summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* tcm_fc: stop using se_tpg_fabric_ptrChristoph Hellwig2015-05-301-9/+8
| | | | | Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* tcm_loop: stop using se_tpg_fabric_ptrChristoph Hellwig2015-05-301-12/+11
| | | | | Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/iscsi: stop using se_tpg_fabric_ptrChristoph Hellwig2015-05-301-28/+15
| | | | | Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: handle odd SG mapping for data transfer memoryAkinobu Mita2015-05-301-39/+83
| | | | | | | | | | | | | | | | | | | | | | | | | | | | sbc_dif_generate() and sbc_dif_verify() currently assume that each SG element for data transfer memory doesn't straddle the block size boundary. However, when using SG_IO ioctl, we can choose the data transfer memory which doesn't satisfy that alignment requirement. In order to handle such cases correctly, this change inverts the outer loop to iterate data transfer memory and the inner loop to iterate protection information and enables to calculate CRC for a block which straddles multiple SG elements. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: "David S. Miller" <davem@davemloft.net> Cc: linux-crypto@vger.kernel.org Cc: Nicholas Bellinger <nab@linux-iscsi.org> Cc: Sagi Grimberg <sagig@mellanox.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: target-devel@vger.kernel.org Cc: linux-scsi@vger.kernel.org Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* lib: introduce crc_t10dif_update()Akinobu Mita2015-05-302-3/+10
| | | | | | | | | | | | | | | | | | | | | | | | This introduces crc_t10dif_update() which enables to calculate CRC for a block which straddles multiple SG elements by calling multiple times. This also converts crc_t10dif() to use crc_t10dif_update() as they are almost same. (remove extra function call in crc_t10dif() and crc_t10dif_update - Tim + Herbert) Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Acked-by: Martin K. Petersen <martin.petersen@oracle.com> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: "David S. Miller" <davem@davemloft.net> Cc: linux-crypto@vger.kernel.org Cc: Nicholas Bellinger <nab@linux-iscsi.org> Cc: Sagi Grimberg <sagig@mellanox.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: target-devel@vger.kernel.org Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: ensure se_cmd->t_prot_sg is allocated when requiredAkinobu Mita2015-05-302-12/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | Even if the device backend is initialized with protection info is enabled, some requests don't have the protection info attached for WRITE SAME command issued by block device helpers, WRITE command with WRPROTECT=0 by SG_IO ioctl, etc. So when TCM loopback fabric module is used, se_cmd->t_prot_sg is NULL for these requests and performing WRITE_INSERT of PI using software emulation by sbc_dif_generate() causes kernel crash. To fix this, introduce SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC for se_cmd_flags, which is used to determine that se_cmd->t_prot_sg needs to be allocated or use pre-allocated protection information by scsi mid-layer. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Nicholas Bellinger <nab@linux-iscsi.org> Cc: Sagi Grimberg <sagig@mellanox.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: target-devel@vger.kernel.org Cc: linux-scsi@vger.kernel.org Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Fix inconsistent address passed to kunmap_atomic() in ↵Akinobu Mita2015-05-301-2/+3
| | | | | | | | | | | | | | | | | | | sbc_dif_copy_prot() In sbc_dif_copy_prot(), the addresses passed to kunmap_atomic() are inconsistent with the addresses which are mapped by kmap_atomic(). That could be problematic if an SG element has its length larger than PAGE_SIZE as kunmap_atomic() will attempt to unmap different page. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Nicholas Bellinger <nab@linux-iscsi.org> Cc: Sagi Grimberg <sagig@mellanox.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: target-devel@vger.kernel.org Cc: linux-scsi@vger.kernel.org Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: move node ACL allocation to core codeChristoph Hellwig2015-05-3018-224/+18
| | | | | Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: refactor node ACL allocationChristoph Hellwig2015-05-301-77/+56
| | | | | | | | Split out two common helpers to share code for allocating and initializing node ACLs. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: refactor init/drop_nodeacl methodsChristoph Hellwig2015-05-3014-421/+77
| | | | | | | | | | | By always allocating and adding, respectively removing and freeing the se_node_acl structure in core code we can remove tons of repeated code in the init_nodeacl and drop_nodeacl routines. Additionally this now respects the get_default_queue_depth method in this code path as well. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: make the tpg_get_default_depth method optionalChristoph Hellwig2015-05-3011-62/+4
| | | | | | | | All fabric drivers except for iSCSI always return 1, so implement that as default behavior. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* vhost/scsi: remove struct vhost_scsi_naclChristoph Hellwig2015-05-301-31/+3
| | | | | | | | Except for the embedded struct se_node_acl none of the fields were ever used. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* sbp_target: remove struct sbp_naclChristoph Hellwig2015-05-302-30/+3
| | | | | | | | Except for the embedded struct se_node_acl none of the fields were ever used. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* tcm_usb: remove struct usbg_naclChristoph Hellwig2015-05-302-30/+3
| | | | | | | | Except for the embedded struct se_node_acl none of the fields were ever used. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* tcm_loop: remove struct tcm_loop_naclChristoph Hellwig2015-05-302-17/+2
| | | | | Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Remove first argument of target_{get,put}_sess_cmd()Bart Van Assche2015-05-3010-34/+33
| | | | | | | | | | | | | | The first argument of these two functions is always identical to se_cmd->se_sess. Hence remove the first argument. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Andy Grover <agrover@redhat.com> Cc: <qla2xxx-upstream@qlogic.com> Cc: Felipe Balbi <balbi@ti.com> Cc: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/user: Add support for bidirectional commandsIlias Tsitsimpis2015-05-302-6/+25
| | | | | | | | | | | | Enable TCMU to handle bidirectional SCSI commands. In such cases, entries in iov[] cover both the Data-In and the Data-Out buffers. The first iov_cnt entries correspond to the Data-Out buffer, while the remaining iov_bidi_cnt entries correspond to the Data-In buffer. Signed-off-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Vangelis Koukis <vkoukis@arrikto.com> Reviewed-by: Andy Grover <agrover@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/user: Refactor data area allocation codeIlias Tsitsimpis2015-05-301-83/+106
| | | | | | | | | | | | | Introduce alloc_and_scatter_data_area()/gather_and_free_data_area() functions that allocate/deallocate space from the data area and copy data to/from a given scatter-gather list. These functions are needed so the next patch, introducing support for bidirectional commands in TCMU, can use the same code path both for t_data_sg and for t_bidi_data_sg. Signed-off-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Vangelis Koukis <vkoukis@arrikto.com> Reviewed-by: Andy Grover <agrover@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/transport: Always initialize bidi fields in se_cmdIlias Tsitsimpis2015-05-301-4/+2
| | | | | | | | | | | | | | | | | | Fields t_bidi_data_sg and t_bidi_data_nents are set only in the presence of BIDI commands. This means that the underlying code (for example TCMU) cannot inspect them when the SCSI command is not a BIDI one. Ensure the code always initializes these fields with the given values, even when the SCSI command is not a BIDI one. Set t_bidi_data_sg to sgl_bidi (which should be NULL for non-BIDI commands) and t_bidi_data_nents to sgl_bidi_count (which should be 0 for non-BIDI commands). This allows the underlying code to use these fields unconditionally. Signed-off-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Vangelis Koukis <vkoukis@arrikto.com> Reviewed-by: Andy Grover <agrover@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/loop: Enable VARLEN CDB supportIlias Tsitsimpis2015-05-302-6/+1
| | | | | | | | | | | | | | | Field shost->max_cmd_len is used to inform Linux / the SCSI midlayer of the maximum CDB size an LLD is capable of handling. Set this field to SCSI_MAX_VARLEN_CDB_SIZE for target, to enable support for variable-sized CDBs (0x7E). Also remove the definition of TL_SCSI_MAX_CMD_LEN since it is now redundant. Signed-off-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Vangelis Koukis <vkoukis@arrikto.com> Reviewed-by: Andy Grover <agrover@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* driver/user: Don't warn for DMA_NONE data directionIlias Tsitsimpis2015-05-301-2/+3
| | | | | | | | | | | Some SCSI commands (for example the TEST UNIT READY command) do not carry data and so data_direction is DMA_NONE. Patch TCMU to not print a warning message about unknown data direction, when it is DMA_NONE. Signed-off-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Vangelis Koukis <vkoukis@arrikto.com> Reviewed-by: Andy Grover <agrover@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: fix DPO and FUA bit checksChristoph Hellwig2015-05-307-38/+40
| | | | | | | | | | | | | | | | | | | | | Drivers may override the WCE flag, in which case the DPOFUA flag in MODE SENSE might differ from the check used to reject invalid FUA bits in sbc_check_dpofua. Also now that we reject invalid FUA bits early there is no need to duplicate the same buggy check down in the fileio code. As the DPOFUA flag controls th support for FUA bits on read and write commands as well as DPO key off all the checks off a single helper, and deprecate the emulate_dpo and emulate_fua_read attributs. This fixes various failures in the libiscsi testsuite. Personally I'd prefer to also remove the emulate_fua_write attribute as there is no good reason to disable it, but I'll leave that for a separate discussion. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* iscsi-target: remove support for obsolete markersChristophe Vu-Brugier2015-05-3010-454/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Support for markers is currently broken because of a bug in iscsi_enforce_integrity_rules(): the "IFMarkInt_Reject" and "OFMarkInt_Reject" variables are always equal to 1 in iscsi_enforce_integrity_rules(). Moreover, fixed interval markers keys (IFMarker, OFMarker, IFMarkInt and OFMarkInt) are obsolete according to iSCSI RFC 7143: >From http://tools.ietf.org/html/rfc7143#section-13.25: 13.25. Obsoleted Keys This document obsoletes the following keys defined in [RFC3720]: IFMarker, OFMarker, OFMarkInt, and IFMarkInt. However, iSCSI implementations compliant to this document may still receive these obsoleted keys -- i.e., in a responder role -- in a text negotiation. When an IFMarker or OFMarker key is received, a compliant iSCSI implementation SHOULD respond with the constant "Reject" value. The implementation MAY alternatively respond with a "No" value. However, the implementation MUST NOT respond with a "NotUnderstood" value for either of these keys. When an IFMarkInt or OFMarkInt key is received, a compliant iSCSI implementation MUST respond with the constant "Reject" value. The implementation MUST NOT respond with a "NotUnderstood" value for either of these keys. This patch disables markers by turning the corresponding parameters to read-only. The default value of IFMarker and OFMarker remains "No" but the user cannot change it to "Yes" anymore. The new value of IFMarkInt and OFMarkInt is "Reject". (Drop left-over iscsi_get_value_from_number_range + make configfs parameters attrs R/W nops - nab) Signed-off-by: Christophe Vu-Brugier <cvubrugier@fastmail.fm> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/sbc: Fix sbc_dif_verify inconsistent map/unmapSagi Grimberg2015-05-301-14/+14
| | | | | | | | | Fix map/unmap consistency and get rid of a redundant local variable psg. Reported-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/file: Remove fd_prot bounce bufferSagi Grimberg2015-05-302-106/+28
| | | | | | | | | | | | | | | | | The reason this bounce buffer exists is to allow code reuse between rd_mcp and fileio in DIF mode. But the fact is, that this bounce is really not needed at all, we can simply call sbc_dif_verify on cmd->t_prot_sg and use it for file IO. This also removes fd_do_prot_rw as fd_do_rw was generalised to receive file pointer, block size (8 bytes for DIF data) and total data length. (Fix apply breakage from commit c836777 - nab) Tested-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Merge sbc_verify_dif_read|writeSagi Grimberg2015-05-305-112/+37
| | | | | | | | | | | | | | | | | | | | | | Instead of providing DIF verify routines for read/write that are almost identical and conditionally copy protection information, just let the caller do the right thing. Have a single sbc_dif_verify that handles an sgl (that does NOT copy any data) and a protection information copy routine used by rd_mcp and fileio backend. In the WRITE case, call sbc_dif_verify with cmd->t_prot_sg and then do the copy from it to local sgl (assuming the verify succeeded of course). In the READ case, call sbc_dif_verify with the local sgl and if it succeeds, copy it to t_prot_sg (or not if we are stripping it). (Fix apply breakage from commit c836777 - nab) Tested-by: Akinobu Mita <akinobu.mita@gmail.com> Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* iser-target: Fix error path in isert_create_pi_ctx()Roland Dreier2015-05-301-3/+3
| | | | | | | | | | | We don't assign pi_ctx to desc->pi_ctx until we're certain to succeed in the function. That means the cleanup path should use the local pi_ctx variable, not desc->pi_ctx. This was detected by Coverity (CID 1260062). Signed-off-by: Roland Dreier <roland@purestorage.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Use a PASSTHROUGH flag instead of transport_typesAndy Grover2015-05-3011-22/+17
| | | | | | | | | | It seems like we only care if a transport is passthrough or not. Convert transport_type to a flags field and replace TRANSPORT_PLUGIN_* with a flag, TRANSPORT_FLAG_PASSTHROUGH. Signed-off-by: Andy Grover <agrover@redhat.com> Reviewed-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Move passthrough CDB parsing into a common functionAndy Grover2015-05-304-94/+78
| | | | | | | | | | | Aside from whether they handle BIDI ops or not, parsing of the CDB by kernel and user SCSI passthrough modules should be identical. Move this into a new passthrough_parse_cdb() and call it from tcm-pscsi and tcm-user. Reported-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Andy Grover <agrover@redhat.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/user: Only support full command pass-throughAndy Grover2015-05-302-70/+75
| | | | | | | | | | | | | | | After much discussion, give up on only passing a subset of SCSI commands to userspace and pass them all. Based on what pscsi is doing, make sure to set SCF_SCSI_DATA_CDB for I/O ops, and define attributes identical to pscsi. Make hw_block_size configurable via dev param. Remove mention of command filtering from tcmu-design.txt. Signed-off-by: Andy Grover <agrover@redhat.com> Reviewed-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/user: Update example code for new ABI requirementsAndy Grover2015-05-301-2/+6
| | | | | | | | | | | We now require that the userspace handler set a bit if the command is not handled. Update calls to tcmu_hdr_get_op for v2. Signed-off-by: Andy Grover <agrover@redhat.com> Reviewed-by: Ilias Tsitsimpis <iliastsi@arrikto.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/pscsi: Don't leak scsi_host if hba is VIRTUAL_HOSTAndy Grover2015-05-302-0/+4
| | | | | | | | | | | | See https://bugzilla.redhat.com/show_bug.cgi?id=1025672 We need to put() the reference to the scsi host that we got in pscsi_configure_device(). In VIRTUAL_HOST mode it is associated with the dev_virt, not the hba_virt. Signed-off-by: Andy Grover <agrover@redhat.com> Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Fix se_tpg_tfo->tf_subsys regression + remove tf_subsystemChristoph Hellwig2015-05-308-64/+34
| | | | | | | | | | | | | | | | | There is just one configfs subsystem in the target code, so we might as well add two helpers to reference / unreference it from the core code instead of passing pointers to it around. This fixes a regression introduced for v4.1-rc1 with commit 9ac8928e6, where configfs_depend_item() callers using se_tpg_tfo->tf_subsys would fail, because the assignment from the original target_core_subsystem[] is no longer happening at target_register_template() time. (Fix target_core_exit_configfs pointer dereference - Sagi) Signed-off-by: Christoph Hellwig <hch@lst.de> Reported-by: Himanshu Madhani <himanshu.madhani@qlogic.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Drop signal_pending checks after interruptible lock acquireNicholas Bellinger2015-05-193-6/+3
| | | | | | | | | | | | | | | | Once upon a time, iscsit_get_tpg() was using an un-interruptible lock. The signal_pending() usage was a check to allow userspace to break out of the operation with SIGINT. AFAICT, there's no reason why this is necessary anymore, and as reported by Alexey can be potentially dangerous. Also, go ahead and drop the other two problematic cases within iscsit_access_np() and sbc_compare_and_write() as well. Found by Linux Driver Verification project (linuxtesting.org). Reported-by: Alexey Khoroshilov <khoroshilov@ispras.ru> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Add missing parenthesesBart Van Assche2015-05-141-2/+2
| | | | | | | | | | | | Code like " &= ~CMD_T_BUSY | ..." only clears CMD_T_BUSY but not the other flag. Modify these statements such that both flags are cleared. (Fix fuzz for target_write_prot_action code in mainline - nab) Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target: Fix bidi command handlingBart Van Assche2015-05-141-2/+1
| | | | | | | | | The function transport_complete_qf() must call either queue_data_in() or queue_status() but not both. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* target/user: Disallow full passthrough (pass_level=0)Andy Grover2015-05-022-76/+10
| | | | | | | | | | | | | | | | | | TCMU requires more work to correctly handle both user handlers that want all SCSI commands (pass_level=0) for a se_device, and also handlers that just want I/O commands and let the others be emulated by the kernel (pass_level=1). Only support the latter for now. For full passthrough, we will need to support a second se_subsystem_api template, due to configfs attributes being different between the two modes. Thus pass_level is extraneous, and we can remove it. The ABI break for TCMU v2 is already applied for this release, so it's best to do this now to avoid another ABI break in the future. Signed-off-by: Andy Grover <agrover@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* ISCSI: fix minor memory leakEvgenii Lepikhin2015-05-021-0/+1
| | | | | | | | This patch adds a missing kfree for sess->sess_ops memory upon transport_init_session() failure. Signed-off-by: Evgenii Lepikhin <johnlepikhin@gmail.com> Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* Linux 4.1-rc1v4.1-rc1Linus Torvalds2015-04-261-2/+2
|
* x86_64, asm: Work around AMD SYSRET SS descriptor attribute issueAndy Lutomirski2015-04-265-0/+48
| | | | | | | | | | | | | | | | | | | AMD CPUs don't reinitialize the SS descriptor on SYSRET, so SYSRET with SS == 0 results in an invalid usermode state in which SS is apparently equal to __USER_DS but causes #SS if used. Work around the issue by setting SS to __KERNEL_DS __switch_to, thus ensuring that SYSRET never happens with SS set to NULL. This was exposed by a recent vDSO cleanup. Fixes: e7d6eefaaa44 x86/vdso32/syscall.S: Do not load __USER32_DS to %ss Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Peter Anvin <hpa@zytor.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Denys Vlasenko <vda.linux@googlemail.com> Cc: Brian Gerst <brgerst@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linuxLinus Torvalds2015-04-265-14/+95
|\ | | | | | | | | | | | | | | | | Pull intel drm fixes from Dave Airlie. * 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: drm/i915: vlv: fix save/restore of GFX_MAX_REQ_COUNT reg drm/i915: Workaround to avoid lite restore with HEAD==TAIL drm/i915: cope with large i2c transfers
| * Merge tag 'drm-intel-next-fixes-2015-04-25' of ↵Dave Airlie2015-04-275-14/+95
| |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://anongit.freedesktop.org/drm-intel into drm-fixes three fixes for i915. * tag 'drm-intel-next-fixes-2015-04-25' of git://anongit.freedesktop.org/drm-intel: drm/i915: vlv: fix save/restore of GFX_MAX_REQ_COUNT reg drm/i915: Workaround to avoid lite restore with HEAD==TAIL drm/i915: cope with large i2c transfers
| | * drm/i915: vlv: fix save/restore of GFX_MAX_REQ_COUNT regImre Deak2015-04-241-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Due this typo we don't save/restore the GFX_MAX_REQ_COUNT register across suspend/resume, so fix this. This was introduced in commit ddeea5b0c36f3665446518c609be91f9336ef674 Author: Imre Deak <imre.deak@intel.com> Date: Mon May 5 15:19:56 2014 +0300 drm/i915: vlv: add runtime PM support I noticed this only by reading the code. To my knowledge it shouldn't cause any real problems at the moment, since the power well backing this register remains on across a runtime s/r. This may change once system-wide s0ix functionality is enabled in the kernel. v2: - resend after a missing git add -u :/ Cc: stable@vger.kernel.org Signed-off-by: Imre Deak <imre.deak@intel.com> Tested-By: PRC QA PRTS (Patch Regression Test System Contact: shuang.he@intel.com) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| | * drm/i915: Workaround to avoid lite restore with HEAD==TAILMichel Thierry2015-04-232-2/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | WaIdleLiteRestore is an execlists-only workaround, and requires the driver to ensure that any context always has HEAD!=TAIL when attempting lite restore. Add two extra MI_NOOP instructions at the end of each request, but keep the requests tail pointing before the MI_NOOPs. We may not need to executed them, and this is why request->tail is sampled before adding these extra instructions. If we submit a context to the ELSP which has previously been submitted, move the tail pointer past the MI_NOOPs. This ensures HEAD!=TAIL. v2: Move overallocation to gen8_emit_request, and added note about sampling request->tail in commit message (Chris). v3: Remove redundant request->tail assignment in __i915_add_request, in lrc mode this is already set in execlists_context_queue. Do not add wa implementation details inside gem (Chris). v4: Apply the wa whenever the req has been resubmitted and update comment (Chris). Cc: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Thomas Daniel <thomas.daniel@intel.com> Signed-off-by: Michel Thierry <michel.thierry@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
| | * drm/i915: cope with large i2c transfersDmitry Torokhov2015-04-232-10/+57
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The hardware, according to the specs, is limited to 256 byte transfers, and current driver has no protections in case users attempt to do larger transfers. The code will just stomp over status register and mayhem ensues. Let's split larger transfers into digestable chunks. Doing this allows Atmel MXT driver on Pixel 1 function properly (it hasn't since commit 9d8dc3e529a19e427fd379118acd132520935c5d "Input: atmel_mxt_ts - implement T44 message handling" which tries to consume multiple touchscreen/touchpad reports in a single transaction). Cc: stable@vger.kernel.org Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com>
* | | Merge git://git.infradead.org/intel-iommuLinus Torvalds2015-04-263-83/+82
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull intel iommu updates from David Woodhouse: "This lays a little of the groundwork for upcoming Shared Virtual Memory support — fixing some bogus #defines for capability bits and adding the new ones, and starting to use the new wider page tables where we can, in anticipation of actually filling in the new fields therein. It also allows graphics devices to be assigned to VM guests again. This got broken in 3.17 by disallowing assignment of RMRR-afflicted devices. Like USB, we do understand why there's an RMRR for graphics devices — and unlike USB, it's actually sane. So we can make an exception for graphics devices, just as we do USB controllers. Finally, tone down the warning about the X2APIC_OPT_OUT bit, due to persistent requests. X2APIC_OPT_OUT was added to the spec as a nasty hack to allow broken BIOSes to forbid us from using X2APIC when they do stupid and invasive things and would break if we did. Someone noticed that since Windows doesn't have full IOMMU support for DMA protection, setting the X2APIC_OPT_OUT bit made Windows avoid initialising the IOMMU on the graphics unit altogether. This means that it would be available for use in "driver mode", where the IOMMU registers are made available through a BAR of the graphics device and the graphics driver can do SVM all for itself. So they started setting the X2APIC_OPT_OUT bit on *all* platforms with SVM capabilities. And even the platforms which *might*, if the planets had been aligned correctly, possibly have had SVM capability but which in practice actually don't" * git://git.infradead.org/intel-iommu: iommu/vt-d: support extended root and context entries iommu/vt-d: Add new extended capabilities from v2.3 VT-d specification iommu/vt-d: Allow RMRR on graphics devices too iommu/vt-d: Print x2apic opt out info instead of printing a warning iommu/vt-d: kill bogus ecap_niotlb_iunits()
| * | | iommu/vt-d: support extended root and context entriesDavid Woodhouse2015-03-251-75/+60
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add a new function iommu_context_addr() which takes care of the differences and returns a pointer to a context entry which may be in either format. The formats are binary compatible for all the old fields anyway; the new one is just larger and some of the reserved bits in the original 128 are now meaningful. So far, nothing actually uses the new fields in the extended context entry. Modulo hardware bugs with interpreting the new-style tables, this should basically be a no-op. Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
| * | | iommu/vt-d: Add new extended capabilities from v2.3 VT-d specificationDavid Woodhouse2015-03-251-0/+14
| | | | | | | | | | | | | | | | Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
| * | | iommu/vt-d: Allow RMRR on graphics devices tooDavid Woodhouse2015-03-251-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit c875d2c1 ("iommu/vt-d: Exclude devices using RMRRs from IOMMU API domains") prevents certain options for devices with RMRRs. This even prevents those devices from getting a 1:1 mapping with 'iommu=pt', because we don't have the code to handle *preserving* the RMRR regions when moving the device between domains. There's already an exclusion for USB devices, because we know the only reason for RMRRs there is a misguided desire to keep legacy keyboard/mouse emulation running in some theoretical OS which doesn't have support for USB in its own right... but which *does* enable the IOMMU. Add an exclusion for graphics devices too, so that 'iommu=pt' works there. We should be able to successfully assign graphics devices to guests too, as long as the initial handling of stolen memory is reconfigured appropriately. This has certainly worked in the past. Signed-off-by: David Woodhouse <David.Woodhouse@intel.com> Cc: stable@vger.kernel.org
| * | | iommu/vt-d: Print x2apic opt out info instead of printing a warningFenghua Yu2015-03-251-4/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | BIOS can set up x2apic_opt_out bit on some platforms, for various misguided reasons like insane SMM code with weird assumptions about what descriptors look like, or wanting Windows not to enable the IOMMU so that the graphics driver will take it over for SVM in "driver mode". A user can either disable the x2apic_opt_out bit in BIOS or by kernel parameter "no_x2apic_optout". Instead of printing a warning, we just print information of x2apic opt out. Signed-off-by: Fenghua Yu <fenghua.yu@intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
OpenPOWER on IntegriCloud