summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* IB/ipath: simplify debugging code after ipath_core and ib_ipath mergerBryan O'Sullivan2006-09-228-134/+17
| | | | | Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: simplify layering codeBryan O'Sullivan2006-09-2217-1329/+1126
| | | | | | | | | A lot of ipath layer code was only called in one place. Now that the ipath_core and ib_ipath drivers are merged, it's more sensible to simply inline the simple stuff that the layer code was doing. Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: merge ipath_core and ib_ipath driversBryan O'Sullivan2006-09-2210-292/+62
| | | | | | | | There is little point in keeping the two drivers separate, so we are merging them. Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: drop requirement that PIO buffers be mmaped write-onlyBryan O'Sullivan2006-09-221-9/+4
| | | | | | | Some userlands try to mmap these pages read-write, so accommodate them. Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: fix handling of kpiobufsBryan O'Sullivan2006-09-221-1/+2
| | | | | | | | | Change comment: no longer imply that user can set ipath_kpiobufs to zero. Actually set ipath_kpiobufs from parameter. Previously only altered per-device ipath_lastport_piobuf, which was over-written in chip init. Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: fix for crash on module unload, if cfgports < portcntBryan O'Sullivan2006-09-221-1/+5
| | | | | | | | Allocate enough pointers for all possible ports, to avoid problems in cleanup/unload. Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: lock resource limit counters correctlyBryan O'Sullivan2006-09-223-8/+38
| | | | | Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: More changes to support InfiniPath on PowerPC 970 systemsBryan O'Sullivan2006-09-224-0/+66
| | | | | | | | | | | Ordering of writethrough store buffers needs to be forced, and we need to use ifdef to get writethrough behavior to InfiniPath buffers, because there is no generic way to specify that at this time (similar to code in char/drm/drm_vm.c and block/z2ram.c). Signed-off-by: John Gregor <john.gregor@qlogic.com> Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipath: Performance improvements via mmap of queuesRalph Campbell2006-09-229-382/+785
| | | | | | | | | | Improve performance of userspace post receive, post SRQ receive, and poll CQ operations for ipath by allowing userspace to directly mmap() receive queues and completion queues. This eliminates the copying between userspace and the kernel in the data path. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/uverbs: Pass userspace data to modify_srq and modify_qp methodsRalph Campbell2006-09-2211-17/+34
| | | | | | | | | | Pass a struct ib_udata to the low-level driver's ->modify_srq() and ->modify_qp() methods, so that it can get to the device-specific data passed in by the userspace driver. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/uverbs: Allow resize CQ operation to return driver-specific dataRalph Campbell2006-09-222-2/+3
| | | | | | | | | | Add a ib_uverbs_resize_cq_resp.driver_data field so that low-level drivers can return data from a resize CQ operation to userspace. Have ib_uverbs_resize_cq() only copy the cqe field, to avoid having to bump the userspace ABI. Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ehca: Add driver for IBM eHCA InfiniBand adaptersHeiko J Schick2006-09-2234-0/+11582
| | | | | | | | Add a driver for IBM GX bus InfiniBand adapters, which are usable with some pSeries/System p systems. Signed-off-by: Heiko J Schick <schickhj.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/srp: Add port/device attributesIshai Rabinovitz2006-09-221-6/+24
| | | | | | | | | | | Add local_ib_device and local_ib_port attributes to srp scsi_host. These are needed when we want to connect to the same target through multiple distinct ports. Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il> Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/mthca: Include the header we really wantJames Lentini2006-09-221-1/+1
| | | | | Signed-off-by: James Lentini <jlentini@netapp.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/uverbs: Fix lockdep warning when QP is created with 2 CQsRoland Dreier2006-09-221-15/+19
| | | | | | | | | | | | Lockdep warns when userspace creates a QP that uses different CQs for send completions and receive completions, because both CQs are locked and their mutexes belong to the same lock class. However, we know that the mutexes are distinct and the nesting is safe (there is no possibility of AB-BA deadlock because the mutexes are locked with down_read()), so annotate the situation with SINGLE_DEPTH_NESTING to get rid of the lockdep warning. Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/uverbs: Use idr_read_cq() where appropriateRoland Dreier2006-09-221-10/+6
| | | | | | | There were two functions that open-coded idr_read_cq() in terms of idr_read_uobj() rather than using the helper. Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/ipoib: Fix flush/start xmit race (from code review)Michael S. Tsirkin2006-09-221-4/+8
| | | | | | | | | | Prevent flush task from freeing the ipoib_neigh pointer, while ipoib_start_xmit() is accessing the ipoib_neigh through the pointer it has loaded from the skb's hardware address. Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/mthca: Don't use privileged UAR for kernel accessMichael S. Tsirkin2006-09-221-1/+1
| | | | | | | | Make kernel use UAR2 instead of UAR1 for hardware access: this adds sanity checking from the hardware side, without any performance cost. Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* IB/mthca: Fix lid used for sending trapsJack Morgenstein2006-09-221-1/+1
| | | | | | | | | | | | | | | The SM LID used to send traps to is incorrectly set to port LID. This is a regression from 2.6.17 -- after a PortInfo MAD is received, no traps are sent to the SM LID. The traps go to the loopback interface instead, and are dropped there. The SM LID should be taken from the sm_lid of the PortInfo response. The bug was introduced by commit 12bbb2b7be7f5564952ebe0196623e97464b8ac5: IB/mthca: Add client reregister event generation Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com>
* Merge git://git.infradead.org/~dwmw2/hdronelineLinus Torvalds2006-09-2229-159/+722
|\ | | | | | | | | | | | | * git://git.infradead.org/~dwmw2/hdroneline: [HEADERS] One line per header in Kbuild files to reduce conflicts Manual (trivial) conflict resolution in include/asm-s390/Kbuild
| * [HEADERS] One line per header in Kbuild files to reduce conflictsDavid Woodhouse2006-09-1929-159/+721
| | | | | | | | Signed-off-by: David Woodhouse <dwmw2@infradead.org>
* | Merge branch 'upstream-linus' of ↵Linus Torvalds2006-09-2221-134/+440
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2 * 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: ocfs2: Remove overzealous BUG_ON() ocfs2: Don't print on unknown remote blocking call ocfs2: Remove EXPERIMENTAL dependency ocfs2: implement directory read-ahead ocfs2: properly update i_mtime on buffered write ocfs2: Fix directory link count checks in ocfs2_link() ocfs2: move nlink check in ocfs2_mknod() ocfs2: Fix heartbeat sector calculation [PATCH] fs/ocfs2/ioctl.c should #include "ioctl.h" ocfs2: add ext2 attributes configfs: Prevent duplicate subsystem names.
| * | ocfs2: Remove overzealous BUG_ON()Mark Fasheh2006-09-201-8/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | The truncate code was never supposed to BUG() on an allocator it doesn't know about, but rather to ignore it. Right now, this does nothing, but when we change our allocation paths to use all suballocator files, this will allow current versions of the fs module to work fine. Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: Don't print on unknown remote blocking callMark Fasheh2006-09-201-6/+4
| | | | | | | | | | | | Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: Remove EXPERIMENTAL dependencyMark Fasheh2006-09-201-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | Things have been working pretty well for a while now. We should've probably done this at least one kernel revision ago, but it doesn't hurt to be paranoid. Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: implement directory read-aheadMark Fasheh2006-09-207-47/+115
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Uptodate.c now knows about read-ahead buffers. Use some more aggressive logic in ocfs2_readdir(). The two functions which currently use directory read-ahead are ocfs2_find_entry() and ocfs2_readdir(). Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: properly update i_mtime on buffered writeMark Fasheh2006-09-201-49/+34
| | | | | | | | | | | | | | | | | | | | | | | | We weren't always updating i_mtime on writes, so fix ocfs2_commit_write() to handle this. Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com> Acked-by: Zach Brown <zach.brown@oracle.com>
| * | ocfs2: Fix directory link count checks in ocfs2_link()Tiger Yang2006-09-201-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | Remove the redundant "i_nlink >= OCFS2_LINK_MAX" check and adds an unlinked directory check in ocfs2_link(). Signed-off-by: Tiger Yang <tiger.yang@oracle.com> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: move nlink check in ocfs2_mknod()Mark Fasheh2006-09-201-7/+5
| | | | | | | | | | | | | | | | | | | | | | | | The dir nlink check in ocfs2_mknod() was being done outside of the cluster lock, which means we could have been checking against a stale version of the inode. Fix this by doing the check after the cluster lock instead. Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: Fix heartbeat sector calculationMathieu Avila2006-09-201-2/+6
| | | | | | | | | | | | | | | | | | This fixes things for devices which set max_sectors to 8. Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | [PATCH] fs/ocfs2/ioctl.c should #include "ioctl.h"Adrian Bunk2006-09-201-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | Every file should #include the headers containing the prototypes for its global functions. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | ocfs2: add ext2 attributesHerbert Poetzl2006-09-209-6/+217
| | | | | | | | | | | | | | | | | | | | | | | | | | | Support immutable, and other attributes. Some renaming and other minor fixes done by myself. Signed-off-by: Herbert Poetzl <herbert@13thfloor.at> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| * | configfs: Prevent duplicate subsystem names.Joel Becker2006-09-201-2/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For all child objects, creation comes through mkdir(2), so duplicate names are prevented. Subsystems, though, are registered by client drivers at init_module()/__init time. This patch prevents duplicate subsystem names. Signed-off-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
* | | Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6Linus Torvalds2006-09-2298-2780/+7726
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (64 commits) [BLOCK] dm-crypt: trivial comment improvements [CRYPTO] api: Deprecate crypto_digest_* and crypto_alg_available [CRYPTO] padlock: Convert padlock-sha to use crypto_hash [CRYPTO] users: Use crypto_comp and crypto_has_* [CRYPTO] api: Add crypto_comp and crypto_has_* [CRYPTO] users: Use crypto_hash interface instead of crypto_digest [SCSI] iscsi: Use crypto_hash interface instead of crypto_digest [CRYPTO] digest: Remove old HMAC implementation [CRYPTO] doc: Update documentation for hash and me [SCTP]: Use HMAC template and hash interface [IPSEC]: Use HMAC template and hash interface [CRYPTO] tcrypt: Use HMAC template and hash interface [CRYPTO] hmac: Add crypto template implementation [CRYPTO] digest: Added user API for new hash type [CRYPTO] api: Mark parts of cipher interface as deprecated [PATCH] scatterlist: Add const to sg_set_buf/sg_init_one pointer argument [CRYPTO] drivers: Remove obsolete block cipher operations [CRYPTO] users: Use block ciphers where applicable [SUNRPC] GSS: Use block ciphers where applicable [IPSEC] ESP: Use block ciphers where applicable ...
| * | | [BLOCK] dm-crypt: trivial comment improvementsRik Snel2006-09-211-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Just some minor comment nits. - little-endian is better than low-endian - and since it is called essiv everywere it should also be essiv in the comments (and not ess_iv) Signed-off-by: Rik Snel <rsnel@cube.dyndns.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] api: Deprecate crypto_digest_* and crypto_alg_availableHerbert Xu2006-09-211-5/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch marks the crypto_digest_* functions and crypto_alg_available as deprecated. They've been replaced by crypto_hash_* and crypto_has_* respectively. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] padlock: Convert padlock-sha to use crypto_hashHerbert Xu2006-09-212-56/+41
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts padlock-sha to use crypto_hash for its fallback. It also changes the fallback selection to use selection by type instead of name. This is done through the new CRYPTO_ALG_NEED_FALLBACK bit, which is set if and only if an algorithm needs a fallback of the same type. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] users: Use crypto_comp and crypto_has_*Herbert Xu2006-09-218-45/+60
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts all users to use the new crypto_comp type and the crypto_has_* functions. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] api: Add crypto_comp and crypto_has_*Herbert Xu2006-09-212-6/+98
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds the crypto_comp type to complete the compile-time checking conversion. The functions crypto_has_alg and crypto_has_cipher, etc. are also added to replace crypto_alg_available. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] users: Use crypto_hash interface instead of crypto_digestHerbert Xu2006-09-216-69/+97
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts all remaining crypto_digest users to use the new crypto_hash interface. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [SCSI] iscsi: Use crypto_hash interface instead of crypto_digestHerbert Xu2006-09-212-65/+78
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts ISCSI to use the new crypto_hash interface instead of crypto_digest. It's a fairly straightforward substitution. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] digest: Remove old HMAC implementationHerbert Xu2006-09-215-133/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch removes the old HMAC implementation now that nobody uses it anymore. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | [CRYPTO] doc: Update documentation for hash and meHerbert Xu2006-09-211-14/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch updates the documentation to reflect the switch from digest to hash. It also replaces notes about emailing James Morris to refer to me instead. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [SCTP]: Use HMAC template and hash interfaceHerbert Xu2006-09-216-28/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts SCTP to use the new HMAC template and hash interface. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | [IPSEC]: Use HMAC template and hash interfaceHerbert Xu2006-09-218-97/+158
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts IPsec to use the new HMAC template. The names of existing simple digest algorithms may still be used to refer to their HMAC composites. The same structure can be used by other MACs such as AES-XCBC-MAC. This patch also switches from the digest interface to hash. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | [CRYPTO] tcrypt: Use HMAC template and hash interfaceHerbert Xu2006-09-212-165/+213
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch converts tcrypt to use the new HMAC template rather than the hard-coded version of HMAC. It also converts all digest users to use the new cipher interface. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | [CRYPTO] hmac: Add crypto template implementationHerbert Xu2006-09-212-6/+236
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch rewrites HMAC as a crypto template. This means that HMAC is no longer a hard-coded part of the API. It's now a template that generates standard digest algorithms like any other. The old HMAC is preserved until all current users are converted. The same structure can be used by other MACs such as AES-XCBC-MAC. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | [CRYPTO] digest: Added user API for new hash typeHerbert Xu2006-09-218-70/+321
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The existing digest user interface is inadequate for support asynchronous operations. For one it doesn't return a value to indicate success or failure, nor does it take a per-operation descriptor which is essential for the issuing of requests while other requests are still outstanding. This patch is the first in a series of steps to remodel the interface for asynchronous operations. For the ease of transition the new interface will be known as "hash" while the old one will remain as "digest". This patch also changes sg_next to allow chaining. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [CRYPTO] api: Mark parts of cipher interface as deprecatedHerbert Xu2006-09-212-18/+64
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Mark the parts of the cipher interface that have been replaced by block ciphers as deprecated. Thanks to Andrew Morton for suggesting doing this before removing them completely. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
| * | | [PATCH] scatterlist: Add const to sg_set_buf/sg_init_one pointer argumentHerbert Xu2006-09-211-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds a const modifier to the buf argument of sg_set_buf and sg_init_one. This lets people call it with pointers that are const. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
OpenPOWER on IntegriCloud