From 88a6099fc3274a27814d26dd688fdc5cd7a480ee Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 Feb 2022 13:22:48 -0500 Subject: NFS: Replace last uses of NFS_INO_REVAL_PAGECACHE Now that we have more fine grained attribute revalidation, let's just get rid of NFS_INO_REVAL_PAGECACHE. Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 987a187bd39a..f88b0eb9b18e 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -306,7 +306,7 @@ static void nfs_set_pageerror(struct address_space *mapping) /* Force file size revalidation */ spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_REVAL_FORCED | - NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); spin_unlock(&inode->i_lock); } -- cgit v1.2.3 From 6c984083ec2453dfd3fcf98f392f34500c73e3f2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 15 Feb 2022 15:58:38 -0500 Subject: NFS: Use of mapping_set_error() results in spurious errors The use of mapping_set_error() in conjunction with calls to filemap_check_errors() is problematic because every error gets reported as either an EIO or an ENOSPC by filemap_check_errors() in functions such as filemap_write_and_wait() or filemap_write_and_wait_range(). In almost all cases, we prefer to use the more nuanced wb errors. Fixes: b8946d7bfb94 ("NFS: Revalidate the file mapping on all fatal writeback errors") Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f88b0eb9b18e..74d258781205 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -316,7 +316,10 @@ static void nfs_mapping_set_error(struct page *page, int error) struct address_space *mapping = page_file_mapping(page); SetPageError(page); - mapping_set_error(mapping, error); + filemap_set_wb_err(mapping, error); + if (mapping->host) + errseq_set(&mapping->host->i_sb->s_wb_err, + error == -ENOSPC ? -ENOSPC : -EIO); nfs_set_pageerror(mapping); } -- cgit v1.2.3 From 8db55a032ac7ac1ed7b98d6b1dc980e6378c652f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: SUNRPC: improve 'swap' handling: scheduling and PF_MEMALLOC rpc tasks can be marked as RPC_TASK_SWAPPER. This causes GFP_MEMALLOC to be used for some allocations. This is needed in some cases, but not in all where it is currently provided, and in some where it isn't provided. Currently *all* tasks associated with a rpc_client on which swap is enabled get the flag and hence some GFP_MEMALLOC support. GFP_MEMALLOC is provided for ->buf_alloc() but only swap-writes need it. However xdr_alloc_bvec does not get GFP_MEMALLOC - though it often does need it. xdr_alloc_bvec is called while the XPRT_LOCK is held. If this blocks, then it blocks all other queued tasks. So this allocation needs GFP_MEMALLOC for *all* requests, not just writes, when the xprt is used for any swap writes. Similarly, if the transport is not connected, that will block all requests including swap writes, so memory allocations should get GFP_MEMALLOC if swap writes are possible. So with this patch: 1/ we ONLY set RPC_TASK_SWAPPER for swap writes. 2/ __rpc_execute() sets PF_MEMALLOC while handling any task with RPC_TASK_SWAPPER set, or when handling any task that holds the XPRT_LOCKED lock on an xprt used for swap. This removes the need for the RPC_IS_SWAPPER() test in ->buf_alloc handlers. 3/ xprt_prepare_transmit() sets PF_MEMALLOC after locking any task to a swapper xprt. __rpc_execute() will clear it. 3/ PF_MEMALLOC is set for all the connect workers. Reviewed-by: Chuck Lever (for xprtrdma parts) Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 2 ++ net/sunrpc/clnt.c | 2 -- net/sunrpc/sched.c | 20 +++++++++++++++++--- net/sunrpc/xprt.c | 3 +++ net/sunrpc/xprtrdma/transport.c | 6 ++++-- net/sunrpc/xprtsock.c | 8 ++++++++ 6 files changed, 34 insertions(+), 7 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 74d258781205..599a82406d38 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1412,6 +1412,8 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, { int priority = flush_task_priority(how); + if (IS_SWAPFILE(hdr->inode)) + task_setup_data->flags |= RPC_TASK_SWAPPER; task_setup_data->priority = priority; rpc_ops->write_setup(hdr, msg, &task_setup_data->rpc_client); trace_nfs_initiate_write(hdr); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9556eb7b065b..4117ea4caa2e 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1085,8 +1085,6 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) task->tk_flags |= RPC_TASK_TIMEOUT; if (clnt->cl_noretranstimeo) task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; - if (atomic_read(&clnt->cl_swapper)) - task->tk_flags |= RPC_TASK_SWAPPER; /* Add to the client's list of all tasks */ spin_lock(&clnt->cl_lock); list_add_tail(&task->tk_task, &clnt->cl_tasks); diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 690bd3401820..7c8f87ebdbc0 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -869,6 +869,15 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata) ops->rpc_release(calldata); } +static bool xprt_needs_memalloc(struct rpc_xprt *xprt, struct rpc_task *tk) +{ + if (!xprt) + return false; + if (!atomic_read(&xprt->swapper)) + return false; + return test_bit(XPRT_LOCKED, &xprt->state) && xprt->snd_task == tk; +} + /* * This is the RPC `scheduler' (or rather, the finite state machine). */ @@ -877,6 +886,7 @@ static void __rpc_execute(struct rpc_task *task) struct rpc_wait_queue *queue; int task_is_async = RPC_IS_ASYNC(task); int status = 0; + unsigned long pflags = current->flags; WARN_ON_ONCE(RPC_IS_QUEUED(task)); if (RPC_IS_QUEUED(task)) @@ -899,6 +909,10 @@ static void __rpc_execute(struct rpc_task *task) } if (!do_action) break; + if (RPC_IS_SWAPPER(task) || + xprt_needs_memalloc(task->tk_xprt, task)) + current->flags |= PF_MEMALLOC; + trace_rpc_task_run_action(task, do_action); do_action(task); @@ -936,7 +950,7 @@ static void __rpc_execute(struct rpc_task *task) rpc_clear_running(task); spin_unlock(&queue->lock); if (task_is_async) - return; + goto out; /* sync task: sleep here */ trace_rpc_task_sync_sleep(task, task->tk_action); @@ -960,6 +974,8 @@ static void __rpc_execute(struct rpc_task *task) /* Release all resources associated with the task */ rpc_release_task(task); +out: + current_restore_flags(pflags, PF_MEMALLOC); } /* @@ -1018,8 +1034,6 @@ int rpc_malloc(struct rpc_task *task) if (RPC_IS_ASYNC(task)) gfp = GFP_NOWAIT | __GFP_NOWARN; - if (RPC_IS_SWAPPER(task)) - gfp |= __GFP_MEMALLOC; size += sizeof(struct rpc_buffer); if (size <= RPC_BUFFER_MAXSIZE) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 2f165634df54..bbe913121f43 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1492,6 +1492,9 @@ bool xprt_prepare_transmit(struct rpc_task *task) return false; } + if (atomic_read(&xprt->swapper)) + /* This will be clear in __rpc_execute */ + current->flags |= PF_MEMALLOC; return true; } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 923e4b512ee9..6b7e10e5a141 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -235,8 +235,11 @@ xprt_rdma_connect_worker(struct work_struct *work) struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt, rx_connect_worker.work); struct rpc_xprt *xprt = &r_xprt->rx_xprt; + unsigned int pflags = current->flags; int rc; + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; rc = rpcrdma_xprt_connect(r_xprt); xprt_clear_connecting(xprt); if (!rc) { @@ -250,6 +253,7 @@ xprt_rdma_connect_worker(struct work_struct *work) rpcrdma_xprt_disconnect(r_xprt); xprt_unlock_connect(xprt, r_xprt); xprt_wake_pending_tasks(xprt, rc); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -572,8 +576,6 @@ xprt_rdma_allocate(struct rpc_task *task) flags = RPCRDMA_DEF_GFP; if (RPC_IS_ASYNC(task)) flags = GFP_NOWAIT | __GFP_NOWARN; - if (RPC_IS_SWAPPER(task)) - flags |= __GFP_MEMALLOC; if (!rpcrdma_check_regbuf(r_xprt, req->rl_sendbuf, rqst->rq_callsize, flags)) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0f39e08ee580..61d3293f1d68 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2052,7 +2052,10 @@ static void xs_udp_setup_socket(struct work_struct *work) struct rpc_xprt *xprt = &transport->xprt; struct socket *sock; int status = -EIO; + unsigned int pflags = current->flags; + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP, false); @@ -2072,6 +2075,7 @@ out: xprt_clear_connecting(xprt); xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -2231,7 +2235,10 @@ static void xs_tcp_setup_socket(struct work_struct *work) struct socket *sock = transport->sock; struct rpc_xprt *xprt = &transport->xprt; int status; + unsigned int pflags = current->flags; + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; if (!sock) { sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_STREAM, @@ -2296,6 +2303,7 @@ out: xprt_clear_connecting(xprt); out_unlock: xprt_unlock_connect(xprt, transport); + current_restore_flags(pflags, PF_MEMALLOC); } /** -- cgit v1.2.3 From 515dcdcd48736576c6f5c197814da6f81c60a21e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 21 Mar 2022 12:34:19 -0400 Subject: NFS: nfsiod should not block forever in mempool_alloc() The concern is that since nfsiod is sometimes required to kick off a commit, it can get locked up waiting forever in mempool_alloc() instead of failing gracefully and leaving the commit until later. Try to allocate from the slab first, with GFP_KERNEL | __GFP_NORETRY, then fall back to a non-blocking attempt to allocate from the memory pool. Signed-off-by: Trond Myklebust --- fs/nfs/internal.h | 7 +++++++ fs/nfs/pnfs_nfs.c | 8 ++++++-- fs/nfs/write.c | 24 +++++++++--------------- include/linux/nfs_fs.h | 2 +- 4 files changed, 23 insertions(+), 18 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 194840a97e3a..57b0497105c8 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -587,6 +587,13 @@ nfs_write_match_verf(const struct nfs_writeverf *verf, !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } +static inline gfp_t nfs_io_gfp_mask(void) +{ + if (current->flags & PF_WQ_WORKER) + return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + return GFP_KERNEL; +} + /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 316f68f96e57..657c242a18ff 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -419,7 +419,7 @@ static struct nfs_commit_data * pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo) { - struct nfs_commit_data *data = nfs_commitdata_alloc(false); + struct nfs_commit_data *data = nfs_commitdata_alloc(); if (!data) return NULL; @@ -515,7 +515,11 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, unsigned int nreq = 0; if (!list_empty(mds_pages)) { - data = nfs_commitdata_alloc(true); + data = nfs_commitdata_alloc(); + if (!data) { + nfs_retry_commit(mds_pages, NULL, cinfo, -1); + return -ENOMEM; + } data->ds_commit_index = -1; list_splice_init(mds_pages, &data->pages); list_add_tail(&data->list, &list); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 599a82406d38..ef47e3700e4b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -70,27 +70,17 @@ static mempool_t *nfs_wdata_mempool; static struct kmem_cache *nfs_cdata_cachep; static mempool_t *nfs_commit_mempool; -struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail) +struct nfs_commit_data *nfs_commitdata_alloc(void) { struct nfs_commit_data *p; - if (never_fail) - p = mempool_alloc(nfs_commit_mempool, GFP_NOIO); - else { - /* It is OK to do some reclaim, not no safe to wait - * for anything to be returned to the pool. - * mempool_alloc() cannot handle that particular combination, - * so we need two separate attempts. - */ + p = kmem_cache_zalloc(nfs_cdata_cachep, nfs_io_gfp_mask()); + if (!p) { p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT); - if (!p) - p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO | - __GFP_NOWARN | __GFP_NORETRY); if (!p) return NULL; + memset(p, 0, sizeof(*p)); } - - memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); return p; } @@ -1826,7 +1816,11 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, if (list_empty(head)) return 0; - data = nfs_commitdata_alloc(true); + data = nfs_commitdata_alloc(); + if (!data) { + nfs_retry_commit(head, NULL, cinfo, -1); + return -ENOMEM; + } /* Set up the argument struct */ nfs_init_commit(data, head, NULL, cinfo); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c47c448befc8..db305abafc9e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -580,7 +580,7 @@ extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -- cgit v1.2.3 From 0bae835b63c53f86cdc524f5962e39409585b22c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 21 Mar 2022 13:48:36 -0400 Subject: NFS: Avoid writeback threads getting stuck in mempool_alloc() In a low memory situation, allow the NFS writeback code to fail without getting stuck in infinite loops in mempool_alloc(). Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 10 +++++----- fs/nfs/write.c | 10 ++++++++-- 2 files changed, 13 insertions(+), 7 deletions(-) (limited to 'fs/nfs/write.c') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ad7f83dc9a2d..3156db526cc4 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -90,10 +90,10 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) } } -static inline struct nfs_page * -nfs_page_alloc(void) +static inline struct nfs_page *nfs_page_alloc(void) { - struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL); + struct nfs_page *p = + kmem_cache_zalloc(nfs_page_cachep, nfs_io_gfp_mask()); if (p) INIT_LIST_HEAD(&p->wb_list); return p; @@ -892,7 +892,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, struct nfs_commit_info cinfo; struct nfs_page_array *pg_array = &hdr->page_array; unsigned int pagecount, pageused; - gfp_t gfp_flags = GFP_KERNEL; + gfp_t gfp_flags = nfs_io_gfp_mask(); pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); pg_array->npages = pagecount; @@ -979,7 +979,7 @@ nfs_pageio_alloc_mirrors(struct nfs_pageio_descriptor *desc, desc->pg_mirrors_dynamic = NULL; if (mirror_count == 1) return desc->pg_mirrors_static; - ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_KERNEL); + ret = kmalloc_array(mirror_count, sizeof(*ret), nfs_io_gfp_mask()); if (ret != NULL) { for (i = 0; i < mirror_count; i++) nfs_pageio_mirror_init(&ret[i], desc->pg_bsize); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ef47e3700e4b..e864ac836237 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -94,9 +94,15 @@ EXPORT_SYMBOL_GPL(nfs_commit_free); static struct nfs_pgio_header *nfs_writehdr_alloc(void) { - struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_KERNEL); + struct nfs_pgio_header *p; - memset(p, 0, sizeof(*p)); + p = kmem_cache_zalloc(nfs_wdata_cachep, nfs_io_gfp_mask()); + if (!p) { + p = mempool_alloc(nfs_wdata_mempool, GFP_NOWAIT); + if (!p) + return NULL; + memset(p, 0, sizeof(*p)); + } p->rw_mode = FMODE_WRITE; return p; } -- cgit v1.2.3