summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* dm kcopyd: introduce configurable throttlingMikulas Patocka2013-03-015-5/+156
| | | | | | | | | | | | | | | | | This patch allows the administrator to reduce the rate at which kcopyd issues I/O. Each module that uses kcopyd acquires a throttle parameter that can be set in /sys/module/*/parameters. We maintain a history of kcopyd usage by each module in the variables io_period and total_period in struct dm_kcopyd_throttle. The actual kcopyd activity is calculated as a percentage of time equal to "(100 * io_period / total_period)". This is compared with the user-defined throttle percentage threshold and if it is exceeded, we sleep. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm ioctl: allow message to return dataMikulas Patocka2013-03-012-1/+40
| | | | | | | | | | | | | | | | This patch introduces enhanced message support that allows the device-mapper core to recognise messages that are common to all devices, and for messages to return data to userspace. Core messages are processed by the function "message_for_md". If the device mapper doesn't support the message, it is passed to the target driver. If the message returns data, the kernel sets the flag DM_MESSAGE_OUT_FLAG. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm ioctl: optimize functions without variable paramsMikulas Patocka2013-03-012-21/+37
| | | | | | | | | | | | | | | | | | | | Device-mapper ioctls receive and send data in a buffer supplied by userspace. The buffer has two parts. The first part contains a 'struct dm_ioctl' and has a fixed size. The second part depends on the ioctl and has a variable size. This patch recognises the specific ioctls that do not use the variable part of the buffer and skips allocating memory for it. In particular, when a device is suspended and a resume ioctl is sent, this now avoid memory allocation completely. The variable "struct dm_ioctl tmp" is moved from the function copy_params to its caller ctl_ioctl and renamed to param_kernel. It is used directly when the ioctl function doesn't need any arguments. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm ioctl: introduce ioctl_flagsMikulas Patocka2013-03-011-23/+41
| | | | | | | | | | | This patch introduces flags for each ioctl function. So far, one flag is defined, IOCTL_FLAGS_NO_PARAMS. It is set if the function processing the ioctl doesn't take or produce any parameters in the section of the data buffer that has a variable size. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: merge io_pool and tio_poolJun'ichi Nomura2013-03-011-49/+27
| | | | | | | | | | | | | | | | | | This patch merges io_pool and tio_pool into io_pool and cleans up related functions. Though device-mapper used to have 2 pools of objects for each dm device, the use of bioset frontbad for per-bio data has shrunk the number of pools to 1 for both bio-based and request-based device types. (See c0820cf5 "dm: introduce per_bio_data" and 94818742 "dm: Use bioset's front_pad for dm_rq_clone_bio_info") So dm no longer has to maintain 2 different pointers. No functional changes. Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: remove unused _rq_bio_info_cacheJun'ichi Nomura2013-03-011-21/+10
| | | | | | | | Remove _rq_bio_info_cache, which is no longer used. No functional changes. Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: fix limits initialization when there are no data devicesMike Christie2013-03-011-5/+7
| | | | | | | | | | | | | | | | | | dm_calculate_queue_limits will first reset the provided limits to defaults using blk_set_stacking_limits; whereby defeating the purpose of retaining the original live table's limits -- as was intended via commit 3ae706561637331aa578e52bb89ecbba5edcb7a9 ("dm: retain table limits when swapping to new table with no devices"). Fix this improper limits initialization (in the no data devices case) by avoiding the call to dm_calculate_queue_limits. [patch header revised by Mike Snitzer] Signed-off-by: Mike Christie <michaelc@cs.wisc.edu> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # v3.6+ Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm snapshot: add missing module aliasesMikulas Patocka2013-03-011-0/+2
| | | | | | | | | | | | Add module aliases so that autoloading works correctly if the user tries to activate "snapshot-origin" or "snapshot-merge" targets. Reference: https://bugzilla.redhat.com/889973 Reported-by: Chao Yang <chyang@redhat.com> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm persistent data: set some btree fn parms constMike Snitzer2013-03-012-9/+9
| | | | | | | Mark some constant parameters constant in some dm-btree functions. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: refactor bio cloningAlasdair G Kergon2013-03-011-68/+96
| | | | | | | Refactor part of the bio splitting and cloning code to try to make it easier to understand. Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: rename bio cloning functionsAlasdair G Kergon2013-03-011-32/+31
| | | | | | | | | | | Rename functions involved in splitting and cloning bios. The sequence of functions is now: (1) __split_and_process* - entry point that selects the processing strategy (2) __send* - prepare the details for each bio needed and loop through them (3) __clone_and_map* - creates a clone and maps it Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: rename request variables to biosAlasdair G Kergon2013-03-0115-81/+81
| | | | | | | | | | Use 'bio' in the name of variables and functions that deal with bios rather than 'request' to avoid confusion with the normal block layer use of 'request'. No functional changes. Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: clean up clone_bioAlasdair G Kergon2013-03-011-45/+57
| | | | | | | | | | | Remove the no-longer-used struct bio_set argument from clone_bio and split_bvec. Use tio->ti in __map_bio() instead of passing in ti. Factor out some code for setting up cloned bios. Take target_request_nr as a parameter to alloc_tio(). Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: Joe Thornber <ejt@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm persistent data: remove CONFIG_EXPERIMENTALKees Cook2013-03-011-1/+1
| | | | | | | | | The CONFIG_EXPERIMENTAL config item has not carried much meaning for a while now and is almost always enabled by default. As agreed during the Linux kernel summit, remove it from any "depends on" lines in Kconfigs. Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: remove CONFIG_EXPERIMENTALAlasdair G Kergon2013-03-011-12/+12
| | | | | | Remove EXPERIMENTAL from all existing device-mapper targets. Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm thin: use block_size_is_power_of_twoMike Snitzer2013-03-011-12/+13
| | | | | | | | | | | Use block_size_is_power_of_two() rather than checking sectors_per_block_shift directly. Also introduce local pool variable in get_bio_block() to eliminate redundant tc->pool dereferences. No functional change. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm bufio: use WRITE_FLUSH instead of REQ_FLUSHMikulas Patocka2013-03-011-1/+1
| | | | | | | | Use WRITE_FLUSH instead of REQ_FLUSH for submitted requests to make it consistent with the rest of the kernel. There is no functional change. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm table: remove superfluous variable resetWang Sheng-Hui2013-03-011-1/+0
| | | | | | | | If allocation fails, the local var *t is not used any more after kfree. Don't need to reset it to NULL. Remove the unnecesary NULL set here. Signed-off-by: Wang Sheng-Hui <shhuiw@gmail.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm thin: support a non power of 2 discard_granularityMike Snitzer2013-03-011-8/+1
| | | | | | | | | | | Support a non-power-of-2 discard granularity in dm-thin, now that the block layer supports this(via 8dd2cb7e880d2f77fba53b523c99133ad5054cfd "block: discard granularity might not be power of 2" and 59771079c18c44e39106f0f30054025acafadb41 "blk: avoid divide-by-zero with zero discard granularity"). Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: fix truncated status stringsMikulas Patocka2013-03-0113-115/+99
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Avoid returning a truncated table or status string instead of setting the DM_BUFFER_FULL_FLAG when the last target of a table fills the buffer. When processing a table or status request, the function retrieve_status calls ti->type->status. If ti->type->status returns non-zero, retrieve_status assumes that the buffer overflowed and sets DM_BUFFER_FULL_FLAG. However, targets don't return non-zero values from their status method on overflow. Most targets returns always zero. If a buffer overflow happens in a target that is not the last in the table, it gets noticed during the next iteration of the loop in retrieve_status; but if a buffer overflow happens in the last target, it goes unnoticed and erroneously truncated data is returned. In the current code, the targets behave in the following way: * dm-crypt returns -ENOMEM if there is not enough space to store the key, but it returns 0 on all other overflows. * dm-thin returns errors from the status method if a disk error happened. This is incorrect because retrieve_status doesn't check the error code, it assumes that all non-zero values mean buffer overflow. * all the other targets always return 0. This patch changes the ti->type->status function to return void (because most targets don't use the return code). Overflow is detected in retrieve_status: if the status method fills up the remaining space completely, it is assumed that buffer overflow happened. Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* dm: do not replace bioset for request based dmJun'ichi Nomura2013-03-011-9/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a regression introduced in v3.8, which causes oops like this when dm-multipath is used: general protection fault: 0000 [#1] SMP RIP: 0010:[<ffffffff810fe754>] [<ffffffff810fe754>] mempool_free+0x24/0xb0 Call Trace: <IRQ> [<ffffffff81187417>] bio_put+0x97/0xc0 [<ffffffffa02247a5>] end_clone_bio+0x35/0x90 [dm_mod] [<ffffffff81185efd>] bio_endio+0x1d/0x30 [<ffffffff811f03a3>] req_bio_endio.isra.51+0xa3/0xe0 [<ffffffff811f2f68>] blk_update_request+0x118/0x520 [<ffffffff811f3397>] blk_update_bidi_request+0x27/0xa0 [<ffffffff811f343c>] blk_end_bidi_request+0x2c/0x80 [<ffffffff811f34d0>] blk_end_request+0x10/0x20 [<ffffffffa000b32b>] scsi_io_completion+0xfb/0x6c0 [scsi_mod] [<ffffffffa000107d>] scsi_finish_command+0xbd/0x120 [scsi_mod] [<ffffffffa000b12f>] scsi_softirq_done+0x13f/0x160 [scsi_mod] [<ffffffff811f9fd0>] blk_done_softirq+0x80/0xa0 [<ffffffff81044551>] __do_softirq+0xf1/0x250 [<ffffffff8142ee8c>] call_softirq+0x1c/0x30 [<ffffffff8100420d>] do_softirq+0x8d/0xc0 [<ffffffff81044885>] irq_exit+0xd5/0xe0 [<ffffffff8142f3e3>] do_IRQ+0x63/0xe0 [<ffffffff814257af>] common_interrupt+0x6f/0x6f <EOI> [<ffffffffa021737c>] srp_queuecommand+0x8c/0xcb0 [ib_srp] [<ffffffffa0002f18>] scsi_dispatch_cmd+0x148/0x310 [scsi_mod] [<ffffffffa000a38e>] scsi_request_fn+0x31e/0x520 [scsi_mod] [<ffffffff811f1e57>] __blk_run_queue+0x37/0x50 [<ffffffff811f1f69>] blk_delay_work+0x29/0x40 [<ffffffff81059003>] process_one_work+0x1c3/0x5c0 [<ffffffff8105b22e>] worker_thread+0x15e/0x440 [<ffffffff8106164b>] kthread+0xdb/0xe0 [<ffffffff8142db9c>] ret_from_fork+0x7c/0xb0 The regression was introduced by the change c0820cf5 "dm: introduce per_bio_data", where dm started to replace bioset during table replacement. For bio-based dm, it is good because clone bios do not exist during the table replacement. For request-based dm, however, (not-yet-mapped) clone bios may stay in request queue and survive during the table replacement. So freeing the old bioset could cause the oops in bio_put(). Since the size of front_pad may change only with bio-based dm, it is not necessary to replace bioset for request-based dm. Reported-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Acked-by: Mikulas Patocka <mpatocka@redhat.com> Acked-by: Mike Snitzer <snitzer@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
* Merge branch 'for-3.9' of git://linux-nfs.org/~bfields/linuxLinus Torvalds2013-02-2842-507/+831
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull nfsd changes from J Bruce Fields: "Miscellaneous bugfixes, plus: - An overhaul of the DRC cache by Jeff Layton. The main effect is just to make it larger. This decreases the chances of intermittent errors especially in the UDP case. But we'll need to watch for any reports of performance regressions. - Containerized nfsd: with some limitations, we now support per-container nfs-service, thanks to extensive work from Stanislav Kinsbursky over the last year." Some notes about conflicts, since there were *two* non-data semantic conflicts here: - idr_remove_all() had been added by a memory leak fix, but has since become deprecated since idr_destroy() does it for us now. - xs_local_connect() had been added by this branch to make AF_LOCAL connections be synchronous, but in the meantime Trond had changed the calling convention in order to avoid a RCU dereference. There were a couple of more obvious actual source-level conflicts due to the hlist traversal changes and one just due to code changes next to each other, but those were trivial. * 'for-3.9' of git://linux-nfs.org/~bfields/linux: (49 commits) SUNRPC: make AF_LOCAL connect synchronous nfsd: fix compiler warning about ambiguous types in nfsd_cache_csum svcrpc: fix rpc server shutdown races svcrpc: make svc_age_temp_xprts enqueue under sv_lock lockd: nlmclnt_reclaim(): avoid stack overflow nfsd: enable NFSv4 state in containers nfsd: disable usermode helper client tracker in container nfsd: use proper net while reading "exports" file nfsd: containerize NFSd filesystem nfsd: fix comments on nfsd_cache_lookup SUNRPC: move cache_detail->cache_request callback call to cache_read() SUNRPC: remove "cache_request" argument in sunrpc_cache_pipe_upcall() function SUNRPC: rework cache upcall logic SUNRPC: introduce cache_detail->cache_request callback NFS: simplify and clean cache library NFS: use SUNRPC cache creation and destruction helper for DNS cache nfsd4: free_stid can be static nfsd: keep a checksum of the first 256 bytes of request sunrpc: trim off trailing checksum before returning decrypted or integrity authenticated buffer sunrpc: fix comment in struct xdr_buf definition ...
| * SUNRPC: make AF_LOCAL connect synchronousJ. Bruce Fields2013-02-281-8/+27
| | | | | | | | | | | | | | | | | | | | | | | | It doesn't appear that anyone actually needs to connect asynchronously. Also, using a workqueue for the connect means we lose the namespace information from the original process. This is a problem since there's no way to explicitly pass in a filesystem namespace for resolution of an AF_LOCAL address. Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: fix compiler warning about ambiguous types in nfsd_cache_csumJeff Layton2013-02-171-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | kbuild test robot says: tree: git://linux-nfs.org/~bfields/linux.git for-3.9 head: deb4534f4f3be7aea7d9d24c3b0d58f370cbf9ef commit: 01a7decf75930925322c5efc87af0b5e58eb8650 [32/44] nfsd: keep a checksum of the first 256 bytes of request config: i386-randconfig-x088 (attached as .config) All warnings: fs/nfsd/nfscache.c: In function 'nfsd_cache_csum': >> fs/nfsd/nfscache.c:266:9: warning: comparison of distinct pointer types lacks a cast [enabled by default] vim +266 fs/nfsd/nfscache.c 250 __wsum csum; 251 struct xdr_buf *buf = &rqstp->rq_arg; 252 const unsigned char *p = buf->head[0].iov_base; 253 size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len, 254 RC_CSUMLEN); 255 size_t len = min(buf->head[0].iov_len, csum_len); 256 257 /* rq_arg.head first */ 258 csum = csum_partial(p, len, 0); 259 csum_len -= len; 260 261 /* Continue into page array */ 262 idx = buf->page_base / PAGE_SIZE; 263 base = buf->page_base & ~PAGE_MASK; 264 while (csum_len) { 265 p = page_address(buf->pages[idx]) + base; > 266 len = min(PAGE_SIZE - base, csum_len); 267 csum = csum_partial(p, len, csum); 268 csum_len -= len; 269 base = 0; 270 ++idx; 271 } 272 return csum; 273 } 274 Signed-off-by: Jeff Layton <jlayton@redhat.com> Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * svcrpc: fix rpc server shutdown racesJ. Bruce Fields2013-02-172-34/+32
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rewrite server shutdown to remove the assumption that there are no longer any threads running (no longer true, for example, when shutting down the service in one network namespace while it's still running in others). Do that by doing what we'd do in normal circumstances: just CLOSE each socket, then enqueue it. Since there may not be threads to handle the resulting queued xprts, also run a simplified version of the svc_recv() loop run by a server to clean up any closed xprts afterwards. Cc: stable@kernel.org Tested-by: Jason Tibbitts <tibbs@math.uh.edu> Tested-by: Paweł Sikora <pawel.sikora@agmk.net> Acked-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * svcrpc: make svc_age_temp_xprts enqueue under sv_lockJ. Bruce Fields2013-02-171-13/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | svc_age_temp_xprts expires xprts in a two-step process: first it takes the sv_lock and moves the xprts to expire off their server-wide list (sv_tempsocks or sv_permsocks) to a local list. Then it drops the sv_lock and enqueues and puts each one. I see no reason for this: svc_xprt_enqueue() will take sp_lock, but the sv_lock and sp_lock are not otherwise nested anywhere (and documentation at the top of this file claims it's correct to nest these with sp_lock inside.) Cc: stable@kernel.org Tested-by: Jason Tibbitts <tibbs@math.uh.edu> Tested-by: Paweł Sikora <pawel.sikora@agmk.net> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * lockd: nlmclnt_reclaim(): avoid stack overflowTim Gardner2013-02-153-6/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Even though nlmclnt_reclaim() is only one call into the stack frame, 928 bytes on the stack seems like a lot. Recode to dynamically allocate the request structure once from within the reclaimer task, then pass this pointer into nlmclnt_reclaim() for reuse on subsequent calls. smatch analysis: fs/lockd/clntproc.c:620 nlmclnt_reclaim() warn: 'reqst' puts 928 bytes on stack Also remove redundant assignment of 0 after memset. Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Tim Gardner <tim.gardner@canonical.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: enable NFSv4 state in containersStanislav Kinsbursky2013-02-151-10/+0
| | | | | | | | | | | | | | | | Currently, NFSd is ready to operate in network namespace based containers. So let's drop check for "init_net" and make it able to fly. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: disable usermode helper client tracker in containerStanislav Kinsbursky2013-02-151-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | This tracker uses khelper kthread to execute binaries. Execution itself is done from kthread context - i.e. global root is used. This is not suitable for containers with own root. So, disable this tracker for a while. Note: one of possible solutions can be pass "init" callback to khelper, which will swap root to desired one. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: use proper net while reading "exports" fileStanislav Kinsbursky2013-02-151-6/+25
| | | | | | | | | | | | | | | | | | | | | | Functuon "exports_open" is used for both "/proc/fs/nfs/exports" and "/proc/fs/nfsd/exports" files. Now NFSd filesystem is containerised, so proper net can be taken from superblock for "/proc/fs/nfsd/exports" reader. But for "/proc/fs/nfsd/exports" only current->nsproxy->net_ns can be used. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: containerize NFSd filesystemStanislav Kinsbursky2013-02-152-16/+35
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch makes NFSD file system superblock to be created per net. This makes possible to get proper network namespace from superblock instead of using hard-coded "init_net". Note: NFSd fs super-block holds network namespace. This garantees, that network namespace won't disappear from underneath of it. This, obviously, means, that in case of kill of a container's "init" (which is not a mount namespace, but network namespace creator) netowrk namespace won't be destroyed. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: fix comments on nfsd_cache_lookupJeff Layton2013-02-151-2/+5
| | | | | | | | | | Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * SUNRPC: move cache_detail->cache_request callback call to cache_read()Stanislav Kinsbursky2013-02-151-12/+20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The reason to move cache_request() callback call from sunrpc_cache_pipe_upcall() to cache_read() is that this garantees, that cache access will be done userspace process context (only userspace process have proper root context). This is required for NFSd support in container: svc_export_request() (which is cache_request callback) calls d_path(), which, in turn, traverse dentry up to current->fs->root. Kernel threads always have global root, while container have be in "root jail" - i.e. have it's own nested root. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * SUNRPC: remove "cache_request" argument in sunrpc_cache_pipe_upcall() functionStanislav Kinsbursky2013-02-153-13/+5
| | | | | | | | | | | | | | | | Passing this pointer is redundant since it's stored on cache_detail structure, which is also passed to sunrpc_cache_pipe_upcall () function. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * SUNRPC: rework cache upcall logicStanislav Kinsbursky2013-02-155-49/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | For most of SUNRPC caches (except NFS DNS cache) cache_detail->cache_upcall is redundant since all that it's implementations are doing is calling sunrpc_cache_pipe_upcall() with proper function address argument. Cache request function address is now stored on cache_detail structure and thus all the code can be simplified. Now, for those cache details, which doesn't have cache_upcall callback (the only one, which still has is nfs_dns_resolve_template) sunrpc_cache_pipe_upcall will be called instead. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * SUNRPC: introduce cache_detail->cache_request callbackStanislav Kinsbursky2013-02-156-8/+20
| | | | | | | | | | | | | | | | This callback will allow to simplify upcalls in further patches in this series. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * NFS: simplify and clean cache libraryStanislav Kinsbursky2013-02-153-16/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | This is a cleanup patch. Such helpers like nfs_cache_init() and nfs_cache_destroy() are redundant, because they are just a wrappers around sunrpc_init_cache_detail() and sunrpc_destroy_cache_detail() respectively. So let's remove them completely and move corresponding logic to nfs_cache_register_net() and nfs_cache_unregister_net() respectively (since they are called together anyway). Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * NFS: use SUNRPC cache creation and destruction helper for DNS cacheStanislav Kinsbursky2013-02-151-35/+25
| | | | | | | | | | | | | | | | | | | | This cache was the first containerized and doesn't use net-aware cache creation and destruction helpers. This is a cleanup patch which just makes code looks clearer and reduce amount of lines of code. Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd4: free_stid can be staticFengguang Wu2013-02-111-1/+1
| | | | | | | | Reported-by: Fengguang Wu <fengguang.wu@intel.com>
| * nfsd: keep a checksum of the first 256 bytes of requestJeff Layton2013-02-082-3/+49
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Now that we're allowing more DRC entries, it becomes a lot easier to hit problems with XID collisions. In order to mitigate those, calculate a checksum of up to the first 256 bytes of each request coming in and store that in the cache entry, along with the total length of the request. This initially used crc32, but Chuck Lever and Jim Rees pointed out that crc32 is probably more heavyweight than we really need for generating these checksums, and recommended looking at using the same routines that are used to generate checksums for IP packets. On an x86_64 KVM guest measurements with ftrace showed ~800ns to use csum_partial vs ~1750ns for crc32. The difference probably isn't terribly significant, but for now we may as well use csum_partial. Signed-off-by: Jeff Layton <jlayton@redhat.com> Stones-thrown-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * sunrpc: trim off trailing checksum before returning decrypted or integrity ↵Jeff Layton2013-02-084-2/+52
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | authenticated buffer When GSSAPI integrity signatures are in use, or when we're using GSSAPI privacy with the v2 token format, there is a trailing checksum on the xdr_buf that is returned. It's checked during the authentication stage, and afterward nothing cares about it. Ordinarily, it's not a problem since the XDR code generally ignores it, but it will be when we try to compute a checksum over the buffer to help prevent XID collisions in the duplicate reply cache. Fix the code to trim off the checksums after verifying them. Note that in unwrap_integ_data, we must avoid trying to reverify the checksum if the request was deferred since it will no longer be present when it's revisited. Signed-off-by: Jeff Layton <jlayton@redhat.com>
| * sunrpc: fix comment in struct xdr_buf definitionJeff Layton2013-02-051-1/+1
| | | | | | | | | | | | | | ...these pages aren't necessarily contiguous. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * sunrpc: move address copy/cmp/convert routines and prototypes from clnt.h to ↵Jeff Layton2013-02-0521-163/+191
| | | | | | | | | | | | | | | | | | | | | | addr.h These routines are used by server and client code, so having them in a separate header would be best. Signed-off-by: Jeff Layton <jlayton@redhat.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * sunrpc: copy scope ID in __rpc_copy_addr6Jeff Layton2013-02-051-0/+1
| | | | | | | | | | | | | | | | When copying an address, we should also copy the scopeid in the event that this is a link-local address and the scope matters. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd4: simplify idr allocationJ. Bruce Fields2013-02-051-29/+52
| | | | | | | | | | | | | | | | We don't really need to preallocate at all; just allocate and initialize everything at once, but leave the sc_type field initially 0 to prevent finding the stateid till it's fully initialized. Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: Fix memleakmajianpeng2013-02-051-0/+2
| | | | | | | | | | | | | | | | When free nfs-client, it must free the ->cl_stateids. Cc: stable@kernel.org Signed-off-by: Jianpeng Ma <majianpeng@gmail.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: register a shrinker for DRC cache entriesJeff Layton2013-02-041-0/+23
| | | | | | | | | | | | | | | | | | | | | | Since we dynamically allocate them now, allow the system to call us up to release them if it gets low on memory. Since these entries aren't replaceable, only free ones that are expired or that are over the cap. The the seeks value is set to '1' however to indicate that freeing the these entries is low-cost. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: add recurring workqueue job to clean the cacheJeff Layton2013-02-041-3/+47
| | | | | | | | | | | | | | | | | | | | | | It's not sufficient to only clean the cache when requests come in. What if we have a flurry of activity and then the server goes idle? Add a workqueue job that will clean the cache every RC_EXPIRE period. Care is taken to only run this when we expect to have entries expiring. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: when updating an entry with RC_NOCACHE, just free itJeff Layton2013-02-041-4/+14
| | | | | | | | | | | | | | | | | | | | | | | | There's no need to keep entries around that we're declaring RC_NOCACHE. Ditto if there's a problem with the entry. With this change too, there's no need to test for RC_UNUSED in the search function. If the entry's in the hash table then it's either INPROG or DONE. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
| * nfsd: remove the cache_disabled flagJeff Layton2013-02-041-7/+3
| | | | | | | | | | | | | | | | With the change to dynamically allocate entries, the cache is never disabled on the fly. Remove this flag. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
OpenPOWER on IntegriCloud