From 3dd4765fce04c0b4af1e0bc4c0b10f906f95fabc Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 2 Aug 2012 14:30:56 -0400 Subject: [PATCH 01/15] nfs: tear down caches in nfs_init_writepagecache when allocation fails ...and ensure that we tear down the nfs_commit_data cache too when unloading the module. Cc: Bryan Schumaker Cc: stable@vger.kernel.org Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5829d0ce7cfb..e3b55372726c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1814,19 +1814,19 @@ int __init nfs_init_writepagecache(void) nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE, nfs_wdata_cachep); if (nfs_wdata_mempool == NULL) - return -ENOMEM; + goto out_destroy_write_cache; nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", sizeof(struct nfs_commit_data), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_cdata_cachep == NULL) - return -ENOMEM; + goto out_destroy_write_mempool; nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, nfs_wdata_cachep); if (nfs_commit_mempool == NULL) - return -ENOMEM; + goto out_destroy_commit_cache; /* * NFS congestion size, scale with available memory. @@ -1849,11 +1849,20 @@ int __init nfs_init_writepagecache(void) nfs_congestion_kb = 256*1024; return 0; + +out_destroy_commit_cache: + kmem_cache_destroy(nfs_cdata_cachep); +out_destroy_write_mempool: + mempool_destroy(nfs_wdata_mempool); +out_destroy_write_cache: + kmem_cache_destroy(nfs_wdata_cachep); + return -ENOMEM; } void nfs_destroy_writepagecache(void) { mempool_destroy(nfs_commit_mempool); + kmem_cache_destroy(nfs_cdata_cachep); mempool_destroy(nfs_wdata_mempool); kmem_cache_destroy(nfs_wdata_cachep); } From 8554116e17eef055d9dd58a94b3427cb2ad1c317 Mon Sep 17 00:00:00 2001 From: Idan Kedar Date: Thu, 2 Aug 2012 11:47:10 +0300 Subject: [PATCH 02/15] pnfs: defer release of pages in layoutget we have encountered a bug whereby reading a lot of files (copying fedora's /bin) from a pNFS mount and hitting Ctrl+C in the middle caused a general protection fault in xdr_shrink_bufhead. this function is called when decoding the response from LAYOUTGET. the decoding is done by a worker thread, and the caller of LAYOUTGET waits for the worker thread to complete. hitting Ctrl+C caused the synchronous wait to end and the next thing the caller does is to free the pages, so when the worker thread calls xdr_shrink_bufhead, the pages are gone. therefore, the cleanup of these pages has been moved to nfs4_layoutget_release. Signed-off-by: Idan Kedar Signed-off-by: Benny Halevy Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++- fs/nfs/pnfs.c | 39 +------------------------------- fs/nfs/pnfs.h | 2 +- 3 files changed, 58 insertions(+), 40 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a99a8d948721..6a78d49da5c1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6223,11 +6223,58 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) dprintk("<-- %s\n", __func__); } +static size_t max_response_pages(struct nfs_server *server) +{ + u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + return nfs_page_array_len(0, max_resp_sz); +} + +static void nfs4_free_pages(struct page **pages, size_t size) +{ + int i; + + if (!pages) + return; + + for (i = 0; i < size; i++) { + if (!pages[i]) + break; + __free_page(pages[i]); + } + kfree(pages); +} + +static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags) +{ + struct page **pages; + int i; + + pages = kcalloc(size, sizeof(struct page *), gfp_flags); + if (!pages) { + dprintk("%s: can't alloc array of %zu pages\n", __func__, size); + return NULL; + } + + for (i = 0; i < size; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) { + dprintk("%s: failed to allocate page\n", __func__); + nfs4_free_pages(pages, size); + return NULL; + } + } + + return pages; +} + static void nfs4_layoutget_release(void *calldata) { struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); dprintk("--> %s\n", __func__); + nfs4_free_pages(lgp->args.layout.pages, max_pages); put_nfs_open_context(lgp->args.ctx); kfree(calldata); dprintk("<-- %s\n", __func__); @@ -6239,9 +6286,10 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = { .rpc_release = nfs4_layoutget_release, }; -int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) +int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) { struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); struct rpc_task *task; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], @@ -6259,6 +6307,13 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) dprintk("--> %s\n", __func__); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); + if (!lgp->args.layout.pages) { + nfs4_layoutget_release(lgp); + return -ENOMEM; + } + lgp->args.layout.pglen = max_pages * PAGE_SIZE; + lgp->res.layoutp = &lgp->args.layout; lgp->res.seq_res.sr_slot = NULL; nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 76875bfcf19c..2e00feacd4be 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -583,9 +583,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_server *server = NFS_SERVER(ino); struct nfs4_layoutget *lgp; struct pnfs_layout_segment *lseg = NULL; - struct page **pages = NULL; - int i; - u32 max_resp_sz, max_pages; dprintk("--> %s\n", __func__); @@ -594,20 +591,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, if (lgp == NULL) return NULL; - /* allocate pages for xdr post processing */ - max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = nfs_page_array_len(0, max_resp_sz); - - pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); - if (!pages) - goto out_err_free; - - for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(gfp_flags); - if (!pages[i]) - goto out_err_free; - } - lgp->args.minlength = PAGE_CACHE_SIZE; if (lgp->args.minlength > range->length) lgp->args.minlength = range->length; @@ -616,39 +599,19 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.type = server->pnfs_curr_ld->id; lgp->args.inode = ino; lgp->args.ctx = get_nfs_open_context(ctx); - lgp->args.layout.pages = pages; - lgp->args.layout.pglen = max_pages * PAGE_SIZE; lgp->lsegpp = &lseg; lgp->gfp_flags = gfp_flags; /* Synchronously retrieve layout information from server and * store in lseg. */ - nfs4_proc_layoutget(lgp); + nfs4_proc_layoutget(lgp, gfp_flags); if (!lseg) { /* remember that LAYOUTGET failed and suspend trying */ set_bit(lo_fail_bit(range->iomode), &lo->plh_flags); } - /* free xdr pages */ - for (i = 0; i < max_pages; i++) - __free_page(pages[i]); - kfree(pages); - return lseg; - -out_err_free: - /* free any allocated xdr pages, lgp as it's not used */ - if (pages) { - for (i = 0; i < max_pages; i++) { - if (!pages[i]) - break; - __free_page(pages[i]); - } - kfree(pages); - } - kfree(lgp); - return NULL; } /* diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 2c6c80503ba4..5ea019e80b4c 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -172,7 +172,7 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server, struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); -extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); +extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); /* pnfs.c */ From 21d1f58aedc5f7ac4bb0c4e3d78c74ea31ac050f Mon Sep 17 00:00:00 2001 From: Idan Kedar Date: Thu, 2 Aug 2012 11:47:11 +0300 Subject: [PATCH 03/15] pnfs: nfs4_proc_layoutget returns void since the only user of nfs4_proc_layoutget is send_layoutget, which ignores its return value, there is no reason to return any value. Signed-off-by: Idan Kedar Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 8 ++++---- fs/nfs/pnfs.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6a78d49da5c1..f94f6b3928fc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6286,7 +6286,7 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = { .rpc_release = nfs4_layoutget_release, }; -int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) +void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) { struct nfs_server *server = NFS_SERVER(lgp->args.inode); size_t max_pages = max_response_pages(server); @@ -6310,7 +6310,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); if (!lgp->args.layout.pages) { nfs4_layoutget_release(lgp); - return -ENOMEM; + return; } lgp->args.layout.pglen = max_pages * PAGE_SIZE; @@ -6319,7 +6319,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) - return PTR_ERR(task); + return; status = nfs4_wait_for_completion_rpc_task(task); if (status == 0) status = task->tk_status; @@ -6327,7 +6327,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) status = pnfs_layout_process(lgp); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); - return status; + return; } static void diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 5ea019e80b4c..745aa1b39e7c 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -172,7 +172,7 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server, struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); -extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); +extern void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); /* pnfs.c */ From f6166384095b7ecf77752b5e9096e6d03d75f7ae Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 2 Aug 2012 15:36:09 +0300 Subject: [PATCH 04/15] NFS41: add pg_layout_private to nfs_pageio_descriptor To allow layout driver to pass private information around pg_init/pg_doio. Signed-off-by: Peng Tao Signed-off-by: Boaz Harrosh Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 2 ++ include/linux/nfs_page.h | 1 + include/linux/nfs_xdr.h | 1 + 3 files changed, 4 insertions(+) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1a6732ed04a4..311a79681e2b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -49,6 +49,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; hdr->dreq = desc->pg_dreq; + hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) @@ -268,6 +269,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_error = 0; desc->pg_lseg = NULL; desc->pg_dreq = NULL; + desc->pg_layout_private = NULL; } EXPORT_SYMBOL_GPL(nfs_pageio_init); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 880805774f9f..92ce5783b707 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -69,6 +69,7 @@ struct nfs_pageio_descriptor { const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; struct nfs_direct_req *pg_dreq; + void *pg_layout_private; }; #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 00485e084394..ac7c8ae254f2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1248,6 +1248,7 @@ struct nfs_pgio_header { void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; struct nfs_direct_req *dreq; + void *layout_private; spinlock_t lock; /* fields protected by lock */ int pnfs_error; From 7de6e28417c65919cf2c1621841a650c4a3afbbd Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 2 Aug 2012 15:38:23 +0300 Subject: [PATCH 05/15] pnfs-obj: Better IO pattern in case of unaligned offset Depending on layout and ARCH, ORE has some limits on max IO sizes which is communicated on (what else) ore_layout->max_io_length, which is always stripe aligned. This was considered as the pg_test boundary for splitting and starting a new IO. But in the case of a long IO where the start offset is not aligned what would happen is that both end of IO[N] and start of IO[N+1] would be unaligned, causing each IO boundary parity unit to be calculated and written twice. So what we do in this patch is split the very start of an unaligned IO, up to a stripe boundary, and then next IO's can continue fully aligned til the end. We might be sacrificing the case where the full unaligned IO would fit within a single max_io_length, but the sacrifice is well worth the elimination of double calculation and parity units IO. Actually the sacrificing is marginal and is almost unmeasurable. TODO: If we know the total expected linear segment that will be received, at pg_init, we could use that information in many places: 1. blocks-layout get_layout write segment size 2. Better mds-threshold 3. In above situation for a better clean split I will do this in future submission. Signed-off-by: Boaz Harrosh Signed-off-by: Trond Myklebust --- fs/nfs/objlayout/objio_osd.c | 55 ++++++++++++++++++++++++++++++++++-- 1 file changed, 52 insertions(+), 3 deletions(-) diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index f50d3e8d6f22..ea6d111b03e9 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -570,17 +570,66 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, return false; return pgio->pg_count + req->wb_bytes <= - OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + (unsigned long)pgio->pg_layout_private; +} + +void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + pnfs_generic_pg_init_read(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; +} + +static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout, + unsigned long *stripe_end) +{ + u32 stripe_off; + unsigned stripe_size; + + if (layout->raid_algorithm == PNFS_OSD_RAID_0) + return true; + + stripe_size = layout->stripe_unit * + (layout->group_width - layout->parity); + + div_u64_rem(offset, stripe_size, &stripe_off); + if (!stripe_off) + return true; + + *stripe_end = stripe_size - stripe_off; + return false; +} + +void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + unsigned long stripe_end = 0; + + pnfs_generic_pg_init_write(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + if (req->wb_offset || + !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE, + &OBJIO_LSEG(pgio->pg_lseg)->layout, + &stripe_end)) { + pgio->pg_layout_private = (void *)stripe_end; + } else { + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + } } static const struct nfs_pageio_ops objio_pg_read_ops = { - .pg_init = pnfs_generic_pg_init_read, + .pg_init = objio_init_read, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops objio_pg_write_ops = { - .pg_init = pnfs_generic_pg_init_write, + .pg_init = objio_init_write, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; From 47fbf7976e0b7d9dcdd799e2a1baba19064d9631 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 8 Aug 2012 16:03:13 -0400 Subject: [PATCH 06/15] NFSv4.1: Remove a bogus BUG_ON() in nfs4_layoutreturn_done Ever since commit 0a57cdac3f (NFSv4.1 send layoutreturn to fence disconnected data server) we've been sending layoutreturn calls while there is potentially still outstanding I/O to the data servers. The reason we do this is to avoid races between replayed writes to the MDS and the original writes to the DS. When this happens, the BUG_ON() in nfs4_layoutreturn_done can be triggered because it assumes that we would never call layoutreturn without knowing that all I/O to the DS is finished. The fix is to remove the BUG_ON() now that the assumptions behind the test are obsolete. Reported-by: Boaz Harrosh Reported-by: Tigran Mkrtchyan Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org [>=3.5] --- fs/nfs/nfs4proc.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f94f6b3928fc..c77d296bdaa6 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6359,12 +6359,8 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) return; } spin_lock(&lo->plh_inode->i_lock); - if (task->tk_status == 0) { - if (lrp->res.lrs_present) { - pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - } else - BUG_ON(!list_empty(&lo->plh_segs)); - } + if (task->tk_status == 0 && lrp->res.lrs_present) + pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); dprintk("<-- %s\n", __func__); From 1ae811ee27912a0521e4b92dc9a1850c0243a247 Mon Sep 17 00:00:00 2001 From: "bjschuma@gmail.com" Date: Wed, 8 Aug 2012 13:57:06 -0400 Subject: [PATCH 07/15] NFS: Fix a regression when loading the NFS v4 module Some systems have a modprobe.d/nfs.conf file that sets an nfs4 alias pointing to nfs.ko, rather than nfs4.ko. This can prevent the v4 module from loading on mount, since the kernel sees that something named "nfs4" has already been loaded. To work around this, I've renamed the modules to "nfsv2.ko" "nfsv3.ko" and "nfsv4.ko". I also had to move the nfs4_fs_type back to nfs.ko to ensure that `mount -t nfs4` still works. Signed-off-by: Bryan Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/Makefile | 18 +++++++++--------- fs/nfs/client.c | 2 +- fs/nfs/nfs4_fs.h | 3 +++ fs/nfs/nfs4super.c | 15 --------------- fs/nfs/super.c | 37 ++++++++++++++++++++++++++++++++++++- 5 files changed, 49 insertions(+), 26 deletions(-) diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 8bf3a3f6925a..b7db60897f91 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,19 +12,19 @@ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o -obj-$(CONFIG_NFS_V2) += nfs2.o -nfs2-y := nfs2super.o proc.o nfs2xdr.o +obj-$(CONFIG_NFS_V2) += nfsv2.o +nfsv2-y := nfs2super.o proc.o nfs2xdr.o -obj-$(CONFIG_NFS_V3) += nfs3.o -nfs3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o -nfs3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o +obj-$(CONFIG_NFS_V3) += nfsv3.o +nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o +nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o -obj-$(CONFIG_NFS_V4) += nfs4.o -nfs4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ +obj-$(CONFIG_NFS_V4) += nfsv4.o +nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \ nfs4namespace.o nfs4getroot.o nfs4client.o -nfs4-$(CONFIG_SYSCTL) += nfs4sysctl.o -nfs4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o +nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9fc0d9dfc91b..99694442b93f 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -105,7 +105,7 @@ struct nfs_subversion *get_nfs_version(unsigned int version) if (IS_ERR(nfs)) { mutex_lock(&nfs_version_mutex); - request_module("nfs%d", version); + request_module("nfsv%d", version); nfs = find_nfs_version(version); mutex_unlock(&nfs_version_mutex); } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3b950dd81e81..da0618aeeadb 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -205,6 +205,9 @@ extern const struct dentry_operations nfs4_dentry_operations; int nfs_atomic_open(struct inode *, struct dentry *, struct file *, unsigned, umode_t, int *); +/* super.c */ +extern struct file_system_type nfs4_fs_type; + /* nfs4namespace.c */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 12a31a9dbcdd..bd61221ad2c5 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -23,14 +23,6 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data); -static struct file_system_type nfs4_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs_fs_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; - static struct file_system_type nfs4_remote_fs_type = { .owner = THIS_MODULE, .name = "nfs4", @@ -344,14 +336,8 @@ static int __init init_nfs_v4(void) if (err) goto out1; - err = register_filesystem(&nfs4_fs_type); - if (err < 0) - goto out2; - register_nfs_version(&nfs_v4); return 0; -out2: - nfs4_unregister_sysctl(); out1: nfs_idmap_quit(); out: @@ -361,7 +347,6 @@ out: static void __exit exit_nfs_v4(void) { unregister_nfs_version(&nfs_v4); - unregister_filesystem(&nfs4_fs_type); nfs4_unregister_sysctl(); nfs_idmap_quit(); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ac6a3c55dce4..c4a15c55519c 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -319,6 +319,34 @@ EXPORT_SYMBOL_GPL(nfs_sops); static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name); + +struct file_system_type nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs_fs_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; +EXPORT_SYMBOL_GPL(nfs4_fs_type); + +static int __init register_nfs4_fs(void) +{ + return register_filesystem(&nfs4_fs_type); +} + +static void unregister_nfs4_fs(void) +{ + unregister_filesystem(&nfs4_fs_type); +} +#else +static int __init register_nfs4_fs(void) +{ + return 0; +} + +static void unregister_nfs4_fs(void) +{ +} #endif static struct shrinker acl_shrinker = { @@ -337,12 +365,18 @@ int __init register_nfs_fs(void) if (ret < 0) goto error_0; - ret = nfs_register_sysctl(); + ret = register_nfs4_fs(); if (ret < 0) goto error_1; + + ret = nfs_register_sysctl(); + if (ret < 0) + goto error_2; register_shrinker(&acl_shrinker); return 0; +error_2: + unregister_nfs4_fs(); error_1: unregister_filesystem(&nfs_fs_type); error_0: @@ -356,6 +390,7 @@ void __exit unregister_nfs_fs(void) { unregister_shrinker(&acl_shrinker); nfs_unregister_sysctl(); + unregister_nfs4_fs(); unregister_filesystem(&nfs_fs_type); } From 425e776d93a7a5070b77d4f458a5bab0f924652c Mon Sep 17 00:00:00 2001 From: "bjschuma@gmail.com" Date: Wed, 8 Aug 2012 13:57:10 -0400 Subject: [PATCH 08/15] NFS: Alias the nfs module to nfs4 This allows distros to remove the line from their modprobe configuration. Signed-off-by: Bryan Schumaker Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- fs/nfs/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index c4a15c55519c..239aff7338eb 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2680,4 +2680,6 @@ MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 " module_param(send_implementation_id, ushort, 0644); MODULE_PARM_DESC(send_implementation_id, "Send implementation ID with NFSv4.1 exchange_id"); +MODULE_ALIAS("nfs4"); + #endif /* CONFIG_NFS_V4 */ From 519d3959e30a98f8e135e7a16647c10af5ad63d5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2012 17:30:10 -0400 Subject: [PATCH 09/15] NFSv4: Fix pointer arithmetic in decode_getacl Resetting the cursor xdr->p to a previous value is not a safe practice: if the xdr_stream has crossed out of the initial iovec, then a bunch of other fields would need to be reset too. Fix this issue by using xdr_enter_page() so that the buffer gets page aligned at the bitmap _before_ we decode it. Also fix the confusion of the ACL length with the page buffer length by not adding the base offset to the ACL length... Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org --- fs/nfs/nfs4proc.c | 2 +- fs/nfs/nfs4xdr.c | 21 +++++++-------------- 2 files changed, 8 insertions(+), 15 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c77d296bdaa6..286ab7078413 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3819,7 +3819,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (ret) goto out_free; - acl_len = res.acl_len - res.acl_data_offset; + acl_len = res.acl_len; if (acl_len > args.acl_len) nfs4_write_cached_acl(inode, NULL, 0, acl_len); else diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ca13483edd60..54d3f5a9faa6 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5049,18 +5049,14 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, uint32_t attrlen, bitmap[3] = {0}; int status; - size_t page_len = xdr->buf->page_len; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto out; + xdr_enter_page(xdr, xdr->buf->page_len); + bm_p = xdr->p; - res->acl_data_offset = be32_to_cpup(bm_p) + 2; - res->acl_data_offset <<= 2; - /* Check if the acl data starts beyond the allocated buffer */ - if (res->acl_data_offset > page_len) - return -ERANGE; if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; @@ -5074,23 +5070,20 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ - xdr->p = bm_p; + res->acl_data_offset = (xdr->p - bm_p) << 2; /* We ignore &savep and don't do consistency checks on * the attr length. Let userspace figure it out.... */ - attrlen += res->acl_data_offset; - if (attrlen > page_len) { + res->acl_len = attrlen; + if (attrlen + res->acl_data_offset > xdr->buf->page_len) { if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { /* getxattr interface called with a NULL buf */ - res->acl_len = attrlen; goto out; } - dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", - attrlen, page_len); + dprintk("NFS: acl reply: attrlen %u > page_len %u\n", + attrlen, xdr->buf->page_len); return -EINVAL; } - xdr_read_pages(xdr, attrlen); - res->acl_len = attrlen; } else status = -EOPNOTSUPP; From b291f1b1c86aa0c7bc3df2994e6a1a4e53f1fde0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2012 18:30:41 -0400 Subject: [PATCH 10/15] NFSv4: Fix the acl cache size calculation Currently, we do not take into account the size of the 16 byte struct nfs4_cached_acl header, when deciding whether or not we should cache the acl data. Consequently, we will end up allocating an 8k buffer in order to fit a maximum size 4k acl. This patch adjusts the calculation so that we limit the cache size to 4k for the acl header+data. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 286ab7078413..635274140b18 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3737,9 +3737,10 @@ out: static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) { struct nfs4_cached_acl *acl; + size_t buflen = sizeof(*acl) + acl_len; - if (pages && acl_len <= PAGE_SIZE) { - acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL); + if (pages && buflen <= PAGE_SIZE) { + acl = kmalloc(buflen, GFP_KERNEL); if (acl == NULL) goto out; acl->cached = 1; From cff298c721099c9ac4cea7196a37097ba2847946 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2012 17:14:17 -0400 Subject: [PATCH 11/15] NFSv4: Don't use private xdr_stream fields in decode_getacl Instead of using the private field xdr->p from struct xdr_stream, use the public xdr_stream_pos(). Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 54d3f5a9faa6..1bfbd67c556d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5045,10 +5045,10 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_getaclres *res) { unsigned int savep; - __be32 *bm_p; uint32_t attrlen, bitmap[3] = {0}; int status; + unsigned int pg_offset; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) @@ -5056,7 +5056,8 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, xdr_enter_page(xdr, xdr->buf->page_len); - bm_p = xdr->p; + /* Calculate the offset of the page data */ + pg_offset = xdr->buf->head[0].iov_len; if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; @@ -5070,18 +5071,18 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ - res->acl_data_offset = (xdr->p - bm_p) << 2; + res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset; /* We ignore &savep and don't do consistency checks on * the attr length. Let userspace figure it out.... */ res->acl_len = attrlen; - if (attrlen + res->acl_data_offset > xdr->buf->page_len) { + if (attrlen > (xdr->nwords << 2)) { if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { /* getxattr interface called with a NULL buf */ goto out; } dprintk("NFS: acl reply: attrlen %u > page_len %u\n", - attrlen, xdr->buf->page_len); + attrlen, xdr->nwords << 2); return -EINVAL; } } else From c5066945b7ea346a11424dbeb7830b7d7d00c206 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 9 Aug 2012 14:05:49 -0400 Subject: [PATCH 12/15] NFS: Clear key construction data if the idmap upcall fails idmap_pipe_downcall already clears this field if the upcall succeeds, but if it fails (rpc.idmapd isn't running) the field will still be set on the next call triggering a BUG_ON(). This patch tries to handle all possible ways that the upcall could fail and clear the idmap key data for each one. Signed-off-by: Bryan Schumaker Tested-by: William Dauchy Cc: stable@vger.kernel.org [>= 3.4] Signed-off-by: Trond Myklebust --- fs/nfs/idmap.c | 56 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 42 insertions(+), 14 deletions(-) diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b701358c39c3..6703c73307a5 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -61,6 +61,12 @@ struct idmap { struct mutex idmap_mutex; }; +struct idmap_legacy_upcalldata { + struct rpc_pipe_msg pipe_msg; + struct idmap_msg idmap_msg; + struct idmap *idmap; +}; + /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields * @fattr: fully initialised struct nfs_fattr @@ -324,6 +330,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + idmap->idmap_key_cons = NULL; mutex_unlock(&idmap->idmap_mutex); } return ret; @@ -380,11 +387,13 @@ static const match_table_t nfs_idmap_tokens = { static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); +static void idmap_release_pipe(struct inode *); static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = idmap_pipe_downcall, + .release_pipe = idmap_release_pipe, .destroy_msg = idmap_pipe_destroy_msg, }; @@ -616,7 +625,8 @@ void nfs_idmap_quit(void) nfs_idmap_quit_keyring(); } -static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im, +static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, + struct idmap_msg *im, struct rpc_pipe_msg *msg) { substring_t substr; @@ -659,6 +669,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, const char *op, void *aux) { + struct idmap_legacy_upcalldata *data; struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; @@ -666,15 +677,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, int ret = -ENOMEM; /* msg and im are freed in idmap_pipe_destroy_msg */ - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - goto out0; - - im = kmalloc(sizeof(*im), GFP_KERNEL); - if (!im) + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) goto out1; - ret = nfs_idmap_prepare_message(key->description, im, msg); + msg = &data->pipe_msg; + im = &data->idmap_msg; + data->idmap = idmap; + + ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) goto out2; @@ -683,15 +694,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - goto out2; + goto out3; return ret; +out3: + idmap->idmap_key_cons = NULL; out2: - kfree(im); + kfree(data); out1: - kfree(msg); -out0: complete_request_key(cons, ret); return ret; } @@ -775,9 +786,26 @@ out_incomplete: static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) { + struct idmap_legacy_upcalldata *data = container_of(msg, + struct idmap_legacy_upcalldata, + pipe_msg); + struct idmap *idmap = data->idmap; + struct key_construction *cons; + if (msg->errno) { + cons = ACCESS_ONCE(idmap->idmap_key_cons); + idmap->idmap_key_cons = NULL; + complete_request_key(cons, msg->errno); + } /* Free memory allocated in nfs_idmap_legacy_upcall() */ - kfree(msg->data); - kfree(msg); + kfree(data); +} + +static void +idmap_release_pipe(struct inode *inode) +{ + struct rpc_inode *rpci = RPC_I(inode); + struct idmap *idmap = (struct idmap *)rpci->private; + idmap->idmap_key_cons = NULL; } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid) From 12dfd080556124088ed61a292184947711b46cbe Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 9 Aug 2012 14:05:50 -0400 Subject: [PATCH 13/15] NFS: return -ENOKEY when the upcall fails to map the name This allows the normal error-paths to handle the error, rather than making a special call to complete_request_key() just for this instance. Signed-off-by: Bryan Schumaker Tested-by: William Dauchy Cc: stable@vger.kernel.org [>= 3.4] Signed-off-by: Trond Myklebust --- fs/nfs/idmap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 6703c73307a5..a850079467d8 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -760,9 +760,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } if (!(im.im_status & IDMAP_STATUS_SUCCESS)) { - ret = mlen; - complete_request_key(cons, -ENOKEY); - goto out_incomplete; + ret = -ENOKEY; + goto out; } namelen_in = strnlen(im.im_name, IDMAP_NAMESZ); @@ -779,7 +778,6 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) out: complete_request_key(cons, ret); -out_incomplete: return ret; } From 7653f6ff4ebab2a094e65b60fb19ee66ed2f78e7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 20 Aug 2012 12:12:29 -0400 Subject: [PATCH 14/15] NFSv4: Ensure that nfs4_alloc_client cleans up on error. Any pointer that was allocated through nfs_alloc_client() needs to be freed via a call to nfs_free_client(). Reported-by: Stanislav Kinsbursky Signed-off-by: Trond Myklebust --- fs/nfs/nfs4client.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index cbcdfaf32505..24eb663f8ed5 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -74,7 +74,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) return clp; error: - kfree(clp); + nfs_free_client(clp); return ERR_PTR(err); } From 086600430493e04b802bee6e5b3ce0458e4eb77f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 20 Aug 2012 12:42:15 -0400 Subject: [PATCH 15/15] NFSv3: Ensure that do_proc_get_root() reports errors correctly If the rpc call to NFS3PROC_FSINFO fails, then we need to report that error so that the mount fails. Otherwise we can end up with a superblock with completely unusable values for block sizes, maxfilesize, etc. Reported-by: Yuanming Chen Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- fs/nfs/nfs3proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 0952c791df36..d6b3b5f2d779 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -69,7 +69,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle, nfs_fattr_init(info->fattr); status = rpc_call_sync(client, &msg, 0); dprintk("%s: reply fsinfo: %d\n", __func__, status); - if (!(info->fattr->valid & NFS_ATTR_FATTR)) { + if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) { msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; msg.rpc_resp = info->fattr; status = rpc_call_sync(client, &msg, 0);