_ORDER)
-
-enum obd_statfs_state {
- OS_STATE_DEGRADED = 0x00000001, /**< RAID degraded/rebuilding */
- OS_STATE_READONLY = 0x00000002, /**< filesystem is read-only */
- OS_STATE_RDONLY_1 = 0x00000004, /**< obsolete 1.6, was EROFS=30 */
- OS_STATE_RDONLY_2 = 0x00000008, /**< obsolete 1.6, was EROFS=30 */
- OS_STATE_RDONLY_3 = 0x00000010, /**< obsolete 1.6, was EROFS=30 */
-};
-
-struct obd_statfs {
- __u64 os_type;
- __u64 os_blocks;
- __u64 os_bfree;
- __u64 os_bavail;
- __u64 os_files;
- __u64 os_ffree;
- __u8 os_fsid[40];
- __u32 os_bsize;
- __u32 os_namelen;
- __u64 os_maxbytes;
- __u32 os_state; /**< obd_statfs_state OS_STATE_* flag */
- __u32 os_fprecreated; /* objs available now to the caller */
- /* used in QoS code to find preferred OSTs */
- __u32 os_spare2;
- __u32 os_spare3;
- __u32 os_spare4;
- __u32 os_spare5;
- __u32 os_spare6;
- __u32 os_spare7;
- __u32 os_spare8;
- __u32 os_spare9;
-};
-
-/**
- * File IDentifier.
- *
- * FID is a cluster-wide unique identifier of a file or an object (stripe).
- * FIDs are never reused.
- **/
-struct lu_fid {
- /**
- * FID sequence. Sequence is a unit of migration: all files (objects)
- * with FIDs from a given sequence are stored on the same server.
- * Lustre should support 2^64 objects, so even if each sequence
- * has only a single object we can still enumerate 2^64 objects.
- **/
- __u64 f_seq;
- /* FID number within sequence. */
- __u32 f_oid;
- /**
- * FID version, used to distinguish different versions (in the sense
- * of snapshots, etc.) of the same file system object. Not currently
- * used.
- **/
- __u32 f_ver;
-};
-
-static inline bool fid_is_zero(const struct lu_fid *fid)
-{
- return !fid->f_seq && !fid->f_oid;
-}
-
-struct filter_fid {
- struct lu_fid ff_parent; /* ff_parent.f_ver == file stripe number */
-};
-
-/* keep this one for compatibility */
-struct filter_fid_old {
- struct lu_fid ff_parent;
- __u64 ff_objid;
- __u64 ff_seq;
-};
-
-/* Userspace should treat lu_fid as opaque, and only use the following methods
- * to print or parse them. Other functions (e.g. compare, swab) could be moved
- * here from lustre_idl.h if needed.
- */
-struct lu_fid;
-
-/**
- * Following struct for object attributes, that will be kept inode's EA.
- * Introduced in 2.0 release (please see b15993, for details)
- * Added to all objects since Lustre 2.4 as contains self FID
- */
-struct lustre_mdt_attrs {
- /**
- * Bitfield for supported data in this structure. From enum lma_compat.
- * lma_self_fid and lma_flags are always available.
- */
- __u32 lma_compat;
- /**
- * Per-file incompat feature list. Lustre version should support all
- * flags set in this field. The supported feature mask is available in
- * LMA_INCOMPAT_SUPP.
- */
- __u32 lma_incompat;
- /** FID of this inode */
- struct lu_fid lma_self_fid;
-};
-
-/**
- * Prior to 2.4, the LMA structure also included SOM attributes which has since
- * been moved to a dedicated xattr
- * lma_flags was also removed because of lma_compat/incompat fields.
- */
-#define LMA_OLD_SIZE (sizeof(struct lustre_mdt_attrs) + 5 * sizeof(__u64))
-
-/**
- * OST object IDentifier.
- */
-struct ost_id {
- union {
- struct {
- __u64 oi_id;
- __u64 oi_seq;
- } oi;
- struct lu_fid oi_fid;
- };
-};
-
-#define DOSTID "%#llx:%llu"
-#define POSTID(oi) ostid_seq(oi), ostid_id(oi)
-
-/*
- * The ioctl naming rules:
- * LL_* - works on the currently opened filehandle instead of parent dir
- * *_OBD_* - gets data for both OSC or MDC (LOV, LMV indirectly)
- * *_MDC_* - gets/sets data related to MDC
- * *_LOV_* - gets/sets data related to OSC/LOV
- * *FILE* - called on parent dir and passes in a filename
- * *STRIPE* - set/get lov_user_md
- * *INFO - set/get lov_user_mds_data
- */
-/* lustre_ioctl.h 101-150 */
-#define LL_IOC_GETFLAGS _IOR('f', 151, long)
-#define LL_IOC_SETFLAGS _IOW('f', 152, long)
-#define LL_IOC_CLRFLAGS _IOW('f', 153, long)
-#define LL_IOC_LOV_SETSTRIPE _IOW('f', 154, long)
-#define LL_IOC_LOV_GETSTRIPE _IOW('f', 155, long)
-#define LL_IOC_LOV_SETEA _IOW('f', 156, long)
-/* LL_IOC_RECREATE_OBJ 157 obsolete */
-/* LL_IOC_RECREATE_FID 158 obsolete */
-#define LL_IOC_GROUP_LOCK _IOW('f', 158, long)
-#define LL_IOC_GROUP_UNLOCK _IOW('f', 159, long)
-/* #define LL_IOC_QUOTACHECK 160 OBD_IOC_QUOTACHECK */
-/* #define LL_IOC_POLL_QUOTACHECK 161 OBD_IOC_POLL_QUOTACHECK */
-/* #define LL_IOC_QUOTACTL 162 OBD_IOC_QUOTACTL */
-#define IOC_OBD_STATFS _IOWR('f', 164, struct obd_statfs *)
-/* IOC_LOV_GETINFO 165 obsolete */
-#define LL_IOC_FLUSHCTX _IOW('f', 166, long)
-/* LL_IOC_RMTACL 167 obsolete */
-#define LL_IOC_GETOBDCOUNT _IOR('f', 168, long)
-#define LL_IOC_LLOOP_ATTACH _IOWR('f', 169, long)
-#define LL_IOC_LLOOP_DETACH _IOWR('f', 170, long)
-#define LL_IOC_LLOOP_INFO _IOWR('f', 171, struct lu_fid)
-#define LL_IOC_LLOOP_DETACH_BYDEV _IOWR('f', 172, long)
-#define LL_IOC_PATH2FID _IOR('f', 173, long)
-#define LL_IOC_GET_CONNECT_FLAGS _IOWR('f', 174, __u64 *)
-#define LL_IOC_GET_MDTIDX _IOR('f', 175, int)
-
-/* lustre_ioctl.h 177-210 */
-#define LL_IOC_HSM_STATE_GET _IOR('f', 211, struct hsm_user_state)
-#define LL_IOC_HSM_STATE_SET _IOW('f', 212, struct hsm_state_set)
-#define LL_IOC_HSM_CT_START _IOW('f', 213, struct lustre_kernelcomm)
-#define LL_IOC_HSM_COPY_START _IOW('f', 214, struct hsm_copy *)
-#define LL_IOC_HSM_COPY_END _IOW('f', 215, struct hsm_copy *)
-#define LL_IOC_HSM_PROGRESS _IOW('f', 216, struct hsm_user_request)
-#define LL_IOC_HSM_REQUEST _IOW('f', 217, struct hsm_user_request)
-#define LL_IOC_DATA_VERSION _IOR('f', 218, struct ioc_data_version)
-#define LL_IOC_LOV_SWAP_LAYOUTS _IOW('f', 219, \
- struct lustre_swap_layouts)
-#define LL_IOC_HSM_ACTION _IOR('f', 220, \
- struct hsm_current_action)
-/* see <lustre_lib.h> for ioctl numbers 221-232 */
-
-#define LL_IOC_LMV_SETSTRIPE _IOWR('f', 240, struct lmv_user_md)
-#define LL_IOC_LMV_GETSTRIPE _IOWR('f', 241, struct lmv_user_md)
-#define LL_IOC_SET_LEASE _IOWR('f', 243, long)
-#define LL_IOC_GET_LEASE _IO('f', 244)
-#define LL_IOC_HSM_IMPORT _IOWR('f', 245, struct hsm_user_import)
-#define LL_IOC_LMV_SET_DEFAULT_STRIPE _IOWR('f', 246, struct lmv_user_md)
-#define LL_IOC_MIGRATE _IOR('f', 247, int)
-#define LL_IOC_FID2MDTIDX _IOWR('f', 248, struct lu_fid)
-#define LL_IOC_GETPARENT _IOWR('f', 249, struct getparent)
-
-/* Lease types for use as arg and return of LL_IOC_{GET,SET}_LEASE ioctl. */
-enum ll_lease_type {
- LL_LEASE_RDLCK = 0x1,
- LL_LEASE_WRLCK = 0x2,
- LL_LEASE_UNLCK = 0x4,
-};
-
-#define LL_STATFS_LMV 1
-#define LL_STATFS_LOV 2
-#define LL_STATFS_NODELAY 4
-
-#define IOC_MDC_TYPE 'i'
-#define IOC_MDC_LOOKUP _IOWR(IOC_MDC_TYPE, 20, struct obd_device *)
-#define IOC_MDC_GETFILESTRIPE _IOWR(IOC_MDC_TYPE, 21, struct lov_user_md *)
-#define IOC_MDC_GETFILEINFO _IOWR(IOC_MDC_TYPE, 22, struct lov_user_mds_data *)
-#define LL_IOC_MDC_GETINFO _IOWR(IOC_MDC_TYPE, 23, struct lov_user_mds_data *)
-
-#define MAX_OBD_NAME 128 /* If this changes, a NEW ioctl must be added */
-
-/* Define O_LOV_DELAY_CREATE to be a mask that is not useful for regular
- * files, but are unlikely to be used in practice and are not harmful if
- * used incorrectly. O_NOCTTY and FASYNC are only meaningful for character
- * devices and are safe for use on new files (See LU-812, LU-4209).
- */
-#define O_LOV_DELAY_CREATE (O_NOCTTY | FASYNC)
-
-#define LL_FILE_IGNORE_LOCK 0x00000001
-#define LL_FILE_GROUP_LOCKED 0x00000002
-#define LL_FILE_READAHEA 0x00000004
-#define LL_FILE_LOCKED_DIRECTIO 0x00000008 /* client-side locks with dio */
-#define LL_FILE_LOCKLESS_IO 0x00000010 /* server-side locks with cio */
-#define LL_FILE_RMTACL 0x00000020
-
-#define LOV_USER_MAGIC_V1 0x0BD10BD0
-#define LOV_USER_MAGIC LOV_USER_MAGIC_V1
-#define LOV_USER_MAGIC_JOIN_V1 0x0BD20BD0
-#define LOV_USER_MAGIC_V3 0x0BD30BD0
-/* 0x0BD40BD0 is occupied by LOV_MAGIC_MIGRATE */
-#define LOV_USER_MAGIC_SPECIFIC 0x0BD50BD0 /* for specific OSTs */
-
-#define LMV_USER_MAGIC 0x0CD30CD0 /*default lmv magic*/
-
-#define LOV_PATTERN_RAID0 0x001
-#define LOV_PATTERN_RAID1 0x002
-#define LOV_PATTERN_FIRST 0x100
-#define LOV_PATTERN_CMOBD 0x200
-
-#define LOV_PATTERN_F_MASK 0xffff0000
-#define LOV_PATTERN_F_HOLE 0x40000000 /* there is hole in LOV EA */
-#define LOV_PATTERN_F_RELEASED 0x80000000 /* HSM released file */
-
-#define LOV_MAXPOOLNAME 15
-#define LOV_POOLNAMEF "%.15s"
-
-#define LOV_MIN_STRIPE_BITS 16 /* maximum PAGE_SIZE (ia64), power of 2 */
-#define LOV_MIN_STRIPE_SIZE (1 << LOV_MIN_STRIPE_BITS)
-#define LOV_MAX_STRIPE_COUNT_OLD 160
-/* This calculation is crafted so that input of 4096 will result in 160
- * which in turn is equal to old maximal stripe count.
- * XXX: In fact this is too simplified for now, what it also need is to get
- * ea_type argument to clearly know how much space each stripe consumes.
- *
- * The limit of 12 pages is somewhat arbitrary, but is a reasonably large
- * allocation that is sufficient for the current generation of systems.
- *
- * (max buffer size - lov+rpc header) / sizeof(struct lov_ost_data_v1)
- */
-#define LOV_MAX_STRIPE_COUNT 2000 /* ((12 * 4096 - 256) / 24) */
-#define LOV_ALL_STRIPES 0xffff /* only valid for directories */
-#define LOV_V1_INSANE_STRIPE_COUNT 65532 /* maximum stripe count bz13933 */
-
-#define XATTR_LUSTRE_PREFIX "lustre."
-#define XATTR_LUSTRE_LOV "lustre.lov"
-
-#define lov_user_ost_data lov_user_ost_data_v1
-struct lov_user_ost_data_v1 { /* per-stripe data structure */
- struct ost_id l_ost_oi; /* OST object ID */
- __u32 l_ost_gen; /* generation of this OST index */
- __u32 l_ost_idx; /* OST index in LOV */
-} __packed;
-
-#define lov_user_md lov_user_md_v1
-struct lov_user_md_v1 { /* LOV EA user data (host-endian) */
- __u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V1 */
- __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
- struct ost_id lmm_oi; /* LOV object ID */
- __u32 lmm_stripe_size; /* size of stripe in bytes */
- __u16 lmm_stripe_count; /* num stripes in use for this object */
- union {
- __u16 lmm_stripe_offset; /* starting stripe offset in
- * lmm_objects, use when writing
- */
- __u16 lmm_layout_gen; /* layout generation number
- * used when reading
- */
- };
- struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
-} __attribute__((packed, __may_alias__));
-
-struct lov_user_md_v3 { /* LOV EA user data (host-endian) */
- __u32 lmm_magic; /* magic number = LOV_USER_MAGIC_V3 */
- __u32 lmm_pattern; /* LOV_PATTERN_RAID0, LOV_PATTERN_RAID1 */
- struct ost_id lmm_oi; /* LOV object ID */
- __u32 lmm_stripe_size; /* size of stripe in bytes */
- __u16 lmm_stripe_count; /* num stripes in use for this object */
- union {
- __u16 lmm_stripe_offset; /* starting stripe offset in
- * lmm_objects, use when writing
- */
- __u16 lmm_layout_gen; /* layout generation number
- * used when reading
- */
- };
- char lmm_pool_name[LOV_MAXPOOLNAME + 1]; /* pool name */
- struct lov_user_ost_data_v1 lmm_objects[0]; /* per-stripe data */
-} __packed;
-
-static inline __u32 lov_user_md_size(__u16 stripes, __u32 lmm_magic)
-{
- if (lmm_magic == LOV_USER_MAGIC_V1)
- return sizeof(struct lov_user_md_v1) +
- stripes * sizeof(struct lov_user_ost_data_v1);
- return sizeof(struct lov_user_md_v3) +
- stripes * sizeof(struct lov_user_ost_data_v1);
-}
-
-/* Compile with -D_LARGEFILE64_SOURCE or -D_GNU_SOURCE (or #define) to
- * use this. It is unsafe to #define those values in this header as it
- * is possible the application has already #included <sys/stat.h>.
- */
-#ifdef HAVE_LOV_USER_MDS_DATA
-#define lov_user_mds_data lov_user_mds_data_v1
-struct lov_user_mds_data_v1 {
- lstat_t lmd_st; /* MDS stat struct */
- struct lov_user_md_v1 lmd_lmm; /* LOV EA V1 user data */
-} __packed;
-
-struct lov_user_mds_data_v3 {
- lstat_t lmd_st; /* MDS stat struct */
- struct lov_user_md_v3 lmd_lmm; /* LOV EA V3 user data */
-} __packed;
-#endif
-
-struct lmv_user_mds_data {
- struct lu_fid lum_fid;
- __u32 lum_padding;
- __u32 lum_mds;
-};
-
-enum lmv_hash_type {
- LMV_HASH_TYPE_UNKNOWN = 0, /* 0 is reserved for testing purpose */
- LMV_HASH_TYPE_ALL_CHARS = 1,
- LMV_HASH_TYPE_FNV_1A_64 = 2,
-};
-
-#define LMV_HASH_NAME_ALL_CHARS "all_char"
-#define LMV_HASH_NAME_FNV_1A_64 "fnv_1a_64"
-
-/*
- * Got this according to how get LOV_MAX_STRIPE_COUNT, see above,
- * (max buffer size - lmv+rpc header) / sizeof(struct lmv_user_mds_data)
- */
-#define LMV_MAX_STRIPE_COUNT 2000 /* ((12 * 4096 - 256) / 24) */
-#define lmv_user_md lmv_user_md_v1
-struct lmv_user_md_v1 {
- __u32 lum_magic; /* must be the first field */
- __u32 lum_stripe_count; /* dirstripe count */
- __u32 lum_stripe_offset; /* MDT idx for default dirstripe */
- __u32 lum_hash_type; /* Dir stripe policy */
- __u32 lum_type; /* LMV type: default or normal */
- __u32 lum_padding1;
- __u32 lum_padding2;
- __u32 lum_padding3;
- char lum_pool_name[LOV_MAXPOOLNAME + 1];
- struct lmv_user_mds_data lum_objects[0];
-} __packed;
-
-static inline int lmv_user_md_size(int stripes, int lmm_magic)
-{
- return sizeof(struct lmv_user_md) +
- stripes * sizeof(struct lmv_user_mds_data);
-}
-
-struct ll_recreate_obj {
- __u64 lrc_id;
- __u32 lrc_ost_idx;
-};
-
-struct ll_fid {
- __u64 id; /* holds object id */
- __u32 generation; /* holds object generation */
- __u32 f_type; /* holds object type or stripe idx when passing it to
- * OST for saving into EA.
- */
-};
-
-#define UUID_MAX 40
-struct obd_uuid {
- char uuid[UUID_MAX];
-};
-
-static inline bool obd_uuid_equals(const struct obd_uuid *u1,
- const struct obd_uuid *u2)
-{
- return strcmp((char *)u1->uuid, (char *)u2->uuid) == 0;
-}
-
-static inline int obd_uuid_empty(struct obd_uuid *uuid)
-{
- return uuid->uuid[0] == '\0';
-}
-
-static inline void obd_str2uuid(struct obd_uuid *uuid, const char *tmp)
-{
- strncpy((char *)uuid->uuid, tmp, sizeof(*uuid));
- uuid->uuid[sizeof(*uuid) - 1] = '\0';
-}
-
-/* For printf's only, make sure uuid is terminated */
-static inline char *obd_uuid2str(const struct obd_uuid *uuid)
-{
- if (!uuid)
- return NULL;
-
- if (uuid->uuid[sizeof(*uuid) - 1] != '\0') {
- /* Obviously not safe, but for printfs, no real harm done...
- * we're always null-terminated, even in a race.
- */
- static char temp[sizeof(*uuid)];
-
- memcpy(temp, uuid->uuid, sizeof(*uuid) - 1);
- temp[sizeof(*uuid) - 1] = '\0';
- return temp;
- }
- return (char *)(uuid->uuid);
-}
-
-/* Extract fsname from uuid (or target name) of a target
- * e.g. (myfs-OST0007_UUID -> myfs)
- * see also deuuidify.
- */
-static inline void obd_uuid2fsname(char *buf, char *uuid, int buflen)
-{
- char *p;
-
- strncpy(buf, uuid, buflen - 1);
- buf[buflen - 1] = '\0';
- p = strrchr(buf, '-');
- if (p)
- *p = '\0';
-}
-
-/* printf display format
- * * usage: printf("file FID is "DFID"\n", PFID(fid));
- */
-#define FID_NOBRACE_LEN 40
-#define FID_LEN (FID_NOBRACE_LEN + 2)
-#define DFID_NOBRACE "%#llx:0x%x:0x%x"
-#define DFID "[" DFID_NOBRACE "]"
-#define PFID(fid) (unsigned long long)(fid)->f_seq, (fid)->f_oid, (fid)->f_ver
-
-/* scanf input parse format for fids in DFID_NOBRACE format
- * Need to strip '[' from DFID format first or use "["SFID"]" at caller.
- * usage: sscanf(fidstr, SFID, RFID(&fid));
- */
-#define SFID "0x%llx:0x%x:0x%x"
-#define RFID(fid) &((fid)->f_seq), &((fid)->f_oid), &((fid)->f_ver)
-
-/********* Quotas **********/
-
-#define Q_QUOTACHECK 0x800100 /* deprecated as of 2.4 */
-#define Q_INITQUOTA 0x800101 /* deprecated as of 2.4 */
-#define Q_GETOINFO 0x800102 /* get obd quota info */
-#define Q_GETOQUOTA 0x800103 /* get obd quotas */
-#define Q_FINVALIDATE 0x800104 /* deprecated as of 2.4 */
-
-/* these must be explicitly translated into linux Q_* in ll_dir_ioctl */
-#define LUSTRE_Q_QUOTAON 0x800002 /* deprecated as of 2.4 */
-#define LUSTRE_Q_QUOTAOFF 0x800003 /* deprecated as of 2.4 */
-#define LUSTRE_Q_GETINFO 0x800005 /* get information about quota files */
-#define LUSTRE_Q_SETINFO 0x800006 /* set information about quota files */
-#define LUSTRE_Q_GETQUOTA 0x800007 /* get user quota structure */
-#define LUSTRE_Q_SETQUOTA 0x800008 /* set user quota structure */
-/* lustre-specific control commands */
-#define LUSTRE_Q_INVALIDATE 0x80000b /* deprecated as of 2.4 */
-#define LUSTRE_Q_FINVALIDATE 0x80000c /* deprecated as of 2.4 */
-
-#define UGQUOTA 2 /* set both USRQUOTA and GRPQUOTA */
-
-#define IDENTITY_DOWNCALL_MAGIC 0x6d6dd629
-
-/* permission */
-#define N_PERMS_MAX 64
-
-struct perm_downcall_data {
- __u64 pdd_nid;
- __u32 pdd_perm;
- __u32 pdd_padding;
-};
-
-struct identity_downcall_data {
- __u32 idd_magic;
- __u32 idd_err;
- __u32 idd_uid;
- __u32 idd_gid;
- __u32 idd_nperms;
- __u32 idd_ngroups;
- struct perm_downcall_data idd_perms[N_PERMS_MAX];
- __u32 idd_groups[0];
-};
-
-/* lustre volatile file support
- * file name header: .^L^S^T^R:volatile"
- */
-#define LUSTRE_VOLATILE_HDR ".\x0c\x13\x14\x12:VOLATILE"
-#define LUSTRE_VOLATILE_HDR_LEN 14
-/* hdr + MDT index */
-#define LUSTRE_VOLATILE_IDX LUSTRE_VOLATILE_HDR":%.4X:"
-
-enum lustre_quota_version {
- LUSTRE_QUOTA_V2 = 1
-};
-
-/* XXX: same as if_dqinfo struct in kernel */
-struct obd_dqinfo {
- __u64 dqi_bgrace;
- __u64 dqi_igrace;
- __u32 dqi_flags;
- __u32 dqi_valid;
-};
-
-/* XXX: same as if_dqblk struct in kernel, plus one padding */
-struct obd_dqblk {
- __u64 dqb_bhardlimit;
- __u64 dqb_bsoftlimit;
- __u64 dqb_curspace;
- __u64 dqb_ihardlimit;
- __u64 dqb_isoftlimit;
- __u64 dqb_curinodes;
- __u64 dqb_btime;
- __u64 dqb_itime;
- __u32 dqb_valid;
- __u32 dqb_padding;
-};
-
-enum {
- QC_GENERAL = 0,
- QC_MDTIDX = 1,
- QC_OSTIDX = 2,
- QC_UUID = 3
-};
-
-struct if_quotactl {
- __u32 qc_cmd;
- __u32 qc_type;
- __u32 qc_id;
- __u32 qc_stat;
- __u32 qc_valid;
- __u32 qc_idx;
- struct obd_dqinfo qc_dqinfo;
- struct obd_dqblk qc_dqblk;
- char obd_type[16];
- struct obd_uuid obd_uuid;
-};
-
-/* swap layout flags */
-#define SWAP_LAYOUTS_CHECK_DV1 (1 << 0)
-#define SWAP_LAYOUTS_CHECK_DV2 (1 << 1)
-#define SWAP_LAYOUTS_KEEP_MTIME (1 << 2)
-#define SWAP_LAYOUTS_KEEP_ATIME (1 << 3)
-#define SWAP_LAYOUTS_CLOSE (1 << 4)
-
-/* Swap XATTR_NAME_HSM as well, only on the MDT so far */
-#define SWAP_LAYOUTS_MDS_HSM (1 << 31)
-struct lustre_swap_layouts {
- __u64 sl_flags;
- __u32 sl_fd;
- __u32 sl_gid;
- __u64 sl_dv1;
- __u64 sl_dv2;
-};
-
-/********* Changelogs **********/
-/** Changelog record types */
-enum changelog_rec_type {
- CL_MARK = 0,
- CL_CREATE = 1, /* namespace */
- CL_MKDIR = 2, /* namespace */
- CL_HARDLINK = 3, /* namespace */
- CL_SOFTLINK = 4, /* namespace */
- CL_MKNOD = 5, /* namespace */
- CL_UNLINK = 6, /* namespace */
- CL_RMDIR = 7, /* namespace */
- CL_RENAME = 8, /* namespace */
- CL_EXT = 9, /* namespace extended record (2nd half of rename) */
- CL_OPEN = 10, /* not currently used */
- CL_CLOSE = 11, /* may be written to log only with mtime change */
- CL_LAYOUT = 12, /* file layout/striping modified */
- CL_TRUNC = 13,
- CL_SETATTR = 14,
- CL_XATTR = 15,
- CL_HSM = 16, /* HSM specific events, see flags */
- CL_MTIME = 17, /* Precedence: setattr > mtime > ctime > atime */
- CL_CTIME = 18,
- CL_ATIME = 19,
- CL_LAST
-};
-
-static inline const char *changelog_type2str(int type)
-{
- static const char *changelog_str[] = {
- "MARK", "CREAT", "MKDIR", "HLINK", "SLINK", "MKNOD", "UNLNK",
- "RMDIR", "RENME", "RNMTO", "OPEN", "CLOSE", "LYOUT", "TRUNC",
- "SATTR", "XATTR", "HSM", "MTIME", "CTIME", "ATIME",
- };
-
- if (type >= 0 && type < CL_LAST)
- return changelog_str[type];
- return NULL;
-}
-
-/* per-record flags */
-#define CLF_FLAGSHIFT 12
-#define CLF_FLAGMASK ((1U << CLF_FLAGSHIFT) - 1)
-#define CLF_VERMASK (~CLF_FLAGMASK)
-enum changelog_rec_flags {
- CLF_VERSION = 0x1000,
- CLF_RENAME = 0x2000,
- CLF_JOBID = 0x4000,
- CLF_SUPPORTED = CLF_VERSION | CLF_RENAME | CLF_JOBID
-};
-
-/* Anything under the flagmask may be per-type (if desired) */
-/* Flags for unlink */
-#define CLF_UNLINK_LAST 0x0001 /* Unlink of last hardlink */
-#define CLF_UNLINK_HSM_EXISTS 0x0002 /* File has something in HSM */
- /* HSM cleaning needed */
-/* Flags for rename */
-#define CLF_RENAME_LAST 0x0001 /* rename unlink last hardlink of
- * target
- */
-#define CLF_RENAME_LAST_EXISTS 0x0002 /* rename unlink last hardlink of target
- * has an archive in backend
- */
-
-/* Flags for HSM */
-/* 12b used (from high weight to low weight):
- * 2b for flags
- * 3b for event
- * 7b for error code
- */
-#define CLF_HSM_ERR_L 0 /* HSM return code, 7 bits */
-#define CLF_HSM_ERR_H 6
-#define CLF_HSM_EVENT_L 7 /* HSM event, 3 bits, see enum hsm_event */
-#define CLF_HSM_EVENT_H 9
-#define CLF_HSM_FLAG_L 10 /* HSM flags, 2 bits, 1 used, 1 spare */
-#define CLF_HSM_FLAG_H 11
-#define CLF_HSM_SPARE_L 12 /* 4 spare bits */
-#define CLF_HSM_SPARE_H 15
-#define CLF_HSM_LAST 15
-
-/* Remove bits higher than _h, then extract the value
- * between _h and _l by shifting lower weigth to bit 0.
- */
-#define CLF_GET_BITS(_b, _h, _l) (((_b << (CLF_HSM_LAST - _h)) & 0xFFFF) \
- >> (CLF_HSM_LAST - _h + _l))
-
-#define CLF_HSM_SUCCESS 0x00
-#define CLF_HSM_MAXERROR 0x7E
-#define CLF_HSM_ERROVERFLOW 0x7F
-
-#define CLF_HSM_DIRTY 1 /* file is dirty after HSM request end */
-
-/* 3 bits field => 8 values allowed */
-enum hsm_event {
- HE_ARCHIVE = 0,
- HE_RESTORE = 1,
- HE_CANCEL = 2,
- HE_RELEASE = 3,
- HE_REMOVE = 4,
- HE_STATE = 5,
- HE_SPARE1 = 6,
- HE_SPARE2 = 7,
-};
-
-static inline enum hsm_event hsm_get_cl_event(__u16 flags)
-{
- return CLF_GET_BITS(flags, CLF_HSM_EVENT_H, CLF_HSM_EVENT_L);
-}
-
-static inline void hsm_set_cl_event(int *flags, enum hsm_event he)
-{
- *flags |= (he << CLF_HSM_EVENT_L);
-}
-
-static inline __u16 hsm_get_cl_flags(int flags)
-{
- return CLF_GET_BITS(flags, CLF_HSM_FLAG_H, CLF_HSM_FLAG_L);
-}
-
-static inline void hsm_set_cl_flags(int *flags, int bits)
-{
- *flags |= (bits << CLF_HSM_FLAG_L);
-}
-
-static inline int hsm_get_cl_error(int flags)
-{
- return CLF_GET_BITS(flags, CLF_HSM_ERR_H, CLF_HSM_ERR_L);
-}
-
-static inline void hsm_set_cl_error(int *flags, int error)
-{
- *flags |= (error << CLF_HSM_ERR_L);
-}
-
-enum changelog_send_flag {
- /* Not yet implemented */
- CHANGELOG_FLAG_FOLLOW = 0x01,
- /*
- * Blocking IO makes sense in case of slow user parsing of the records,
- * but it also prevents us from cleaning up if the records are not
- * consumed.
- */
- CHANGELOG_FLAG_BLOCK = 0x02,
- /* Pack jobid into the changelog records if available. */
- CHANGELOG_FLAG_JOBID = 0x04,
-};
-
-#define CR_MAXSIZE cfs_size_round(2 * NAME_MAX + 2 + \
- changelog_rec_offset(CLF_SUPPORTED))
-
-/* 31 usable bytes string + null terminator. */
-#define LUSTRE_JOBID_SIZE 32
-
-/*
- * This is the minimal changelog record. It can contain extensions
- * such as rename fields or process jobid. Its exact content is described
- * by the cr_flags.
- *
- * Extensions are packed in the same order as their corresponding flags.
- */
-struct changelog_rec {
- __u16 cr_namelen;
- __u16 cr_flags; /**< \a changelog_rec_flags */
- __u32 cr_type; /**< \a changelog_rec_type */
- __u64 cr_index; /**< changelog record number */
- __u64 cr_prev; /**< last index for this target fid */
- __u64 cr_time;
- union {
- struct lu_fid cr_tfid; /**< target fid */
- __u32 cr_markerflags; /**< CL_MARK flags */
- };
- struct lu_fid cr_pfid; /**< parent fid */
-} __packed;
-
-/* Changelog extension for RENAME. */
-struct changelog_ext_rename {
- struct lu_fid cr_sfid; /**< source fid, or zero */
- struct lu_fid cr_spfid; /**< source parent fid, or zero */
-};
-
-/* Changelog extension to include JOBID. */
-struct changelog_ext_jobid {
- char cr_jobid[LUSTRE_JOBID_SIZE]; /**< zero-terminated string. */
-};
-
-static inline size_t changelog_rec_offset(enum changelog_rec_flags crf)
-{
- size_t size = sizeof(struct changelog_rec);
-
- if (crf & CLF_RENAME)
- size += sizeof(struct changelog_ext_rename);
-
- if (crf & CLF_JOBID)
- size += sizeof(struct changelog_ext_jobid);
-
- return size;
-}
-
-static inline size_t changelog_rec_size(struct changelog_rec *rec)
-{
- return changelog_rec_offset(rec->cr_flags);
-}
-
-static inline size_t changelog_rec_varsize(struct changelog_rec *rec)
-{
- return changelog_rec_size(rec) - sizeof(*rec) + rec->cr_namelen;
-}
-
-static inline
-struct changelog_ext_rename *changelog_rec_rename(struct changelog_rec *rec)
-{
- enum changelog_rec_flags crf = rec->cr_flags & CLF_VERSION;
-
- return (struct changelog_ext_rename *)((char *)rec +
- changelog_rec_offset(crf));
-}
-
-/* The jobid follows the rename extension, if present */
-static inline
-struct changelog_ext_jobid *changelog_rec_jobid(struct changelog_rec *rec)
-{
- enum changelog_rec_flags crf = rec->cr_flags &
- (CLF_VERSION | CLF_RENAME);
-
- return (struct changelog_ext_jobid *)((char *)rec +
- changelog_rec_offset(crf));
-}
-
-/* The name follows the rename and jobid extensions, if present */
-static inline char *changelog_rec_name(struct changelog_rec *rec)
-{
- return (char *)rec + changelog_rec_offset(rec->cr_flags &
- CLF_SUPPORTED);
-}
-
-static inline size_t changelog_rec_snamelen(struct changelog_rec *rec)
-{
- return rec->cr_namelen - strlen(changelog_rec_name(rec)) - 1;
-}
-
-static inline char *changelog_rec_sname(struct changelog_rec *rec)
-{
- char *cr_name = changelog_rec_name(rec);
-
- return cr_name + strlen(cr_name) + 1;
-}
-
-/**
- * Remap a record to the desired format as specified by the crf flags.
- * The record must be big enough to contain the final remapped version.
- * Superfluous extension fields are removed and missing ones are added
- * and zeroed. The flags of the record are updated accordingly.
- *
- * The jobid and rename extensions can be added to a record, to match the
- * format an application expects, typically. In this case, the newly added
- * fields will be zeroed.
- * The Jobid field can be removed, to guarantee compatibility with older
- * clients that don't expect this field in the records they process.
- *
- * The following assumptions are being made:
- * - CLF_RENAME will not be removed
- * - CLF_JOBID will not be added without CLF_RENAME being added too
- *
- * @param[in,out] rec The record to remap.
- * @param[in] crf_wanted Flags describing the desired extensions.
- */
-static inline void changelog_remap_rec(struct changelog_rec *rec,
- enum changelog_rec_flags crf_wanted)
-{
- char *jid_mov, *rnm_mov;
-
- crf_wanted &= CLF_SUPPORTED;
-
- if ((rec->cr_flags & CLF_SUPPORTED) == crf_wanted)
- return;
-
- /* First move the variable-length name field */
- memmove((char *)rec + changelog_rec_offset(crf_wanted),
- changelog_rec_name(rec), rec->cr_namelen);
-
- /* Locations of jobid and rename extensions in the remapped record */
- jid_mov = (char *)rec +
- changelog_rec_offset(crf_wanted & ~CLF_JOBID);
- rnm_mov = (char *)rec +
- changelog_rec_offset(crf_wanted & ~(CLF_JOBID | CLF_RENAME));
-
- /* Move the extension fields to the desired positions */
- if ((crf_wanted & CLF_JOBID) && (rec->cr_flags & CLF_JOBID))
- memmove(jid_mov, changelog_rec_jobid(rec),
- sizeof(struct changelog_ext_jobid));
-
- if ((crf_wanted & CLF_RENAME) && (rec->cr_flags & CLF_RENAME))
- memmove(rnm_mov, changelog_rec_rename(rec),
- sizeof(struct changelog_ext_rename));
-
- /* Clear newly added fields */
- if ((crf_wanted & CLF_JOBID) && !(rec->cr_flags & CLF_JOBID))
- memset(jid_mov, 0, sizeof(struct changelog_ext_jobid));
-
- if ((crf_wanted & CLF_RENAME) && !(rec->cr_flags & CLF_RENAME))
- memset(rnm_mov, 0, sizeof(struct changelog_ext_rename));
-
- /* Update the record's flags accordingly */
- rec->cr_flags = (rec->cr_flags & CLF_FLAGMASK) | crf_wanted;
-}
-
-struct ioc_changelog {
- __u64 icc_recno;
- __u32 icc_mdtindex;
- __u32 icc_id;
- __u32 icc_flags;
-};
-
-enum changelog_message_type {
- CL_RECORD = 10, /* message is a changelog_rec */
- CL_EOF = 11, /* at end of current changelog */
-};
-
-/********* Misc **********/
-
-struct ioc_data_version {
- __u64 idv_version;
- __u64 idv_flags; /* See LL_DV_xxx */
-};
-
-#define LL_DV_RD_FLUSH (1 << 0) /* Flush dirty pages from clients */
-#define LL_DV_WR_FLUSH (1 << 1) /* Flush all caching pages from clients */
-
-#ifndef offsetof
-# define offsetof(typ, memb) ((unsigned long)((char *)&(((typ *)0)->memb)))
-#endif
-
-#define dot_lustre_name ".lustre"
-
-/********* HSM **********/
-
-/** HSM per-file state
- * See HSM_FLAGS below.
- */
-enum hsm_states {
- HS_NONE = 0x00000000,
- HS_EXISTS = 0x00000001,
- HS_DIRTY = 0x00000002,
- HS_RELEASED = 0x00000004,
- HS_ARCHIVED = 0x00000008,
- HS_NORELEASE = 0x00000010,
- HS_NOARCHIVE = 0x00000020,
- HS_LOST = 0x00000040,
-};
-
-/* HSM user-setable flags. */
-#define HSM_USER_MASK (HS_NORELEASE | HS_NOARCHIVE | HS_DIRTY)
-
-/* Other HSM flags. */
-#define HSM_STATUS_MASK (HS_EXISTS | HS_LOST | HS_RELEASED | HS_ARCHIVED)
-
-/*
- * All HSM-related possible flags that could be applied to a file.
- * This should be kept in sync with hsm_states.
- */
-#define HSM_FLAGS_MASK (HSM_USER_MASK | HSM_STATUS_MASK)
-
-/**
- * HSM request progress state
- */
-enum hsm_progress_states {
- HPS_WAITING = 1,
- HPS_RUNNING = 2,
- HPS_DONE = 3,
-};
-
-#define HPS_NONE 0
-
-static inline char *hsm_progress_state2name(enum hsm_progress_states s)
-{
- switch (s) {
- case HPS_WAITING: return "waiting";
- case HPS_RUNNING: return "running";
- case HPS_DONE: return "done";
- default: return "unknown";
- }
-}
-
-struct hsm_extent {
- __u64 offset;
- __u64 length;
-} __packed;
-
-/**
- * Current HSM states of a Lustre file.
- *
- * This structure purpose is to be sent to user-space mainly. It describes the
- * current HSM flags and in-progress action.
- */
-struct hsm_user_state {
- /** Current HSM states, from enum hsm_states. */
- __u32 hus_states;
- __u32 hus_archive_id;
- /** The current undergoing action, if there is one */
- __u32 hus_in_progress_state;
- __u32 hus_in_progress_action;
- struct hsm_extent hus_in_progress_location;
- char hus_extended_info[];
-};
-
-struct hsm_state_set_ioc {
- struct lu_fid hssi_fid;
- __u64 hssi_setmask;
- __u64 hssi_clearmask;
-};
-
-/*
- * This structure describes the current in-progress action for a file.
- * it is returned to user space and send over the wire
- */
-struct hsm_current_action {
- /** The current undergoing action, if there is one */
- /* state is one of hsm_progress_states */
- __u32 hca_state;
- /* action is one of hsm_user_action */
- __u32 hca_action;
- struct hsm_extent hca_location;
-};
-
-/***** HSM user requests ******/
-/* User-generated (lfs/ioctl) request types */
-enum hsm_user_action {
- HUA_NONE = 1, /* no action (noop) */
- HUA_ARCHIVE = 10, /* copy to hsm */
- HUA_RESTORE = 11, /* prestage */
- HUA_RELEASE = 12, /* drop ost objects */
- HUA_REMOVE = 13, /* remove from archive */
- HUA_CANCEL = 14 /* cancel a request */
-};
-
-static inline char *hsm_user_action2name(enum hsm_user_action a)
-{
- switch (a) {
- case HUA_NONE: return "NOOP";
- case HUA_ARCHIVE: return "ARCHIVE";
- case HUA_RESTORE: return "RESTORE";
- case HUA_RELEASE: return "RELEASE";
- case HUA_REMOVE: return "REMOVE";
- case HUA_CANCEL: return "CANCEL";
- default: return "UNKNOWN";
- }
-}
-
-/*
- * List of hr_flags (bit field)
- */
-#define HSM_FORCE_ACTION 0x0001
-/* used by CT, connot be set by user */
-#define HSM_GHOST_COPY 0x0002
-
-/**
- * Contains all the fixed part of struct hsm_user_request.
- *
- */
-struct hsm_request {
- __u32 hr_action; /* enum hsm_user_action */
- __u32 hr_archive_id; /* archive id, used only with HUA_ARCHIVE */
- __u64 hr_flags; /* request flags */
- __u32 hr_itemcount; /* item count in hur_user_item vector */
- __u32 hr_data_len;
-};
-
-struct hsm_user_item {
- struct lu_fid hui_fid;
- struct hsm_extent hui_extent;
-} __packed;
-
-struct hsm_user_request {
- struct hsm_request hur_request;
- struct hsm_user_item hur_user_item[0];
- /* extra data blob at end of struct (after all
- * hur_user_items), only use helpers to access it
- */
-} __packed;
-
-/** Return pointer to data field in a hsm user request */
-static inline void *hur_data(struct hsm_user_request *hur)
-{
- return &hur->hur_user_item[hur->hur_request.hr_itemcount];
-}
-
-/**
- * Compute the current length of the provided hsm_user_request. This returns -1
- * instead of an errno because ssize_t is defined to be only [ -1, SSIZE_MAX ]
- *
- * return -1 on bounds check error.
- */
-static inline ssize_t hur_len(struct hsm_user_request *hur)
-{
- __u64 size;
-
- /* can't overflow a __u64 since hr_itemcount is only __u32 */
- size = offsetof(struct hsm_user_request, hur_user_item[0]) +
- (__u64)hur->hur_request.hr_itemcount *
- sizeof(hur->hur_user_item[0]) + hur->hur_request.hr_data_len;
-
- if (size != (ssize_t)size)
- return -1;
-
- return size;
-}
-
-/****** HSM RPCs to copytool *****/
-/* Message types the copytool may receive */
-enum hsm_message_type {
- HMT_ACTION_LIST = 100, /* message is a hsm_action_list */
-};
-
-/* Actions the copytool may be instructed to take for a given action_item */
-enum hsm_copytool_action {
- HSMA_NONE = 10, /* no action */
- HSMA_ARCHIVE = 20, /* arbitrary offset */
- HSMA_RESTORE = 21,
- HSMA_REMOVE = 22,
- HSMA_CANCEL = 23
-};
-
-static inline char *hsm_copytool_action2name(enum hsm_copytool_action a)
-{
- switch (a) {
- case HSMA_NONE: return "NOOP";
- case HSMA_ARCHIVE: return "ARCHIVE";
- case HSMA_RESTORE: return "RESTORE";
- case HSMA_REMOVE: return "REMOVE";
- case HSMA_CANCEL: return "CANCEL";
- default: return "UNKNOWN";
- }
-}
-
-/* Copytool item action description */
-struct hsm_action_item {
- __u32 hai_len; /* valid size of this struct */
- __u32 hai_action; /* hsm_copytool_action, but use known size */
- struct lu_fid hai_fid; /* Lustre FID to operated on */
- struct lu_fid hai_dfid; /* fid used for data access */
- struct hsm_extent hai_extent; /* byte range to operate on */
- __u64 hai_cookie; /* action cookie from coordinator */
- __u64 hai_gid; /* grouplock id */
- char hai_data[0]; /* variable length */
-} __packed;
-
-/*
- * helper function which print in hexa the first bytes of
- * hai opaque field
- * \param hai [IN] record to print
- * \param buffer [OUT] output buffer
- * \param len [IN] max buffer len
- * \retval buffer
- */
-static inline char *hai_dump_data_field(struct hsm_action_item *hai,
- char *buffer, size_t len)
-{
- int i, data_len;
- char *ptr;
-
- ptr = buffer;
- data_len = hai->hai_len - sizeof(*hai);
- for (i = 0; (i < data_len) && (len > 2); i++) {
- snprintf(ptr, 3, "%02X", (unsigned char)hai->hai_data[i]);
- ptr += 2;
- len -= 2;
- }
-
- *ptr = '\0';
-
- return buffer;
-}
-
-/* Copytool action list */
-#define HAL_VERSION 1
-#define HAL_MAXSIZE LNET_MTU /* bytes, used in userspace only */
-struct hsm_action_list {
- __u32 hal_version;
- __u32 hal_count; /* number of hai's to follow */
- __u64 hal_compound_id; /* returned by coordinator */
- __u64 hal_flags;
- __u32 hal_archive_id; /* which archive backend */
- __u32 padding1;
- char hal_fsname[0]; /* null-terminated */
- /* struct hsm_action_item[hal_count] follows, aligned on 8-byte
- * boundaries. See hai_first
- */
-} __packed;
-
-#ifndef HAVE_CFS_SIZE_ROUND
-static inline int cfs_size_round(int val)
-{
- return (val + 7) & (~0x7);
-}
-
-#define HAVE_CFS_SIZE_ROUND
-#endif
-
-/* Return pointer to first hai in action list */
-static inline struct hsm_action_item *hai_first(struct hsm_action_list *hal)
-{
- return (struct hsm_action_item *)(hal->hal_fsname +
- cfs_size_round(strlen(hal-> \
- hal_fsname)
- + 1));
-}
-
-/* Return pointer to next hai */
-static inline struct hsm_action_item *hai_next(struct hsm_action_item *hai)
-{
- return (struct hsm_action_item *)((char *)hai +
- cfs_size_round(hai->hai_len));
-}
-
-/* Return size of an hsm_action_list */
-static inline int hal_size(struct hsm_action_list *hal)
-{
- int i, sz;
- struct hsm_action_item *hai;
-
- sz = sizeof(*hal) + cfs_size_round(strlen(hal->hal_fsname) + 1);
- hai = hai_first(hal);
- for (i = 0; i < hal->hal_count; i++, hai = hai_next(hai))
- sz += cfs_size_round(hai->hai_len);
-
- return sz;
-}
-
-/* HSM file import
- * describe the attributes to be set on imported file
- */
-struct hsm_user_import {
- __u64 hui_size;
- __u64 hui_atime;
- __u64 hui_mtime;
- __u32 hui_atime_ns;
- __u32 hui_mtime_ns;
- __u32 hui_uid;
- __u32 hui_gid;
- __u32 hui_mode;
- __u32 hui_archive_id;
-};
-
-/* Copytool progress reporting */
-#define HP_FLAG_COMPLETED 0x01
-#define HP_FLAG_RETRY 0x02
-
-struct hsm_progress {
- struct lu_fid hp_fid;
- __u64 hp_cookie;
- struct hsm_extent hp_extent;
- __u16 hp_flags;
- __u16 hp_errval; /* positive val */
- __u32 padding;
-};
-
-struct hsm_copy {
- __u64 hc_data_version;
- __u16 hc_flags;
- __u16 hc_errval; /* positive val */
- __u32 padding;
- struct hsm_action_item hc_hai;
-};
-
-/** @} lustreuser */
-
-#endif /* _LUSTRE_USER_H */
diff --git a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ver.h b/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ver.h
deleted file mode 100644
index 19c9135e2273..000000000000
--- a/drivers/staging/lustre/include/uapi/linux/lustre/lustre_ver.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _LUSTRE_VER_H_
-#define _LUSTRE_VER_H_
-
-#define LUSTRE_MAJOR 2
-#define LUSTRE_MINOR 6
-#define LUSTRE_PATCH 99
-#define LUSTRE_FIX 0
-#define LUSTRE_VERSION_STRING "2.6.99"
-
-#define OBD_OCD_VERSION(major, minor, patch, fix) \
- (((major) << 24) + ((minor) << 16) + ((patch) << 8) + (fix))
-
-#define OBD_OCD_VERSION_MAJOR(version) ((int)((version) >> 24) & 255)
-#define OBD_OCD_VERSION_MINOR(version) ((int)((version) >> 16) & 255)
-#define OBD_OCD_VERSION_PATCH(version) ((int)((version) >> 8) & 255)
-#define OBD_OCD_VERSION_FIX(version) ((int)((version) >> 0) & 255)
-
-#define LUSTRE_VERSION_CODE \
- OBD_OCD_VERSION(LUSTRE_MAJOR, LUSTRE_MINOR, LUSTRE_PATCH, LUSTRE_FIX)
-
-/*
- * If lustre version of client and servers it connects to differs by more
- * than this amount, client would issue a warning.
- */
-#define LUSTRE_VERSION_OFFSET_WARN OBD_OCD_VERSION(0, 4, 0, 0)
-
-#endif
diff --git a/drivers/staging/lustre/lnet/Kconfig b/drivers/staging/lustre/lnet/Kconfig
deleted file mode 100644
index ad049e6f24e4..000000000000
--- a/drivers/staging/lustre/lnet/Kconfig
+++ /dev/null
@@ -1,46 +0,0 @@
-config LNET
- tristate "Lustre networking subsystem (LNet)"
- depends on INET
- help
- The Lustre network layer, also known as LNet, is a networking abstaction
- level API that was initially created to allow Lustre Filesystem to utilize
- very different networks like tcp and ib verbs in a uniform way. In the
- case of Lustre routers only the LNet layer is required. Lately other
- projects are also looking into using LNet as their networking API as well.
-
-config LNET_MAX_PAYLOAD
- int "Lustre lnet max transfer payload (default 1MB)"
- depends on LNET
- default "1048576"
- help
- This option defines the maximum size of payload in bytes that lnet
- can put into its transport.
-
- If unsure, use default.
-
-config LNET_SELFTEST
- tristate "Lustre networking self testing"
- depends on LNET
- help
- Choose Y here if you want to do lnet self testing. To compile this
- as a module, choose M here: the module will be called lnet_selftest.
-
- To compile this as a kernel modules, choose M here and it will be
- called lnet_selftest.
-
- If unsure, say N.
-
- See also http://wiki.lustre.org/
-
-config LNET_XPRT_IB
- tristate "LNET infiniband support"
- depends on LNET && PCI && INFINIBAND && INFINIBAND_ADDR_TRANS
- default LNET && INFINIBAND
- help
- This option allows the LNET users to use infiniband as an
- RDMA-enabled transport.
-
- To compile this as a kernel module, choose M here and it will be
- called ko2iblnd.
-
- If unsure, say N.
diff --git a/drivers/staging/lustre/lnet/Makefile b/drivers/staging/lustre/lnet/Makefile
deleted file mode 100644
index 0a380fe88ce8..000000000000
--- a/drivers/staging/lustre/lnet/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-$(CONFIG_LNET) += libcfs/ lnet/ klnds/ selftest/
diff --git a/drivers/staging/lustre/lnet/klnds/Makefile b/drivers/staging/lustre/lnet/klnds/Makefile
deleted file mode 100644
index c23e4f67f837..000000000000
--- a/drivers/staging/lustre/lnet/klnds/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-$(CONFIG_LNET) += o2iblnd/ socklnd/
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/Makefile b/drivers/staging/lustre/lnet/klnds/o2iblnd/Makefile
deleted file mode 100644
index 4affe1d79948..000000000000
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-subdir-ccflags-y += -I$(srctree)/drivers/staging/lustre/include
-subdir-ccflags-y += -I$(srctree)/drivers/staging/lustre/lustre/include
-
-obj-$(CONFIG_LNET_XPRT_IB) += ko2iblnd.o
-ko2iblnd-y := o2iblnd.o o2iblnd_cb.o o2iblnd_modparams.o
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c
deleted file mode 100644
index f0b4eb42bc1d..000000000000
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c
+++ /dev/null
@@ -1,2958 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * lnet/klnds/o2iblnd/o2iblnd.c
- *
- * Author: Eric Barton <eric@bartonsoftware.com>
- */
-
-#include <asm/div64.h>
-#include <asm/page.h>
-#include "o2iblnd.h"
-
-static struct lnet_lnd the_o2iblnd;
-
-struct kib_data kiblnd_data;
-
-static __u32 kiblnd_cksum(void *ptr, int nob)
-{
- char *c = ptr;
- __u32 sum = 0;
-
- while (nob-- > 0)
- sum = ((sum << 1) | (sum >> 31)) + *c++;
-
- /* ensure I don't return 0 (== no checksum) */
- return !sum ? 1 : sum;
-}
-
-static char *kiblnd_msgtype2str(int type)
-{
- switch (type) {
- case IBLND_MSG_CONNREQ:
- return "CONNREQ";
-
- case IBLND_MSG_CONNACK:
- return "CONNACK";
-
- case IBLND_MSG_NOOP:
- return "NOOP";
-
- case IBLND_MSG_IMMEDIATE:
- return "IMMEDIATE";
-
- case IBLND_MSG_PUT_REQ:
- return "PUT_REQ";
-
- case IBLND_MSG_PUT_NAK:
- return "PUT_NAK";
-
- case IBLND_MSG_PUT_ACK:
- return "PUT_ACK";
-
- case IBLND_MSG_PUT_DONE:
- return "PUT_DONE";
-
- case IBLND_MSG_GET_REQ:
- return "GET_REQ";
-
- case IBLND_MSG_GET_DONE:
- return "GET_DONE";
-
- default:
- return "???";
- }
-}
-
-static int kiblnd_msgtype2size(int type)
-{
- const int hdr_size = offsetof(struct kib_msg, ibm_u);
-
- switch (type) {
- case IBLND_MSG_CONNREQ:
- case IBLND_MSG_CONNACK:
- return hdr_size + sizeof(struct kib_connparams);
-
- case IBLND_MSG_NOOP:
- return hdr_size;
-
- case IBLND_MSG_IMMEDIATE:
- return offsetof(struct kib_msg, ibm_u.immediate.ibim_payload[0]);
-
- case IBLND_MSG_PUT_REQ:
- return hdr_size + sizeof(struct kib_putreq_msg);
-
- case IBLND_MSG_PUT_ACK:
- return hdr_size + sizeof(struct kib_putack_msg);
-
- case IBLND_MSG_GET_REQ:
- return hdr_size + sizeof(struct kib_get_msg);
-
- case IBLND_MSG_PUT_NAK:
- case IBLND_MSG_PUT_DONE:
- case IBLND_MSG_GET_DONE:
- return hdr_size + sizeof(struct kib_completion_msg);
- default:
- return -1;
- }
-}
-
-static int kiblnd_unpack_rd(struct kib_msg *msg, int flip)
-{
- struct kib_rdma_desc *rd;
- int msg_size;
- int nob;
- int n;
- int i;
-
- LASSERT(msg->ibm_type == IBLND_MSG_GET_REQ ||
- msg->ibm_type == IBLND_MSG_PUT_ACK);
-
- rd = msg->ibm_type == IBLND_MSG_GET_REQ ?
- &msg->ibm_u.get.ibgm_rd :
- &msg->ibm_u.putack.ibpam_rd;
-
- if (flip) {
- __swab32s(&rd->rd_key);
- __swab32s(&rd->rd_nfrags);
- }
-
- n = rd->rd_nfrags;
-
- nob = offsetof(struct kib_msg, ibm_u) +
- kiblnd_rd_msg_size(rd, msg->ibm_type, n);
-
- if (msg->ibm_nob < nob) {
- CERROR("Short %s: %d(%d)\n",
- kiblnd_msgtype2str(msg->ibm_type), msg->ibm_nob, nob);
- return 1;
- }
-
- msg_size = kiblnd_rd_size(rd);
- if (msg_size <= 0 || msg_size > LNET_MAX_PAYLOAD) {
- CERROR("Bad msg_size: %d, should be 0 < n <= %d\n",
- msg_size, LNET_MAX_PAYLOAD);
- return 1;
- }
-
- if (!flip)
- return 0;
-
- for (i = 0; i < n; i++) {
- __swab32s(&rd->rd_frags[i].rf_nob);
- __swab64s(&rd->rd_frags[i].rf_addr);
- }
-
- return 0;
-}
-
-void kiblnd_pack_msg(struct lnet_ni *ni, struct kib_msg *msg, int version,
- int credits, lnet_nid_t dstnid, __u64 dststamp)
-{
- struct kib_net *net = ni->ni_data;
-
- /*
- * CAVEAT EMPTOR! all message fields not set here should have been
- * initialised previously.
- */
- msg->ibm_magic = IBLND_MSG_MAGIC;
- msg->ibm_version = version;
- /* ibm_type */
- msg->ibm_credits = credits;
- /* ibm_nob */
- msg->ibm_cksum = 0;
- msg->ibm_srcnid = ni->ni_nid;
- msg->ibm_srcstamp = net->ibn_incarnation;
- msg->ibm_dstnid = dstnid;
- msg->ibm_dststamp = dststamp;
-
- if (*kiblnd_tunables.kib_cksum) {
- /* NB ibm_cksum zero while computing cksum */
- msg->ibm_cksum = kiblnd_cksum(msg, msg->ibm_nob);
- }
-}
-
-int kiblnd_unpack_msg(struct kib_msg *msg, int nob)
-{
- const int hdr_size = offsetof(struct kib_msg, ibm_u);
- __u32 msg_cksum;
- __u16 version;
- int msg_nob;
- int flip;
-
- /* 6 bytes are enough to have received magic + version */
- if (nob < 6) {
- CERROR("Short message: %d\n", nob);
- return -EPROTO;
- }
-
- if (msg->ibm_magic == IBLND_MSG_MAGIC) {
- flip = 0;
- } else if (msg->ibm_magic == __swab32(IBLND_MSG_MAGIC)) {
- flip = 1;
- } else {
- CERROR("Bad magic: %08x\n", msg->ibm_magic);
- return -EPROTO;
- }
-
- version = flip ? __swab16(msg->ibm_version) : msg->ibm_version;
- if (version != IBLND_MSG_VERSION &&
- version != IBLND_MSG_VERSION_1) {
- CERROR("Bad version: %x\n", version);
- return -EPROTO;
- }
-
- if (nob < hdr_size) {
- CERROR("Short message: %d\n", nob);
- return -EPROTO;
- }
-
- msg_nob = flip ? __swab32(msg->ibm_nob) : msg->ibm_nob;
- if (msg_nob > nob) {
- CERROR("Short message: got %d, wanted %d\n", nob, msg_nob);
- return -EPROTO;
- }
-
- /*
- * checksum must be computed with ibm_cksum zero and BEFORE anything
- * gets flipped
- */
- msg_cksum = flip ? __swab32(msg->ibm_cksum) : msg->ibm_cksum;
- msg->ibm_cksum = 0;
- if (msg_cksum &&
- msg_cksum != kiblnd_cksum(msg, msg_nob)) {
- CERROR("Bad checksum\n");
- return -EPROTO;
- }
-
- msg->ibm_cksum = msg_cksum;
-
- if (flip) {
- /* leave magic unflipped as a clue to peer endianness */
- msg->ibm_version = version;
- BUILD_BUG_ON(sizeof(msg->ibm_type) != 1);
- BUILD_BUG_ON(sizeof(msg->ibm_credits) != 1);
- msg->ibm_nob = msg_nob;
- __swab64s(&msg->ibm_srcnid);
- __swab64s(&msg->ibm_srcstamp);
- __swab64s(&msg->ibm_dstnid);
- __swab64s(&msg->ibm_dststamp);
- }
-
- if (msg->ibm_srcnid == LNET_NID_ANY) {
- CERROR("Bad src nid: %s\n", libcfs_nid2str(msg->ibm_srcnid));
- return -EPROTO;
- }
-
- if (msg_nob < kiblnd_msgtype2size(msg->ibm_type)) {
- CERROR("Short %s: %d(%d)\n", kiblnd_msgtype2str(msg->ibm_type),
- msg_nob, kiblnd_msgtype2size(msg->ibm_type));
- return -EPROTO;
- }
-
- switch (msg->ibm_type) {
- default:
- CERROR("Unknown message type %x\n", msg->ibm_type);
- return -EPROTO;
-
- case IBLND_MSG_NOOP:
- case IBLND_MSG_IMMEDIATE:
- case IBLND_MSG_PUT_REQ:
- break;
-
- case IBLND_MSG_PUT_ACK:
- case IBLND_MSG_GET_REQ:
- if (kiblnd_unpack_rd(msg, flip))
- return -EPROTO;
- break;
-
- case IBLND_MSG_PUT_NAK:
- case IBLND_MSG_PUT_DONE:
- case IBLND_MSG_GET_DONE:
- if (flip)
- __swab32s(&msg->ibm_u.completion.ibcm_status);
- break;
-
- case IBLND_MSG_CONNREQ:
- case IBLND_MSG_CONNACK:
- if (flip) {
- __swab16s(&msg->ibm_u.connparams.ibcp_queue_depth);
- __swab16s(&msg->ibm_u.connparams.ibcp_max_frags);
- __swab32s(&msg->ibm_u.connparams.ibcp_max_msg_size);
- }
- break;
- }
- return 0;
-}
-
-int kiblnd_create_peer(struct lnet_ni *ni, struct kib_peer **peerp,
- lnet_nid_t nid)
-{
- struct kib_peer *peer;
- struct kib_net *net = ni->ni_data;
- int cpt = lnet_cpt_of_nid(nid);
- unsigned long flags;
-
- LASSERT(net);
- LASSERT(nid != LNET_NID_ANY);
-
- peer = kzalloc_cpt(sizeof(*peer), GFP_NOFS, cpt);
- if (!peer) {
- CERROR("Cannot allocate peer\n");
- return -ENOMEM;
- }
-
- peer->ibp_ni = ni;
- peer->ibp_nid = nid;
- peer->ibp_error = 0;
- peer->ibp_last_alive = 0;
- peer->ibp_max_frags = kiblnd_cfg_rdma_frags(peer->ibp_ni);
- peer->ibp_queue_depth = ni->ni_peertxcredits;
- atomic_set(&peer->ibp_refcount, 1); /* 1 ref for caller */
-
- INIT_LIST_HEAD(&peer->ibp_list); /* not in the peer table yet */
- INIT_LIST_HEAD(&peer->ibp_conns);
- INIT_LIST_HEAD(&peer->ibp_tx_queue);
-
- write_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- /* always called with a ref on ni, which prevents ni being shutdown */
- LASSERT(!net->ibn_shutdown);
-
- /* npeers only grows with the global lock held */
- atomic_inc(&net->ibn_npeers);
-
- write_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
-
- *peerp = peer;
- return 0;
-}
-
-void kiblnd_destroy_peer(struct kib_peer *peer)
-{
- struct kib_net *net = peer->ibp_ni->ni_data;
-
- LASSERT(net);
- LASSERT(!atomic_read(&peer->ibp_refcount));
- LASSERT(!kiblnd_peer_active(peer));
- LASSERT(kiblnd_peer_idle(peer));
- LASSERT(list_empty(&peer->ibp_tx_queue));
-
- kfree(peer);
-
- /*
- * NB a peer's connections keep a reference on their peer until
- * they are destroyed, so we can be assured that _all_ state to do
- * with this peer has been cleaned up when its refcount drops to
- * zero.
- */
- atomic_dec(&net->ibn_npeers);
-}
-
-struct kib_peer *kiblnd_find_peer_locked(lnet_nid_t nid)
-{
- /*
- * the caller is responsible for accounting the additional reference
- * that this creates
- */
- struct list_head *peer_list = kiblnd_nid2peerlist(nid);
- struct list_head *tmp;
- struct kib_peer *peer;
-
- list_for_each(tmp, peer_list) {
- peer = list_entry(tmp, struct kib_peer, ibp_list);
- LASSERT(!kiblnd_peer_idle(peer));
-
- if (peer->ibp_nid != nid)
- continue;
-
- CDEBUG(D_NET, "got peer [%p] -> %s (%d) version: %x\n",
- peer, libcfs_nid2str(nid),
- atomic_read(&peer->ibp_refcount),
- peer->ibp_version);
- return peer;
- }
- return NULL;
-}
-
-void kiblnd_unlink_peer_locked(struct kib_peer *peer)
-{
- LASSERT(list_empty(&peer->ibp_conns));
-
- LASSERT(kiblnd_peer_active(peer));
- list_del_init(&peer->ibp_list);
- /* lose peerlist's ref */
- kiblnd_peer_decref(peer);
-}
-
-static int kiblnd_get_peer_info(struct lnet_ni *ni, int index,
- lnet_nid_t *nidp, int *count)
-{
- struct kib_peer *peer;
- struct list_head *ptmp;
- int i;
- unsigned long flags;
-
- read_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- for (i = 0; i < kiblnd_data.kib_peer_hash_size; i++) {
- list_for_each(ptmp, &kiblnd_data.kib_peers[i]) {
- peer = list_entry(ptmp, struct kib_peer, ibp_list);
- LASSERT(!kiblnd_peer_idle(peer));
-
- if (peer->ibp_ni != ni)
- continue;
-
- if (index-- > 0)
- continue;
-
- *nidp = peer->ibp_nid;
- *count = atomic_read(&peer->ibp_refcount);
-
- read_unlock_irqrestore(&kiblnd_data.kib_global_lock,
- flags);
- return 0;
- }
- }
-
- read_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
- return -ENOENT;
-}
-
-static void kiblnd_del_peer_locked(struct kib_peer *peer)
-{
- struct list_head *ctmp;
- struct list_head *cnxt;
- struct kib_conn *conn;
-
- if (list_empty(&peer->ibp_conns)) {
- kiblnd_unlink_peer_locked(peer);
- } else {
- list_for_each_safe(ctmp, cnxt, &peer->ibp_conns) {
- conn = list_entry(ctmp, struct kib_conn, ibc_list);
-
- kiblnd_close_conn_locked(conn, 0);
- }
- /* NB closing peer's last conn unlinked it. */
- }
- /*
- * NB peer now unlinked; might even be freed if the peer table had the
- * last ref on it.
- */
-}
-
-static int kiblnd_del_peer(struct lnet_ni *ni, lnet_nid_t nid)
-{
- LIST_HEAD(zombies);
- struct list_head *ptmp;
- struct list_head *pnxt;
- struct kib_peer *peer;
- int lo;
- int hi;
- int i;
- unsigned long flags;
- int rc = -ENOENT;
-
- write_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- if (nid != LNET_NID_ANY) {
- lo = kiblnd_nid2peerlist(nid) - kiblnd_data.kib_peers;
- hi = kiblnd_nid2peerlist(nid) - kiblnd_data.kib_peers;
- } else {
- lo = 0;
- hi = kiblnd_data.kib_peer_hash_size - 1;
- }
-
- for (i = lo; i <= hi; i++) {
- list_for_each_safe(ptmp, pnxt, &kiblnd_data.kib_peers[i]) {
- peer = list_entry(ptmp, struct kib_peer, ibp_list);
- LASSERT(!kiblnd_peer_idle(peer));
-
- if (peer->ibp_ni != ni)
- continue;
-
- if (!(nid == LNET_NID_ANY || peer->ibp_nid == nid))
- continue;
-
- if (!list_empty(&peer->ibp_tx_queue)) {
- LASSERT(list_empty(&peer->ibp_conns));
-
- list_splice_init(&peer->ibp_tx_queue,
- &zombies);
- }
-
- kiblnd_del_peer_locked(peer);
- rc = 0; /* matched something */
- }
- }
-
- write_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
-
- kiblnd_txlist_done(ni, &zombies, -EIO);
-
- return rc;
-}
-
-static struct kib_conn *kiblnd_get_conn_by_idx(struct lnet_ni *ni, int index)
-{
- struct kib_peer *peer;
- struct list_head *ptmp;
- struct kib_conn *conn;
- struct list_head *ctmp;
- int i;
- unsigned long flags;
-
- read_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- for (i = 0; i < kiblnd_data.kib_peer_hash_size; i++) {
- list_for_each(ptmp, &kiblnd_data.kib_peers[i]) {
- peer = list_entry(ptmp, struct kib_peer, ibp_list);
- LASSERT(!kiblnd_peer_idle(peer));
-
- if (peer->ibp_ni != ni)
- continue;
-
- list_for_each(ctmp, &peer->ibp_conns) {
- if (index-- > 0)
- continue;
-
- conn = list_entry(ctmp, struct kib_conn,
- ibc_list);
- kiblnd_conn_addref(conn);
- read_unlock_irqrestore(
- &kiblnd_data.kib_global_lock,
- flags);
- return conn;
- }
- }
- }
-
- read_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
- return NULL;
-}
-
-int kiblnd_translate_mtu(int value)
-{
- switch (value) {
- default:
- return -1;
- case 0:
- return 0;
- case 256:
- return IB_MTU_256;
- case 512:
- return IB_MTU_512;
- case 1024:
- return IB_MTU_1024;
- case 2048:
- return IB_MTU_2048;
- case 4096:
- return IB_MTU_4096;
- }
-}
-
-static void kiblnd_setup_mtu_locked(struct rdma_cm_id *cmid)
-{
- int mtu;
-
- /* XXX There is no path record for iWARP, set by netdev->change_mtu? */
- if (!cmid->route.path_rec)
- return;
-
- mtu = kiblnd_translate_mtu(*kiblnd_tunables.kib_ib_mtu);
- LASSERT(mtu >= 0);
- if (mtu)
- cmid->route.path_rec->mtu = mtu;
-}
-
-static int kiblnd_get_completion_vector(struct kib_conn *conn, int cpt)
-{
- cpumask_var_t *mask;
- int vectors;
- int off;
- int i;
- lnet_nid_t nid = conn->ibc_peer->ibp_nid;
-
- vectors = conn->ibc_cmid->device->num_comp_vectors;
- if (vectors <= 1)
- return 0;
-
- mask = cfs_cpt_cpumask(lnet_cpt_table(), cpt);
- if (!mask)
- return 0;
-
- /* hash NID to CPU id in this partition... */
- off = do_div(nid, cpumask_weight(*mask));
- for_each_cpu(i, *mask) {
- if (!off--)
- return i % vectors;
- }
-
- LBUG();
- return 1;
-}
-
-struct kib_conn *kiblnd_create_conn(struct kib_peer *peer, struct rdma_cm_id *cmid,
- int state, int version)
-{
- /*
- * CAVEAT EMPTOR:
- * If the new conn is created successfully it takes over the caller's
- * ref on 'peer'. It also "owns" 'cmid' and destroys it when it itself
- * is destroyed. On failure, the caller's ref on 'peer' remains and
- * she must dispose of 'cmid'. (Actually I'd block forever if I tried
- * to destroy 'cmid' here since I'm called from the CM which still has
- * its ref on 'cmid').
- */
- rwlock_t *glock = &kiblnd_data.kib_global_lock;
- struct kib_net *net = peer->ibp_ni->ni_data;
- struct kib_dev *dev;
- struct ib_qp_init_attr *init_qp_attr;
- struct kib_sched_info *sched;
- struct ib_cq_init_attr cq_attr = {};
- struct kib_conn *conn;
- struct ib_cq *cq;
- unsigned long flags;
- int cpt;
- int rc;
- int i;
-
- LASSERT(net);
- LASSERT(!in_interrupt());
-
- dev = net->ibn_dev;
-
- cpt = lnet_cpt_of_nid(peer->ibp_nid);
- sched = kiblnd_data.kib_scheds[cpt];
-
- LASSERT(sched->ibs_nthreads > 0);
-
- init_qp_attr = kzalloc_cpt(sizeof(*init_qp_attr), GFP_NOFS, cpt);
- if (!init_qp_attr) {
- CERROR("Can't allocate qp_attr for %s\n",
- libcfs_nid2str(peer->ibp_nid));
- goto failed_0;
- }
-
- conn = kzalloc_cpt(sizeof(*conn), GFP_NOFS, cpt);
- if (!conn) {
- CERROR("Can't allocate connection for %s\n",
- libcfs_nid2str(peer->ibp_nid));
- goto failed_1;
- }
-
- conn->ibc_state = IBLND_CONN_INIT;
- conn->ibc_version = version;
- conn->ibc_peer = peer; /* I take the caller's ref */
- cmid->context = conn; /* for future CM callbacks */
- conn->ibc_cmid = cmid;
- conn->ibc_max_frags = peer->ibp_max_frags;
- conn->ibc_queue_depth = peer->ibp_queue_depth;
-
- INIT_LIST_HEAD(&conn->ibc_early_rxs);
- INIT_LIST_HEAD(&conn->ibc_tx_noops);
- INIT_LIST_HEAD(&conn->ibc_tx_queue);
- INIT_LIST_HEAD(&conn->ibc_tx_queue_rsrvd);
- INIT_LIST_HEAD(&conn->ibc_tx_queue_nocred);
- INIT_LIST_HEAD(&conn->ibc_active_txs);
- spin_lock_init(&conn->ibc_lock);
-
- conn->ibc_connvars = kzalloc_cpt(sizeof(*conn->ibc_connvars), GFP_NOFS, cpt);
- if (!conn->ibc_connvars) {
- CERROR("Can't allocate in-progress connection state\n");
- goto failed_2;
- }
-
- write_lock_irqsave(glock, flags);
- if (dev->ibd_failover) {
- write_unlock_irqrestore(glock, flags);
- CERROR("%s: failover in progress\n", dev->ibd_ifname);
- goto failed_2;
- }
-
- if (dev->ibd_hdev->ibh_ibdev != cmid->device) {
- /* wakeup failover thread and teardown connection */
- if (kiblnd_dev_can_failover(dev)) {
- list_add_tail(&dev->ibd_fail_list,
- &kiblnd_data.kib_failed_devs);
- wake_up(&kiblnd_data.kib_failover_waitq);
- }
-
- write_unlock_irqrestore(glock, flags);
- CERROR("cmid HCA(%s), kib_dev(%s) need failover\n",
- cmid->device->name, dev->ibd_ifname);
- goto failed_2;
- }
-
- kiblnd_hdev_addref_locked(dev->ibd_hdev);
- conn->ibc_hdev = dev->ibd_hdev;
-
- kiblnd_setup_mtu_locked(cmid);
-
- write_unlock_irqrestore(glock, flags);
-
- conn->ibc_rxs = kzalloc_cpt(IBLND_RX_MSGS(conn) * sizeof(struct kib_rx),
- GFP_NOFS, cpt);
- if (!conn->ibc_rxs) {
- CERROR("Cannot allocate RX buffers\n");
- goto failed_2;
- }
-
- rc = kiblnd_alloc_pages(&conn->ibc_rx_pages, cpt,
- IBLND_RX_MSG_PAGES(conn));
- if (rc)
- goto failed_2;
-
- kiblnd_map_rx_descs(conn);
-
- cq_attr.cqe = IBLND_CQ_ENTRIES(conn);
- cq_attr.comp_vector = kiblnd_get_completion_vector(conn, cpt);
- cq = ib_create_cq(cmid->device,
- kiblnd_cq_completion, kiblnd_cq_event, conn,
- &cq_attr);
- if (IS_ERR(cq)) {
- CERROR("Failed to create CQ with %d CQEs: %ld\n",
- IBLND_CQ_ENTRIES(conn), PTR_ERR(cq));
- goto failed_2;
- }
-
- conn->ibc_cq = cq;
-
- rc = ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
- if (rc) {
- CERROR("Can't request completion notification: %d\n", rc);
- goto failed_2;
- }
-
- init_qp_attr->event_handler = kiblnd_qp_event;
- init_qp_attr->qp_context = conn;
- init_qp_attr->cap.max_send_wr = IBLND_SEND_WRS(conn);
- init_qp_attr->cap.max_recv_wr = IBLND_RECV_WRS(conn);
- init_qp_attr->cap.max_send_sge = 1;
- init_qp_attr->cap.max_recv_sge = 1;
- init_qp_attr->sq_sig_type = IB_SIGNAL_REQ_WR;
- init_qp_attr->qp_type = IB_QPT_RC;
- init_qp_attr->send_cq = cq;
- init_qp_attr->recv_cq = cq;
-
- conn->ibc_sched = sched;
-
- rc = rdma_create_qp(cmid, conn->ibc_hdev->ibh_pd, init_qp_attr);
- if (rc) {
- CERROR("Can't create QP: %d, send_wr: %d, recv_wr: %d\n",
- rc, init_qp_attr->cap.max_send_wr,
- init_qp_attr->cap.max_recv_wr);
- goto failed_2;
- }
-
- kfree(init_qp_attr);
-
- /* 1 ref for caller and each rxmsg */
- atomic_set(&conn->ibc_refcount, 1 + IBLND_RX_MSGS(conn));
- conn->ibc_nrx = IBLND_RX_MSGS(conn);
-
- /* post receives */
- for (i = 0; i < IBLND_RX_MSGS(conn); i++) {
- rc = kiblnd_post_rx(&conn->ibc_rxs[i],
- IBLND_POSTRX_NO_CREDIT);
- if (rc) {
- CERROR("Can't post rxmsg: %d\n", rc);
-
- /* Make posted receives complete */
- kiblnd_abort_receives(conn);
-
- /*
- * correct # of posted buffers
- * NB locking needed now I'm racing with completion
- */
- spin_lock_irqsave(&sched->ibs_lock, flags);
- conn->ibc_nrx -= IBLND_RX_MSGS(conn) - i;
- spin_unlock_irqrestore(&sched->ibs_lock, flags);
-
- /*
- * cmid will be destroyed by CM(ofed) after cm_callback
- * returned, so we can't refer it anymore
- * (by kiblnd_connd()->kiblnd_destroy_conn)
- */
- rdma_destroy_qp(conn->ibc_cmid);
- conn->ibc_cmid = NULL;
-
- /* Drop my own and unused rxbuffer refcounts */
- while (i++ <= IBLND_RX_MSGS(conn))
- kiblnd_conn_decref(conn);
-
- return NULL;
- }
- }
-
- /* Init successful! */
- LASSERT(state == IBLND_CONN_ACTIVE_CONNECT ||
- state == IBLND_CONN_PASSIVE_WAIT);
- conn->ibc_state = state;
-
- /* 1 more conn */
- atomic_inc(&net->ibn_nconns);
- return conn;
-
- failed_2:
- kiblnd_destroy_conn(conn);
- kfree(conn);
- failed_1:
- kfree(init_qp_attr);
- failed_0:
- return NULL;
-}
-
-void kiblnd_destroy_conn(struct kib_conn *conn)
-{
- struct rdma_cm_id *cmid = conn->ibc_cmid;
- struct kib_peer *peer = conn->ibc_peer;
- int rc;
-
- LASSERT(!in_interrupt());
- LASSERT(!atomic_read(&conn->ibc_refcount));
- LASSERT(list_empty(&conn->ibc_early_rxs));
- LASSERT(list_empty(&conn->ibc_tx_noops));
- LASSERT(list_empty(&conn->ibc_tx_queue));
- LASSERT(list_empty(&conn->ibc_tx_queue_rsrvd));
- LASSERT(list_empty(&conn->ibc_tx_queue_nocred));
- LASSERT(list_empty(&conn->ibc_active_txs));
- LASSERT(!conn->ibc_noops_posted);
- LASSERT(!conn->ibc_nsends_posted);
-
- switch (conn->ibc_state) {
- default:
- /* conn must be completely disengaged from the network */
- LBUG();
-
- case IBLND_CONN_DISCONNECTED:
- /* connvars should have been freed already */
- LASSERT(!conn->ibc_connvars);
- break;
-
- case IBLND_CONN_INIT:
- break;
- }
-
- /* conn->ibc_cmid might be destroyed by CM already */
- if (cmid && cmid->qp)
- rdma_destroy_qp(cmid);
-
- if (conn->ibc_cq) {
- rc = ib_destroy_cq(conn->ibc_cq);
- if (rc)
- CWARN("Error destroying CQ: %d\n", rc);
- }
-
- if (conn->ibc_rx_pages)
- kiblnd_unmap_rx_descs(conn);
-
- kfree(conn->ibc_rxs);
- kfree(conn->ibc_connvars);
-
- if (conn->ibc_hdev)
- kiblnd_hdev_decref(conn->ibc_hdev);
-
- /* See CAVEAT EMPTOR above in kiblnd_create_conn */
- if (conn->ibc_state != IBLND_CONN_INIT) {
- struct kib_net *net = peer->ibp_ni->ni_data;
-
- kiblnd_peer_decref(peer);
- rdma_destroy_id(cmid);
- atomic_dec(&net->ibn_nconns);
- }
-}
-
-int kiblnd_close_peer_conns_locked(struct kib_peer *peer, int why)
-{
- struct kib_conn *conn;
- struct list_head *ctmp;
- struct list_head *cnxt;
- int count = 0;
-
- list_for_each_safe(ctmp, cnxt, &peer->ibp_conns) {
- conn = list_entry(ctmp, struct kib_conn, ibc_list);
-
- CDEBUG(D_NET, "Closing conn -> %s, version: %x, reason: %d\n",
- libcfs_nid2str(peer->ibp_nid),
- conn->ibc_version, why);
-
- kiblnd_close_conn_locked(conn, why);
- count++;
- }
-
- return count;
-}
-
-int kiblnd_close_stale_conns_locked(struct kib_peer *peer,
- int version, __u64 incarnation)
-{
- struct kib_conn *conn;
- struct list_head *ctmp;
- struct list_head *cnxt;
- int count = 0;
-
- list_for_each_safe(ctmp, cnxt, &peer->ibp_conns) {
- conn = list_entry(ctmp, struct kib_conn, ibc_list);
-
- if (conn->ibc_version == version &&
- conn->ibc_incarnation == incarnation)
- continue;
-
- CDEBUG(D_NET,
- "Closing stale conn -> %s version: %x, incarnation:%#llx(%x, %#llx)\n",
- libcfs_nid2str(peer->ibp_nid),
- conn->ibc_version, conn->ibc_incarnation,
- version, incarnation);
-
- kiblnd_close_conn_locked(conn, -ESTALE);
- count++;
- }
-
- return count;
-}
-
-static int kiblnd_close_matching_conns(struct lnet_ni *ni, lnet_nid_t nid)
-{
- struct kib_peer *peer;
- struct list_head *ptmp;
- struct list_head *pnxt;
- int lo;
- int hi;
- int i;
- unsigned long flags;
- int count = 0;
-
- write_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- if (nid != LNET_NID_ANY) {
- lo = kiblnd_nid2peerlist(nid) - kiblnd_data.kib_peers;
- hi = kiblnd_nid2peerlist(nid) - kiblnd_data.kib_peers;
- } else {
- lo = 0;
- hi = kiblnd_data.kib_peer_hash_size - 1;
- }
-
- for (i = lo; i <= hi; i++) {
- list_for_each_safe(ptmp, pnxt, &kiblnd_data.kib_peers[i]) {
- peer = list_entry(ptmp, struct kib_peer, ibp_list);
- LASSERT(!kiblnd_peer_idle(peer));
-
- if (peer->ibp_ni != ni)
- continue;
-
- if (!(nid == LNET_NID_ANY || nid == peer->ibp_nid))
- continue;
-
- count += kiblnd_close_peer_conns_locked(peer, 0);
- }
- }
-
- write_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
-
- /* wildcards always succeed */
- if (nid == LNET_NID_ANY)
- return 0;
-
- return !count ? -ENOENT : 0;
-}
-
-static int kiblnd_ctl(struct lnet_ni *ni, unsigned int cmd, void *arg)
-{
- struct libcfs_ioctl_data *data = arg;
- int rc = -EINVAL;
-
- switch (cmd) {
- case IOC_LIBCFS_GET_PEER: {
- lnet_nid_t nid = 0;
- int count = 0;
-
- rc = kiblnd_get_peer_info(ni, data->ioc_count,
- &nid, &count);
- data->ioc_nid = nid;
- data->ioc_count = count;
- break;
- }
-
- case IOC_LIBCFS_DEL_PEER: {
- rc = kiblnd_del_peer(ni, data->ioc_nid);
- break;
- }
- case IOC_LIBCFS_GET_CONN: {
- struct kib_conn *conn;
-
- rc = 0;
- conn = kiblnd_get_conn_by_idx(ni, data->ioc_count);
- if (!conn) {
- rc = -ENOENT;
- break;
- }
-
- LASSERT(conn->ibc_cmid);
- data->ioc_nid = conn->ibc_peer->ibp_nid;
- if (!conn->ibc_cmid->route.path_rec)
- data->ioc_u32[0] = 0; /* iWarp has no path MTU */
- else
- data->ioc_u32[0] =
- ib_mtu_enum_to_int(conn->ibc_cmid->route.path_rec->mtu);
- kiblnd_conn_decref(conn);
- break;
- }
- case IOC_LIBCFS_CLOSE_CONNECTION: {
- rc = kiblnd_close_matching_conns(ni, data->ioc_nid);
- break;
- }
-
- default:
- break;
- }
-
- return rc;
-}
-
-static void kiblnd_query(struct lnet_ni *ni, lnet_nid_t nid,
- unsigned long *when)
-{
- unsigned long last_alive = 0;
- unsigned long now = jiffies;
- rwlock_t *glock = &kiblnd_data.kib_global_lock;
- struct kib_peer *peer;
- unsigned long flags;
-
- read_lock_irqsave(glock, flags);
-
- peer = kiblnd_find_peer_locked(nid);
- if (peer)
- last_alive = peer->ibp_last_alive;
-
- read_unlock_irqrestore(glock, flags);
-
- if (last_alive)
- *when = last_alive;
-
- /*
- * peer is not persistent in hash, trigger peer creation
- * and connection establishment with a NULL tx
- */
- if (!peer)
- kiblnd_launch_tx(ni, NULL, nid);
-
- CDEBUG(D_NET, "Peer %s %p, alive %ld secs ago\n",
- libcfs_nid2str(nid), peer,
- last_alive ? (now - last_alive) / HZ : -1);
-}
-
-static void kiblnd_free_pages(struct kib_pages *p)
-{
- int npages = p->ibp_npages;
- int i;
-
- for (i = 0; i < npages; i++) {
- if (p->ibp_pages[i])
- __free_page(p->ibp_pages[i]);
- }
-
- kfree(p);
-}
-
-int kiblnd_alloc_pages(struct kib_pages **pp, int cpt, int npages)
-{
- struct kib_pages *p;
- int i;
-
- p = kzalloc_cpt(offsetof(struct kib_pages, ibp_pages[npages]),
- GFP_NOFS, cpt);
- if (!p) {
- CERROR("Can't allocate descriptor for %d pages\n", npages);
- return -ENOMEM;
- }
-
- p->ibp_npages = npages;
-
- for (i = 0; i < npages; i++) {
- p->ibp_pages[i] = alloc_pages_node(
- cfs_cpt_spread_node(lnet_cpt_table(), cpt),
- GFP_NOFS, 0);
- if (!p->ibp_pages[i]) {
- CERROR("Can't allocate page %d of %d\n", i, npages);
- kiblnd_free_pages(p);
- return -ENOMEM;
- }
- }
-
- *pp = p;
- return 0;
-}
-
-void kiblnd_unmap_rx_descs(struct kib_conn *conn)
-{
- struct kib_rx *rx;
- int i;
-
- LASSERT(conn->ibc_rxs);
- LASSERT(conn->ibc_hdev);
-
- for (i = 0; i < IBLND_RX_MSGS(conn); i++) {
- rx = &conn->ibc_rxs[i];
-
- LASSERT(rx->rx_nob >= 0); /* not posted */
-
- kiblnd_dma_unmap_single(conn->ibc_hdev->ibh_ibdev,
- KIBLND_UNMAP_ADDR(rx, rx_msgunmap,
- rx->rx_msgaddr),
- IBLND_MSG_SIZE, DMA_FROM_DEVICE);
- }
-
- kiblnd_free_pages(conn->ibc_rx_pages);
-
- conn->ibc_rx_pages = NULL;
-}
-
-void kiblnd_map_rx_descs(struct kib_conn *conn)
-{
- struct kib_rx *rx;
- struct page *pg;
- int pg_off;
- int ipg;
- int i;
-
- for (pg_off = ipg = i = 0; i < IBLND_RX_MSGS(conn); i++) {
- pg = conn->ibc_rx_pages->ibp_pages[ipg];
- rx = &conn->ibc_rxs[i];
-
- rx->rx_conn = conn;
- rx->rx_msg = (struct kib_msg *)(((char *)page_address(pg)) + pg_off);
-
- rx->rx_msgaddr = kiblnd_dma_map_single(conn->ibc_hdev->ibh_ibdev,
- rx->rx_msg,
- IBLND_MSG_SIZE,
- DMA_FROM_DEVICE);
- LASSERT(!kiblnd_dma_mapping_error(conn->ibc_hdev->ibh_ibdev,
- rx->rx_msgaddr));
- KIBLND_UNMAP_ADDR_SET(rx, rx_msgunmap, rx->rx_msgaddr);
-
- CDEBUG(D_NET, "rx %d: %p %#llx(%#llx)\n",
- i, rx->rx_msg, rx->rx_msgaddr,
- (__u64)(page_to_phys(pg) + pg_off));
-
- pg_off += IBLND_MSG_SIZE;
- LASSERT(pg_off <= PAGE_SIZE);
-
- if (pg_off == PAGE_SIZE) {
- pg_off = 0;
- ipg++;
- LASSERT(ipg <= IBLND_RX_MSG_PAGES(conn));
- }
- }
-}
-
-static void kiblnd_unmap_tx_pool(struct kib_tx_pool *tpo)
-{
- struct kib_hca_dev *hdev = tpo->tpo_hdev;
- struct kib_tx *tx;
- int i;
-
- LASSERT(!tpo->tpo_pool.po_allocated);
-
- if (!hdev)
- return;
-
- for (i = 0; i < tpo->tpo_pool.po_size; i++) {
- tx = &tpo->tpo_tx_descs[i];
- kiblnd_dma_unmap_single(hdev->ibh_ibdev,
- KIBLND_UNMAP_ADDR(tx, tx_msgunmap,
- tx->tx_msgaddr),
- IBLND_MSG_SIZE, DMA_TO_DEVICE);
- }
-
- kiblnd_hdev_decref(hdev);
- tpo->tpo_hdev = NULL;
-}
-
-static struct kib_hca_dev *kiblnd_current_hdev(struct kib_dev *dev)
-{
- struct kib_hca_dev *hdev;
- unsigned long flags;
- int i = 0;
-
- read_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
- while (dev->ibd_failover) {
- read_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
- if (!(i++ % 50))
- CDEBUG(D_NET, "%s: Wait for failover\n",
- dev->ibd_ifname);
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(HZ / 100);
-
- read_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
- }
-
- kiblnd_hdev_addref_locked(dev->ibd_hdev);
- hdev = dev->ibd_hdev;
-
- read_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
-
- return hdev;
-}
-
-static void kiblnd_map_tx_pool(struct kib_tx_pool *tpo)
-{
- struct kib_pages *txpgs = tpo->tpo_tx_pages;
- struct kib_pool *pool = &tpo->tpo_pool;
- struct kib_net *net = pool->po_owner->ps_net;
- struct kib_dev *dev;
- struct page *page;
- struct kib_tx *tx;
- int page_offset;
- int ipage;
- int i;
-
- LASSERT(net);
-
- dev = net->ibn_dev;
-
- /* pre-mapped messages are not bigger than 1 page */
- BUILD_BUG_ON(IBLND_MSG_SIZE > PAGE_SIZE);
-
- /* No fancy arithmetic when we do the buffer calculations */
- BUILD_BUG_ON(PAGE_SIZE % IBLND_MSG_SIZE);
-
- tpo->tpo_hdev = kiblnd_current_hdev(dev);
-
- for (ipage = page_offset = i = 0; i < pool->po_size; i++) {
- page = txpgs->ibp_pages[ipage];
- tx = &tpo->tpo_tx_descs[i];
-
- tx->tx_msg = (struct kib_msg *)(((char *)page_address(page)) +
- page_offset);
-
- tx->tx_msgaddr = kiblnd_dma_map_single(
- tpo->tpo_hdev->ibh_ibdev, tx->tx_msg,
- IBLND_MSG_SIZE, DMA_TO_DEVICE);
- LASSERT(!kiblnd_dma_mapping_error(tpo->tpo_hdev->ibh_ibdev,
- tx->tx_msgaddr));
- KIBLND_UNMAP_ADDR_SET(tx, tx_msgunmap, tx->tx_msgaddr);
-
- list_add(&tx->tx_list, &pool->po_free_list);
-
- page_offset += IBLND_MSG_SIZE;
- LASSERT(page_offset <= PAGE_SIZE);
-
- if (page_offset == PAGE_SIZE) {
- page_offset = 0;
- ipage++;
- LASSERT(ipage <= txpgs->ibp_npages);
- }
- }
-}
-
-static void kiblnd_destroy_fmr_pool(struct kib_fmr_pool *fpo)
-{
- LASSERT(!fpo->fpo_map_count);
-
- if (fpo->fpo_is_fmr) {
- if (fpo->fmr.fpo_fmr_pool)
- ib_destroy_fmr_pool(fpo->fmr.fpo_fmr_pool);
- } else {
- struct kib_fast_reg_descriptor *frd, *tmp;
- int i = 0;
-
- list_for_each_entry_safe(frd, tmp, &fpo->fast_reg.fpo_pool_list,
- frd_list) {
- list_del(&frd->frd_list);
- ib_dereg_mr(frd->frd_mr);
- kfree(frd);
- i++;
- }
- if (i < fpo->fast_reg.fpo_pool_size)
- CERROR("FastReg pool still has %d regions registered\n",
- fpo->fast_reg.fpo_pool_size - i);
- }
-
- if (fpo->fpo_hdev)
- kiblnd_hdev_decref(fpo->fpo_hdev);
-
- kfree(fpo);
-}
-
-static void kiblnd_destroy_fmr_pool_list(struct list_head *head)
-{
- struct kib_fmr_pool *fpo, *tmp;
-
- list_for_each_entry_safe(fpo, tmp, head, fpo_list) {
- list_del(&fpo->fpo_list);
- kiblnd_destroy_fmr_pool(fpo);
- }
-}
-
-static int
-kiblnd_fmr_pool_size(struct lnet_ioctl_config_o2iblnd_tunables *tunables,
- int ncpts)
-{
- int size = tunables->lnd_fmr_pool_size / ncpts;
-
- return max(IBLND_FMR_POOL, size);
-}
-
-static int
-kiblnd_fmr_flush_trigger(struct lnet_ioctl_config_o2iblnd_tunables *tunables,
- int ncpts)
-{
- int size = tunables->lnd_fmr_flush_trigger / ncpts;
-
- return max(IBLND_FMR_POOL_FLUSH, size);
-}
-
-static int kiblnd_alloc_fmr_pool(struct kib_fmr_poolset *fps, struct kib_fmr_pool *fpo)
-{
- struct ib_fmr_pool_param param = {
- .max_pages_per_fmr = LNET_MAX_PAYLOAD / PAGE_SIZE,
- .page_shift = PAGE_SHIFT,
- .access = (IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE),
- .pool_size = fps->fps_pool_size,
- .dirty_watermark = fps->fps_flush_trigger,
- .flush_function = NULL,
- .flush_arg = NULL,
- .cache = !!fps->fps_cache };
- int rc = 0;
-
- fpo->fmr.fpo_fmr_pool = ib_create_fmr_pool(fpo->fpo_hdev->ibh_pd,
- &param);
- if (IS_ERR(fpo->fmr.fpo_fmr_pool)) {
- rc = PTR_ERR(fpo->fmr.fpo_fmr_pool);
- if (rc != -ENOSYS)
- CERROR("Failed to create FMR pool: %d\n", rc);
- else
- CERROR("FMRs are not supported\n");
- }
-
- return rc;
-}
-
-static int kiblnd_alloc_freg_pool(struct kib_fmr_poolset *fps, struct kib_fmr_pool *fpo)
-{
- struct kib_fast_reg_descriptor *frd, *tmp;
- int i, rc;
-
- INIT_LIST_HEAD(&fpo->fast_reg.fpo_pool_list);
- fpo->fast_reg.fpo_pool_size = 0;
- for (i = 0; i < fps->fps_pool_size; i++) {
- frd = kzalloc_cpt(sizeof(*frd), GFP_NOFS, fps->fps_cpt);
- if (!frd) {
- CERROR("Failed to allocate a new fast_reg descriptor\n");
- rc = -ENOMEM;
- goto out;
- }
-
- frd->frd_mr = ib_alloc_mr(fpo->fpo_hdev->ibh_pd,
- IB_MR_TYPE_MEM_REG,
- LNET_MAX_PAYLOAD / PAGE_SIZE);
- if (IS_ERR(frd->frd_mr)) {
- rc = PTR_ERR(frd->frd_mr);
- CERROR("Failed to allocate ib_alloc_mr: %d\n", rc);
- frd->frd_mr = NULL;
- goto out_middle;
- }
-
- frd->frd_valid = true;
-
- list_add_tail(&frd->frd_list, &fpo->fast_reg.fpo_pool_list);
- fpo->fast_reg.fpo_pool_size++;
- }
-
- return 0;
-
-out_middle:
- if (frd->frd_mr)
- ib_dereg_mr(frd->frd_mr);
- kfree(frd);
-
-out:
- list_for_each_entry_safe(frd, tmp, &fpo->fast_reg.fpo_pool_list,
- frd_list) {
- list_del(&frd->frd_list);
- ib_dereg_mr(frd->frd_mr);
- kfree(frd);
- }
-
- return rc;
-}
-
-static int kiblnd_create_fmr_pool(struct kib_fmr_poolset *fps,
- struct kib_fmr_pool **pp_fpo)
-{
- struct kib_dev *dev = fps->fps_net->ibn_dev;
- struct ib_device_attr *dev_attr;
- struct kib_fmr_pool *fpo;
- int rc;
-
- fpo = kzalloc_cpt(sizeof(*fpo), GFP_NOFS, fps->fps_cpt);
- if (!fpo)
- return -ENOMEM;
-
- fpo->fpo_hdev = kiblnd_current_hdev(dev);
- dev_attr = &fpo->fpo_hdev->ibh_ibdev->attrs;
-
- /* Check for FMR or FastReg support */
- fpo->fpo_is_fmr = 0;
- if (fpo->fpo_hdev->ibh_ibdev->alloc_fmr &&
- fpo->fpo_hdev->ibh_ibdev->dealloc_fmr &&
- fpo->fpo_hdev->ibh_ibdev->map_phys_fmr &&
- fpo->fpo_hdev->ibh_ibdev->unmap_fmr) {
- LCONSOLE_INFO("Using FMR for registration\n");
- fpo->fpo_is_fmr = 1;
- } else if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
- LCONSOLE_INFO("Using FastReg for registration\n");
- } else {
- rc = -ENOSYS;
- LCONSOLE_ERROR_MSG(rc, "IB device does not support FMRs nor FastRegs, can't register memory\n");
- goto out_fpo;
- }
-
- if (fpo->fpo_is_fmr)
- rc = kiblnd_alloc_fmr_pool(fps, fpo);
- else
- rc = kiblnd_alloc_freg_pool(fps, fpo);
- if (rc)
- goto out_fpo;
-
- fpo->fpo_deadline = jiffies + IBLND_POOL_DEADLINE * HZ;
- fpo->fpo_owner = fps;
- *pp_fpo = fpo;
-
- return 0;
-
-out_fpo:
- kiblnd_hdev_decref(fpo->fpo_hdev);
- kfree(fpo);
- return rc;
-}
-
-static void kiblnd_fail_fmr_poolset(struct kib_fmr_poolset *fps,
- struct list_head *zombies)
-{
- if (!fps->fps_net) /* initialized? */
- return;
-
- spin_lock(&fps->fps_lock);
-
- while (!list_empty(&fps->fps_pool_list)) {
- struct kib_fmr_pool *fpo = list_entry(fps->fps_pool_list.next,
- struct kib_fmr_pool, fpo_list);
- fpo->fpo_failed = 1;
- list_del(&fpo->fpo_list);
- if (!fpo->fpo_map_count)
- list_add(&fpo->fpo_list, zombies);
- else
- list_add(&fpo->fpo_list, &fps->fps_failed_pool_list);
- }
-
- spin_unlock(&fps->fps_lock);
-}
-
-static void kiblnd_fini_fmr_poolset(struct kib_fmr_poolset *fps)
-{
- if (fps->fps_net) { /* initialized? */
- kiblnd_destroy_fmr_pool_list(&fps->fps_failed_pool_list);
- kiblnd_destroy_fmr_pool_list(&fps->fps_pool_list);
- }
-}
-
-static int
-kiblnd_init_fmr_poolset(struct kib_fmr_poolset *fps, int cpt, int ncpts,
- struct kib_net *net,
- struct lnet_ioctl_config_o2iblnd_tunables *tunables)
-{
- struct kib_fmr_pool *fpo;
- int rc;
-
- memset(fps, 0, sizeof(*fps));
-
- fps->fps_net = net;
- fps->fps_cpt = cpt;
-
- fps->fps_pool_size = kiblnd_fmr_pool_size(tunables, ncpts);
- fps->fps_flush_trigger = kiblnd_fmr_flush_trigger(tunables, ncpts);
- fps->fps_cache = tunables->lnd_fmr_cache;
-
- spin_lock_init(&fps->fps_lock);
- INIT_LIST_HEAD(&fps->fps_pool_list);
- INIT_LIST_HEAD(&fps->fps_failed_pool_list);
-
- rc = kiblnd_create_fmr_pool(fps, &fpo);
- if (!rc)
- list_add_tail(&fpo->fpo_list, &fps->fps_pool_list);
-
- return rc;
-}
-
-static int kiblnd_fmr_pool_is_idle(struct kib_fmr_pool *fpo, unsigned long now)
-{
- if (fpo->fpo_map_count) /* still in use */
- return 0;
- if (fpo->fpo_failed)
- return 1;
- return time_after_eq(now, fpo->fpo_deadline);
-}
-
-static int
-kiblnd_map_tx_pages(struct kib_tx *tx, struct kib_rdma_desc *rd)
-{
- __u64 *pages = tx->tx_pages;
- struct kib_hca_dev *hdev;
- int npages;
- int size;
- int i;
-
- hdev = tx->tx_pool->tpo_hdev;
-
- for (i = 0, npages = 0; i < rd->rd_nfrags; i++) {
- for (size = 0; size < rd->rd_frags[i].rf_nob;
- size += hdev->ibh_page_size) {
- pages[npages++] = (rd->rd_frags[i].rf_addr &
- hdev->ibh_page_mask) + size;
- }
- }
-
- return npages;
-}
-
-void kiblnd_fmr_pool_unmap(struct kib_fmr *fmr, int status)
-{
- LIST_HEAD(zombies);
- struct kib_fmr_pool *fpo = fmr->fmr_pool;
- struct kib_fmr_poolset *fps;
- unsigned long now = jiffies;
- struct kib_fmr_pool *tmp;
- int rc;
-
- if (!fpo)
- return;
-
- fps = fpo->fpo_owner;
- if (fpo->fpo_is_fmr) {
- if (fmr->fmr_pfmr) {
- rc = ib_fmr_pool_unmap(fmr->fmr_pfmr);
- LASSERT(!rc);
- fmr->fmr_pfmr = NULL;
- }
-
- if (status) {
- rc = ib_flush_fmr_pool(fpo->fmr.fpo_fmr_pool);
- LASSERT(!rc);
- }
- } else {
- struct kib_fast_reg_descriptor *frd = fmr->fmr_frd;
-
- if (frd) {
- frd->frd_valid = false;
- spin_lock(&fps->fps_lock);
- list_add_tail(&frd->frd_list, &fpo->fast_reg.fpo_pool_list);
- spin_unlock(&fps->fps_lock);
- fmr->fmr_frd = NULL;
- }
- }
- fmr->fmr_pool = NULL;
-
- spin_lock(&fps->fps_lock);
- fpo->fpo_map_count--; /* decref the pool */
-
- list_for_each_entry_safe(fpo, tmp, &fps->fps_pool_list, fpo_list) {
- /* the first pool is persistent */
- if (fps->fps_pool_list.next == &fpo->fpo_list)
- continue;
-
- if (kiblnd_fmr_pool_is_idle(fpo, now)) {
- list_move(&fpo->fpo_list, &zombies);
- fps->fps_version++;
- }
- }
- spin_unlock(&fps->fps_lock);
-
- if (!list_empty(&zombies))
- kiblnd_destroy_fmr_pool_list(&zombies);
-}
-
-int kiblnd_fmr_pool_map(struct kib_fmr_poolset *fps, struct kib_tx *tx,
- struct kib_rdma_desc *rd, __u32 nob, __u64 iov,
- struct kib_fmr *fmr)
-{
- __u64 *pages = tx->tx_pages;
- bool is_rx = (rd != tx->tx_rd);
- bool tx_pages_mapped = false;
- struct kib_fmr_pool *fpo;
- int npages = 0;
- __u64 version;
- int rc;
-
- again:
- spin_lock(&fps->fps_lock);
- version = fps->fps_version;
- list_for_each_entry(fpo, &fps->fps_pool_list, fpo_list) {
- fpo->fpo_deadline = jiffies + IBLND_POOL_DEADLINE * HZ;
- fpo->fpo_map_count++;
-
- if (fpo->fpo_is_fmr) {
- struct ib_pool_fmr *pfmr;
-
- spin_unlock(&fps->fps_lock);
-
- if (!tx_pages_mapped) {
- npages = kiblnd_map_tx_pages(tx, rd);
- tx_pages_mapped = 1;
- }
-
- pfmr = ib_fmr_pool_map_phys(fpo->fmr.fpo_fmr_pool,
- pages, npages, iov);
- if (likely(!IS_ERR(pfmr))) {
- fmr->fmr_key = is_rx ? pfmr->fmr->rkey :
- pfmr->fmr->lkey;
- fmr->fmr_frd = NULL;
- fmr->fmr_pfmr = pfmr;
- fmr->fmr_pool = fpo;
- return 0;
- }
- rc = PTR_ERR(pfmr);
- } else {
- if (!list_empty(&fpo->fast_reg.fpo_pool_list)) {
- struct kib_fast_reg_descriptor *frd;
- struct ib_reg_wr *wr;
- struct ib_mr *mr;
- int n;
-
- frd = list_first_entry(&fpo->fast_reg.fpo_pool_list,
- struct kib_fast_reg_descriptor,
- frd_list);
- list_del(&frd->frd_list);
- spin_unlock(&fps->fps_lock);
-
- mr = frd->frd_mr;
-
- if (!frd->frd_valid) {
- __u32 key = is_rx ? mr->rkey : mr->lkey;
- struct ib_send_wr *inv_wr;
-
- inv_wr = &frd->frd_inv_wr;
- memset(inv_wr, 0, sizeof(*inv_wr));
- inv_wr->opcode = IB_WR_LOCAL_INV;
- inv_wr->wr_id = IBLND_WID_MR;
- inv_wr->ex.invalidate_rkey = key;
-
- /* Bump the key */
- key = ib_inc_rkey(key);
- ib_update_fast_reg_key(mr, key);
- }
-
- n = ib_map_mr_sg(mr, tx->tx_frags,
- tx->tx_nfrags, NULL, PAGE_SIZE);
- if (unlikely(n != tx->tx_nfrags)) {
- CERROR("Failed to map mr %d/%d elements\n",
- n, tx->tx_nfrags);
- return n < 0 ? n : -EINVAL;
- }
-
- mr->iova = iov;
-
- /* Prepare FastReg WR */
- wr = &frd->frd_fastreg_wr;
- memset(wr, 0, sizeof(*wr));
- wr->wr.opcode = IB_WR_REG_MR;
- wr->wr.wr_id = IBLND_WID_MR;
- wr->wr.num_sge = 0;
- wr->wr.send_flags = 0;
- wr->mr = mr;
- wr->key = is_rx ? mr->rkey : mr->lkey;
- wr->access = (IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_WRITE);
-
- fmr->fmr_key = is_rx ? mr->rkey : mr->lkey;
- fmr->fmr_frd = frd;
- fmr->fmr_pfmr = NULL;
- fmr->fmr_pool = fpo;
- return 0;
- }
- spin_unlock(&fps->fps_lock);
- rc = -EAGAIN;
- }
-
- spin_lock(&fps->fps_lock);
- fpo->fpo_map_count--;
- if (rc != -EAGAIN) {
- spin_unlock(&fps->fps_lock);
- return rc;
- }
-
- /* EAGAIN and ... */
- if (version != fps->fps_version) {
- spin_unlock(&fps->fps_lock);
- goto again;
- }
- }
-
- if (fps->fps_increasing) {
- spin_unlock(&fps->fps_lock);
- CDEBUG(D_NET, "Another thread is allocating new FMR pool, waiting for her to complete\n");
- schedule();
- goto again;
- }
-
- if (time_before(jiffies, fps->fps_next_retry)) {
- /* someone failed recently */
- spin_unlock(&fps->fps_lock);
- return -EAGAIN;
- }
-
- fps->fps_increasing = 1;
- spin_unlock(&fps->fps_lock);
-
- CDEBUG(D_NET, "Allocate new FMR pool\n");
- rc = kiblnd_create_fmr_pool(fps, &fpo);
- spin_lock(&fps->fps_lock);
- fps->fps_increasing = 0;
- if (!rc) {
- fps->fps_version++;
- list_add_tail(&fpo->fpo_list, &fps->fps_pool_list);
- } else {
- fps->fps_next_retry = jiffies + IBLND_POOL_RETRY * HZ;
- }
- spin_unlock(&fps->fps_lock);
-
- goto again;
-}
-
-static void kiblnd_fini_pool(struct kib_pool *pool)
-{
- LASSERT(list_empty(&pool->po_free_list));
- LASSERT(!pool->po_allocated);
-
- CDEBUG(D_NET, "Finalize %s pool\n", pool->po_owner->ps_name);
-}
-
-static void kiblnd_init_pool(struct kib_poolset *ps, struct kib_pool *pool, int size)
-{
- CDEBUG(D_NET, "Initialize %s pool\n", ps->ps_name);
-
- memset(pool, 0, sizeof(*pool));
- INIT_LIST_HEAD(&pool->po_free_list);
- pool->po_deadline = jiffies + IBLND_POOL_DEADLINE * HZ;
- pool->po_owner = ps;
- pool->po_size = size;
-}
-
-static void kiblnd_destroy_pool_list(struct list_head *head)
-{
- struct kib_pool *pool;
-
- while (!list_empty(head)) {
- pool = list_entry(head->next, struct kib_pool, po_list);
- list_del(&pool->po_list);
-
- LASSERT(pool->po_owner);
- pool->po_owner->ps_pool_destroy(pool);
- }
-}
-
-static void kiblnd_fail_poolset(struct kib_poolset *ps, struct list_head *zombies)
-{
- if (!ps->ps_net) /* initialized? */
- return;
-
- spin_lock(&ps->ps_lock);
- while (!list_empty(&ps->ps_pool_list)) {
- struct kib_pool *po = list_entry(ps->ps_pool_list.next,
- struct kib_pool, po_list);
- po->po_failed = 1;
- list_del(&po->po_list);
- if (!po->po_allocated)
- list_add(&po->po_list, zombies);
- else
- list_add(&po->po_list, &ps->ps_failed_pool_list);
- }
- spin_unlock(&ps->ps_lock);
-}
-
-static void kiblnd_fini_poolset(struct kib_poolset *ps)
-{
- if (ps->ps_net) { /* initialized? */
- kiblnd_destroy_pool_list(&ps->ps_failed_pool_list);
- kiblnd_destroy_pool_list(&ps->ps_pool_list);
- }
-}
-
-static int kiblnd_init_poolset(struct kib_poolset *ps, int cpt,
- struct kib_net *net, char *name, int size,
- kib_ps_pool_create_t po_create,
- kib_ps_pool_destroy_t po_destroy,
- kib_ps_node_init_t nd_init,
- kib_ps_node_fini_t nd_fini)
-{
- struct kib_pool *pool;
- int rc;
-
- memset(ps, 0, sizeof(*ps));
-
- ps->ps_cpt = cpt;
- ps->ps_net = net;
- ps->ps_pool_create = po_create;
- ps->ps_pool_destroy = po_destroy;
- ps->ps_node_init = nd_init;
- ps->ps_node_fini = nd_fini;
- ps->ps_pool_size = size;
- if (strlcpy(ps->ps_name, name, sizeof(ps->ps_name))
- >= sizeof(ps->ps_name))
- return -E2BIG;
- spin_lock_init(&ps->ps_lock);
- INIT_LIST_HEAD(&ps->ps_pool_list);
- INIT_LIST_HEAD(&ps->ps_failed_pool_list);
-
- rc = ps->ps_pool_create(ps, size, &pool);
- if (!rc)
- list_add(&pool->po_list, &ps->ps_pool_list);
- else
- CERROR("Failed to create the first pool for %s\n", ps->ps_name);
-
- return rc;
-}
-
-static int kiblnd_pool_is_idle(struct kib_pool *pool, unsigned long now)
-{
- if (pool->po_allocated) /* still in use */
- return 0;
- if (pool->po_failed)
- return 1;
- return time_after_eq(now, pool->po_deadline);
-}
-
-void kiblnd_pool_free_node(struct kib_pool *pool, struct list_head *node)
-{
- LIST_HEAD(zombies);
- struct kib_poolset *ps = pool->po_owner;
- struct kib_pool *tmp;
- unsigned long now = jiffies;
-
- spin_lock(&ps->ps_lock);
-
- if (ps->ps_node_fini)
- ps->ps_node_fini(pool, node);
-
- LASSERT(pool->po_allocated > 0);
- list_add(node, &pool->po_free_list);
- pool->po_allocated--;
-
- list_for_each_entry_safe(pool, tmp, &ps->ps_pool_list, po_list) {
- /* the first pool is persistent */
- if (ps->ps_pool_list.next == &pool->po_list)
- continue;
-
- if (kiblnd_pool_is_idle(pool, now))
- list_move(&pool->po_list, &zombies);
- }
- spin_unlock(&ps->ps_lock);
-
- if (!list_empty(&zombies))
- kiblnd_destroy_pool_list(&zombies);
-}
-
-struct list_head *kiblnd_pool_alloc_node(struct kib_poolset *ps)
-{
- struct list_head *node;
- struct kib_pool *pool;
- unsigned int interval = 1;
- unsigned long time_before;
- unsigned int trips = 0;
- int rc;
-
- again:
- spin_lock(&ps->ps_lock);
- list_for_each_entry(pool, &ps->ps_pool_list, po_list) {
- if (list_empty(&pool->po_free_list))
- continue;
-
- pool->po_allocated++;
- pool->po_deadline = jiffies + IBLND_POOL_DEADLINE * HZ;
- node = pool->po_free_list.next;
- list_del(node);
-
- if (ps->ps_node_init) {
- /* still hold the lock */
- ps->ps_node_init(pool, node);
- }
- spin_unlock(&ps->ps_lock);
- return node;
- }
-
- /* no available tx pool and ... */
- if (ps->ps_increasing) {
- /* another thread is allocating a new pool */
- spin_unlock(&ps->ps_lock);
- trips++;
- CDEBUG(D_NET, "Another thread is allocating new %s pool, waiting %d HZs for her to complete. trips = %d\n",
- ps->ps_name, interval, trips);
-
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(interval);
- if (interval < HZ)
- interval *= 2;
-
- goto again;
- }
-
- if (time_before(jiffies, ps->ps_next_retry)) {
- /* someone failed recently */
- spin_unlock(&ps->ps_lock);
- return NULL;
- }
-
- ps->ps_increasing = 1;
- spin_unlock(&ps->ps_lock);
-
- CDEBUG(D_NET, "%s pool exhausted, allocate new pool\n", ps->ps_name);
- time_before = jiffies;
- rc = ps->ps_pool_create(ps, ps->ps_pool_size, &pool);
- CDEBUG(D_NET, "ps_pool_create took %lu HZ to complete",
- jiffies - time_before);
-
- spin_lock(&ps->ps_lock);
- ps->ps_increasing = 0;
- if (!rc) {
- list_add_tail(&pool->po_list, &ps->ps_pool_list);
- } else {
- ps->ps_next_retry = jiffies + IBLND_POOL_RETRY * HZ;
- CERROR("Can't allocate new %s pool because out of memory\n",
- ps->ps_name);
- }
- spin_unlock(&ps->ps_lock);
-
- goto again;
-}
-
-static void kiblnd_destroy_tx_pool(struct kib_pool *pool)
-{
- struct kib_tx_pool *tpo = container_of(pool, struct kib_tx_pool, tpo_pool);
- int i;
-
- LASSERT(!pool->po_allocated);
-
- if (tpo->tpo_tx_pages) {
- kiblnd_unmap_tx_pool(tpo);
- kiblnd_free_pages(tpo->tpo_tx_pages);
- }
-
- if (!tpo->tpo_tx_descs)
- goto out;
-
- for (i = 0; i < pool->po_size; i++) {
- struct kib_tx *tx = &tpo->tpo_tx_descs[i];
-
- list_del(&tx->tx_list);
- kfree(tx->tx_pages);
- kfree(tx->tx_frags);
- kfree(tx->tx_wrq);
- kfree(tx->tx_sge);
- kfree(tx->tx_rd);
- }
-
- kfree(tpo->tpo_tx_descs);
-out:
- kiblnd_fini_pool(pool);
- kfree(tpo);
-}
-
-static int kiblnd_tx_pool_size(int ncpts)
-{
- int ntx = *kiblnd_tunables.kib_ntx / ncpts;
-
- return max(IBLND_TX_POOL, ntx);
-}
-
-static int kiblnd_create_tx_pool(struct kib_poolset *ps, int size,
- struct kib_pool **pp_po)
-{
- int i;
- int npg;
- struct kib_pool *pool;
- struct kib_tx_pool *tpo;
-
- tpo = kzalloc_cpt(sizeof(*tpo), GFP_NOFS, ps->ps_cpt);
- if (!tpo) {
- CERROR("Failed to allocate TX pool\n");
- return -ENOMEM;
- }
-
- pool = &tpo->tpo_pool;
- kiblnd_init_pool(ps, pool, size);
- tpo->tpo_tx_descs = NULL;
- tpo->tpo_tx_pages = NULL;
-
- npg = DIV_ROUND_UP(size * IBLND_MSG_SIZE, PAGE_SIZE);
- if (kiblnd_alloc_pages(&tpo->tpo_tx_pages, ps->ps_cpt, npg)) {
- CERROR("Can't allocate tx pages: %d\n", npg);
- kfree(tpo);
- return -ENOMEM;
- }
-
- tpo->tpo_tx_descs = kzalloc_cpt(size * sizeof(struct kib_tx),
- GFP_NOFS, ps->ps_cpt);
- if (!tpo->tpo_tx_descs) {
- CERROR("Can't allocate %d tx descriptors\n", size);
- ps->ps_pool_destroy(pool);
- return -ENOMEM;
- }
-
- memset(tpo->tpo_tx_descs, 0, size * sizeof(struct kib_tx));
-
- for (i = 0; i < size; i++) {
- struct kib_tx *tx = &tpo->tpo_tx_descs[i];
-
- tx->tx_pool = tpo;
- if (ps->ps_net->ibn_fmr_ps) {
- tx->tx_pages = kzalloc_cpt(LNET_MAX_IOV * sizeof(*tx->tx_pages),
- GFP_NOFS, ps->ps_cpt);
- if (!tx->tx_pages)
- break;
- }
-
- tx->tx_frags = kzalloc_cpt((1 + IBLND_MAX_RDMA_FRAGS) *
- sizeof(*tx->tx_frags),
- GFP_NOFS, ps->ps_cpt);
- if (!tx->tx_frags)
- break;
-
- sg_init_table(tx->tx_frags, IBLND_MAX_RDMA_FRAGS + 1);
-
- tx->tx_wrq = kzalloc_cpt((1 + IBLND_MAX_RDMA_FRAGS) *
- sizeof(*tx->tx_wrq),
- GFP_NOFS, ps->ps_cpt);
- if (!tx->tx_wrq)
- break;
-
- tx->tx_sge = kzalloc_cpt((1 + IBLND_MAX_RDMA_FRAGS) *
- sizeof(*tx->tx_sge),
- GFP_NOFS, ps->ps_cpt);
- if (!tx->tx_sge)
- break;
-
- tx->tx_rd = kzalloc_cpt(offsetof(struct kib_rdma_desc,
- rd_frags[IBLND_MAX_RDMA_FRAGS]),
- GFP_NOFS, ps->ps_cpt);
- if (!tx->tx_rd)
- break;
- }
-
- if (i == size) {
- kiblnd_map_tx_pool(tpo);
- *pp_po = pool;
- return 0;
- }
-
- ps->ps_pool_destroy(pool);
- return -ENOMEM;
-}
-
-static void kiblnd_tx_init(struct kib_pool *pool, struct list_head *node)
-{
- struct kib_tx_poolset *tps = container_of(pool->po_owner,
- struct kib_tx_poolset,
- tps_poolset);
- struct kib_tx *tx = list_entry(node, struct kib_tx, tx_list);
-
- tx->tx_cookie = tps->tps_next_tx_cookie++;
-}
-
-static void kiblnd_net_fini_pools(struct kib_net *net)
-{
- int i;
-
- cfs_cpt_for_each(i, lnet_cpt_table()) {
- struct kib_tx_poolset *tps;
- struct kib_fmr_poolset *fps;
-
- if (net->ibn_tx_ps) {
- tps = net->ibn_tx_ps[i];
- kiblnd_fini_poolset(&tps->tps_poolset);
- }
-
- if (net->ibn_fmr_ps) {
- fps = net->ibn_fmr_ps[i];
- kiblnd_fini_fmr_poolset(fps);
- }
- }
-
- if (net->ibn_tx_ps) {
- cfs_percpt_free(net->ibn_tx_ps);
- net->ibn_tx_ps = NULL;
- }
-
- if (net->ibn_fmr_ps) {
- cfs_percpt_free(net->ibn_fmr_ps);
- net->ibn_fmr_ps = NULL;
- }
-}
-
-static int kiblnd_net_init_pools(struct kib_net *net, struct lnet_ni *ni,
- __u32 *cpts, int ncpts)
-{
- struct lnet_ioctl_config_o2iblnd_tunables *tunables;
- int cpt;
- int rc;
- int i;
-
- tunables = &ni->ni_lnd_tunables->lt_tun_u.lt_o2ib;
-
- if (tunables->lnd_fmr_pool_size < *kiblnd_tunables.kib_ntx / 4) {
- CERROR("Can't set fmr pool size (%d) < ntx / 4(%d)\n",
- tunables->lnd_fmr_pool_size,
- *kiblnd_tunables.kib_ntx / 4);
- rc = -EINVAL;
- goto failed;
- }
-
- /*
- * TX pool must be created later than FMR, see LU-2268
- * for details
- */
- LASSERT(!net->ibn_tx_ps);
-
- /*
- * premapping can fail if ibd_nmr > 1, so we always create
- * FMR pool and map-on-demand if premapping failed
- *
- * cfs_precpt_alloc is creating an array of struct kib_fmr_poolset
- * The number of struct kib_fmr_poolsets create is equal to the
- * number of CPTs that exist, i.e net->ibn_fmr_ps[cpt].
- */
- net->ibn_fmr_ps = cfs_percpt_alloc(lnet_cpt_table(),
- sizeof(struct kib_fmr_poolset));
- if (!net->ibn_fmr_ps) {
- CERROR("Failed to allocate FMR pool array\n");
- rc = -ENOMEM;
- goto failed;
- }
-
- for (i = 0; i < ncpts; i++) {
- cpt = !cpts ? i : cpts[i];
- rc = kiblnd_init_fmr_poolset(net->ibn_fmr_ps[cpt], cpt, ncpts,
- net, tunables);
- if (rc) {
- CERROR("Can't initialize FMR pool for CPT %d: %d\n",
- cpt, rc);
- goto failed;
- }
- }
-
- if (i > 0)
- LASSERT(i == ncpts);
-
- /*
- * cfs_precpt_alloc is creating an array of struct kib_tx_poolset
- * The number of struct kib_tx_poolsets create is equal to the
- * number of CPTs that exist, i.e net->ibn_tx_ps[cpt].
- */
- net->ibn_tx_ps = cfs_percpt_alloc(lnet_cpt_table(),
- sizeof(struct kib_tx_poolset));
- if (!net->ibn_tx_ps) {
- CERROR("Failed to allocate tx pool array\n");
- rc = -ENOMEM;
- goto failed;
- }
-
- for (i = 0; i < ncpts; i++) {
- cpt = !cpts ? i : cpts[i];
- rc = kiblnd_init_poolset(&net->ibn_tx_ps[cpt]->tps_poolset,
- cpt, net, "TX",
- kiblnd_tx_pool_size(ncpts),
- kiblnd_create_tx_pool,
- kiblnd_destroy_tx_pool,
- kiblnd_tx_init, NULL);
- if (rc) {
- CERROR("Can't initialize TX pool for CPT %d: %d\n",
- cpt, rc);
- goto failed;
- }
- }
-
- return 0;
- failed:
- kiblnd_net_fini_pools(net);
- LASSERT(rc);
- return rc;
-}
-
-static int kiblnd_hdev_get_attr(struct kib_hca_dev *hdev)
-{
- /*
- * It's safe to assume a HCA can handle a page size
- * matching that of the native system
- */
- hdev->ibh_page_shift = PAGE_SHIFT;
- hdev->ibh_page_size = 1 << PAGE_SHIFT;
- hdev->ibh_page_mask = ~((__u64)hdev->ibh_page_size - 1);
-
- hdev->ibh_mr_size = hdev->ibh_ibdev->attrs.max_mr_size;
- if (hdev->ibh_mr_size == ~0ULL) {
- hdev->ibh_mr_shift = 64;
- return 0;
- }
-
- CERROR("Invalid mr size: %#llx\n", hdev->ibh_mr_size);
- return -EINVAL;
-}
-
-void kiblnd_hdev_destroy(struct kib_hca_dev *hdev)
-{
- if (hdev->ibh_pd)
- ib_dealloc_pd(hdev->ibh_pd);
-
- if (hdev->ibh_cmid)
- rdma_destroy_id(hdev->ibh_cmid);
-
- kfree(hdev);
-}
-
-/* DUMMY */
-static int kiblnd_dummy_callback(struct rdma_cm_id *cmid,
- struct rdma_cm_event *event)
-{
- return 0;
-}
-
-static int kiblnd_dev_need_failover(struct kib_dev *dev)
-{
- struct rdma_cm_id *cmid;
- struct sockaddr_in srcaddr;
- struct sockaddr_in dstaddr;
- int rc;
-
- if (!dev->ibd_hdev || /* initializing */
- !dev->ibd_hdev->ibh_cmid || /* listener is dead */
- *kiblnd_tunables.kib_dev_failover > 1) /* debugging */
- return 1;
-
- /*
- * XXX: it's UGLY, but I don't have better way to find
- * ib-bonding HCA failover because:
- *
- * a. no reliable CM event for HCA failover...
- * b. no OFED API to get ib_device for current net_device...
- *
- * We have only two choices at this point:
- *
- * a. rdma_bind_addr(), it will conflict with listener cmid
- * b. rdma_resolve_addr() to zero addr
- */
- cmid = kiblnd_rdma_create_id(kiblnd_dummy_callback, dev, RDMA_PS_TCP,
- IB_QPT_RC);
- if (IS_ERR(cmid)) {
- rc = PTR_ERR(cmid);
- CERROR("Failed to create cmid for failover: %d\n", rc);
- return rc;
- }
-
- memset(&srcaddr, 0, sizeof(srcaddr));
- srcaddr.sin_family = AF_INET;
- srcaddr.sin_addr.s_addr = htonl(dev->ibd_ifip);
-
- memset(&dstaddr, 0, sizeof(dstaddr));
- dstaddr.sin_family = AF_INET;
- rc = rdma_resolve_addr(cmid, (struct sockaddr *)&srcaddr,
- (struct sockaddr *)&dstaddr, 1);
- if (rc || !cmid->device) {
- CERROR("Failed to bind %s:%pI4h to device(%p): %d\n",
- dev->ibd_ifname, &dev->ibd_ifip,
- cmid->device, rc);
- rdma_destroy_id(cmid);
- return rc;
- }
-
- rc = dev->ibd_hdev->ibh_ibdev != cmid->device; /* true for failover */
- rdma_destroy_id(cmid);
-
- return rc;
-}
-
-int kiblnd_dev_failover(struct kib_dev *dev)
-{
- LIST_HEAD(zombie_tpo);
- LIST_HEAD(zombie_ppo);
- LIST_HEAD(zombie_fpo);
- struct rdma_cm_id *cmid = NULL;
- struct kib_hca_dev *hdev = NULL;
- struct ib_pd *pd;
- struct kib_net *net;
- struct sockaddr_in addr;
- unsigned long flags;
- int rc = 0;
- int i;
-
- LASSERT(*kiblnd_tunables.kib_dev_failover > 1 ||
- dev->ibd_can_failover || !dev->ibd_hdev);
-
- rc = kiblnd_dev_need_failover(dev);
- if (rc <= 0)
- goto out;
-
- if (dev->ibd_hdev &&
- dev->ibd_hdev->ibh_cmid) {
- /*
- * XXX it's not good to close old listener at here,
- * because we can fail to create new listener.
- * But we have to close it now, otherwise rdma_bind_addr
- * will return EADDRINUSE... How crap!
- */
- write_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- cmid = dev->ibd_hdev->ibh_cmid;
- /*
- * make next schedule of kiblnd_dev_need_failover()
- * return 1 for me
- */
- dev->ibd_hdev->ibh_cmid = NULL;
- write_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
-
- rdma_destroy_id(cmid);
- }
-
- cmid = kiblnd_rdma_create_id(kiblnd_cm_callback, dev, RDMA_PS_TCP,
- IB_QPT_RC);
- if (IS_ERR(cmid)) {
- rc = PTR_ERR(cmid);
- CERROR("Failed to create cmid for failover: %d\n", rc);
- goto out;
- }
-
- memset(&addr, 0, sizeof(addr));
- addr.sin_family = AF_INET;
- addr.sin_addr.s_addr = htonl(dev->ibd_ifip);
- addr.sin_port = htons(*kiblnd_tunables.kib_service);
-
- /* Bind to failover device or port */
- rc = rdma_bind_addr(cmid, (struct sockaddr *)&addr);
- if (rc || !cmid->device) {
- CERROR("Failed to bind %s:%pI4h to device(%p): %d\n",
- dev->ibd_ifname, &dev->ibd_ifip,
- cmid->device, rc);
- rdma_destroy_id(cmid);
- goto out;
- }
-
- hdev = kzalloc(sizeof(*hdev), GFP_NOFS);
- if (!hdev) {
- CERROR("Failed to allocate kib_hca_dev\n");
- rdma_destroy_id(cmid);
- rc = -ENOMEM;
- goto out;
- }
-
- atomic_set(&hdev->ibh_ref, 1);
- hdev->ibh_dev = dev;
- hdev->ibh_cmid = cmid;
- hdev->ibh_ibdev = cmid->device;
-
- pd = ib_alloc_pd(cmid->device, 0);
- if (IS_ERR(pd)) {
- rc = PTR_ERR(pd);
- CERROR("Can't allocate PD: %d\n", rc);
- goto out;
- }
-
- hdev->ibh_pd = pd;
-
- rc = rdma_listen(cmid, 0);
- if (rc) {
- CERROR("Can't start new listener: %d\n", rc);
- goto out;
- }
-
- rc = kiblnd_hdev_get_attr(hdev);
- if (rc) {
- CERROR("Can't get device attributes: %d\n", rc);
- goto out;
- }
-
- write_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
-
- swap(dev->ibd_hdev, hdev); /* take over the refcount */
-
- list_for_each_entry(net, &dev->ibd_nets, ibn_list) {
- cfs_cpt_for_each(i, lnet_cpt_table()) {
- kiblnd_fail_poolset(&net->ibn_tx_ps[i]->tps_poolset,
- &zombie_tpo);
-
- if (net->ibn_fmr_ps)
- kiblnd_fail_fmr_poolset(net->ibn_fmr_ps[i],
- &zombie_fpo);
- }
- }
-
- write_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
- out:
- if (!list_empty(&zombie_tpo))
- kiblnd_destroy_pool_list(&zombie_tpo);
- if (!list_empty(&zombie_ppo))
- kiblnd_destroy_pool_list(&zombie_ppo);
- if (!list_empty(&zombie_fpo))
- kiblnd_destroy_fmr_pool_list(&zombie_fpo);
- if (hdev)
- kiblnd_hdev_decref(hdev);
-
- if (rc)
- dev->ibd_failed_failover++;
- else
- dev->ibd_failed_failover = 0;
-
- return rc;
-}
-
-void kiblnd_destroy_dev(struct kib_dev *dev)
-{
- LASSERT(!dev->ibd_nnets);
- LASSERT(list_empty(&dev->ibd_nets));
-
- list_del(&dev->ibd_fail_list);
- list_del(&dev->ibd_list);
-
- if (dev->ibd_hdev)
- kiblnd_hdev_decref(dev->ibd_hdev);
-
- kfree(dev);
-}
-
-static struct kib_dev *kiblnd_create_dev(char *ifname)
-{
- struct net_device *netdev;
- struct kib_dev *dev;
- __u32 netmask;
- __u32 ip;
- int up;
- int rc;
-
- rc = lnet_ipif_query(ifname, &up, &ip, &netmask);
- if (rc) {
- CERROR("Can't query IPoIB interface %s: %d\n",
- ifname, rc);
- return NULL;
- }
-
- if (!up) {
- CERROR("Can't query IPoIB interface %s: it's down\n", ifname);
- return NULL;
- }
-
- dev = kzalloc(sizeof(*dev), GFP_NOFS);
- if (!dev)
- return NULL;
-
- netdev = dev_get_by_name(&init_net, ifname);
- if (!netdev) {
- dev->ibd_can_failover = 0;
- } else {
- dev->ibd_can_failover = !!(netdev->flags & IFF_MASTER);
- dev_put(netdev);
- }
-
- INIT_LIST_HEAD(&dev->ibd_nets);
- INIT_LIST_HEAD(&dev->ibd_list); /* not yet in kib_devs */
- INIT_LIST_HEAD(&dev->ibd_fail_list);
- dev->ibd_ifip = ip;
- strcpy(&dev->ibd_ifname[0], ifname);
-
- /* initialize the device */
- rc = kiblnd_dev_failover(dev);
- if (rc) {
- CERROR("Can't initialize device: %d\n", rc);
- kfree(dev);
- return NULL;
- }
-
- list_add_tail(&dev->ibd_list, &kiblnd_data.kib_devs);
- return dev;
-}
-
-static void kiblnd_base_shutdown(void)
-{
- struct kib_sched_info *sched;
- int i;
-
- LASSERT(list_empty(&kiblnd_data.kib_devs));
-
- switch (kiblnd_data.kib_init) {
- default:
- LBUG();
-
- case IBLND_INIT_ALL:
- case IBLND_INIT_DATA:
- LASSERT(kiblnd_data.kib_peers);
- for (i = 0; i < kiblnd_data.kib_peer_hash_size; i++)
- LASSERT(list_empty(&kiblnd_data.kib_peers[i]));
- LASSERT(list_empty(&kiblnd_data.kib_connd_zombies));
- LASSERT(list_empty(&kiblnd_data.kib_connd_conns));
- LASSERT(list_empty(&kiblnd_data.kib_reconn_list));
- LASSERT(list_empty(&kiblnd_data.kib_reconn_wait));
-
- /* flag threads to terminate; wake and wait for them to die */
- kiblnd_data.kib_shutdown = 1;
-
- /*
- * NB: we really want to stop scheduler threads net by net
- * instead of the whole module, this should be improved
- * with dynamic configuration LNet
- */
- cfs_percpt_for_each(sched, i, kiblnd_data.kib_scheds)
- wake_up_all(&sched->ibs_waitq);
-
- wake_up_all(&kiblnd_data.kib_connd_waitq);
- wake_up_all(&kiblnd_data.kib_failover_waitq);
-
- i = 2;
- while (atomic_read(&kiblnd_data.kib_nthreads)) {
- i++;
- /* power of 2 ? */
- CDEBUG(((i & (-i)) == i) ? D_WARNING : D_NET,
- "Waiting for %d threads to terminate\n",
- atomic_read(&kiblnd_data.kib_nthreads));
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(HZ);
- }
-
- /* fall through */
-
- case IBLND_INIT_NOTHING:
- break;
- }
-
- kvfree(kiblnd_data.kib_peers);
-
- if (kiblnd_data.kib_scheds)
- cfs_percpt_free(kiblnd_data.kib_scheds);
-
- kiblnd_data.kib_init = IBLND_INIT_NOTHING;
- module_put(THIS_MODULE);
-}
-
-static void kiblnd_shutdown(struct lnet_ni *ni)
-{
- struct kib_net *net = ni->ni_data;
- rwlock_t *g_lock = &kiblnd_data.kib_global_lock;
- int i;
- unsigned long flags;
-
- LASSERT(kiblnd_data.kib_init == IBLND_INIT_ALL);
-
- if (!net)
- goto out;
-
- write_lock_irqsave(g_lock, flags);
- net->ibn_shutdown = 1;
- write_unlock_irqrestore(g_lock, flags);
-
- switch (net->ibn_init) {
- default:
- LBUG();
-
- case IBLND_INIT_ALL:
- /* nuke all existing peers within this net */
- kiblnd_del_peer(ni, LNET_NID_ANY);
-
- /* Wait for all peer state to clean up */
- i = 2;
- while (atomic_read(&net->ibn_npeers)) {
- i++;
- CDEBUG(((i & (-i)) == i) ? D_WARNING : D_NET, /* 2**n? */
- "%s: waiting for %d peers to disconnect\n",
- libcfs_nid2str(ni->ni_nid),
- atomic_read(&net->ibn_npeers));
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(HZ);
- }
-
- kiblnd_net_fini_pools(net);
-
- write_lock_irqsave(g_lock, flags);
- LASSERT(net->ibn_dev->ibd_nnets > 0);
- net->ibn_dev->ibd_nnets--;
- list_del(&net->ibn_list);
- write_unlock_irqrestore(g_lock, flags);
-
- /* fall through */
-
- case IBLND_INIT_NOTHING:
- LASSERT(!atomic_read(&net->ibn_nconns));
-
- if (net->ibn_dev && !net->ibn_dev->ibd_nnets)
- kiblnd_destroy_dev(net->ibn_dev);
-
- break;
- }
-
- net->ibn_init = IBLND_INIT_NOTHING;
- ni->ni_data = NULL;
-
- kfree(net);
-
-out:
- if (list_empty(&kiblnd_data.kib_devs))
- kiblnd_base_shutdown();
-}
-
-static int kiblnd_base_startup(void)
-{
- struct kib_sched_info *sched;
- int rc;
- int i;
-
- LASSERT(kiblnd_data.kib_init == IBLND_INIT_NOTHING);
-
- try_module_get(THIS_MODULE);
- /* zero pointers, flags etc */
- memset(&kiblnd_data, 0, sizeof(kiblnd_data));
-
- rwlock_init(&kiblnd_data.kib_global_lock);
-
- INIT_LIST_HEAD(&kiblnd_data.kib_devs);
- INIT_LIST_HEAD(&kiblnd_data.kib_failed_devs);
-
- kiblnd_data.kib_peer_hash_size = IBLND_PEER_HASH_SIZE;
- kiblnd_data.kib_peers = kvmalloc_array(kiblnd_data.kib_peer_hash_size,
- sizeof(struct list_head),
- GFP_KERNEL);
- if (!kiblnd_data.kib_peers)
- goto failed;
- for (i = 0; i < kiblnd_data.kib_peer_hash_size; i++)
- INIT_LIST_HEAD(&kiblnd_data.kib_peers[i]);
-
- spin_lock_init(&kiblnd_data.kib_connd_lock);
- INIT_LIST_HEAD(&kiblnd_data.kib_connd_conns);
- INIT_LIST_HEAD(&kiblnd_data.kib_connd_zombies);
- INIT_LIST_HEAD(&kiblnd_data.kib_reconn_list);
- INIT_LIST_HEAD(&kiblnd_data.kib_reconn_wait);
-
- init_waitqueue_head(&kiblnd_data.kib_connd_waitq);
- init_waitqueue_head(&kiblnd_data.kib_failover_waitq);
-
- kiblnd_data.kib_scheds = cfs_percpt_alloc(lnet_cpt_table(),
- sizeof(*sched));
- if (!kiblnd_data.kib_scheds)
- goto failed;
-
- cfs_percpt_for_each(sched, i, kiblnd_data.kib_scheds) {
- int nthrs;
-
- spin_lock_init(&sched->ibs_lock);
- INIT_LIST_HEAD(&sched->ibs_conns);
- init_waitqueue_head(&sched->ibs_waitq);
-
- nthrs = cfs_cpt_weight(lnet_cpt_table(), i);
- if (*kiblnd_tunables.kib_nscheds > 0) {
- nthrs = min(nthrs, *kiblnd_tunables.kib_nscheds);
- } else {
- /*
- * max to half of CPUs, another half is reserved for
- * upper layer modules
- */
- nthrs = min(max(IBLND_N_SCHED, nthrs >> 1), nthrs);
- }
-
- sched->ibs_nthreads_max = nthrs;
- sched->ibs_cpt = i;
- }
-
- kiblnd_data.kib_error_qpa.qp_state = IB_QPS_ERR;
-
- /* lists/ptrs/locks initialised */
- kiblnd_data.kib_init = IBLND_INIT_DATA;
- /*****************************************************/
-
- rc = kiblnd_thread_start(kiblnd_connd, NULL, "kiblnd_connd");
- if (rc) {
- CERROR("Can't spawn o2iblnd connd: %d\n", rc);
- goto failed;
- }
-
- if (*kiblnd_tunables.kib_dev_failover)
- rc = kiblnd_thread_start(kiblnd_failover_thread, NULL,
- "kiblnd_failover");
-
- if (rc) {
- CERROR("Can't spawn o2iblnd failover thread: %d\n", rc);
- goto failed;
- }
-
- /* flag everything initialised */
- kiblnd_data.kib_init = IBLND_INIT_ALL;
- /*****************************************************/
-
- return 0;
-
- failed:
- kiblnd_base_shutdown();
- return -ENETDOWN;
-}
-
-static int kiblnd_start_schedulers(struct kib_sched_info *sched)
-{
- int rc = 0;
- int nthrs;
- int i;
-
- if (!sched->ibs_nthreads) {
- if (*kiblnd_tunables.kib_nscheds > 0) {
- nthrs = sched->ibs_nthreads_max;
- } else {
- nthrs = cfs_cpt_weight(lnet_cpt_table(),
- sched->ibs_cpt);
- nthrs = min(max(IBLND_N_SCHED, nthrs >> 1), nthrs);
- nthrs = min(IBLND_N_SCHED_HIGH, nthrs);
- }
- } else {
- LASSERT(sched->ibs_nthreads <= sched->ibs_nthreads_max);
- /* increase one thread if there is new interface */
- nthrs = sched->ibs_nthreads < sched->ibs_nthreads_max;
- }
-
- for (i = 0; i < nthrs; i++) {
- long id;
- char name[20];
-
- id = KIB_THREAD_ID(sched->ibs_cpt, sched->ibs_nthreads + i);
- snprintf(name, sizeof(name), "kiblnd_sd_%02ld_%02ld",
- KIB_THREAD_CPT(id), KIB_THREAD_TID(id));
- rc = kiblnd_thread_start(kiblnd_scheduler, (void *)id, name);
- if (!rc)
- continue;
-
- CERROR("Can't spawn thread %d for scheduler[%d]: %d\n",
- sched->ibs_cpt, sched->ibs_nthreads + i, rc);
- break;
- }
-
- sched->ibs_nthreads += i;
- return rc;
-}
-
-static int kiblnd_dev_start_threads(struct kib_dev *dev, int newdev, __u32 *cpts,
- int ncpts)
-{
- int cpt;
- int rc;
- int i;
-
- for (i = 0; i < ncpts; i++) {
- struct kib_sched_info *sched;
-
- cpt = !cpts ? i : cpts[i];
- sched = kiblnd_data.kib_scheds[cpt];
-
- if (!newdev && sched->ibs_nthreads > 0)
- continue;
-
- rc = kiblnd_start_schedulers(kiblnd_data.kib_scheds[cpt]);
- if (rc) {
- CERROR("Failed to start scheduler threads for %s\n",
- dev->ibd_ifname);
- return rc;
- }
- }
- return 0;
-}
-
-static struct kib_dev *kiblnd_dev_search(char *ifname)
-{
- struct kib_dev *alias = NULL;
- struct kib_dev *dev;
- char *colon;
- char *colon2;
-
- colon = strchr(ifname, ':');
- list_for_each_entry(dev, &kiblnd_data.kib_devs, ibd_list) {
- if (!strcmp(&dev->ibd_ifname[0], ifname))
- return dev;
-
- if (alias)
- continue;
-
- colon2 = strchr(dev->ibd_ifname, ':');
- if (colon)
- *colon = 0;
- if (colon2)
- *colon2 = 0;
-
- if (!strcmp(&dev->ibd_ifname[0], ifname))
- alias = dev;
-
- if (colon)
- *colon = ':';
- if (colon2)
- *colon2 = ':';
- }
- return alias;
-}
-
-static int kiblnd_startup(struct lnet_ni *ni)
-{
- char *ifname;
- struct kib_dev *ibdev = NULL;
- struct kib_net *net;
- struct timespec64 tv;
- unsigned long flags;
- int rc;
- int newdev;
-
- LASSERT(ni->ni_lnd == &the_o2iblnd);
-
- if (kiblnd_data.kib_init == IBLND_INIT_NOTHING) {
- rc = kiblnd_base_startup();
- if (rc)
- return rc;
- }
-
- net = kzalloc(sizeof(*net), GFP_NOFS);
- ni->ni_data = net;
- if (!net)
- goto net_failed;
-
- ktime_get_real_ts64(&tv);
- net->ibn_incarnation = tv.tv_sec * USEC_PER_SEC +
- tv.tv_nsec / NSEC_PER_USEC;
-
- rc = kiblnd_tunables_setup(ni);
- if (rc)
- goto net_failed;
-
- if (ni->ni_interfaces[0]) {
- /* Use the IPoIB interface specified in 'networks=' */
-
- BUILD_BUG_ON(LNET_MAX_INTERFACES <= 1);
- if (ni->ni_interfaces[1]) {
- CERROR("Multiple interfaces not supported\n");
- goto failed;
- }
-
- ifname = ni->ni_interfaces[0];
- } else {
- ifname = *kiblnd_tunables.kib_default_ipif;
- }
-
- if (strlen(ifname) >= sizeof(ibdev->ibd_ifname)) {
- CERROR("IPoIB interface name too long: %s\n", ifname);
- goto failed;
- }
-
- ibdev = kiblnd_dev_search(ifname);
-
- newdev = !ibdev;
- /* hmm...create kib_dev even for alias */
- if (!ibdev || strcmp(&ibdev->ibd_ifname[0], ifname))
- ibdev = kiblnd_create_dev(ifname);
-
- if (!ibdev)
- goto failed;
-
- net->ibn_dev = ibdev;
- ni->ni_nid = LNET_MKNID(LNET_NIDNET(ni->ni_nid), ibdev->ibd_ifip);
-
- rc = kiblnd_dev_start_threads(ibdev, newdev,
- ni->ni_cpts, ni->ni_ncpts);
- if (rc)
- goto failed;
-
- rc = kiblnd_net_init_pools(net, ni, ni->ni_cpts, ni->ni_ncpts);
- if (rc) {
- CERROR("Failed to initialize NI pools: %d\n", rc);
- goto failed;
- }
-
- write_lock_irqsave(&kiblnd_data.kib_global_lock, flags);
- ibdev->ibd_nnets++;
- list_add_tail(&net->ibn_list, &ibdev->ibd_nets);
- write_unlock_irqrestore(&kiblnd_data.kib_global_lock, flags);
-
- net->ibn_init = IBLND_INIT_ALL;
-
- return 0;
-
-failed:
- if (!net->ibn_dev && ibdev)
- kiblnd_destroy_dev(ibdev);
-
-net_failed:
- kiblnd_shutdown(ni);
-
- CDEBUG(D_NET, "%s failed\n", __func__);
- return -ENETDOWN;
-}
-
-static struct lnet_lnd the_o2iblnd = {
- .lnd_type = O2IBLND,
- .lnd_startup = kiblnd_startup,
- .lnd_shutdown = kiblnd_shutdown,
- .lnd_ctl = kiblnd_ctl,
- .lnd_query = kiblnd_query,
- .lnd_send = kiblnd_send,
- .lnd_recv = kiblnd_recv,
-};
-
-static void __exit ko2iblnd_exit(void)
-{
- lnet_unregister_lnd(&the_o2iblnd);
-}
-
-static int __init ko2iblnd_init(void)
-{
- int rc;
-
- BUILD_BUG_ON(sizeof(struct kib_msg) > IBLND_MSG_SIZE);
- BUILD_BUG_ON(offsetof(struct kib_msg,
- ibm_u.get.ibgm_rd.rd_frags[IBLND_MAX_RDMA_FRAGS])
- > IBLND_MSG_SIZE);
- BUILD_BUG_ON(offsetof(struct kib_msg,
- ibm_u.putack.ibpam_rd.rd_frags[IBLND_MAX_RDMA_FRAGS])
- > IBLND_MSG_SIZE);
-
- kiblnd_tunables_init();
-
- rc = libcfs_setup();
- if (rc)
- return rc;
-
- lnet_register_lnd(&the_o2iblnd);
-
- return 0;
-}
-
-MODULE_AUTHOR("OpenSFS, Inc. <http://www.lustre.org/>");
-MODULE_DESCRIPTION("OpenIB gen2 LNet Network Driver");
-MODULE_VERSION("2.7.0");
-MODULE_LICENSE("GPL");
-
-module_init(ko2iblnd_init);
-module_exit(ko2iblnd_exit);
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
deleted file mode 100644
index 217503f125bc..000000000000
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
+++ /dev/null
@@ -1,1048 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2011, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * lnet/klnds/o2iblnd/o2iblnd.h
- *
- * Author: Eric Barton <eric@bartonsoftware.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/errno.h>
-#include <linux/unistd.h>
-#include <linux/uio.h>
-#include <linux/uaccess.h>
-
-#include <linux/io.h>
-
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/list.h>
-#include <linux/kmod.h>
-#include <linux/sysctl.h>
-#include <linux/pci.h>
-
-#include <net/sock.h>
-#include <linux/in.h>
-
-#include <rdma/rdma_cm.h>
-#include <rdma/ib_cm.h>
-#include <rdma/ib_verbs.h>
-#include <rdma/ib_fmr_pool.h>
-
-#define DEBUG_SUBSYSTEM S_LND
-
-#include <linux/lnet/lib-lnet.h>
-
-#define IBLND_PEER_HASH_SIZE 101 /* # peer lists */
-/* # scheduler loops before reschedule */
-#define IBLND_RESCHED 100
-
-#define IBLND_N_SCHED 2
-#define IBLND_N_SCHED_HIGH 4
-
-struct kib_tunables {
- int *kib_dev_failover; /* HCA failover */
- unsigned int *kib_service; /* IB service number */
- int *kib_min_reconnect_interval; /* first failed connection retry... */
- int *kib_max_reconnect_interval; /* exponentially increasing to this */
- int *kib_cksum; /* checksum struct kib_msg? */
- int *kib_timeout; /* comms timeout (seconds) */
- int *kib_keepalive; /* keepalive timeout (seconds) */
- int *kib_ntx; /* # tx descs */
- char **kib_default_ipif; /* default IPoIB interface */
- int *kib_retry_count;
- int *kib_rnr_retry_count;
- int *kib_ib_mtu; /* IB MTU */
- int *kib_require_priv_port; /* accept only privileged ports */
- int *kib_use_priv_port; /* use privileged port for active connect */
- int *kib_nscheds; /* # threads on each CPT */
-};
-
-extern struct kib_tunables kiblnd_tunables;
-
-#define IBLND_MSG_QUEUE_SIZE_V1 8 /* V1 only : # messages/RDMAs in-flight */
-#define IBLND_CREDIT_HIGHWATER_V1 7 /* V1 only : when eagerly to return credits */
-
-#define IBLND_CREDITS_DEFAULT 8 /* default # of peer credits */
-#define IBLND_CREDITS_MAX ((typeof(((struct kib_msg *)0)->ibm_credits)) - 1) /* Max # of peer credits */
-
-/* when eagerly to return credits */
-#define IBLND_CREDITS_HIGHWATER(t, v) ((v) == IBLND_MSG_VERSION_1 ? \
- IBLND_CREDIT_HIGHWATER_V1 : \
- t->lnd_peercredits_hiw)
-
-#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(current->nsproxy->net_ns, \
- cb, dev, \
- ps, qpt)
-
-/* 2 OOB shall suffice for 1 keepalive and 1 returning credits */
-#define IBLND_OOB_CAPABLE(v) ((v) != IBLND_MSG_VERSION_1)
-#define IBLND_OOB_MSGS(v) (IBLND_OOB_CAPABLE(v) ? 2 : 0)
-
-#define IBLND_FRAG_SHIFT (PAGE_SHIFT - 12) /* frag size on wire is in 4K units */
-#define IBLND_MSG_SIZE (4 << 10) /* max size of queued messages (inc hdr) */
-#define IBLND_MAX_RDMA_FRAGS (LNET_MAX_PAYLOAD >> 12)/* max # of fragments supported in 4K size */
-
-/************************/
-/* derived constants... */
-/* Pools (shared by connections on each CPT) */
-/* These pools can grow at runtime, so don't need give a very large value */
-#define IBLND_TX_POOL 256
-#define IBLND_FMR_POOL 256
-#define IBLND_FMR_POOL_FLUSH 192
-
-#define IBLND_RX_MSGS(c) \
- ((c->ibc_queue_depth) * 2 + IBLND_OOB_MSGS(c->ibc_version))
-#define IBLND_RX_MSG_BYTES(c) (IBLND_RX_MSGS(c) * IBLND_MSG_SIZE)
-#define IBLND_RX_MSG_PAGES(c) \
- ((IBLND_RX_MSG_BYTES(c) + PAGE_SIZE - 1) / PAGE_SIZE)
-
-/* WRs and CQEs (per connection) */
-#define IBLND_RECV_WRS(c) IBLND_RX_MSGS(c)
-#define IBLND_SEND_WRS(c) \
- (((c->ibc_max_frags + 1) << IBLND_FRAG_SHIFT) * \
- kiblnd_concurrent_sends(c->ibc_version, c->ibc_peer->ibp_ni))
-#define IBLND_CQ_ENTRIES(c) (IBLND_RECV_WRS(c) + IBLND_SEND_WRS(c))
-
-struct kib_hca_dev;
-
-/* o2iblnd can run over aliased interface */
-#ifdef IFALIASZ
-#define KIB_IFNAME_SIZE IFALIASZ
-#else
-#define KIB_IFNAME_SIZE 256
-#endif
-
-struct kib_dev {
- struct list_head ibd_list; /* chain on kib_devs */
- struct list_head ibd_fail_list; /* chain on kib_failed_devs */
- __u32 ibd_ifip; /* IPoIB interface IP */
-
- /* IPoIB interface name */
- char ibd_ifname[KIB_IFNAME_SIZE];
- int ibd_nnets; /* # nets extant */
-
- unsigned long ibd_next_failover;
- int ibd_failed_failover; /* # failover failures */
- unsigned int ibd_failover; /* failover in progress */
- unsigned int ibd_can_failover; /* IPoIB interface is a bonding master */
- struct list_head ibd_nets;
- struct kib_hca_dev *ibd_hdev;
-};
-
-struct kib_hca_dev {
- struct rdma_cm_id *ibh_cmid; /* listener cmid */
- struct ib_device *ibh_ibdev; /* IB device */
- int ibh_page_shift; /* page shift of current HCA */
- int ibh_page_size; /* page size of current HCA */
- __u64 ibh_page_mask; /* page mask of current HCA */
- int ibh_mr_shift; /* bits shift of max MR size */
- __u64 ibh_mr_size; /* size of MR */
- struct ib_pd *ibh_pd; /* PD */
- struct kib_dev *ibh_dev; /* owner */
- atomic_t ibh_ref; /* refcount */
-};
-
-/** # of seconds to keep pool alive */
-#define IBLND_POOL_DEADLINE 300
-/** # of seconds to retry if allocation failed */
-#define IBLND_POOL_RETRY 1
-
-struct kib_pages {
- int ibp_npages; /* # pages */
- struct page *ibp_pages[0]; /* page array */
-};
-
-struct kib_pool;
-struct kib_poolset;
-
-typedef int (*kib_ps_pool_create_t)(struct kib_poolset *ps,
- int inc, struct kib_pool **pp_po);
-typedef void (*kib_ps_pool_destroy_t)(struct kib_pool *po);
-typedef void (*kib_ps_node_init_t)(struct kib_pool *po, struct list_head *node);
-typedef void (*kib_ps_node_fini_t)(struct kib_pool *po, struct list_head *node);
-
-struct kib_net;
-
-#define IBLND_POOL_NAME_LEN 32
-
-struct kib_poolset {
- spinlock_t ps_lock; /* serialize */
- struct kib_net *ps_net; /* network it belongs to */
- char ps_name[IBLND_POOL_NAME_LEN]; /* pool set name */
- struct list_head ps_pool_list; /* list of pools */
- struct list_head ps_failed_pool_list;/* failed pool list */
- unsigned long ps_next_retry; /* time stamp for retry if */
- /* failed to allocate */
- int ps_increasing; /* is allocating new pool */
- int ps_pool_size; /* new pool size */
- int ps_cpt; /* CPT id */
-
- kib_ps_pool_create_t ps_pool_create; /* create a new pool */
- kib_ps_pool_destroy_t ps_pool_destroy; /* destroy a pool */
- kib_ps_node_init_t ps_node_init; /* initialize new allocated node */
- kib_ps_node_fini_t ps_node_fini; /* finalize node */
-};
-
-struct kib_pool {
- struct list_head po_list; /* chain on pool list */
- struct list_head po_free_list; /* pre-allocated node */
- struct kib_poolset *po_owner; /* pool_set of this pool */
- unsigned long po_deadline; /* deadline of this pool */
- int po_allocated; /* # of elements in use */
- int po_failed; /* pool is created on failed HCA */
- int po_size; /* # of pre-allocated elements */
-};
-
-struct kib_tx_poolset {
- struct kib_poolset tps_poolset; /* pool-set */
- __u64 tps_next_tx_cookie; /* cookie of TX */
-};
-
-struct kib_tx_pool {
- struct kib_pool tpo_pool; /* pool */
- struct kib_hca_dev *tpo_hdev; /* device for this pool */
- struct kib_tx *tpo_tx_descs; /* all the tx descriptors */
- struct kib_pages *tpo_tx_pages; /* premapped tx msg pages */
-};
-
-struct kib_fmr_poolset {
- spinlock_t fps_lock; /* serialize */
- struct kib_net *fps_net; /* IB network */
- struct list_head fps_pool_list; /* FMR pool list */
- struct list_head fps_failed_pool_list;/* FMR pool list */
- __u64 fps_version; /* validity stamp */
- int fps_cpt; /* CPT id */
- int fps_pool_size;
- int fps_flush_trigger;
- int fps_cache;
- int fps_increasing; /* is allocating new pool */
- unsigned long fps_next_retry; /* time stamp for retry if*/
- /* failed to allocate */
-};
-
-struct kib_fast_reg_descriptor { /* For fast registration */
- struct list_head frd_list;
- struct ib_send_wr frd_inv_wr;
- struct ib_reg_wr frd_fastreg_wr;
- struct ib_mr *frd_mr;
- bool frd_valid;
-};
-
-struct kib_fmr_pool {
- struct list_head fpo_list; /* chain on pool list */
- struct kib_hca_dev *fpo_hdev; /* device for this pool */
- struct kib_fmr_poolset *fpo_owner; /* owner of this pool */
- union {
- struct {
- struct ib_fmr_pool *fpo_fmr_pool; /* IB FMR pool */
- } fmr;
- struct { /* For fast registration */
- struct list_head fpo_pool_list;
- int fpo_pool_size;
- } fast_reg;
- };
- unsigned long fpo_deadline; /* deadline of this pool */
- int fpo_failed; /* fmr pool is failed */
- int fpo_map_count; /* # of mapped FMR */
- int fpo_is_fmr;
-};
-
-struct kib_fmr {
- struct kib_fmr_pool *fmr_pool; /* pool of FMR */
- struct ib_pool_fmr *fmr_pfmr; /* IB pool fmr */
- struct kib_fast_reg_descriptor *fmr_frd;
- u32 fmr_key;
-};
-
-struct kib_net {
- struct list_head ibn_list; /* chain on struct kib_dev::ibd_nets */
- __u64 ibn_incarnation;/* my epoch */
- int ibn_init; /* initialisation state */
- int ibn_shutdown; /* shutting down? */
-
- atomic_t ibn_npeers; /* # peers extant */
- atomic_t ibn_nconns; /* # connections extant */
-
- struct kib_tx_poolset **ibn_tx_ps; /* tx pool-set */
- struct kib_fmr_poolset **ibn_fmr_ps; /* fmr pool-set */
-
- struct kib_dev *ibn_dev; /* underlying IB device */
-};
-
-#define KIB_THREAD_SHIFT 16
-#define KIB_THREAD_ID(cpt, tid) ((cpt) << KIB_THREAD_SHIFT | (tid))
-#define KIB_THREAD_CPT(id) ((id) >> KIB_THREAD_SHIFT)
-#define KIB_THREAD_TID(id) ((id) & ((1UL << KIB_THREAD_SHIFT) - 1))
-
-struct kib_sched_info {
- spinlock_t ibs_lock; /* serialise */
- wait_queue_head_t ibs_waitq; /* schedulers sleep here */
- struct list_head ibs_conns; /* conns to check for rx completions */
- int ibs_nthreads; /* number of scheduler threads */
- int ibs_nthreads_max; /* max allowed scheduler threads */
- int ibs_cpt; /* CPT id */
-};
-
-struct kib_data {
- int kib_init; /* initialisation state */
- int kib_shutdown; /* shut down? */
- struct list_head kib_devs; /* IB devices extant */
- struct list_head kib_failed_devs; /* list head of failed devices */
- wait_queue_head_t kib_failover_waitq; /* schedulers sleep here */
- atomic_t kib_nthreads; /* # live threads */
- rwlock_t kib_global_lock; /* stabilize net/dev/peer/conn ops */
- struct list_head *kib_peers; /* hash table of all my known peers */
- int kib_peer_hash_size; /* size of kib_peers */
- void *kib_connd; /* the connd task (serialisation assertions) */
- struct list_head kib_connd_conns; /* connections to setup/teardown */
- struct list_head kib_connd_zombies; /* connections with zero refcount */
- /* connections to reconnect */
- struct list_head kib_reconn_list;
- /* peers wait for reconnection */
- struct list_head kib_reconn_wait;
- /**
- * The second that peers are pulled out from \a kib_reconn_wait
- * for reconnection.
- */
- time64_t kib_reconn_sec;
-
- wait_queue_head_t kib_connd_waitq; /* connection daemon sleeps here */
- spinlock_t kib_connd_lock; /* serialise */
- struct ib_qp_attr kib_error_qpa; /* QP->ERROR */
- struct kib_sched_info **kib_scheds; /* percpt data for schedulers */
-};
-
-#define IBLND_INIT_NOTHING 0
-#define IBLND_INIT_DATA 1
-#define IBLND_INIT_ALL 2
-
-/************************************************************************
- * IB Wire message format.
- * These are sent in sender's byte order (i.e. receiver flips).
- */
-
-struct kib_connparams {
- __u16 ibcp_queue_depth;
- __u16 ibcp_max_frags;
- __u32 ibcp_max_msg_size;
-} WIRE_ATTR;
-
-struct kib_immediate_msg {
- struct lnet_hdr ibim_hdr; /* portals header */
- char ibim_payload[0]; /* piggy-backed payload */
-} WIRE_ATTR;
-
-struct kib_rdma_frag {
- __u32 rf_nob; /* # bytes this frag */
- __u64 rf_addr; /* CAVEAT EMPTOR: misaligned!! */
-} WIRE_ATTR;
-
-struct kib_rdma_desc {
- __u32 rd_key; /* local/remote key */
- __u32 rd_nfrags; /* # fragments */
- struct kib_rdma_frag rd_frags[0]; /* buffer frags */
-} WIRE_ATTR;
-
-struct kib_putreq_msg {
- struct lnet_hdr ibprm_hdr; /* portals header */
- __u64 ibprm_cookie; /* opaque completion cookie */
-} WIRE_ATTR;
-
-struct kib_putack_msg {
- __u64 ibpam_src_cookie; /* reflected completion cookie */
- __u64 ibpam_dst_cookie; /* opaque completion cookie */
- struct kib_rdma_desc ibpam_rd; /* sender's sink buffer */
-} WIRE_ATTR;
-
-struct kib_get_msg {
- struct lnet_hdr ibgm_hdr; /* portals header */
- __u64 ibgm_cookie; /* opaque completion cookie */
- struct kib_rdma_desc ibgm_rd; /* rdma descriptor */
-} WIRE_ATTR;
-
-struct kib_completion_msg {
- __u64 ibcm_cookie; /* opaque completion cookie */
- __s32 ibcm_status; /* < 0 failure: >= 0 length */
-} WIRE_ATTR;
-
-struct kib_msg {
- /* First 2 fields fixed FOR ALL TIME */
- __u32 ibm_magic; /* I'm an ibnal message */
- __u16 ibm_version; /* this is my version number */
-
- __u8 ibm_type; /* msg type */
- __u8 ibm_credits; /* returned credits */
- __u32 ibm_nob; /* # bytes in whole message */
- __u32 ibm_cksum; /* checksum (0 == no checksum) */
- __u64 ibm_srcnid; /* sender's NID */
- __u64 ibm_srcstamp; /* sender's incarnation */
- __u64 ibm_dstnid; /* destination's NID */
- __u64 ibm_dststamp; /* destination's incarnation */
-
- union {
- struct kib_connparams connparams;
- struct kib_immediate_msg immediate;
- struct kib_putreq_msg putreq;
- struct kib_putack_msg putack;
- struct kib_get_msg get;
- struct kib_completion_msg completion;
- } WIRE_ATTR ibm_u;
-} WIRE_ATTR;
-
-#define IBLND_MSG_MAGIC LNET_PROTO_IB_MAGIC /* unique magic */
-
-#define IBLND_MSG_VERSION_1 0x11
-#define IBLND_MSG_VERSION_2 0x12
-#define IBLND_MSG_VERSION IBLND_MSG_VERSION_2
-
-#define IBLND_MSG_CONNREQ 0xc0 /* connection request */
-#define IBLND_MSG_CONNACK 0xc1 /* connection acknowledge */
-#define IBLND_MSG_NOOP 0xd0 /* nothing (just credits) */
-#define IBLND_MSG_IMMEDIATE 0xd1 /* immediate */
-#define IBLND_MSG_PUT_REQ 0xd2 /* putreq (src->sink) */
-#define IBLND_MSG_PUT_NAK 0xd3 /* completion (sink->src) */
-#define IBLND_MSG_PUT_ACK 0xd4 /* putack (sink->src) */
-#define IBLND_MSG_PUT_DONE 0xd5 /* completion (src->sink) */
-#define IBLND_MSG_GET_REQ 0xd6 /* getreq (sink->src) */
-#define IBLND_MSG_GET_DONE 0xd7 /* completion (src->sink: all OK) */
-
-struct kib_rej {
- __u32 ibr_magic; /* sender's magic */
- __u16 ibr_version; /* sender's version */
- __u8 ibr_why; /* reject reason */
- __u8 ibr_padding; /* padding */
- __u64 ibr_incarnation; /* incarnation of peer */
- struct kib_connparams ibr_cp; /* connection parameters */
-} WIRE_ATTR;
-
-/* connection rejection reasons */
-#define IBLND_REJECT_CONN_RACE 1 /* You lost connection race */
-#define IBLND_REJECT_NO_RESOURCES 2 /* Out of memory/conns etc */
-#define IBLND_REJECT_FATAL 3 /* Anything else */
-#define IBLND_REJECT_CONN_UNCOMPAT 4 /* incompatible version peer */
-#define IBLND_REJECT_CONN_STALE 5 /* stale peer */
-/* peer's rdma frags doesn't match mine */
-#define IBLND_REJECT_RDMA_FRAGS 6
-/* peer's msg queue size doesn't match mine */
-#define IBLND_REJECT_MSG_QUEUE_SIZE 7
-
-/***********************************************************************/
-
-struct kib_rx { /* receive message */
- struct list_head rx_list; /* queue for attention */
- struct kib_conn *rx_conn; /* owning conn */
- int rx_nob; /* # bytes received (-1 while posted) */
- enum ib_wc_status rx_status; /* completion status */
- struct kib_msg *rx_msg; /* message buffer (host vaddr) */
- __u64 rx_msgaddr; /* message buffer (I/O addr) */
- DECLARE_PCI_UNMAP_ADDR(rx_msgunmap); /* for dma_unmap_single() */
- struct ib_recv_wr rx_wrq; /* receive work item... */
- struct ib_sge rx_sge; /* ...and its memory */
-};
-
-#define IBLND_POSTRX_DONT_POST 0 /* don't post */
-#define IBLND_POSTRX_NO_CREDIT 1 /* post: no credits */
-#define IBLND_POSTRX_PEER_CREDIT 2 /* post: give peer back 1 credit */
-#define IBLND_POSTRX_RSRVD_CREDIT 3 /* post: give self back 1 reserved credit */
-
-struct kib_tx { /* transmit message */
- struct list_head tx_list; /* queue on idle_txs ibc_tx_queue etc. */
- struct kib_tx_pool *tx_pool; /* pool I'm from */
- struct kib_conn *tx_conn; /* owning conn */
- short tx_sending; /* # tx callbacks outstanding */
- short tx_queued; /* queued for sending */
- short tx_waiting; /* waiting for peer */
- int tx_status; /* LNET completion status */
- unsigned long tx_deadline; /* completion deadline */
- __u64 tx_cookie; /* completion cookie */
- struct lnet_msg *tx_lntmsg[2]; /* lnet msgs to finalize on completion */
- struct kib_msg *tx_msg; /* message buffer (host vaddr) */
- __u64 tx_msgaddr; /* message buffer (I/O addr) */
- DECLARE_PCI_UNMAP_ADDR(tx_msgunmap); /* for dma_unmap_single() */
- int tx_nwrq; /* # send work items */
- struct ib_rdma_wr *tx_wrq; /* send work items... */
- struct ib_sge *tx_sge; /* ...and their memory */
- struct kib_rdma_desc *tx_rd; /* rdma descriptor */
- int tx_nfrags; /* # entries in... */
- struct scatterlist *tx_frags; /* dma_map_sg descriptor */
- __u64 *tx_pages; /* rdma phys page addrs */
- struct kib_fmr fmr; /* FMR */
- int tx_dmadir; /* dma direction */
-};
-
-struct kib_connvars {
- struct kib_msg cv_msg; /* connection-in-progress variables */
-};
-
-struct kib_conn {
- struct kib_sched_info *ibc_sched; /* scheduler information */
- struct kib_peer *ibc_peer; /* owning peer */
- struct kib_hca_dev *ibc_hdev; /* HCA bound on */
- struct list_head ibc_list; /* stash on peer's conn list */
- struct list_head ibc_sched_list; /* schedule for attention */
- __u16 ibc_version; /* version of connection */
- /* reconnect later */
- __u16 ibc_reconnect:1;
- __u64 ibc_incarnation; /* which instance of the peer */
- atomic_t ibc_refcount; /* # users */
- int ibc_state; /* what's happening */
- int ibc_nsends_posted; /* # uncompleted sends */
- int ibc_noops_posted; /* # uncompleted NOOPs */
- int ibc_credits; /* # credits I have */
- int ibc_outstanding_credits; /* # credits to return */
- int ibc_reserved_credits; /* # ACK/DONE msg credits */
- int ibc_comms_error; /* set on comms error */
- /* connections queue depth */
- __u16 ibc_queue_depth;
- /* connections max frags */
- __u16 ibc_max_frags;
- unsigned int ibc_nrx:16; /* receive buffers owned */
- unsigned int ibc_scheduled:1; /* scheduled for attention */
- unsigned int ibc_ready:1; /* CQ callback fired */
- unsigned long ibc_last_send; /* time of last send */
- struct list_head ibc_connd_list; /* link chain for */
- /* kiblnd_check_conns only */
- struct list_head ibc_early_rxs; /* rxs completed before ESTABLISHED */
- struct list_head ibc_tx_noops; /* IBLND_MSG_NOOPs for */
- /* IBLND_MSG_VERSION_1 */
- struct list_head ibc_tx_queue; /* sends that need a credit */
- struct list_head ibc_tx_queue_nocred; /* sends that don't need a */
- /* credit */
- struct list_head ibc_tx_queue_rsrvd; /* sends that need to */
- /* reserve an ACK/DONE msg */
- struct list_head ibc_active_txs; /* active tx awaiting completion */
- spinlock_t ibc_lock; /* serialise */
- struct kib_rx *ibc_rxs; /* the rx descs */
- struct kib_pages *ibc_rx_pages; /* premapped rx msg pages */
-
- struct rdma_cm_id *ibc_cmid; /* CM id */
- struct ib_cq *ibc_cq; /* completion queue */
-
- struct kib_connvars *ibc_connvars; /* in-progress connection state */
-};
-
-#define IBLND_CONN_INIT 0 /* being initialised */
-#define IBLND_CONN_ACTIVE_CONNECT 1 /* active sending req */
-#define IBLND_CONN_PASSIVE_WAIT 2 /* passive waiting for rtu */
-#define IBLND_CONN_ESTABLISHED 3 /* connection established */
-#define IBLND_CONN_CLOSING 4 /* being closed */
-#define IBLND_CONN_DISCONNECTED 5 /* disconnected */
-
-struct kib_peer {
- struct list_head ibp_list; /* stash on global peer list */
- lnet_nid_t ibp_nid; /* who's on the other end(s) */
- struct lnet_ni *ibp_ni; /* LNet interface */
- struct list_head ibp_conns; /* all active connections */
- struct kib_conn *ibp_next_conn; /* next connection to send on for
- * round robin */
- struct list_head ibp_tx_queue; /* msgs waiting for a conn */
- __u64 ibp_incarnation; /* incarnation of peer */
- /* when (in jiffies) I was last alive */
- unsigned long ibp_last_alive;
- /* # users */
- atomic_t ibp_refcount;
- /* version of peer */
- __u16 ibp_version;
- /* current passive connection attempts */
- unsigned short ibp_accepting;
- /* current active connection attempts */
- unsigned short ibp_connecting;
- /* reconnect this peer later */
- unsigned char ibp_reconnecting;
- /* counter of how many times we triggered a conn race */
- unsigned char ibp_races;
- /* # consecutive reconnection attempts to this peer */
- unsigned int ibp_reconnected;
- /* errno on closing this peer */
- int ibp_error;
- /* max map_on_demand */
- __u16 ibp_max_frags;
- /* max_peer_credits */
- __u16 ibp_queue_depth;
-};
-
-extern struct kib_data kiblnd_data;
-
-void kiblnd_hdev_destroy(struct kib_hca_dev *hdev);
-
-int kiblnd_msg_queue_size(int version, struct lnet_ni *ni);
-
-/* max # of fragments configured by user */
-static inline int
-kiblnd_cfg_rdma_frags(struct lnet_ni *ni)
-{
- struct lnet_ioctl_config_o2iblnd_tunables *tunables;
- int mod;
-
- tunables = &ni->ni_lnd_tunables->lt_tun_u.lt_o2ib;
- mod = tunables->lnd_map_on_demand;
- return mod ? mod : IBLND_MAX_RDMA_FRAGS >> IBLND_FRAG_SHIFT;
-}
-
-static inline int
-kiblnd_rdma_frags(int version, struct lnet_ni *ni)
-{
- return version == IBLND_MSG_VERSION_1 ?
- (IBLND_MAX_RDMA_FRAGS >> IBLND_FRAG_SHIFT) :
- kiblnd_cfg_rdma_frags(ni);
-}
-
-static inline int
-kiblnd_concurrent_sends(int version, struct lnet_ni *ni)
-{
- struct lnet_ioctl_config_o2iblnd_tunables *tunables;
- int concurrent_sends;
-
- tunables = &ni->ni_lnd_tunables->lt_tun_u.lt_o2ib;
- concurrent_sends = tunables->lnd_concurrent_sends;
-
- if (version == IBLND_MSG_VERSION_1) {
- if (concurrent_sends > IBLND_MSG_QUEUE_SIZE_V1 * 2)
- return IBLND_MSG_QUEUE_SIZE_V1 * 2;
-
- if (concurrent_sends < IBLND_MSG_QUEUE_SIZE_V1 / 2)
- return IBLND_MSG_QUEUE_SIZE_V1 / 2;
- }
-
- return concurrent_sends;
-}
-
-static inline void
-kiblnd_hdev_addref_locked(struct kib_hca_dev *hdev)
-{
- LASSERT(atomic_read(&hdev->ibh_ref) > 0);
- atomic_inc(&hdev->ibh_ref);
-}
-
-static inline void
-kiblnd_hdev_decref(struct kib_hca_dev *hdev)
-{
- LASSERT(atomic_read(&hdev->ibh_ref) > 0);
- if (atomic_dec_and_test(&hdev->ibh_ref))
- kiblnd_hdev_destroy(hdev);
-}
-
-static inline int
-kiblnd_dev_can_failover(struct kib_dev *dev)
-{
- if (!list_empty(&dev->ibd_fail_list)) /* already scheduled */
- return 0;
-
- if (!*kiblnd_tunables.kib_dev_failover) /* disabled */
- return 0;
-
- if (*kiblnd_tunables.kib_dev_failover > 1) /* force failover */
- return 1;
-
- return dev->ibd_can_failover;
-}
-
-#define kiblnd_conn_addref(conn) \
-do { \
- CDEBUG(D_NET, "conn[%p] (%d)++\n", \
- (conn), atomic_read(&(conn)->ibc_refcount)); \
- atomic_inc(&(conn)->ibc_refcount); \
-} while (0)
-
-#define kiblnd_conn_decref(conn) \
-do { \
- unsigned long flags; \
- \
- CDEBUG(D_NET, "conn[%p] (%d)--\n", \
- (conn), atomic_read(&(conn)->ibc_refcount)); \
- LASSERT_ATOMIC_POS(&(conn)->ibc_refcount); \
- if (atomic_dec_and_test(&(conn)->ibc_refcount)) { \
- spin_lock_irqsave(&kiblnd_data.kib_connd_lock, flags); \
- list_add_tail(&(conn)->ibc_list, \
- &kiblnd_data.kib_connd_zombies); \
- wake_up(&kiblnd_data.kib_connd_waitq); \
- spin_unlock_irqrestore(&kiblnd_data.kib_connd_lock, flags);\
- } \
-} while (0)
-
-#define kiblnd_peer_addref(peer) \
-do { \
- CDEBUG(D_NET, "peer[%p] -> %s (%d)++\n", \
- (peer), libcfs_nid2str((peer)->ibp_nid), \
- atomic_read(&(peer)->ibp_refcount)); \
- atomic_inc(&(peer)->ibp_refcount); \
-} while (0)
-
-#define kiblnd_peer_decref(peer) \
-do { \
- CDEBUG(D_NET, "peer[%p] -> %s (%d)--\n", \
- (peer), libcfs_nid2str((peer)->ibp_nid), \
- atomic_read(&(peer)->ibp_refcount)); \
- LASSERT_ATOMIC_POS(&(peer)->ibp_refcount); \
- if (atomic_dec_and_test(&(peer)->ibp_refcount)) \
- kiblnd_destroy_peer(peer); \
-} while (0)
-
-static inline bool
-kiblnd_peer_connecting(struct kib_peer *peer)
-{
- return peer->ibp_connecting ||
- peer->ibp_reconnecting ||
- peer->ibp_accepting;
-}
-
-static inline bool
-kiblnd_peer_idle(struct kib_peer *peer)
-{
- return !kiblnd_peer_connecting(peer) && list_empty(&peer->ibp_conns);
-}
-
-static inline struct list_head *
-kiblnd_nid2peerlist(lnet_nid_t nid)
-{
- unsigned int hash =
- ((unsigned int)nid) % kiblnd_data.kib_peer_hash_size;
-
- return &kiblnd_data.kib_peers[hash];
-}
-
-static inline int
-kiblnd_peer_active(struct kib_peer *peer)
-{
- /* Am I in the peer hash table? */
- return !list_empty(&peer->ibp_list);
-}
-
-static inline struct kib_conn *
-kiblnd_get_conn_locked(struct kib_peer *peer)
-{
- struct list_head *next;
-
- LASSERT(!list_empty(&peer->ibp_conns));
-
- /* Advance to next connection, be sure to skip the head node */
- if (!peer->ibp_next_conn ||
- peer->ibp_next_conn->ibc_list.next == &peer->ibp_conns)
- next = peer->ibp_conns.next;
- else
- next = peer->ibp_next_conn->ibc_list.next;
- peer->ibp_next_conn = list_entry(next, struct kib_conn, ibc_list);
-
- return peer->ibp_next_conn;
-}
-
-static inline int
-kiblnd_send_keepalive(struct kib_conn *conn)
-{
- return (*kiblnd_tunables.kib_keepalive > 0) &&
- time_after(jiffies, conn->ibc_last_send +
- msecs_to_jiffies(*kiblnd_tunables.kib_keepalive *
- MSEC_PER_SEC));
-}
-
-static inline int
-kiblnd_need_noop(struct kib_conn *conn)
-{
- struct lnet_ioctl_config_o2iblnd_tunables *tunables;
- struct lnet_ni *ni = conn->ibc_peer->ibp_ni;
-
- LASSERT(conn->ibc_state >= IBLND_CONN_ESTABLISHED);
- tunables = &ni->ni_lnd_tunables->lt_tun_u.lt_o2ib;
-
- if (conn->ibc_outstanding_credits <
- IBLND_CREDITS_HIGHWATER(tunables, conn->ibc_version) &&
- !kiblnd_send_keepalive(conn))
- return 0; /* No need to send NOOP */
-
- if (IBLND_OOB_CAPABLE(conn->ibc_version)) {
- if (!list_empty(&conn->ibc_tx_queue_nocred))
- return 0; /* NOOP can be piggybacked */
-
- /* No tx to piggyback NOOP onto or no credit to send a tx */
- return (list_empty(&conn->ibc_tx_queue) ||
- !conn->ibc_credits);
- }
-
- if (!list_empty(&conn->ibc_tx_noops) || /* NOOP already queued */
- !list_empty(&conn->ibc_tx_queue_nocred) || /* piggyback NOOP */
- !conn->ibc_credits) /* no credit */
- return 0;
-
- if (conn->ibc_credits == 1 && /* last credit reserved for */
- !conn->ibc_outstanding_credits) /* giving back credits */
- return 0;
-
- /* No tx to piggyback NOOP onto or no credit to send a tx */
- return (list_empty(&conn->ibc_tx_queue) || conn->ibc_credits == 1);
-}
-
-static inline void
-kiblnd_abort_receives(struct kib_conn *conn)
-{
- ib_modify_qp(conn->ibc_cmid->qp,
- &kiblnd_data.kib_error_qpa, IB_QP_STATE);
-}
-
-static inline const char *
-kiblnd_queue2str(struct kib_conn *conn, struct list_head *q)
-{
- if (q == &conn->ibc_tx_queue)
- return "tx_queue";
-
- if (q == &conn->ibc_tx_queue_rsrvd)
- return "tx_queue_rsrvd";
-
- if (q == &conn->ibc_tx_queue_nocred)
- return "tx_queue_nocred";
-
- if (q == &conn->ibc_active_txs)
- return "active_txs";
-
- LBUG();
- return NULL;
-}
-
-/* CAVEAT EMPTOR: We rely on descriptor alignment to allow us to use the */
-/* lowest bits of the work request id to stash the work item type. */
-
-#define IBLND_WID_INVAL 0
-#define IBLND_WID_TX 1
-#define IBLND_WID_RX 2
-#define IBLND_WID_RDMA 3
-#define IBLND_WID_MR 4
-#define IBLND_WID_MASK 7UL
-
-static inline __u64
-kiblnd_ptr2wreqid(void *ptr, int type)
-{
- unsigned long lptr = (unsigned long)ptr;
-
- LASSERT(!(lptr & IBLND_WID_MASK));
- LASSERT(!(type & ~IBLND_WID_MASK));
- return (__u64)(lptr | type);
-}
-
-static inline void *
-kiblnd_wreqid2ptr(__u64 wreqid)
-{
- return (void *)(((unsigned long)wreqid) & ~IBLND_WID_MASK);
-}
-
-static inline int
-kiblnd_wreqid2type(__u64 wreqid)
-{
- return wreqid & IBLND_WID_MASK;
-}
-
-static inline void
-kiblnd_set_conn_state(struct kib_conn *conn, int state)
-{
- conn->ibc_state = state;
- mb();
-}
-
-static inline void
-kiblnd_init_msg(struct kib_msg *msg, int type, int body_nob)
-{
- msg->ibm_type = type;
- msg->ibm_nob = offsetof(struct kib_msg, ibm_u) + body_nob;
-}
-
-static inline int
-kiblnd_rd_size(struct kib_rdma_desc *rd)
-{
- int i;
- int size;
-
- for (i = size = 0; i < rd->rd_nfrags; i++)
- size += rd->rd_frags[i].rf_nob;
-
- return size;
-}
-
-static inline __u64
-kiblnd_rd_frag_addr(struct kib_rdma_desc *rd, int index)
-{
- return rd->rd_frags[index].rf_addr;
-}
-
-static inline __u32
-kiblnd_rd_frag_size(struct kib_rdma_desc *rd, int index)
-{
- return rd->rd_frags[index].rf_nob;
-}
-
-static inline __u32
-kiblnd_rd_frag_key(struct kib_rdma_desc *rd, int index)
-{
- return rd->rd_key;
-}
-
-static inline int
-kiblnd_rd_consume_frag(struct kib_rdma_desc *rd, int index, __u32 nob)
-{
- if (nob < rd->rd_frags[index].rf_nob) {
- rd->rd_frags[index].rf_addr += nob;
- rd->rd_frags[index].rf_nob -= nob;
- } else {
- index++;
- }
-
- return index;
-}
-
-static inline int
-kiblnd_rd_msg_size(struct kib_rdma_desc *rd, int msgtype, int n)
-{
- LASSERT(msgtype == IBLND_MSG_GET_REQ ||
- msgtype == IBLND_MSG_PUT_ACK);
-
- return msgtype == IBLND_MSG_GET_REQ ?
- offsetof(struct kib_get_msg, ibgm_rd.rd_frags[n]) :
- offsetof(struct kib_putack_msg, ibpam_rd.rd_frags[n]);
-}
-
-static inline __u64
-kiblnd_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
-{
- return ib_dma_mapping_error(dev, dma_addr);
-}
-
-static inline __u64 kiblnd_dma_map_single(struct ib_device *dev,
- void *msg, size_t size,
- enum dma_data_direction direction)
-{
- return ib_dma_map_single(dev, msg, size, direction);
-}
-
-static inline void kiblnd_dma_unmap_single(struct ib_device *dev,
- __u64 addr, size_t size,
- enum dma_data_direction direction)
-{
- ib_dma_unmap_single(dev, addr, size, direction);
-}
-
-#define KIBLND_UNMAP_ADDR_SET(p, m, a) do {} while (0)
-#define KIBLND_UNMAP_ADDR(p, m, a) (a)
-
-static inline int kiblnd_dma_map_sg(struct ib_device *dev,
- struct scatterlist *sg, int nents,
- enum dma_data_direction direction)
-{
- return ib_dma_map_sg(dev, sg, nents, direction);
-}
-
-static inline void kiblnd_dma_unmap_sg(struct ib_device *dev,
- struct scatterlist *sg, int nents,
- enum dma_data_direction direction)
-{
- ib_dma_unmap_sg(dev, sg, nents, direction);
-}
-
-static inline __u64 kiblnd_sg_dma_address(struct ib_device *dev,
- struct scatterlist *sg)
-{
- return ib_sg_dma_address(dev, sg);
-}
-
-static inline unsigned int kiblnd_sg_dma_len(struct ib_device *dev,
- struct scatterlist *sg)
-{
- return ib_sg_dma_len(dev, sg);
-}
-
-/* XXX We use KIBLND_CONN_PARAM(e) as writable buffer, it's not strictly */
-/* right because OFED1.2 defines it as const, to use it we have to add */
-/* (void *) cast to overcome "const" */
-
-#define KIBLND_CONN_PARAM(e) ((e)->param.conn.private_data)
-#define KIBLND_CONN_PARAM_LEN(e) ((e)->param.conn.private_data_len)
-
-void kiblnd_map_rx_descs(struct kib_conn *conn);
-void kiblnd_unmap_rx_descs(struct kib_conn *conn);
-void kiblnd_pool_free_node(struct kib_pool *pool, struct list_head *node);
-struct list_head *kiblnd_pool_alloc_node(struct kib_poolset *ps);
-
-int kiblnd_fmr_pool_map(struct kib_fmr_poolset *fps, struct kib_tx *tx,
- struct kib_rdma_desc *rd, __u32 nob, __u64 iov,
- struct kib_fmr *fmr);
-void kiblnd_fmr_pool_unmap(struct kib_fmr *fmr, int status);
-
-int kiblnd_tunables_setup(struct lnet_ni *ni);
-void kiblnd_tunables_init(void);
-
-int kiblnd_connd(void *arg);
-int kiblnd_scheduler(void *arg);
-int kiblnd_thread_start(int (*fn)(void *arg), void *arg, char *name);
-int kiblnd_failover_thread(void *arg);
-
-int kiblnd_alloc_pages(struct kib_pages **pp, int cpt, int npages);
-
-int kiblnd_cm_callback(struct rdma_cm_id *cmid,
- struct rdma_cm_event *event);
-int kiblnd_translate_mtu(int value);
-
-int kiblnd_dev_failover(struct kib_dev *dev);
-int kiblnd_create_peer(struct lnet_ni *ni, struct kib_peer **peerp,
- lnet_nid_t nid);
-void kiblnd_destroy_peer(struct kib_peer *peer);
-bool kiblnd_reconnect_peer(struct kib_peer *peer);
-void kiblnd_destroy_dev(struct kib_dev *dev);
-void kiblnd_unlink_peer_locked(struct kib_peer *peer);
-struct kib_peer *kiblnd_find_peer_locked(lnet_nid_t nid);
-int kiblnd_close_stale_conns_locked(struct kib_peer *peer,
- int version, __u64 incarnation);
-int kiblnd_close_peer_conns_locked(struct kib_peer *peer, int why);
-
-struct kib_conn *kiblnd_create_conn(struct kib_peer *peer,
- struct rdma_cm_id *cmid,
- int state, int version);
-void kiblnd_destroy_conn(struct kib_conn *conn);
-void kiblnd_close_conn(struct kib_conn *conn, int error);
-void kiblnd_close_conn_locked(struct kib_conn *conn, int error);
-
-void kiblnd_launch_tx(struct lnet_ni *ni, struct kib_tx *tx, lnet_nid_t nid);
-void kiblnd_txlist_done(struct lnet_ni *ni, struct list_head *txlist,
- int status);
-
-void kiblnd_qp_event(struct ib_event *event, void *arg);
-void kiblnd_cq_event(struct ib_event *event, void *arg);
-void kiblnd_cq_completion(struct ib_cq *cq, void *arg);
-
-void kiblnd_pack_msg(struct lnet_ni *ni, struct kib_msg *msg, int version,
- int credits, lnet_nid_t dstnid, __u64 dststamp);
-int kiblnd_unpack_msg(struct kib_msg *msg, int nob);
-int kiblnd_post_rx(struct kib_rx *rx, int credit);
-
-int kiblnd_send(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg);
-int kiblnd_recv(struct lnet_ni *ni, void *private, struct lnet_msg *lntmsg,
- int delayed, struct iov_iter *to, unsigned int rlen);
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
deleted file mode 100644
index 65b7a62943ad..000000000000
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c
+++ /dev/null
@@ -1,3763 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see
- * http://www.gnu.org/licenses/gpl-2.0.html
- *
- * GPL HEADER END
- */
-/*
- * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
- * Use is subject to license terms.
- *
- * Copyright (c) 2012, 2015, Intel Corporation.
- */
-/*
- * This file is part of Lustre, http://www.lustre.org/
- * Lustre is a trademark of Sun Microsystems, Inc.
- *
- * lnet/klnds/o2iblnd/o2iblnd_cb.c
- *
- * Author: Eric Barton <eric@bartonsoftware.com>
- */
-
-#include <linux/highmem.h>
-#include "o2iblnd.h"
-
-#define MAX_CONN_RACES_BEFORE_ABORT 20
-
-static void kiblnd_peer_alive(struct kib_peer *peer);
-static void kiblnd_peer_connect_failed(struct kib_peer *peer, int active, int error);
-static void kiblnd_init_tx_msg(struct lnet_ni *ni, struct kib_tx *tx,
- int type, int body_nob);
-static int kiblnd_init_rdma(struct kib_conn *conn, struct kib_tx *tx, int type,
- int resid, struct kib_rdma_desc *dstrd,
- __u64 dstcookie);
-static void kiblnd_queue_tx_locked(struct kib_tx *tx, struct kib_conn *conn);
-static void kiblnd_queue_tx(struct kib_tx *tx, struct kib_conn *conn);
-static void kiblnd_unmap_tx(struct kib_tx *tx);
-static void kiblnd_check_sends_locked(struct kib_conn *conn);
-
-static void
-kiblnd_tx_done(struct lnet_ni *ni, struct kib_tx *tx)
-{
- struct lnet_msg *lntmsg[2];
- struct kib_net *net = ni->ni_data;
- int rc;
- int i;
-
- LASSERT(net);
- LASSERT(!in_interrupt());
- LASSERT(!tx->tx_queued); /* mustn't be queued for sending */
- LASSERT(!tx->tx_sending); /* mustn't be awaiting sent callback */
- LASSERT(!tx->tx_waiting); /* mustn't be awaiting peer response */
- LASSERT(tx->tx_pool);
-
- kiblnd_unmap_tx(tx);
-
- /* tx may have up to 2 lnet msgs to finalise */
- lntmsg[0] = tx->tx_lntmsg[0]; tx->tx_lntmsg[0] = NULL;
- lntmsg[1] = tx->tx_lntmsg[1]; tx->tx_lntmsg[1] = NULL;
- rc = tx->tx_status;
-
- if (tx->tx_conn) {
- LASSERT(ni == tx->tx_conn->ibc_peer->ibp_ni);
-
- kiblnd_conn_decref(tx->tx_conn);
- tx->tx_conn = NULL;
- }
-
- tx->tx_nwrq = 0;
- tx->tx_status = 0;
-
- kiblnd_pool_free_node(&tx->tx_pool->tpo_pool, &tx->tx_list);
-
- /* delay finalize until my descs have been freed */
- for (i = 0; i < 2; i++) {
- if (!lntmsg[i])
- continue;
-
- lnet_finalize(ni, lntmsg[i], rc);
- }
-}
-
-void
-kiblnd_txlist_done(struct lnet_ni *ni, struct list_head *txlist, int status)
-{
- struct kib_tx *tx;
-
- while (!list_empty(txlist)) {
- tx = list_entry(txlist->next, struct kib_tx, tx_list);
-
- list_del(&tx->tx_list);
- /* complete now */
- tx->tx_waiting = 0;
- tx->tx_status = status;
- kiblnd_tx_done(ni, tx);
- }
-}
-
-static struct kib_tx *
-kiblnd_get_idle_tx(struct lnet_ni *ni, lnet_nid_t target)
-{
- struct kib_net *net = (struct kib_net *)ni->ni_data;
- struct list_head *node;
- struct kib_tx *tx;
- struct kib_tx_poolset *tps;
-
- tps = net->ibn_tx_ps[lnet_cpt_of_nid(target)];
- node = kiblnd_pool_alloc_node(&tps->tps_poolset);
- if (!node)
- return NULL;
- tx = list_entry(node, struct kib_tx, tx_list);
-
- LASSERT(!tx->tx_nwrq);
- LASSERT(!tx->tx_queued);
- LASSERT(!tx->tx_sending);
- LASSERT(!tx->tx_waiting);
- LASSERT(!tx->tx_status);
- LASSERT(!tx->tx_conn);
- LASSERT(!tx->tx_lntmsg[0]);
- LASSERT(!tx->tx_lntmsg[1]);
- LASSERT(!tx->tx_nfrags);
-
- return tx;
-}
-
-static void
-kiblnd_drop_rx(struct kib_rx *rx)
-{
- struct kib_conn *conn = rx->rx_conn;
- struct kib_sched_info *sched = conn->ibc_sched;
- unsigned long flags;
-
- spin_lock_irqsave(&sched->ibs_lock, flags);
- LASSERT(conn->ibc_nrx > 0);
- conn->ibc_nrx--;
- spin_unlock_irqrestore(&sched->ibs_lock, flags);
-
- kiblnd_conn_decref(conn);
-}
-
-int
-kiblnd_post_rx(struct kib_rx *rx, int credit)
-{
- struct kib_conn *conn = rx->rx_conn;
- struct kib_net *net = conn->ibc_peer->ibp_ni->ni_data;
- struct ib_recv_wr *bad_wrq = NULL;
- int rc;
-
- LASSERT(net);
- LASSERT(!in_interrupt());
- LASSERT(credit == IBLND_POSTRX_NO_CREDIT ||
- credit == IBLND_POSTRX_PEER_CREDIT ||
- credit == IBLND_POSTRX_RSRVD_CREDIT);
-
- rx->rx_sge.lkey = conn->ibc_hdev->ibh_pd->local_dma_lkey;
- rx->rx_sge.addr = rx->rx_msgaddr;
- rx->rx_sge.length = IBLND_MSG_SIZE;
-
- rx->rx_wrq.next = NULL;
- rx->rx_wrq.sg_list = &rx->rx_sge;
- rx->rx_wrq.num_sge = 1;
- rx->rx_wrq.wr_id = kiblnd_ptr2wreqid(rx, IBLND_WID_RX);
-
- LASSERT(conn->ibc_state >= IBLND_CONN_INIT);
- LASSERT(rx->rx_nob >= 0); /* not posted */
-
- if (conn->ibc_state > IBLND_CONN_ESTABLISHED) {
- kiblnd_drop_rx(rx); /* No more posts for this rx */
- return 0;
- }
-
- rx->rx_nob = -1; /* flag posted */
-
- /* NB: need an extra reference after ib_post_recv because we don't
- * own this rx (and rx::rx_conn) anymore, LU-5678.
- */
- kiblnd_conn_addref(conn);
- rc = ib_post_recv(conn->ibc_cmid->qp, &rx->rx_wrq, &bad_wrq);
- if (unlikely(rc)) {
- CERROR("Can't post rx for %s: %d, bad_wrq: %p\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid), rc, bad_wrq);
- rx->rx_nob = 0;
- }
-
- if (conn->ibc_state < IBLND_CONN_ESTABLISHED) /* Initial post */
- goto out;
-
- if (unlikely(rc)) {
- kiblnd_close_conn(conn, rc);
- kiblnd_drop_rx(rx); /* No more posts for this rx */
- goto out;
- }
-
- if (credit == IBLND_POSTRX_NO_CREDIT)
- goto out;
-
- spin_lock(&conn->ibc_lock);
- if (credit == IBLND_POSTRX_PEER_CREDIT)
- conn->ibc_outstanding_credits++;
- else
- conn->ibc_reserved_credits++;
- kiblnd_check_sends_locked(conn);
- spin_unlock(&conn->ibc_lock);
-
-out:
- kiblnd_conn_decref(conn);
- return rc;
-}
-
-static struct kib_tx *
-kiblnd_find_waiting_tx_locked(struct kib_conn *conn, int txtype, __u64 cookie)
-{
- struct list_head *tmp;
-
- list_for_each(tmp, &conn->ibc_active_txs) {
- struct kib_tx *tx = list_entry(tmp, struct kib_tx, tx_list);
-
- LASSERT(!tx->tx_queued);
- LASSERT(tx->tx_sending || tx->tx_waiting);
-
- if (tx->tx_cookie != cookie)
- continue;
-
- if (tx->tx_waiting &&
- tx->tx_msg->ibm_type == txtype)
- return tx;
-
- CWARN("Bad completion: %swaiting, type %x (wanted %x)\n",
- tx->tx_waiting ? "" : "NOT ",
- tx->tx_msg->ibm_type, txtype);
- }
- return NULL;
-}
-
-static void
-kiblnd_handle_completion(struct kib_conn *conn, int txtype, int status, __u64 cookie)
-{
- struct kib_tx *tx;
- struct lnet_ni *ni = conn->ibc_peer->ibp_ni;
- int idle;
-
- spin_lock(&conn->ibc_lock);
-
- tx = kiblnd_find_waiting_tx_locked(conn, txtype, cookie);
- if (!tx) {
- spin_unlock(&conn->ibc_lock);
-
- CWARN("Unmatched completion type %x cookie %#llx from %s\n",
- txtype, cookie, libcfs_nid2str(conn->ibc_peer->ibp_nid));
- kiblnd_close_conn(conn, -EPROTO);
- return;
- }
-
- if (!tx->tx_status) { /* success so far */
- if (status < 0) /* failed? */
- tx->tx_status = status;
- else if (txtype == IBLND_MSG_GET_REQ)
- lnet_set_reply_msg_len(ni, tx->tx_lntmsg[1], status);
- }
-
- tx->tx_waiting = 0;
-
- idle = !tx->tx_queued && !tx->tx_sending;
- if (idle)
- list_del(&tx->tx_list);
-
- spin_unlock(&conn->ibc_lock);
-
- if (idle)
- kiblnd_tx_done(ni, tx);
-}
-
-static void
-kiblnd_send_completion(struct kib_conn *conn, int type, int status, __u64 cookie)
-{
- struct lnet_ni *ni = conn->ibc_peer->ibp_ni;
- struct kib_tx *tx = kiblnd_get_idle_tx(ni, conn->ibc_peer->ibp_nid);
-
- if (!tx) {
- CERROR("Can't get tx for completion %x for %s\n",
- type, libcfs_nid2str(conn->ibc_peer->ibp_nid));
- return;
- }
-
- tx->tx_msg->ibm_u.completion.ibcm_status = status;
- tx->tx_msg->ibm_u.completion.ibcm_cookie = cookie;
- kiblnd_init_tx_msg(ni, tx, type, sizeof(struct kib_completion_msg));
-
- kiblnd_queue_tx(tx, conn);
-}
-
-static void
-kiblnd_handle_rx(struct kib_rx *rx)
-{
- struct kib_msg *msg = rx->rx_msg;
- struct kib_conn *conn = rx->rx_conn;
- struct lnet_ni *ni = conn->ibc_peer->ibp_ni;
- int credits = msg->ibm_credits;
- struct kib_tx *tx;
- int rc = 0;
- int rc2;
- int post_credit;
-
- LASSERT(conn->ibc_state >= IBLND_CONN_ESTABLISHED);
-
- CDEBUG(D_NET, "Received %x[%d] from %s\n",
- msg->ibm_type, credits,
- libcfs_nid2str(conn->ibc_peer->ibp_nid));
-
- if (credits) {
- /* Have I received credits that will let me send? */
- spin_lock(&conn->ibc_lock);
-
- if (conn->ibc_credits + credits >
- conn->ibc_queue_depth) {
- rc2 = conn->ibc_credits;
- spin_unlock(&conn->ibc_lock);
-
- CERROR("Bad credits from %s: %d + %d > %d\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid),
- rc2, credits, conn->ibc_queue_depth);
-
- kiblnd_close_conn(conn, -EPROTO);
- kiblnd_post_rx(rx, IBLND_POSTRX_NO_CREDIT);
- return;
- }
-
- conn->ibc_credits += credits;
-
- /* This ensures the credit taken by NOOP can be returned */
- if (msg->ibm_type == IBLND_MSG_NOOP &&
- !IBLND_OOB_CAPABLE(conn->ibc_version)) /* v1 only */
- conn->ibc_outstanding_credits++;
-
- kiblnd_check_sends_locked(conn);
- spin_unlock(&conn->ibc_lock);
- }
-
- switch (msg->ibm_type) {
- default:
- CERROR("Bad IBLND message type %x from %s\n",
- msg->ibm_type, libcfs_nid2str(conn->ibc_peer->ibp_nid));
- post_credit = IBLND_POSTRX_NO_CREDIT;
- rc = -EPROTO;
- break;
-
- case IBLND_MSG_NOOP:
- if (IBLND_OOB_CAPABLE(conn->ibc_version)) {
- post_credit = IBLND_POSTRX_NO_CREDIT;
- break;
- }
-
- if (credits) /* credit already posted */
- post_credit = IBLND_POSTRX_NO_CREDIT;
- else /* a keepalive NOOP */
- post_credit = IBLND_POSTRX_PEER_CREDIT;
- break;
-
- case IBLND_MSG_IMMEDIATE:
- post_credit = IBLND_POSTRX_DONT_POST;
- rc = lnet_parse(ni, &msg->ibm_u.immediate.ibim_hdr,
- msg->ibm_srcnid, rx, 0);
- if (rc < 0) /* repost on error */
- post_credit = IBLND_POSTRX_PEER_CREDIT;
- break;
-
- case IBLND_MSG_PUT_REQ:
- post_credit = IBLND_POSTRX_DONT_POST;
- rc = lnet_parse(ni, &msg->ibm_u.putreq.ibprm_hdr,
- msg->ibm_srcnid, rx, 1);
- if (rc < 0) /* repost on error */
- post_credit = IBLND_POSTRX_PEER_CREDIT;
- break;
-
- case IBLND_MSG_PUT_NAK:
- CWARN("PUT_NACK from %s\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid));
- post_credit = IBLND_POSTRX_RSRVD_CREDIT;
- kiblnd_handle_completion(conn, IBLND_MSG_PUT_REQ,
- msg->ibm_u.completion.ibcm_status,
- msg->ibm_u.completion.ibcm_cookie);
- break;
-
- case IBLND_MSG_PUT_ACK:
- post_credit = IBLND_POSTRX_RSRVD_CREDIT;
-
- spin_lock(&conn->ibc_lock);
- tx = kiblnd_find_waiting_tx_locked(conn, IBLND_MSG_PUT_REQ,
- msg->ibm_u.putack.ibpam_src_cookie);
- if (tx)
- list_del(&tx->tx_list);
- spin_unlock(&conn->ibc_lock);
-
- if (!tx) {
- CERROR("Unmatched PUT_ACK from %s\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid));
- rc = -EPROTO;
- break;
- }
-
- LASSERT(tx->tx_waiting);
- /*
- * CAVEAT EMPTOR: I could be racing with tx_complete, but...
- * (a) I can overwrite tx_msg since my peer has received it!
- * (b) tx_waiting set tells tx_complete() it's not done.
- */
- tx->tx_nwrq = 0; /* overwrite PUT_REQ */
-
- rc2 = kiblnd_init_rdma(conn, tx, IBLND_MSG_PUT_DONE,
- kiblnd_rd_size(&msg->ibm_u.putack.ibpam_rd),
- &msg->ibm_u.putack.ibpam_rd,
- msg->ibm_u.putack.ibpam_dst_cookie);
- if (rc2 < 0)
- CERROR("Can't setup rdma for PUT to %s: %d\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid), rc2);
-
- spin_lock(&conn->ibc_lock);
- tx->tx_waiting = 0; /* clear waiting and queue atomically */
- kiblnd_queue_tx_locked(tx, conn);
- spin_unlock(&conn->ibc_lock);
- break;
-
- case IBLND_MSG_PUT_DONE:
- post_credit = IBLND_POSTRX_PEER_CREDIT;
- kiblnd_handle_completion(conn, IBLND_MSG_PUT_ACK,
- msg->ibm_u.completion.ibcm_status,
- msg->ibm_u.completion.ibcm_cookie);
- break;
-
- case IBLND_MSG_GET_REQ:
- post_credit = IBLND_POSTRX_DONT_POST;
- rc = lnet_parse(ni, &msg->ibm_u.get.ibgm_hdr,
- msg->ibm_srcnid, rx, 1);
- if (rc < 0) /* repost on error */
- post_credit = IBLND_POSTRX_PEER_CREDIT;
- break;
-
- case IBLND_MSG_GET_DONE:
- post_credit = IBLND_POSTRX_RSRVD_CREDIT;
- kiblnd_handle_completion(conn, IBLND_MSG_GET_REQ,
- msg->ibm_u.completion.ibcm_status,
- msg->ibm_u.completion.ibcm_cookie);
- break;
- }
-
- if (rc < 0) /* protocol error */
- kiblnd_close_conn(conn, rc);
-
- if (post_credit != IBLND_POSTRX_DONT_POST)
- kiblnd_post_rx(rx, post_credit);
-}
-
-static void
-kiblnd_rx_complete(struct kib_rx *rx, int status, int nob)
-{
- struct kib_msg *msg = rx->rx_msg;
- struct kib_conn *conn = rx->rx_conn;
- struct lnet_ni *ni = conn->ibc_peer->ibp_ni;
- struct kib_net *net = ni->ni_data;
- int rc;
- int err = -EIO;
-
- LASSERT(net);
- LASSERT(rx->rx_nob < 0); /* was posted */
- rx->rx_nob = 0; /* isn't now */
-
- if (conn->ibc_state > IBLND_CONN_ESTABLISHED)
- goto ignore;
-
- if (status != IB_WC_SUCCESS) {
- CNETERR("Rx from %s failed: %d\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid), status);
- goto failed;
- }
-
- LASSERT(nob >= 0);
- rx->rx_nob = nob;
-
- rc = kiblnd_unpack_msg(msg, rx->rx_nob);
- if (rc) {
- CERROR("Error %d unpacking rx from %s\n",
- rc, libcfs_nid2str(conn->ibc_peer->ibp_nid));
- goto failed;
- }
-
- if (msg->ibm_srcnid != conn->ibc_peer->ibp_nid ||
- msg->ibm_dstnid != ni->ni_nid ||
- msg->ibm_srcstamp != conn->ibc_incarnation ||
- msg->ibm_dststamp != net->ibn_incarnation) {
- CERROR("Stale rx from %s\n",
- libcfs_nid2str(conn->ibc_peer->ibp_nid));
- err = -ESTALE;
- goto failed;
- }
-
- /* set time last known alive */
- kiblnd_peer_alive(conn->ibc_peer);
-
- /* racing with connection establishment/teardown! */
-
- if (conn->ibc_state < IBLND_CONN_ESTABLISHED) {
- rwlock_t *g_lock = &kiblnd_data.kib_global_lock;
- unsigned long flags;
-
- write_lock_irqsave(g_lock, flags);
- /* must check holding global lock to eliminate race */
- if (conn->ibc_state < IBLND_CONN_ESTABLISHED) {
- list_add_tail(&rx->rx_list, &conn->ibc_early_rxs);
- write_unlock_irqrestore(g_lock, flags);
- return;
- }
- write_unlock_irqrestore(g_lock, flags);
- }
- kiblnd_handle_rx(rx);
- return;
-
- failed:
- CDEBUG(D_NET, "rx %p conn %p\n", rx, conn);
- kiblnd_close_conn(conn, err);
- ignore:
- kiblnd_drop_rx(rx); /* Don't re-post rx. */
-}
-
-static struct page *
-kiblnd_kvaddr_to_page(unsigned long vaddr)
-{
- struct page *page;
-
- if (is_vmalloc_addr((void *)vaddr)) {
- page = vmalloc_to_page((void *)vaddr);
- LASSERT(page);
- return page;
- }
-#ifdef CONFIG_HIGHMEM
- if (vaddr >= PKMAP_BASE &&
- vaddr < (PKMAP_BASE + LAST_PKMAP * PAGE_SIZE)) {
- /* No highmem pages only used for bulk (kiov) I/O */
- CERROR("find page for address in highmem\n");
- LBUG();
- }
-#endif
- page = virt_to_page(vaddr);
- LASSERT(page);
- return page;
-}
-
-static int
-kiblnd_fmr_map_tx(struct kib_net *net, struct kib_tx *tx, struct kib_rdma_desc *rd, __u32 nob)
-{
- struct kib_hca_dev *hdev;
- struct kib_fmr_poolset *fps;
- int cpt;
- int rc;
-
- LASSERT(tx->tx_pool);
- LASSERT(tx->tx_pool->tpo_pool.po_owner);
-
- hdev = tx->tx_pool->tpo_hdev;
- cpt = tx->tx_pool->tpo_pool.po_owner->ps_cpt;
-
- fps = net->ibn_fmr_ps[cpt];
- rc = kiblnd_fmr_pool_map(fps, tx, rd, nob, 0, &tx->fmr);
- if (rc) {
- CERROR("Can't map %u bytes: %d\n", nob, rc);
- return rc;
- }
-
- /*
- * If rd is not tx_rd, it's going to get sent to a peer, who will need
- * the rkey
- */
- rd->rd_key = tx->fmr.fmr_key;
- rd->rd_frags[0].rf_addr &= ~hdev->ibh_page_mask;
- rd->rd_frags[0].rf_nob = nob;
- rd->rd_nfrags = 1;
-
- return 0;
-}
-
-static void kiblnd_unmap_tx(struct kib_tx *tx)
-{
- if (tx->fmr.fmr_pfmr || tx->fmr.fmr_frd)
- kiblnd_fmr_pool_unmap(&tx->fmr, tx->tx_status);
-
- if (tx->tx_nfrags) {
- kiblnd_dma_unmap_sg(tx->tx_pool->tpo_hdev->ibh_ibdev,
- tx->tx_frags, tx->tx_nfrags, tx->tx_dmadir);
- tx->tx_nfrags = 0;
- }
-}
-
-static int kiblnd_map_tx(struct lnet_ni *ni, struct kib_tx *tx,
- struct kib_rdma_desc *rd, int nfrags)
-{
- struct kib_net *net = ni->ni_data;
- struct kib_hca_dev *hdev = net->ibn_dev->ibd_hdev;
- __u32 nob;
- int i;
-
- /*
- * If rd is not tx_rd, it's going to get sent to a peer and I'm the
- * RDMA sink
- */
- tx->tx_dmadir = (rd != tx->tx_rd) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
- tx->tx_nfrags = nfrags;
-
- rd->rd_nfrags = kiblnd_dma_map_sg(hdev->ibh_ibdev, tx->tx_frags,
- tx->tx_nfrags, tx->tx_dmadir);
-
- for (i = 0, nob = 0; i < rd->rd_nfrags; i++) {
- rd->rd_frags[i].rf_nob = kiblnd_sg_dma_len(
- hdev->ibh_ibdev, &tx->tx_frags[i]);
- rd->rd_frags[i].rf_addr = kiblnd_sg_dma_address(
- hdev->ibh_ibdev, &tx->tx_frags[i]);
- nob += rd->rd_frags[i].rf_nob;
- }
-
- if (net->ibn_fmr_ps)
- return kiblnd_fmr_map_tx(net, tx, rd, nob);
-
- return -EINVAL;
-}
-
-static int
-kiblnd_setup_rd_iov(struct lnet_ni *ni, struct kib_tx *tx,
- struct kib_rdma_desc *rd, unsigned int niov,
- const struct kvec *iov, int offset, int nob)
-{
- struct kib_net *net = ni->ni_data;
- struct page *page;
- struct scatterlist *sg;
- unsigned long vaddr;
- int fragnob;
- int page_offset;
-
- LASSERT(nob > 0);
- LASSERT(niov > 0);
- LASSERT(net);
-
- while (offset >= iov->iov_len) {
- offset -= iov->iov_len;
- niov--;
- iov++;
- LASSERT(niov > 0);
- }
-
- sg = tx->tx_frags;
- do {
- LASSERT(niov > 0);
-
- vaddr = ((unsigned long)iov->iov_base) + offset;
- page_offset = vaddr & (PAGE_SIZE - 1);
- page = kiblnd_kvaddr_to_page(vaddr);
- if (!page) {
- CERROR("Can't find page\n");
- return -EFAULT;
- }
-
- fragnob = min((int)(iov->iov_len - offset), nob);
- fragnob = min(fragnob, (int)PAGE_SIZE - page_offset);
-
- sg_set_page(sg, page, fragnob, page_offset);
- sg = sg_next(sg);
- if (!sg) {
- CERROR("lacking enough sg entries to map tx\n");
- return -EFAULT;
- }
-
- if (offset + fragnob < iov->iov_len) {
- offset += fragnob;
- } else {
- offset = 0;
- iov++;
- niov--;
- }
- nob -= fragnob;
- } while (nob > 0);
-
- return kiblnd_map_tx(ni, tx, rd, sg - tx->tx_frags);
-}