From 3dd4765fce04c0b4af1e0bc4c0b10f906f95fabc Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 2 Aug 2012 14:30:56 -0400 Subject: 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(-) (limited to 'fs/nfs') 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); } -- cgit v1.2.3 From 8554116e17eef055d9dd58a94b3427cb2ad1c317 Mon Sep 17 00:00:00 2001 From: Idan Kedar Date: Thu, 2 Aug 2012 11:47:10 +0300 Subject: 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(-) (limited to 'fs/nfs') 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 */ -- cgit v1.2.3 From 21d1f58aedc5f7ac4bb0c4e3d78c74ea31ac050f Mon Sep 17 00:00:00 2001 From: Idan Kedar Date: Thu, 2 Aug 2012 11:47:11 +0300 Subject: 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(-) (limited to 'fs/nfs') 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 */ -- cgit v1.2.3 From f6166384095b7ecf77752b5e9096e6d03d75f7ae Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 2 Aug 2012 15:36:09 +0300 Subject: 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(+) (limited to 'fs/nfs') 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; -- cgit v1.2.3 From 7de6e28417c65919cf2c1621841a650c4a3afbbd Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 2 Aug 2012 15:38:23 +0300 Subject: 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(-) (limited to 'fs/nfs') 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, }; -- cgit v1.2.3 From 47fbf7976e0b7d9dcdd799e2a1baba19064d9631 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 8 Aug 2012 16:03:13 -0400 Subject: 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(-) (limited to 'fs/nfs') 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__); -- cgit v1.2.3 From 41f63c5359d14ca995172b8f6eaffd93f60fec54 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 3 Aug 2012 10:30:47 -0700 Subject: workqueue: use mod_delayed_work() instead of cancel + queue Convert delayed_work users doing cancel_delayed_work() followed by queue_delayed_work() to mod_delayed_work(). Most conversions are straight-forward. Ones worth mentioning are, * drivers/edac/edac_mc.c: edac_mc_workq_setup() converted to always use mod_delayed_work() and cancel loop in edac_mc_reset_delay_period() is dropped. * drivers/platform/x86/thinkpad_acpi.c: No need to remember whether watchdog is active or not. @fan_watchdog_active and related code dropped. * drivers/power/charger-manager.c: Seemingly a lot of delayed_work_pending() abuse going on here. [delayed_]work_pending() are unsynchronized and racy when used like this. I converted one instance in fullbatt_handler(). Please conver the rest so that it invokes workqueue APIs for the intended target state rather than trying to game work item pending state transitions. e.g. if timer should be modified - call mod_delayed_work(), canceled - call cancel_delayed_work[_sync](). * drivers/thermal/thermal_sys.c: thermal_zone_device_set_polling() simplified. Note that round_jiffies() calls in this function are meaningless. round_jiffies() work on absolute jiffies not delta delay used by delayed_work. v2: Tomi pointed out that __cancel_delayed_work() users can't be safely converted to mod_delayed_work(). They could be calling it from irq context and if that happens while delayed_work_timer_fn() is running, it could deadlock. __cancel_delayed_work() users are dropped. Signed-off-by: Tejun Heo Acked-by: Henrique de Moraes Holschuh Acked-by: Dmitry Torokhov Acked-by: Anton Vorontsov Acked-by: David Howells Cc: Tomi Valkeinen Cc: Jens Axboe Cc: Jiri Kosina Cc: Doug Thompson Cc: David Airlie Cc: Roland Dreier Cc: "John W. Linville" Cc: Zhang Rui Cc: Len Brown Cc: "J. Bruce Fields" Cc: Johannes Berg --- block/genhd.c | 6 ++---- drivers/edac/edac_mc.c | 17 +---------------- drivers/infiniband/core/addr.c | 4 +--- drivers/infiniband/hw/nes/nes_hw.c | 6 ++---- drivers/infiniband/hw/nes/nes_nic.c | 5 ++--- drivers/net/wireless/ipw2x00/ipw2100.c | 8 +++----- drivers/net/wireless/zd1211rw/zd_usb.c | 3 +-- drivers/platform/x86/thinkpad_acpi.c | 20 +++++--------------- drivers/power/charger-manager.c | 9 +++------ drivers/power/ds2760_battery.c | 9 +++------ drivers/power/jz4740-battery.c | 6 ++---- drivers/thermal/thermal_sys.c | 15 ++++++--------- fs/afs/callback.c | 4 +--- fs/afs/server.c | 10 ++-------- fs/afs/vlocation.c | 14 +++----------- fs/nfs/nfs4renewd.c | 3 +-- net/core/dst.c | 4 ++-- net/rfkill/input.c | 3 +-- 18 files changed, 41 insertions(+), 105 deletions(-) (limited to 'fs/nfs') diff --git a/block/genhd.c b/block/genhd.c index cac7366957c3..5d8b44a6442b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1534,10 +1534,8 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask) spin_lock_irq(&ev->lock); ev->clearing |= mask; - if (!ev->block) { - cancel_delayed_work(&ev->dwork); - queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0); - } + if (!ev->block) + mod_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0); spin_unlock_irq(&ev->lock); } diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 616d90bcb3a4..7c0df4af9ef7 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -538,7 +538,7 @@ static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec) return; INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function); - queue_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec)); + mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec)); } /* @@ -578,21 +578,6 @@ void edac_mc_reset_delay_period(int value) mutex_lock(&mem_ctls_mutex); - /* scan the list and turn off all workq timers, doing so under lock - */ - list_for_each(item, &mc_devices) { - mci = list_entry(item, struct mem_ctl_info, link); - - if (mci->op_state == OP_RUNNING_POLL) - cancel_delayed_work(&mci->work); - } - - mutex_unlock(&mem_ctls_mutex); - - - /* re-walk the list, and reset the poll delay */ - mutex_lock(&mem_ctls_mutex); - list_for_each(item, &mc_devices) { mci = list_entry(item, struct mem_ctl_info, link); diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 28058ae33d38..eaec8d7a3b73 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -152,13 +152,11 @@ static void set_timeout(unsigned long time) { unsigned long delay; - cancel_delayed_work(&work); - delay = time - jiffies; if ((long)delay <= 0) delay = 1; - queue_delayed_work(addr_wq, &work, delay); + mod_delayed_work(addr_wq, &work, delay); } static void queue_req(struct addr_req *req) diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c index d42c9f435b1b..9e0895b45eb8 100644 --- a/drivers/infiniband/hw/nes/nes_hw.c +++ b/drivers/infiniband/hw/nes/nes_hw.c @@ -2679,11 +2679,9 @@ static void nes_process_mac_intr(struct nes_device *nesdev, u32 mac_number) } } if (nesadapter->phy_type[mac_index] == NES_PHY_TYPE_SFP_D) { - if (nesdev->link_recheck) - cancel_delayed_work(&nesdev->work); nesdev->link_recheck = 1; - schedule_delayed_work(&nesdev->work, - NES_LINK_RECHECK_DELAY); + mod_delayed_work(system_wq, &nesdev->work, + NES_LINK_RECHECK_DELAY); } } diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c index f3a3ecf8d09e..e43f6e41a6bd 100644 --- a/drivers/infiniband/hw/nes/nes_nic.c +++ b/drivers/infiniband/hw/nes/nes_nic.c @@ -243,10 +243,9 @@ static int nes_netdev_open(struct net_device *netdev) spin_lock_irqsave(&nesdev->nesadapter->phy_lock, flags); if (nesdev->nesadapter->phy_type[nesdev->mac_index] == NES_PHY_TYPE_SFP_D) { - if (nesdev->link_recheck) - cancel_delayed_work(&nesdev->work); nesdev->link_recheck = 1; - schedule_delayed_work(&nesdev->work, NES_LINK_RECHECK_DELAY); + mod_delayed_work(system_wq, &nesdev->work, + NES_LINK_RECHECK_DELAY); } spin_unlock_irqrestore(&nesdev->nesadapter->phy_lock, flags); diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 95aa8e1683ec..8a3420257eeb 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -2180,8 +2180,7 @@ static void isr_indicate_rf_kill(struct ipw2100_priv *priv, u32 status) /* Make sure the RF Kill check timer is running */ priv->stop_rf_kill = 0; - cancel_delayed_work(&priv->rf_kill); - schedule_delayed_work(&priv->rf_kill, round_jiffies_relative(HZ)); + mod_delayed_work(system_wq, &priv->rf_kill, round_jiffies_relative(HZ)); } static void send_scan_event(void *data) @@ -4321,9 +4320,8 @@ static int ipw_radio_kill_sw(struct ipw2100_priv *priv, int disable_radio) "disabled by HW switch\n"); /* Make sure the RF_KILL check timer is running */ priv->stop_rf_kill = 0; - cancel_delayed_work(&priv->rf_kill); - schedule_delayed_work(&priv->rf_kill, - round_jiffies_relative(HZ)); + mod_delayed_work(system_wq, &priv->rf_kill, + round_jiffies_relative(HZ)); } else schedule_reset(priv); } diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c index af83c43bcdb1..ef2b171e3514 100644 --- a/drivers/net/wireless/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zd1211rw/zd_usb.c @@ -1164,8 +1164,7 @@ void zd_usb_reset_rx_idle_timer(struct zd_usb *usb) { struct zd_usb_rx *rx = &usb->rx; - cancel_delayed_work(&rx->idle_work); - queue_delayed_work(zd_workqueue, &rx->idle_work, ZD_RX_IDLE_INTERVAL); + mod_delayed_work(zd_workqueue, &rx->idle_work, ZD_RX_IDLE_INTERVAL); } static inline void init_usb_interrupt(struct zd_usb *usb) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index e7f73287636c..06d2502ffb37 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -7682,25 +7682,15 @@ static int fan_set_speed(int speed) static void fan_watchdog_reset(void) { - static int fan_watchdog_active; - if (fan_control_access_mode == TPACPI_FAN_WR_NONE) return; - if (fan_watchdog_active) - cancel_delayed_work(&fan_watchdog_task); - if (fan_watchdog_maxinterval > 0 && - tpacpi_lifecycle != TPACPI_LIFE_EXITING) { - fan_watchdog_active = 1; - if (!queue_delayed_work(tpacpi_wq, &fan_watchdog_task, - msecs_to_jiffies(fan_watchdog_maxinterval - * 1000))) { - pr_err("failed to queue the fan watchdog, " - "watchdog will not trigger\n"); - } - } else - fan_watchdog_active = 0; + tpacpi_lifecycle != TPACPI_LIFE_EXITING) + mod_delayed_work(tpacpi_wq, &fan_watchdog_task, + msecs_to_jiffies(fan_watchdog_maxinterval * 1000)); + else + cancel_delayed_work(&fan_watchdog_task); } static void fan_watchdog_fire(struct work_struct *ignored) diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c index 526e5c931294..7ff83cf43c8c 100644 --- a/drivers/power/charger-manager.c +++ b/drivers/power/charger-manager.c @@ -509,9 +509,8 @@ static void _setup_polling(struct work_struct *work) if (!delayed_work_pending(&cm_monitor_work) || (delayed_work_pending(&cm_monitor_work) && time_after(next_polling, _next_polling))) { - cancel_delayed_work_sync(&cm_monitor_work); next_polling = jiffies + polling_jiffy; - queue_delayed_work(cm_wq, &cm_monitor_work, polling_jiffy); + mod_delayed_work(cm_wq, &cm_monitor_work, polling_jiffy); } out: @@ -546,10 +545,8 @@ static void fullbatt_handler(struct charger_manager *cm) if (cm_suspended) device_set_wakeup_capable(cm->dev, true); - if (delayed_work_pending(&cm->fullbatt_vchk_work)) - cancel_delayed_work(&cm->fullbatt_vchk_work); - queue_delayed_work(cm_wq, &cm->fullbatt_vchk_work, - msecs_to_jiffies(desc->fullbatt_vchkdrop_ms)); + mod_delayed_work(cm_wq, &cm->fullbatt_vchk_work, + msecs_to_jiffies(desc->fullbatt_vchkdrop_ms)); cm->fullbatt_vchk_jiffies_at = jiffies + msecs_to_jiffies( desc->fullbatt_vchkdrop_ms); diff --git a/drivers/power/ds2760_battery.c b/drivers/power/ds2760_battery.c index 076e211a40b7..704e652072be 100644 --- a/drivers/power/ds2760_battery.c +++ b/drivers/power/ds2760_battery.c @@ -355,8 +355,7 @@ static void ds2760_battery_external_power_changed(struct power_supply *psy) dev_dbg(di->dev, "%s\n", __func__); - cancel_delayed_work(&di->monitor_work); - queue_delayed_work(di->monitor_wqueue, &di->monitor_work, HZ/10); + mod_delayed_work(di->monitor_wqueue, &di->monitor_work, HZ/10); } @@ -401,8 +400,7 @@ static void ds2760_battery_set_charged(struct power_supply *psy) /* postpone the actual work by 20 secs. This is for debouncing GPIO * signals and to let the current value settle. See AN4188. */ - cancel_delayed_work(&di->set_charged_work); - queue_delayed_work(di->monitor_wqueue, &di->set_charged_work, HZ * 20); + mod_delayed_work(di->monitor_wqueue, &di->set_charged_work, HZ * 20); } static int ds2760_battery_get_property(struct power_supply *psy, @@ -616,8 +614,7 @@ static int ds2760_battery_resume(struct platform_device *pdev) di->charge_status = POWER_SUPPLY_STATUS_UNKNOWN; power_supply_changed(&di->bat); - cancel_delayed_work(&di->monitor_work); - queue_delayed_work(di->monitor_wqueue, &di->monitor_work, HZ); + mod_delayed_work(di->monitor_wqueue, &di->monitor_work, HZ); return 0; } diff --git a/drivers/power/jz4740-battery.c b/drivers/power/jz4740-battery.c index 8dbc7bfaab14..ffbed5e5b945 100644 --- a/drivers/power/jz4740-battery.c +++ b/drivers/power/jz4740-battery.c @@ -173,16 +173,14 @@ static void jz_battery_external_power_changed(struct power_supply *psy) { struct jz_battery *jz_battery = psy_to_jz_battery(psy); - cancel_delayed_work(&jz_battery->work); - schedule_delayed_work(&jz_battery->work, 0); + mod_delayed_work(system_wq, &jz_battery->work, 0); } static irqreturn_t jz_battery_charge_irq(int irq, void *data) { struct jz_battery *jz_battery = data; - cancel_delayed_work(&jz_battery->work); - schedule_delayed_work(&jz_battery->work, 0); + mod_delayed_work(system_wq, &jz_battery->work, 0); return IRQ_HANDLED; } diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c index 2ab31e4f02cc..67789b8345d2 100644 --- a/drivers/thermal/thermal_sys.c +++ b/drivers/thermal/thermal_sys.c @@ -694,17 +694,14 @@ thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) static void thermal_zone_device_set_polling(struct thermal_zone_device *tz, int delay) { - cancel_delayed_work(&(tz->poll_queue)); - - if (!delay) - return; - if (delay > 1000) - queue_delayed_work(system_freezable_wq, &(tz->poll_queue), - round_jiffies(msecs_to_jiffies(delay))); + mod_delayed_work(system_freezable_wq, &tz->poll_queue, + round_jiffies(msecs_to_jiffies(delay))); + else if (delay) + mod_delayed_work(system_freezable_wq, &tz->poll_queue, + msecs_to_jiffies(delay)); else - queue_delayed_work(system_freezable_wq, &(tz->poll_queue), - msecs_to_jiffies(delay)); + cancel_delayed_work(&tz->poll_queue); } static void thermal_zone_device_passive(struct thermal_zone_device *tz, diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 587ef5123cd8..7ef637d7f3a5 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -351,9 +351,7 @@ void afs_dispatch_give_up_callbacks(struct work_struct *work) */ void afs_flush_callback_breaks(struct afs_server *server) { - cancel_delayed_work(&server->cb_break_work); - queue_delayed_work(afs_callback_update_worker, - &server->cb_break_work, 0); + mod_delayed_work(afs_callback_update_worker, &server->cb_break_work, 0); } #if 0 diff --git a/fs/afs/server.c b/fs/afs/server.c index d59b7516e943..f342acf3547d 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -285,12 +285,7 @@ static void afs_reap_server(struct work_struct *work) expiry = server->time_of_death + afs_server_timeout; if (expiry > now) { delay = (expiry - now) * HZ; - if (!queue_delayed_work(afs_wq, &afs_server_reaper, - delay)) { - cancel_delayed_work(&afs_server_reaper); - queue_delayed_work(afs_wq, &afs_server_reaper, - delay); - } + mod_delayed_work(afs_wq, &afs_server_reaper, delay); break; } @@ -323,6 +318,5 @@ static void afs_reap_server(struct work_struct *work) void __exit afs_purge_servers(void) { afs_server_timeout = 0; - cancel_delayed_work(&afs_server_reaper); - queue_delayed_work(afs_wq, &afs_server_reaper, 0); + mod_delayed_work(afs_wq, &afs_server_reaper, 0); } diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 431984d2e372..57bcb1596530 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -561,12 +561,7 @@ static void afs_vlocation_reaper(struct work_struct *work) if (expiry > now) { delay = (expiry - now) * HZ; _debug("delay %lu", delay); - if (!queue_delayed_work(afs_wq, &afs_vlocation_reap, - delay)) { - cancel_delayed_work(&afs_vlocation_reap); - queue_delayed_work(afs_wq, &afs_vlocation_reap, - delay); - } + mod_delayed_work(afs_wq, &afs_vlocation_reap, delay); break; } @@ -614,13 +609,10 @@ void afs_vlocation_purge(void) spin_lock(&afs_vlocation_updates_lock); list_del_init(&afs_vlocation_updates); spin_unlock(&afs_vlocation_updates_lock); - cancel_delayed_work(&afs_vlocation_update); - queue_delayed_work(afs_vlocation_update_worker, - &afs_vlocation_update, 0); + mod_delayed_work(afs_vlocation_update_worker, &afs_vlocation_update, 0); destroy_workqueue(afs_vlocation_update_worker); - cancel_delayed_work(&afs_vlocation_reap); - queue_delayed_work(afs_wq, &afs_vlocation_reap, 0); + mod_delayed_work(afs_wq, &afs_vlocation_reap, 0); } /* diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 6930bec91bca..1720d32ffa54 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -117,8 +117,7 @@ nfs4_schedule_state_renewal(struct nfs_client *clp) timeout = 5 * HZ; dprintk("%s: requeueing work. Lease period = %ld\n", __func__, (timeout + HZ - 1) / HZ); - cancel_delayed_work(&clp->cl_renewd); - schedule_delayed_work(&clp->cl_renewd, timeout); + mod_delayed_work(system_wq, &clp->cl_renewd, timeout); set_bit(NFS_CS_RENEWD, &clp->cl_res_state); spin_unlock(&clp->cl_lock); } diff --git a/net/core/dst.c b/net/core/dst.c index 069d51d29414..ed5a0b409aa3 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -214,8 +214,8 @@ void __dst_free(struct dst_entry *dst) if (dst_garbage.timer_inc > DST_GC_INC) { dst_garbage.timer_inc = DST_GC_INC; dst_garbage.timer_expires = DST_GC_MIN; - cancel_delayed_work(&dst_gc_work); - schedule_delayed_work(&dst_gc_work, dst_garbage.timer_expires); + mod_delayed_work(system_wq, &dst_gc_work, + dst_garbage.timer_expires); } spin_unlock_bh(&dst_garbage.lock); } diff --git a/net/rfkill/input.c b/net/rfkill/input.c index 24c55c53e6a2..c9d931e7ffec 100644 --- a/net/rfkill/input.c +++ b/net/rfkill/input.c @@ -164,8 +164,7 @@ static void rfkill_schedule_global_op(enum rfkill_sched_op op) rfkill_op_pending = true; if (op == RFKILL_GLOBAL_OP_EPO && !rfkill_is_epo_lock_active()) { /* bypass the limiter for EPO */ - cancel_delayed_work(&rfkill_op_work); - schedule_delayed_work(&rfkill_op_work, 0); + mod_delayed_work(system_wq, &rfkill_op_work, 0); rfkill_last_scheduled = jiffies; } else rfkill_schedule_ratelimited(); -- cgit v1.2.3 From 1ae811ee27912a0521e4b92dc9a1850c0243a247 Mon Sep 17 00:00:00 2001 From: "bjschuma@gmail.com" Date: Wed, 8 Aug 2012 13:57:06 -0400 Subject: 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(-) (limited to 'fs/nfs') 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); } -- cgit v1.2.3 From 425e776d93a7a5070b77d4f458a5bab0f924652c Mon Sep 17 00:00:00 2001 From: "bjschuma@gmail.com" Date: Wed, 8 Aug 2012 13:57:10 -0400 Subject: 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(+) (limited to 'fs/nfs') 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 */ -- cgit v1.2.3 From 519d3959e30a98f8e135e7a16647c10af5ad63d5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2012 17:30:10 -0400 Subject: 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(-) (limited to 'fs/nfs') 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; -- cgit v1.2.3 From b291f1b1c86aa0c7bc3df2994e6a1a4e53f1fde0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2012 18:30:41 -0400 Subject: 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(-) (limited to 'fs/nfs') 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; -- cgit v1.2.3 From cff298c721099c9ac4cea7196a37097ba2847946 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2012 17:14:17 -0400 Subject: 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(-) (limited to 'fs/nfs') 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 -- cgit v1.2.3 From c5066945b7ea346a11424dbeb7830b7d7d00c206 Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 9 Aug 2012 14:05:49 -0400 Subject: 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(-) (limited to 'fs/nfs') 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) -- cgit v1.2.3 From 12dfd080556124088ed61a292184947711b46cbe Mon Sep 17 00:00:00 2001 From: Bryan Schumaker Date: Thu, 9 Aug 2012 14:05:50 -0400 Subject: 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(-) (limited to 'fs/nfs') 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; } -- cgit v1.2.3 From 7653f6ff4ebab2a094e65b60fb19ee66ed2f78e7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 20 Aug 2012 12:12:29 -0400 Subject: 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(-) (limited to 'fs/nfs') 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); } -- cgit v1.2.3 From 086600430493e04b802bee6e5b3ce0458e4eb77f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 20 Aug 2012 12:42:15 -0400 Subject: 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(-) (limited to 'fs/nfs') 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); -- cgit v1.2.3 From 1856b225ca1f80446938c9ec4a0b330c1772ec45 Mon Sep 17 00:00:00 2001 From: Peter Meerwald Date: Sat, 18 Aug 2012 17:38:54 +0200 Subject: nfs: comment fix Signed-off-by: Peter Meerwald Signed-off-by: Jiri Kosina --- fs/nfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 8b2a2977b720..120d8e98ee5f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1590,7 +1590,7 @@ static int nfs_parse_mount_options(char *raw, /* * verify that any proto=/mountproto= options match the address - * familiies in the addr=/mountaddr= options. + * families in the addr=/mountaddr= options. */ if (protofamily != AF_UNSPEC && protofamily != mnt->nfs_server.address.ss_family) -- cgit v1.2.3 From c3f52af3e03013db5237e339c817beaae5ec9e3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2012 14:56:02 -0400 Subject: NFS: Fix the initialisation of the readdir 'cookieverf' array When the NFS_COOKIEVERF helper macro was converted into a static inline function in commit 99fadcd764 (nfs: convert NFS_*(inode) helpers to static inline), we broke the initialisation of the readdir cookies, since that depended on doing a memset with an argument of 'sizeof(NFS_COOKIEVERF(inode))' which therefore changed from sizeof(be32 cookieverf[2]) to sizeof(be32 *). At this point, NFS_COOKIEVERF seems to be more of an obfuscation than a helper, so the best thing would be to just get rid of it. Also see: https://bugzilla.kernel.org/show_bug.cgi?id=46881 Reported-by: Andi Kleen Reported-by: David Binderman Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org --- fs/nfs/inode.c | 2 +- fs/nfs/nfs3proc.c | 2 +- fs/nfs/nfs4proc.c | 4 ++-- include/linux/nfs_fs.h | 5 ----- 4 files changed, 4 insertions(+), 9 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c6e895f0fbf3..9b47610338f5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -154,7 +154,7 @@ static void nfs_zap_caches_locked(struct inode *inode) nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; - memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode))); + memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf)); if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE; else diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index d6b3b5f2d779..69322096c325 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -643,7 +643,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, u64 cookie, struct page **pages, unsigned int count, int plus) { struct inode *dir = dentry->d_inode; - __be32 *verf = NFS_COOKIEVERF(dir); + __be32 *verf = NFS_I(dir)->cookieverf; struct nfs3_readdirargs arg = { .fh = NFS_FH(dir), .cookie = cookie, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 635274140b18..86b4c7361036 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3215,11 +3215,11 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, dentry->d_parent->d_name.name, dentry->d_name.name, (unsigned long long)cookie); - nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args); + nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args); res.pgbase = args.pgbase; status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); if (status >= 0) { - memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE); + memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE); status += args.pgbase; } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1f8fc7f9bcd8..4b03f56e280e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -265,11 +265,6 @@ static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode) return NFS_SERVER(inode)->nfs_client->rpc_ops; } -static inline __be32 *NFS_COOKIEVERF(const struct inode *inode) -{ - return NFS_I(inode)->cookieverf; -} - static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode) { struct nfs_server *nfss = NFS_SERVER(inode); -- cgit v1.2.3 From 872ece86ea5c367aa92f44689c2d01a1c767aeb3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 4 Sep 2012 11:05:07 -0400 Subject: NFS: Fix a problem with the legacy binary mount code Apparently, am-utils is still using the legacy binary mountdata interface, and is having trouble parsing /proc/mounts due to the 'port=' field being incorrectly set. The following patch should fix up the regression. Reported-by: Marius Tolzmann Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org --- fs/nfs/super.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 239aff7338eb..b8eda700584b 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1867,6 +1867,7 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); + args->nfs_server.port = ntohs(data->addr.sin_port); if (!nfs_verify_server_address(sap)) goto out_no_address; @@ -2564,6 +2565,7 @@ static int nfs4_validate_mount_data(void *options, return -EFAULT; if (!nfs_verify_server_address(sap)) goto out_no_address; + args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); if (data->auth_flavourlen) { if (data->auth_flavourlen > 1) -- cgit v1.2.3 From 21f498c2f73bd6150d82931f09965826dca0b5f2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Aug 2012 10:59:25 -0400 Subject: NFSv4: Fix range checking in __nfs4_get_acl_uncached and __nfs4_proc_set_acl Ensure that the user supplied buffer size doesn't cause us to overflow the 'pages' array. Also fix up some confusion between the use of PAGE_SIZE and PAGE_CACHE_SIZE when calculating buffer sizes. We're not using the page cache for anything here. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 86b4c7361036..6b94f2d52532 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3653,11 +3653,11 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server) && (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL); } -/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_CACHE_SIZE, and that - * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_CACHE_SIZE) bytes on +/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that + * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_SIZE) bytes on * the stack. */ -#define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT) +#define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) static int buf_to_pages_noslab(const void *buf, size_t buflen, struct page **pages, unsigned int *pgbase) @@ -3668,7 +3668,7 @@ static int buf_to_pages_noslab(const void *buf, size_t buflen, spages = pages; do { - len = min_t(size_t, PAGE_CACHE_SIZE, buflen); + len = min_t(size_t, PAGE_SIZE, buflen); newpage = alloc_page(GFP_KERNEL); if (newpage == NULL) @@ -3782,17 +3782,16 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu .rpc_argp = &args, .rpc_resp = &res, }; - int ret = -ENOMEM, npages, i; + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); + int ret = -ENOMEM, i; size_t acl_len = 0; - npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT; /* As long as we're doing a round trip to the server anyway, * let's be prepared for a page of acl data. */ if (npages == 0) npages = 1; - - /* Add an extra page to handle the bitmap returned */ - npages++; + if (npages > ARRAY_SIZE(pages)) + return -ERANGE; for (i = 0; i < npages; i++) { pages[i] = alloc_page(GFP_KERNEL); @@ -3891,10 +3890,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl .rpc_argp = &arg, .rpc_resp = &res, }; + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); int ret, i; if (!nfs4_server_supports_acls(server)) return -EOPNOTSUPP; + if (npages > ARRAY_SIZE(pages)) + return -ERANGE; i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase); if (i < 0) return i; -- cgit v1.2.3 From 1f1ea6c2d9d8c0be9ec56454b05315273b5de8ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 26 Aug 2012 11:44:43 -0700 Subject: NFSv4: Fix buffer overflow checking in __nfs4_get_acl_uncached Pass the checks made by decode_getacl back to __nfs4_get_acl_uncached so that it knows if the acl has been truncated. The current overflow checking is broken, resulting in Oopses on user-triggered nfs4_getfacl calls, and is opaque to the point where several attempts at fixing it have failed. This patch tries to clean up the code in addition to fixing the Oopses by ensuring that the overflow checks are performed in a single place (decode_getacl). If the overflow check failed, we will still be able to report the acl length, but at least we will no longer attempt to cache the acl or copy the truncated contents to user space. Reported-by: Sachin Prabhu Signed-off-by: Trond Myklebust Tested-by: Sachin Prabhu --- fs/nfs/nfs4proc.c | 31 ++++++++++++------------------- fs/nfs/nfs4xdr.c | 14 +++++--------- include/linux/nfs_xdr.h | 2 +- 3 files changed, 18 insertions(+), 29 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6b94f2d52532..1e50326d00dd 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3739,7 +3739,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size struct nfs4_cached_acl *acl; size_t buflen = sizeof(*acl) + acl_len; - if (pages && buflen <= PAGE_SIZE) { + if (buflen <= PAGE_SIZE) { acl = kmalloc(buflen, GFP_KERNEL); if (acl == NULL) goto out; @@ -3784,7 +3784,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu }; unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); int ret = -ENOMEM, i; - size_t acl_len = 0; /* As long as we're doing a round trip to the server anyway, * let's be prepared for a page of acl data. */ @@ -3807,11 +3806,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu args.acl_len = npages * PAGE_SIZE; args.acl_pgbase = 0; - /* Let decode_getfacl know not to fail if the ACL data is larger than - * the page we send as a guess */ - if (buf == NULL) - res.acl_flags |= NFS4_ACL_LEN_REQUEST; - dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), @@ -3819,20 +3813,19 @@ 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; - if (acl_len > args.acl_len) - nfs4_write_cached_acl(inode, NULL, 0, acl_len); - else - nfs4_write_cached_acl(inode, pages, res.acl_data_offset, - acl_len); - if (buf) { + /* Handle the case where the passed-in buffer is too short */ + if (res.acl_flags & NFS4_ACL_TRUNC) { + /* Did the user only issue a request for the acl length? */ + if (buf == NULL) + goto out_ok; ret = -ERANGE; - if (acl_len > buflen) - goto out_free; - _copy_from_pages(buf, pages, res.acl_data_offset, - acl_len); + goto out_free; } - ret = acl_len; + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len); + if (buf) + _copy_from_pages(buf, pages, res.acl_data_offset, res.acl_len); +out_ok: + ret = res.acl_len; out_free: for (i = 0; i < npages; i++) if (pages[i]) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 1bfbd67c556d..541e796e6db5 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5072,18 +5072,14 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, * are stored with the acl data to handle the problem of * variable length bitmaps.*/ 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 > (xdr->nwords << 2)) { - if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { - /* getxattr interface called with a NULL buf */ - goto out; - } + + /* Check for receive buffer overflow */ + if (res->acl_len > (xdr->nwords << 2) || + res->acl_len + res->acl_data_offset > xdr->buf->page_len) { + res->acl_flags |= NFS4_ACL_TRUNC; dprintk("NFS: acl reply: attrlen %u > page_len %u\n", attrlen, xdr->nwords << 2); - return -EINVAL; } } else status = -EOPNOTSUPP; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index ac7c8ae254f2..be9cf3c7e79e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -652,7 +652,7 @@ struct nfs_getaclargs { }; /* getxattr ACL interface flags */ -#define NFS4_ACL_LEN_REQUEST 0x0001 /* zero length getxattr buffer */ +#define NFS4_ACL_TRUNC 0x0001 /* ACL was truncated */ struct nfs_getaclres { size_t acl_len; size_t acl_data_offset; -- cgit v1.2.3 From 01913b49cf1dc6409a07dd2a4cc6af2e77f3c410 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Thu, 6 Sep 2012 15:54:27 -0400 Subject: NFS: return error from decode_getfh in decode open If decode_getfh failed, nfs4_xdr_dec_open would return 0 since the last decode_* call must have succeeded. Cc: stable@vger.kernel.org Signed-off-by: Weston Andros Adamson Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 541e796e6db5..8dba6bd48557 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6225,7 +6225,8 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_open(xdr, res); if (status) goto out; - if (decode_getfh(xdr, &res->fh) != 0) + status = decode_getfh(xdr, &res->fh); + if (status) goto out; decode_getfattr(xdr, res->f_attr, res->server); out: -- cgit v1.2.3 From 7b281ee026552f10862b617a2a51acf49c829554 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 11 Sep 2012 15:38:32 -0400 Subject: NFS: fsync() must exit with an error if page writeback failed We need to ensure that if the call to filemap_write_and_wait_range() fails, then we report that error back to the application. Signed-off-by: Trond Myklebust --- fs/nfs/file.c | 4 +++- fs/nfs/nfs4file.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 75d6d0a3d32e..6a7fcab7ecb3 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -287,10 +287,12 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file->f_path.dentry->d_inode; ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret != 0) + goto out; mutex_lock(&inode->i_mutex); ret = nfs_file_fsync_commit(file, start, end, datasync); mutex_unlock(&inode->i_mutex); - +out: return ret; } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index acb65e7887f8..eb5eb8eef4d3 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -96,13 +96,15 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file->f_path.dentry->d_inode; ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret != 0) + goto out; mutex_lock(&inode->i_mutex); ret = nfs_file_fsync_commit(file, start, end, datasync); if (!ret && !datasync) /* application has asked for meta-data sync */ ret = pnfs_layoutcommit_inode(inode, true); mutex_unlock(&inode->i_mutex); - +out: return ret; } -- cgit v1.2.3 From 5f3a4a28ec140a90e6058d1d09f6b1f235d485e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 10 Sep 2012 20:17:44 -0700 Subject: userns: Pass a userns parameter into posix_acl_to_xattr and posix_acl_from_xattr - Pass the user namespace the uid and gid values in the xattr are stored in into posix_acl_from_xattr. - Pass the user namespace kuid and kgid values should be converted into when storing uid and gid values in an xattr in posix_acl_to_xattr. - Modify all callers of posix_acl_from_xattr and posix_acl_to_xattr to pass in &init_user_ns. In the short term this change is not strictly needed but it makes the code clearer. In the longer term this change is necessary to be able to mount filesystems outside of the initial user namespace that natively store posix acls in the linux xattr format. Cc: Theodore Tso Cc: Andrew Morton Cc: Andreas Dilger Cc: Jan Kara Cc: Al Viro Signed-off-by: "Eric W. Biederman" --- fs/9p/acl.c | 8 ++++---- fs/btrfs/acl.c | 8 ++++---- fs/ext2/acl.c | 4 ++-- fs/ext3/acl.c | 4 ++-- fs/ext4/acl.c | 4 ++-- fs/generic_acl.c | 4 ++-- fs/gfs2/acl.c | 14 +++++++------- fs/jffs2/acl.c | 4 ++-- fs/jfs/acl.c | 4 ++-- fs/jfs/xattr.c | 4 ++-- fs/nfs/nfs3acl.c | 4 ++-- fs/nfsd/vfs.c | 8 ++++---- fs/ocfs2/acl.c | 4 ++-- fs/reiserfs/xattr_acl.c | 4 ++-- fs/xattr_acl.c | 14 ++++++++------ fs/xfs/xfs_acl.c | 4 ++-- include/linux/posix_acl_xattr.h | 6 ++++-- 17 files changed, 53 insertions(+), 49 deletions(-) (limited to 'fs/nfs') diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 9a1d42630751..15b679166201 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -37,7 +37,7 @@ static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name) return ERR_PTR(-ENOMEM); size = v9fs_fid_xattr_get(fid, name, value, size); if (size > 0) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) goto err_out; } @@ -131,7 +131,7 @@ static int v9fs_set_acl(struct dentry *dentry, int type, struct posix_acl *acl) buffer = kmalloc(size, GFP_KERNEL); if (!buffer) return -ENOMEM; - retval = posix_acl_to_xattr(acl, buffer, size); + retval = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); if (retval < 0) goto err_free_out; switch (type) { @@ -251,7 +251,7 @@ static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -304,7 +304,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, return -EPERM; if (value) { /* update the cached acl value */ - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); else if (acl) { diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 761e2cd8fed1..0c16e3dbfd56 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -61,7 +61,7 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type) size = __btrfs_getxattr(inode, name, value, size); } if (size > 0) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); } else if (size == -ENOENT || size == -ENODATA || size == 0) { /* FIXME, who returns -ENOENT? I think nobody */ acl = NULL; @@ -91,7 +91,7 @@ static int btrfs_xattr_acl_get(struct dentry *dentry, const char *name, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - ret = posix_acl_to_xattr(acl, value, size); + ret = posix_acl_to_xattr(&init_user_ns, acl, value, size); posix_acl_release(acl); return ret; @@ -141,7 +141,7 @@ static int btrfs_set_acl(struct btrfs_trans_handle *trans, goto out; } - ret = posix_acl_to_xattr(acl, value, size); + ret = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (ret < 0) goto out; } @@ -169,7 +169,7 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name, return -EOPNOTSUPP; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 35d6a3cfd9ff..70bb1bccc957 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -350,7 +350,7 @@ ext2_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -371,7 +371,7 @@ ext2_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); else if (acl) { diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index c76832c8d192..2cf6a8044c80 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -369,7 +369,7 @@ ext3_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -392,7 +392,7 @@ ext3_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); else if (acl) { diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index a5c29bb3b835..42b95fccfb2f 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -374,7 +374,7 @@ ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -397,7 +397,7 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); else if (acl) { diff --git a/fs/generic_acl.c b/fs/generic_acl.c index d0dddaceac59..b3f3676796d3 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -56,7 +56,7 @@ generic_acl_get(struct dentry *dentry, const char *name, void *buffer, acl = get_cached_acl(dentry->d_inode, type); if (!acl) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -77,7 +77,7 @@ generic_acl_set(struct dentry *dentry, const char *name, const void *value, if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); } diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index bd4a5892c93c..f850020ad906 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -63,7 +63,7 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type) if (len == 0) return NULL; - acl = posix_acl_from_xattr(data, len); + acl = posix_acl_from_xattr(&init_user_ns, data, len); kfree(data); return acl; } @@ -88,13 +88,13 @@ static int gfs2_acl_set(struct inode *inode, int type, struct posix_acl *acl) const char *name = gfs2_acl_name(type); BUG_ON(name == NULL); - len = posix_acl_to_xattr(acl, NULL, 0); + len = posix_acl_to_xattr(&init_user_ns, acl, NULL, 0); if (len == 0) return 0; data = kmalloc(len, GFP_NOFS); if (data == NULL) return -ENOMEM; - error = posix_acl_to_xattr(acl, data, len); + error = posix_acl_to_xattr(&init_user_ns, acl, data, len); if (error < 0) goto out; error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS); @@ -166,12 +166,12 @@ int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr) if (error) return error; - len = posix_acl_to_xattr(acl, NULL, 0); + len = posix_acl_to_xattr(&init_user_ns, acl, NULL, 0); data = kmalloc(len, GFP_NOFS); error = -ENOMEM; if (data == NULL) goto out; - posix_acl_to_xattr(acl, data, len); + posix_acl_to_xattr(&init_user_ns, acl, data, len); error = gfs2_xattr_acl_chmod(ip, attr, data); kfree(data); set_cached_acl(&ip->i_inode, ACL_TYPE_ACCESS, acl); @@ -212,7 +212,7 @@ static int gfs2_xattr_system_get(struct dentry *dentry, const char *name, if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; @@ -245,7 +245,7 @@ static int gfs2_xattr_system_set(struct dentry *dentry, const char *name, if (!value) goto set_acl; - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (!acl) { /* * acl_set_file(3) may request that we set default ACLs with diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 922f146e4235..42e4edc17a90 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -363,7 +363,7 @@ static int jffs2_acl_getxattr(struct dentry *dentry, const char *name, return PTR_ERR(acl); if (!acl) return -ENODATA; - rc = posix_acl_to_xattr(acl, buffer, size); + rc = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return rc; @@ -381,7 +381,7 @@ static int jffs2_acl_setxattr(struct dentry *dentry, const char *name, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 45559dc3ea2f..d254d6d35995 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -64,7 +64,7 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type) else acl = ERR_PTR(size); } else { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); } kfree(value); if (!IS_ERR(acl)) @@ -100,7 +100,7 @@ static int jfs_set_acl(tid_t tid, struct inode *inode, int type, value = kmalloc(size, GFP_KERNEL); if (!value) return -ENOMEM; - rc = posix_acl_to_xattr(acl, value, size); + rc = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (rc < 0) goto out; } diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 26683e15b3ac..42d67f9757bf 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -685,7 +685,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, * POSIX_ACL_XATTR_ACCESS is tied to i_mode */ if (strcmp(name, POSIX_ACL_XATTR_ACCESS) == 0) { - acl = posix_acl_from_xattr(value, value_len); + acl = posix_acl_from_xattr(&init_user_ns, value, value_len); if (IS_ERR(acl)) { rc = PTR_ERR(acl); printk(KERN_ERR "posix_acl_from_xattr returned %d\n", @@ -710,7 +710,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, return 0; } else if (strcmp(name, POSIX_ACL_XATTR_DEFAULT) == 0) { - acl = posix_acl_from_xattr(value, value_len); + acl = posix_acl_from_xattr(&init_user_ns, value, value_len); if (IS_ERR(acl)) { rc = PTR_ERR(acl); printk(KERN_ERR "posix_acl_from_xattr returned %d\n", diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index e4498dc351a8..4a1aafba6a20 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -70,7 +70,7 @@ ssize_t nfs3_getxattr(struct dentry *dentry, const char *name, if (type == ACL_TYPE_ACCESS && acl->a_count == 0) error = -ENODATA; else - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); } else error = -ENODATA; @@ -92,7 +92,7 @@ int nfs3_setxattr(struct dentry *dentry, const char *name, else return -EOPNOTSUPP; - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); error = nfs3_proc_setacl(inode, type, acl); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index a9269f142cc4..3f67b8e12251 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -480,7 +480,7 @@ set_nfsv4_acl_one(struct dentry *dentry, struct posix_acl *pacl, char *key) if (buf == NULL) goto out; - len = posix_acl_to_xattr(pacl, buf, buflen); + len = posix_acl_to_xattr(&init_user_ns, pacl, buf, buflen); if (len < 0) { error = len; goto out; @@ -549,7 +549,7 @@ _get_posix_acl(struct dentry *dentry, char *key) if (buflen <= 0) return ERR_PTR(buflen); - pacl = posix_acl_from_xattr(buf, buflen); + pacl = posix_acl_from_xattr(&init_user_ns, buf, buflen); kfree(buf); return pacl; } @@ -2264,7 +2264,7 @@ nfsd_get_posix_acl(struct svc_fh *fhp, int type) if (size < 0) return ERR_PTR(size); - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); kfree(value); return acl; } @@ -2297,7 +2297,7 @@ nfsd_set_posix_acl(struct svc_fh *fhp, int type, struct posix_acl *acl) value = kmalloc(size, GFP_KERNEL); if (!value) return -ENOMEM; - error = posix_acl_to_xattr(acl, value, size); + error = posix_acl_to_xattr(&init_user_ns, acl, value, size); if (error < 0) goto getout; size = error; diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index a7219075b4de..260b16281fc3 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -452,7 +452,7 @@ static int ocfs2_xattr_get_acl(struct dentry *dentry, const char *name, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - ret = posix_acl_to_xattr(acl, buffer, size); + ret = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return ret; @@ -475,7 +475,7 @@ static int ocfs2_xattr_set_acl(struct dentry *dentry, const char *name, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) return PTR_ERR(acl); else if (acl) { diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 44474f9b990d..87d6911c659d 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -30,7 +30,7 @@ posix_acl_set(struct dentry *dentry, const char *name, const void *value, return -EPERM; if (value) { - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (IS_ERR(acl)) { return PTR_ERR(acl); } else if (acl) { @@ -77,7 +77,7 @@ posix_acl_get(struct dentry *dentry, const char *name, void *buffer, return PTR_ERR(acl); if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, buffer, size); + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); posix_acl_release(acl); return error; diff --git a/fs/xattr_acl.c b/fs/xattr_acl.c index bf472ca1b348..11efd830b5f5 100644 --- a/fs/xattr_acl.c +++ b/fs/xattr_acl.c @@ -73,7 +73,8 @@ void posix_acl_fix_xattr_to_user(void *value, size_t size) * Convert from extended attribute to in-memory representation. */ struct posix_acl * -posix_acl_from_xattr(const void *value, size_t size) +posix_acl_from_xattr(struct user_namespace *user_ns, + const void *value, size_t size) { posix_acl_xattr_header *header = (posix_acl_xattr_header *)value; posix_acl_xattr_entry *entry = (posix_acl_xattr_entry *)(header+1), *end; @@ -112,14 +113,14 @@ posix_acl_from_xattr(const void *value, size_t size) case ACL_USER: acl_e->e_uid = - make_kuid(&init_user_ns, + make_kuid(user_ns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = - make_kgid(&init_user_ns, + make_kgid(user_ns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; @@ -141,7 +142,8 @@ EXPORT_SYMBOL (posix_acl_from_xattr); * Convert from in-memory to extended attribute representation. */ int -posix_acl_to_xattr(const struct posix_acl *acl, void *buffer, size_t size) +posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, + void *buffer, size_t size) { posix_acl_xattr_header *ext_acl = (posix_acl_xattr_header *)buffer; posix_acl_xattr_entry *ext_entry = ext_acl->a_entries; @@ -162,11 +164,11 @@ posix_acl_to_xattr(const struct posix_acl *acl, void *buffer, size_t size) switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = - cpu_to_le32(from_kuid(&init_user_ns, acl_e->e_uid)); + cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = - cpu_to_le32(from_kgid(&init_user_ns, acl_e->e_gid)); + cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index ac702a6eab9b..1d32f1d52763 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -337,7 +337,7 @@ xfs_xattr_acl_get(struct dentry *dentry, const char *name, if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, value, size); + error = posix_acl_to_xattr(&init_user_ns, acl, value, size); posix_acl_release(acl); return error; @@ -361,7 +361,7 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name, if (!value) goto set_acl; - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (!acl) { /* * acl_set_file(3) may request that we set default ACLs with diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 8bd5fcf06916..ad93ad0f1db0 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -64,7 +64,9 @@ static inline void posix_acl_fix_xattr_to_user(void *value, size_t size) } #endif -struct posix_acl *posix_acl_from_xattr(const void *value, size_t size); -int posix_acl_to_xattr(const struct posix_acl *acl, void *buffer, size_t size); +struct posix_acl *posix_acl_from_xattr(struct user_namespace *user_ns, + const void *value, size_t size); +int posix_acl_to_xattr(struct user_namespace *user_ns, + const struct posix_acl *acl, void *buffer, size_t size); #endif /* _POSIX_ACL_XATTR_H */ -- cgit v1.2.3 From 8c0a85377048b64c880e76ec7368904fe46d0b94 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 26 Sep 2012 11:33:07 +1000 Subject: fs: push rcu_barrier() from deactivate_locked_super() to filesystems There's no reason to call rcu_barrier() on every deactivate_locked_super(). We only need to make sure that all delayed rcu free inodes are flushed before we destroy related cache. Removing rcu_barrier() from deactivate_locked_super() affects some fast paths. E.g. on my machine exit_group() of a last process in IPC namespace takes 0.07538s. rcu_barrier() takes 0.05188s of that time. Signed-off-by: Kirill A. Shutemov Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- fs/9p/v9fs.c | 5 +++++ fs/adfs/super.c | 5 +++++ fs/affs/super.c | 5 +++++ fs/afs/super.c | 5 +++++ fs/befs/linuxvfs.c | 5 +++++ fs/bfs/inode.c | 5 +++++ fs/btrfs/extent_io.c | 6 ++++++ fs/btrfs/inode.c | 5 +++++ fs/ceph/super.c | 5 +++++ fs/cifs/cifsfs.c | 5 +++++ fs/coda/inode.c | 5 +++++ fs/ecryptfs/main.c | 6 ++++++ fs/efs/super.c | 5 +++++ fs/exofs/super.c | 5 +++++ fs/ext2/super.c | 5 +++++ fs/ext3/super.c | 5 +++++ fs/ext4/super.c | 5 +++++ fs/fat/inode.c | 5 +++++ fs/freevxfs/vxfs_super.c | 5 +++++ fs/fuse/inode.c | 6 ++++++ fs/hfs/super.c | 6 ++++++ fs/hfsplus/super.c | 6 ++++++ fs/hpfs/super.c | 5 +++++ fs/hugetlbfs/inode.c | 5 +++++ fs/isofs/inode.c | 5 +++++ fs/jffs2/super.c | 6 ++++++ fs/jfs/super.c | 6 ++++++ fs/logfs/inode.c | 5 +++++ fs/minix/inode.c | 5 +++++ fs/ncpfs/inode.c | 5 +++++ fs/nfs/inode.c | 5 +++++ fs/nilfs2/super.c | 6 ++++++ fs/ntfs/super.c | 6 ++++++ fs/ocfs2/dlmfs/dlmfs.c | 5 +++++ fs/ocfs2/super.c | 5 +++++ fs/openpromfs/inode.c | 5 +++++ fs/qnx4/inode.c | 5 +++++ fs/qnx6/inode.c | 5 +++++ fs/reiserfs/super.c | 5 +++++ fs/romfs/super.c | 5 +++++ fs/squashfs/super.c | 5 +++++ fs/super.c | 6 ------ fs/sysv/inode.c | 5 +++++ fs/ubifs/super.c | 6 ++++++ fs/udf/super.c | 5 +++++ fs/ufs/super.c | 5 +++++ fs/xfs/xfs_super.c | 5 +++++ 47 files changed, 240 insertions(+), 6 deletions(-) (limited to 'fs/nfs') diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index b85efa773949..392c5dac1981 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -560,6 +560,11 @@ static int v9fs_init_inode_cache(void) */ static void v9fs_destroy_inode_cache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(v9fs_inode_cache); } diff --git a/fs/adfs/super.c b/fs/adfs/super.c index bdaec92353c2..c830c857c663 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -275,6 +275,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(adfs_inode_cachep); } diff --git a/fs/affs/super.c b/fs/affs/super.c index c70f1e5fc024..2f57053bf26c 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -147,6 +147,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(affs_inode_cachep); } diff --git a/fs/afs/super.c b/fs/afs/super.c index df8c6047c2a1..43165009428d 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -123,6 +123,11 @@ void __exit afs_fs_exit(void) BUG(); } + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(afs_inode_cachep); _leave(""); } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index cf7f3c67c8b7..962b4f8f7994 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -454,6 +454,11 @@ befs_init_inodecache(void) static void befs_destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(befs_inode_cachep); } diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 9870417c26e7..d5fc598d6e4a 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -280,6 +280,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(bfs_inode_cachep); } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4c878476bb91..b08ea4717e9d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -107,6 +107,12 @@ void extent_io_exit(void) list_del(&eb->leak_list); kmem_cache_free(extent_buffer_cache, eb); } + + /* + * Make sure all delayed rcu free are flushed before we + * destroy caches. + */ + rcu_barrier(); if (extent_state_cache) kmem_cache_destroy(extent_state_cache); if (extent_buffer_cache) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ec154f954646..cf03a91d806f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7076,6 +7076,11 @@ static void init_once(void *foo) void btrfs_destroy_cachep(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); if (btrfs_inode_cachep) kmem_cache_destroy(btrfs_inode_cachep); if (btrfs_trans_handle_cachep) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index b982239f38f9..3a42d9326378 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -603,6 +603,11 @@ bad_cap: static void destroy_caches(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ceph_inode_cachep); kmem_cache_destroy(ceph_cap_cachep); kmem_cache_destroy(ceph_dentry_cachep); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index db8a404a51dd..d4ce77a02327 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -977,6 +977,11 @@ cifs_init_inodecache(void) static void cifs_destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(cifs_inode_cachep); } diff --git a/fs/coda/inode.c b/fs/coda/inode.c index d315c6c5891a..be2aa4909487 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -85,6 +85,11 @@ int coda_init_inodecache(void) void coda_destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(coda_inode_cachep); } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 9b627c15010a..34fcde765d24 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -710,6 +710,12 @@ static void ecryptfs_free_kmem_caches(void) { int i; + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + for (i = 0; i < ARRAY_SIZE(ecryptfs_cache_infos); i++) { struct ecryptfs_cache_info *info; diff --git a/fs/efs/super.c b/fs/efs/super.c index e755ec746c69..2002431ef9a0 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -96,6 +96,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(efs_inode_cachep); } diff --git a/fs/exofs/super.c b/fs/exofs/super.c index dde41a75c7c8..59e3bbfac0b1 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -206,6 +206,11 @@ static int init_inodecache(void) */ static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(exofs_inode_cachep); } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index af74d9e27b71..6c205d0c565b 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -206,6 +206,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ext2_inode_cachep); } diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 8c892e93d8e7..8d41c8889eee 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -532,6 +532,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ext3_inode_cachep); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c6e0cb3d1f4a..455b7d8c6d62 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1019,6 +1019,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ext4_inode_cachep); } diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 05e897fe9866..fd8e47cd898b 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -521,6 +521,11 @@ static int __init fat_init_inodecache(void) static void __exit fat_destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(fat_inode_cachep); } diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index d4fabd26084e..fed2c8afb3a9 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -279,6 +279,11 @@ static void __exit vxfs_cleanup(void) { unregister_filesystem(&vxfs_fs_type); + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(vxfs_inode_cachep); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index fca222dabe3c..f0eda124cffb 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1197,6 +1197,12 @@ static void fuse_fs_cleanup(void) { unregister_filesystem(&fuse_fs_type); unregister_fuseblk(); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(fuse_inode_cachep); } diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 4eb873e0c07b..941d7a8c2197 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -482,6 +482,12 @@ static int __init init_hfs_fs(void) static void __exit exit_hfs_fs(void) { unregister_filesystem(&hfs_fs_type); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(hfs_inode_cachep); } diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index fdafb2d71654..811a84d2d964 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -635,6 +635,12 @@ static int __init init_hfsplus_fs(void) static void __exit exit_hfsplus_fs(void) { unregister_filesystem(&hfsplus_fs_type); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(hfsplus_inode_cachep); } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 706a12c083ea..3cb1da56eb73 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -210,6 +210,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(hpfs_inode_cachep); } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8349a899912e..c4b85d064e6b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1042,6 +1042,11 @@ static int __init init_hugetlbfs_fs(void) static void __exit exit_hugetlbfs_fs(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(hugetlbfs_inode_cachep); kern_unmount(hugetlbfs_vfsmount); unregister_filesystem(&hugetlbfs_fs_type); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 29037c365ba4..f94cde4527e8 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -114,6 +114,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(isofs_inode_cachep); } diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 61ea41389f90..ff487954cd96 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -418,6 +418,12 @@ static void __exit exit_jffs2_fs(void) unregister_filesystem(&jffs2_fs_type); jffs2_destroy_slab_caches(); jffs2_compressors_exit(); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(jffs2_inode_cachep); } diff --git a/fs/jfs/super.c b/fs/jfs/super.c index c55c7452d285..3735347fd5f6 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -903,6 +903,12 @@ static void __exit exit_jfs_fs(void) jfs_proc_clean(); #endif unregister_filesystem(&jfs_fs_type); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(jfs_inode_cachep); } diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index 6984562738d3..121bba2cf6f2 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -417,5 +417,10 @@ int logfs_init_inode_cache(void) void logfs_destroy_inode_cache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(logfs_inode_cache); } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 2a503ad020d5..dc8d3629c20a 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -100,6 +100,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(minix_inode_cachep); } diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 333df07ae3bd..0c62c55b25d7 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -89,6 +89,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ncp_inode_cachep); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 9b47610338f5..e4c716d374a8 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1571,6 +1571,11 @@ static int __init nfs_init_inodecache(void) static void nfs_destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(nfs_inode_cachep); } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 6a10812711c1..3c991dc84f2f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1382,6 +1382,12 @@ static void nilfs_segbuf_init_once(void *obj) static void nilfs_destroy_cachep(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + if (nilfs_inode_cachep) kmem_cache_destroy(nilfs_inode_cachep); if (nilfs_transaction_cachep) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 2bc149d6a784..fe08d4afa106 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -3168,6 +3168,12 @@ static void __exit exit_ntfs_fs(void) ntfs_debug("Unregistering NTFS driver."); unregister_filesystem(&ntfs_fs_type); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ntfs_big_inode_cache); kmem_cache_destroy(ntfs_inode_cache); kmem_cache_destroy(ntfs_name_cache); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 83b6f98e0665..16b712d260d4 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -691,6 +691,11 @@ static void __exit exit_dlmfs_fs(void) flush_workqueue(user_dlm_worker); destroy_workqueue(user_dlm_worker); + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(dlmfs_inode_cache); bdi_destroy(&dlmfs_backing_dev_info); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 68f4541c2db9..0e91ec22a940 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1818,6 +1818,11 @@ static int ocfs2_initialize_mem_caches(void) static void ocfs2_free_mem_caches(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); if (ocfs2_inode_cachep) kmem_cache_destroy(ocfs2_inode_cachep); ocfs2_inode_cachep = NULL; diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 4a3477949bca..2ad080faca34 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -463,6 +463,11 @@ static int __init init_openprom_fs(void) static void __exit exit_openprom_fs(void) { unregister_filesystem(&openprom_fs_type); + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(op_inode_cachep); } diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 552e994e3aa1..9534b4f76579 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -391,6 +391,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(qnx4_inode_cachep); } diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 2049c814bda4..1b37fff7b5ff 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -651,6 +651,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(qnx6_inode_cachep); } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 7a37dabf5a96..1078ae179993 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -608,6 +608,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(reiserfs_inode_cachep); } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 77c5f2173983..fd7c5f60b46b 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -648,6 +648,11 @@ error_register: static void __exit exit_romfs_fs(void) { unregister_filesystem(&romfs_fs_type); + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(romfs_inode_cachep); } diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 29cd014ed3a1..260e3928d4f5 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -425,6 +425,11 @@ static int __init init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(squashfs_inode_cachep); } diff --git a/fs/super.c b/fs/super.c index 0902cfa6a12e..5fdf7ff32c4e 100644 --- a/fs/super.c +++ b/fs/super.c @@ -307,12 +307,6 @@ void deactivate_locked_super(struct super_block *s) /* caches are now gone, we can safely kill the shrinker now */ unregister_shrinker(&s->s_shrink); - - /* - * We need to call rcu_barrier so all the delayed rcu free - * inodes are flushed before we release the fs module. - */ - rcu_barrier(); put_filesystem(fs); put_super(s); } else { diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 80e1e2b18df1..0d0c50bd3321 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -360,5 +360,10 @@ int __init sysv_init_icache(void) void sysv_destroy_icache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(sysv_inode_cachep); } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 71a197f0f93d..36e09ca9130b 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2298,6 +2298,12 @@ static void __exit ubifs_exit(void) dbg_debugfs_exit(); ubifs_compressors_exit(); unregister_shrinker(&ubifs_shrinker_info); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ubifs_inode_slab); unregister_filesystem(&ubifs_fs_type); } diff --git a/fs/udf/super.c b/fs/udf/super.c index 18fc038a438d..b8d27642ab06 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -171,6 +171,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(udf_inode_cachep); } diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 444927e5706b..f7cfecfe1cab 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1466,6 +1466,11 @@ static int init_inodecache(void) static void destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(ufs_inode_cachep); } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 19e2380fb867..83d36e473d2f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1506,6 +1506,11 @@ xfs_init_zones(void) STATIC void xfs_destroy_zones(void) { + /* + * Make sure all delayed rcu free are flushed before we + * destroy caches. + */ + rcu_barrier(); kmem_zone_destroy(xfs_ili_zone); kmem_zone_destroy(xfs_inode_zone); kmem_zone_destroy(xfs_efi_zone); -- cgit v1.2.3 From 0b173bc4daa8f8ec03a85abf5e47b23502ff80af Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:28:46 -0700 Subject: mm: kill vma flag VM_CAN_NONLINEAR Move actual pte filling for non-linear file mappings into the new special vma operation: ->remap_pages(). Filesystems must implement this method to get non-linear mapping support, if it uses filemap_fault() then generic_file_remap_pages() can be used. Now device drivers can implement this method and obtain nonlinear vma support. Signed-off-by: Konstantin Khlebnikov Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf #arch/tile Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/android/ashmem.c | 1 - fs/9p/vfs_file.c | 1 + fs/btrfs/file.c | 2 +- fs/ceph/addr.c | 2 +- fs/cifs/file.c | 1 + fs/ext4/file.c | 2 +- fs/fuse/file.c | 1 + fs/gfs2/file.c | 2 +- fs/nfs/file.c | 1 + fs/nilfs2/file.c | 2 +- fs/ocfs2/mmap.c | 2 +- fs/ubifs/file.c | 1 + fs/xfs/xfs_file.c | 2 +- include/linux/fs.h | 2 ++ include/linux/mm.h | 7 ++++--- mm/filemap.c | 2 +- mm/filemap_xip.c | 3 ++- mm/fremap.c | 14 ++++++++------ mm/mmap.c | 3 +-- mm/nommu.c | 8 ++++++++ mm/shmem.c | 3 +-- 21 files changed, 39 insertions(+), 23 deletions(-) (limited to 'fs/nfs') diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 94a740d2883d..634b9ae713e0 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -332,7 +332,6 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); vma->vm_file = asma->file; - vma->vm_flags |= VM_CAN_NONLINEAR; out: mutex_unlock(&ashmem_mutex); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index dd6f7ee1e312..c2483e97beee 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -738,6 +738,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data, static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = v9fs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5caf285c6e4d..f6b40e86121b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1599,6 +1599,7 @@ out: static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = btrfs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) @@ -1610,7 +1611,6 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) file_accessed(filp); vma->vm_ops = &btrfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 22b6e4583faa..6690269f5dde 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1224,6 +1224,7 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = filemap_fault, .page_mkwrite = ceph_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) @@ -1234,6 +1235,5 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ceph_vmops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7d7bbdc4c8e7..edb25b4bbb95 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3003,6 +3003,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = cifs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ca6f07afe601..bf3966bccd34 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -207,6 +207,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -217,7 +218,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ext4_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index aba15f1b7ad2..78d2837bc940 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1379,6 +1379,7 @@ static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, .page_mkwrite = fuse_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 30e21997a1a1..0def0504afc1 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -492,6 +492,7 @@ out: static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .page_mkwrite = gfs2_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; /** @@ -526,7 +527,6 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) return error; } vma->vm_ops = &gfs2_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 6a7fcab7ecb3..f692be97676d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -578,6 +578,7 @@ out: static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int nfs_need_sync_write(struct file *filp, struct inode *inode) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 5b387a4c293e..16f35f7423c5 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -135,13 +135,13 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nilfs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &nilfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index d150372fd81d..47a87dda54ce 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -173,6 +173,7 @@ out: static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) @@ -188,7 +189,6 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) ocfs2_inode_unlock(file->f_dentry->d_inode, lock_level); out: vma->vm_ops = &ocfs2_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index ff48c5a85309..5bc77817f382 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1536,6 +1536,7 @@ out_unlock: static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ubifs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1eaeb8be3aae..aa473fa640a2 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -940,7 +940,6 @@ xfs_file_mmap( struct vm_area_struct *vma) { vma->vm_ops = &xfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; file_accessed(filp); return 0; @@ -1443,4 +1442,5 @@ const struct file_operations xfs_dir_file_operations = { static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = xfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index ca6d8c806f47..5a8a273d5b2f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2552,6 +2552,8 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, + unsigned long size, pgoff_t pgoff); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); diff --git a/include/linux/mm.h b/include/linux/mm.h index fb0685b17914..44d3fc25f556 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -105,7 +105,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_NODUMP 0x04000000 /* Do not include in the core dump */ -#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ @@ -171,8 +170,7 @@ extern pgprot_t protection_map[16]; * of VM_FAULT_xxx flags that give details about how the fault was handled. * * pgoff should be used in favour of virtual_address, if possible. If pgoff - * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear - * mapping support. + * is used, one may implement ->remap_pages to get nonlinear mapping support. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ @@ -230,6 +228,9 @@ struct vm_operations_struct { int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from, const nodemask_t *to, unsigned long flags); #endif + /* called by sys_remap_file_pages() to populate non-linear mapping */ + int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, + unsigned long size, pgoff_t pgoff); }; struct mmu_gather; diff --git a/mm/filemap.c b/mm/filemap.c index 384344575c37..a9827b42556e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1737,6 +1737,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite); const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = filemap_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ @@ -1749,7 +1750,6 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 13e013b1270c..91750227a191 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -305,6 +305,7 @@ out: static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, .page_mkwrite = filemap_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int xip_file_mmap(struct file * file, struct vm_area_struct * vma) @@ -313,7 +314,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma) file_accessed(file); vma->vm_ops = &xip_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR | VM_MIXEDMAP; + vma->vm_flags |= VM_MIXEDMAP; return 0; } EXPORT_SYMBOL_GPL(xip_file_mmap); diff --git a/mm/fremap.c b/mm/fremap.c index 048659c0c03d..3d731a498788 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -5,6 +5,7 @@ * * started by Ingo Molnar, Copyright (C) 2002, 2003 */ +#include #include #include #include @@ -80,9 +81,10 @@ out: return err; } -static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, unsigned long size, pgoff_t pgoff) +int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, + unsigned long size, pgoff_t pgoff) { + struct mm_struct *mm = vma->vm_mm; int err; do { @@ -95,9 +97,9 @@ static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma, pgoff++; } while (size); - return 0; - + return 0; } +EXPORT_SYMBOL(generic_file_remap_pages); /** * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma @@ -167,7 +169,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR)) goto out; - if (!(vma->vm_flags & VM_CAN_NONLINEAR)) + if (!vma->vm_ops->remap_pages) goto out; if (start < vma->vm_start || start + size > vma->vm_end) @@ -228,7 +230,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, } mmu_notifier_invalidate_range_start(mm, start, start + size); - err = populate_range(mm, vma, start, size, pgoff); + err = vma->vm_ops->remap_pages(vma, start, size, pgoff); mmu_notifier_invalidate_range_end(mm, start, start + size); if (!err && !(flags & MAP_NONBLOCK)) { if (vma->vm_flags & VM_LOCKED) { diff --git a/mm/mmap.c b/mm/mmap.c index b0989f4d4f09..d0686d355113 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -669,8 +669,7 @@ again: remove_next = 1 + (end > next->vm_end); static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags) { - /* VM_CAN_NONLINEAR may get set later by f_op->mmap() */ - if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR) + if (vma->vm_flags ^ vm_flags) return 0; if (vma->vm_file != file) return 0; diff --git a/mm/nommu.c b/mm/nommu.c index dee2ff89fd58..98318dcff742 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1961,6 +1961,14 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); +int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, + unsigned long size, pgoff_t pgoff) +{ + BUG(); + return 0; +} +EXPORT_SYMBOL(generic_file_remap_pages); + static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { diff --git a/mm/shmem.c b/mm/shmem.c index d3752110c8c7..cc12072f8787 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1339,7 +1339,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &shmem_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } @@ -2643,6 +2642,7 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif + .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, @@ -2836,7 +2836,6 @@ int shmem_zero_setup(struct vm_area_struct *vma) fput(vma->vm_file); vma->vm_file = file; vma->vm_ops = &shmem_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } -- cgit v1.2.3