From 378520b837cf4da769600b83690d8e825f16a611 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 7 Aug 2014 10:15:02 +0800 Subject: nfs41: add a helper function to set layoutcommit after commit Track lwb in nfs_commit_data so that we can use it to setup layoutcommit in commit_done callback. Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0040629894df..e563b2c976ef 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1328,6 +1328,7 @@ struct nfs_commit_data { struct pnfs_layout_segment *lseg; struct nfs_client *ds_clp; /* pNFS data server */ int ds_commit_index; + loff_t lwb; const struct rpc_call_ops *mds_ops; const struct nfs_commit_completion_ops *completion_ops; int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); -- cgit v1.2.3-59-g8ed1b From 5f919c9f10c1cf821ee5f414683214a361a1b98c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Aug 2014 11:09:25 -0500 Subject: pnfs: allow splicing pre-encoded pages into the layoutcommit args Currently there is no XDR buffer space allocated for the per-layout driver layoutcommit payload, which leads to server buffer overflows in the blocklayout driver even under simple workloads. As we can't do per-layout sizes for XDR operations we'll have to splice a previously encoded list of pages into the XDR stream, similar to how we handle ACL buffers. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 18 +++++++++++++----- fs/nfs/pnfs.c | 15 +++++++++++++++ fs/nfs/pnfs.h | 4 ++-- include/linux/nfs_xdr.h | 3 +++ 4 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index e13b59d8d9aa..f2cd957adb90 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -395,7 +395,10 @@ static int nfs4_stat_to_errno(int); 2 /* last byte written */ + \ 1 /* nt_timechanged (false) */ + \ 1 /* layoutupdate4 layout type */ + \ - 1 /* NULL filelayout layoutupdate4 payload */) + 1 /* layoutupdate4 opaqueue len */) + /* the actual content of layoutupdate4 should + be allocated by drivers and spliced in + using xdr_write_pages */ #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3) #define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ @@ -1990,7 +1993,7 @@ encode_layoutget(struct xdr_stream *xdr, static int encode_layoutcommit(struct xdr_stream *xdr, struct inode *inode, - const struct nfs4_layoutcommit_args *args, + struct nfs4_layoutcommit_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -2011,11 +2014,16 @@ encode_layoutcommit(struct xdr_stream *xdr, *p++ = cpu_to_be32(0); /* Never send time_modify_changed */ *p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */ - if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) + if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) { NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit( NFS_I(inode)->layout, xdr, args); - else - encode_uint32(xdr, 0); /* no layout-type payload */ + } else { + encode_uint32(xdr, args->layoutupdate_len); + if (args->layoutupdate_pages) { + xdr_write_pages(xdr, args->layoutupdate_pages, 0, + args->layoutupdate_len); + } + } return 0; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 57b5728e0b8e..8827ab130ed3 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1854,6 +1854,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data) int pnfs_layoutcommit_inode(struct inode *inode, bool sync) { + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; struct nfs4_layoutcommit_data *data; struct nfs_inode *nfsi = NFS_I(inode); loff_t end_pos; @@ -1904,6 +1905,20 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) data->args.lastbytewritten = end_pos - 1; data->res.server = NFS_SERVER(inode); + if (ld->prepare_layoutcommit) { + status = ld->prepare_layoutcommit(&data->args); + if (status) { + spin_lock(&inode->i_lock); + if (end_pos < nfsi->layout->plh_lwb) + nfsi->layout->plh_lwb = end_pos; + spin_unlock(&inode->i_lock); + put_rpccred(data->cred); + set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags); + goto clear_layoutcommitting; + } + } + + status = nfs4_proc_layoutcommit(data, sync); out: if (status) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 1dd8a5e96c9f..8835b5a320cc 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -128,8 +128,8 @@ struct pnfs_layoutdriver_type { const struct nfs4_layoutreturn_args *args); void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data); - - void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid, + int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args); + void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo, struct xdr_stream *xdr, const struct nfs4_layoutcommit_args *args); }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e563b2c976ef..f4092c6b90fb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -279,6 +279,9 @@ struct nfs4_layoutcommit_args { __u64 lastbytewritten; struct inode *inode; const u32 *bitmask; + size_t layoutupdate_len; + struct page *layoutupdate_page; + struct page **layoutupdate_pages; }; struct nfs4_layoutcommit_res { -- cgit v1.2.3-59-g8ed1b From d4b18c3e00b8d18fbd316abe9639b91ad416e1f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Sep 2014 17:36:31 -0700 Subject: pnfs: remove GETDEVICELIST implementation The current GETDEVICELIST implementation is buggy in that it doesn't handle cursors correctly, and in that it returns an error if the server returns NFSERR_NOTSUPP. Given that there is no actual need for GETDEVICELIST, it has various issues and might get removed for NFSv4.2 stop using it in the blocklayout driver, and thus the Linux NFS client as whole. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/blocklayout.c | 2 +- fs/nfs/nfs4proc.c | 48 --------------- fs/nfs/nfs4xdr.c | 130 --------------------------------------- fs/nfs/pnfs.h | 5 -- fs/nfs/pnfs_dev.c | 30 --------- include/linux/nfs_xdr.h | 11 ---- 6 files changed, 1 insertion(+), 225 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 25ba9e0e6fff..3e1f1afc6db4 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -532,7 +532,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) return -EINVAL; } - return nfs4_deviceid_getdevicelist(server, fh); + return 0; } static bool diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 47fa67a3a8cf..0b711227cfa5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7808,54 +7808,6 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) return status; } -/* - * Retrieve the list of Data Server devices from the MDS. - */ -static int _nfs4_getdevicelist(struct nfs_server *server, - const struct nfs_fh *fh, - struct pnfs_devicelist *devlist) -{ - struct nfs4_getdevicelist_args args = { - .fh = fh, - .layoutclass = server->pnfs_curr_ld->id, - }; - struct nfs4_getdevicelist_res res = { - .devlist = devlist, - }; - struct rpc_message msg = { - .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICELIST], - .rpc_argp = &args, - .rpc_resp = &res, - }; - int status; - - dprintk("--> %s\n", __func__); - status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, - &res.seq_res, 0); - dprintk("<-- %s status=%d\n", __func__, status); - return status; -} - -int nfs4_proc_getdevicelist(struct nfs_server *server, - const struct nfs_fh *fh, - struct pnfs_devicelist *devlist) -{ - struct nfs4_exception exception = { }; - int err; - - do { - err = nfs4_handle_exception(server, - _nfs4_getdevicelist(server, fh, devlist), - &exception); - } while (exception.retry); - - dprintk("%s: err=%d, num_devs=%u\n", __func__, - err, devlist->num_devs); - - return err; -} -EXPORT_SYMBOL_GPL(nfs4_proc_getdevicelist); - static int _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index f2cd957adb90..b8165eab0a32 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -362,17 +362,6 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) #define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) #define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) -#define encode_getdevicelist_maxsz (op_encode_hdr_maxsz + 4 + \ - encode_verifier_maxsz) -#define decode_getdevicelist_maxsz (op_decode_hdr_maxsz + \ - 2 /* nfs_cookie4 gdlr_cookie */ + \ - decode_verifier_maxsz \ - /* verifier4 gdlr_verifier */ + \ - 1 /* gdlr_deviceid_list count */ + \ - XDR_QUADLEN(NFS4_PNFS_GETDEVLIST_MAXNUM * \ - NFS4_DEVICEID4_SIZE) \ - /* gdlr_deviceid_list */ + \ - 1 /* bool gdlr_eof */) #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \ XDR_QUADLEN(NFS4_DEVICEID4_SIZE)) #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ @@ -812,14 +801,6 @@ static int nfs4_stat_to_errno(int); #define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_reclaim_complete_maxsz) -#define NFS4_enc_getdevicelist_sz (compound_encode_hdr_maxsz + \ - encode_sequence_maxsz + \ - encode_putfh_maxsz + \ - encode_getdevicelist_maxsz) -#define NFS4_dec_getdevicelist_sz (compound_decode_hdr_maxsz + \ - decode_sequence_maxsz + \ - decode_putfh_maxsz + \ - decode_getdevicelist_maxsz) #define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz +\ encode_getdeviceinfo_maxsz) @@ -1929,24 +1910,6 @@ static void encode_sequence(struct xdr_stream *xdr, } #ifdef CONFIG_NFS_V4_1 -static void -encode_getdevicelist(struct xdr_stream *xdr, - const struct nfs4_getdevicelist_args *args, - struct compound_hdr *hdr) -{ - __be32 *p; - nfs4_verifier dummy = { - .data = "dummmmmy", - }; - - encode_op_hdr(xdr, OP_GETDEVICELIST, decode_getdevicelist_maxsz, hdr); - p = reserve_space(xdr, 16); - *p++ = cpu_to_be32(args->layoutclass); - *p++ = cpu_to_be32(NFS4_PNFS_GETDEVLIST_MAXNUM); - xdr_encode_hyper(p, 0ULL); /* cookie */ - encode_nfs4_verifier(xdr, &dummy); -} - static void encode_getdeviceinfo(struct xdr_stream *xdr, const struct nfs4_getdeviceinfo_args *args, @@ -2900,24 +2863,6 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, encode_nops(&hdr); } -/* - * Encode GETDEVICELIST request - */ -static void nfs4_xdr_enc_getdevicelist(struct rpc_rqst *req, - struct xdr_stream *xdr, - struct nfs4_getdevicelist_args *args) -{ - struct compound_hdr hdr = { - .minorversion = nfs4_xdr_minorversion(&args->seq_args), - }; - - encode_compound_hdr(xdr, req, &hdr); - encode_sequence(xdr, &args->seq_args, &hdr); - encode_putfh(xdr, args->fh, &hdr); - encode_getdevicelist(xdr, args, &hdr); - encode_nops(&hdr); -} - /* * Encode GETDEVICEINFO request */ @@ -5773,54 +5718,6 @@ out_overflow: } #if defined(CONFIG_NFS_V4_1) -/* - * TODO: Need to handle case when EOF != true; - */ -static int decode_getdevicelist(struct xdr_stream *xdr, - struct pnfs_devicelist *res) -{ - __be32 *p; - int status, i; - nfs4_verifier verftemp; - - status = decode_op_hdr(xdr, OP_GETDEVICELIST); - if (status) - return status; - - p = xdr_inline_decode(xdr, 8 + 8 + 4); - if (unlikely(!p)) - goto out_overflow; - - /* TODO: Skip cookie for now */ - p += 2; - - /* Read verifier */ - p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE); - - res->num_devs = be32_to_cpup(p); - - dprintk("%s: num_dev %d\n", __func__, res->num_devs); - - if (res->num_devs > NFS4_PNFS_GETDEVLIST_MAXNUM) { - printk(KERN_ERR "NFS: %s too many result dev_num %u\n", - __func__, res->num_devs); - return -EIO; - } - - p = xdr_inline_decode(xdr, - res->num_devs * NFS4_DEVICEID4_SIZE + 4); - if (unlikely(!p)) - goto out_overflow; - for (i = 0; i < res->num_devs; i++) - p = xdr_decode_opaque_fixed(p, res->dev_id[i].data, - NFS4_DEVICEID4_SIZE); - res->eof = be32_to_cpup(p); - return 0; -out_overflow: - print_overflow_msg(__func__, xdr); - return -EIO; -} - static int decode_getdeviceinfo(struct xdr_stream *xdr, struct pnfs_device *pdev) { @@ -7104,32 +7001,6 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, return status; } -/* - * Decode GETDEVICELIST response - */ -static int nfs4_xdr_dec_getdevicelist(struct rpc_rqst *rqstp, - struct xdr_stream *xdr, - struct nfs4_getdevicelist_res *res) -{ - struct compound_hdr hdr; - int status; - - dprintk("encoding getdevicelist!\n"); - - status = decode_compound_hdr(xdr, &hdr); - if (status != 0) - goto out; - status = decode_sequence(xdr, &res->seq_res, rqstp); - if (status != 0) - goto out; - status = decode_putfh(xdr); - if (status != 0) - goto out; - status = decode_getdevicelist(xdr, res->devlist); -out: - return status; -} - /* * Decode GETDEVINFO response */ @@ -7498,7 +7369,6 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(SECINFO_NO_NAME, enc_secinfo_no_name, dec_secinfo_no_name), PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), - PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), PROC(BIND_CONN_TO_SESSION, enc_bind_conn_to_session, dec_bind_conn_to_session), PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid), diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index d84fe29fc88b..b10f12fc6818 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -180,9 +180,6 @@ extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); /* nfs4proc.c */ -extern int nfs4_proc_getdevicelist(struct nfs_server *server, - const struct nfs_fh *fh, - struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev, struct rpc_cred *cred); @@ -277,8 +274,6 @@ bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *); void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node); bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node); void nfs4_deviceid_purge_client(const struct nfs_client *); -int nfs4_deviceid_getdevicelist(struct nfs_server *server, - const struct nfs_fh *fh); static inline struct nfs4_deviceid_node * nfs4_get_deviceid(struct nfs4_deviceid_node *d) diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index 82c2836fdb38..aa2ec0015183 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -358,33 +358,3 @@ nfs4_deviceid_mark_client_invalid(struct nfs_client *clp) } rcu_read_unlock(); } - -int -nfs4_deviceid_getdevicelist(struct nfs_server *server, - const struct nfs_fh *fh) -{ - struct pnfs_devicelist *dlist; - struct nfs4_deviceid_node *d; - int error = 0, i; - - dlist = kzalloc(sizeof(struct pnfs_devicelist), GFP_NOFS); - if (!dlist) - return -ENOMEM; - - while (!dlist->eof) { - error = nfs4_proc_getdevicelist(server, fh, dlist); - if (error) - break; - - for (i = 0; i < dlist->num_devs; i++) { - d = nfs4_find_get_deviceid(server, &dlist->dev_id[i], - NULL, GFP_NOFS); - if (d) - nfs4_put_deviceid_node(d); - } - } - - kfree(dlist); - return error; -} -EXPORT_SYMBOL_GPL(nfs4_deviceid_getdevicelist); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index f4092c6b90fb..7ae249ccb78d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -252,17 +252,6 @@ struct nfs4_layoutget { gfp_t gfp_flags; }; -struct nfs4_getdevicelist_args { - struct nfs4_sequence_args seq_args; - const struct nfs_fh *fh; - u32 layoutclass; -}; - -struct nfs4_getdevicelist_res { - struct nfs4_sequence_res seq_res; - struct pnfs_devicelist *devlist; -}; - struct nfs4_getdeviceinfo_args { struct nfs4_sequence_args seq_args; struct pnfs_device *pdev; -- cgit v1.2.3-59-g8ed1b From f418c64b71590bac8fdebd0969a1eeaffaf036d2 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 3 Sep 2014 12:19:07 -0400 Subject: NFS: Unconditionally enable commit code The goal is to create a generic NFS module with code that does not depend on what versions of NFS are enabled. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 14 ------------ fs/nfs/write.c | 61 -------------------------------------------------- include/linux/nfs_fs.h | 8 ------- 3 files changed, 83 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 65ef6e00deee..dda4b8667c02 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -178,7 +178,6 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq, return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); } -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) /* * nfs_direct_cmp_commit_data_verf - compare verifier for commit data * @dreq - direct request possibly spanning multiple servers @@ -197,7 +196,6 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, WARN_ON_ONCE(verfp->committed < 0); return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf)); } -#endif /** * nfs_direct_IO - NFS address space operation for direct I/O @@ -576,7 +574,6 @@ out: return result; } -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { struct nfs_pageio_descriptor desc; @@ -700,17 +697,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */ } -#else -static void nfs_direct_write_schedule_work(struct work_struct *work) -{ -} - -static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode) -{ - nfs_direct_complete(dreq, true); -} -#endif - static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 128d97f01d1c..6786873a2901 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -720,7 +720,6 @@ nfs_mark_request_dirty(struct nfs_page *req) __set_page_dirty_nobuffers(req->wb_page); } -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) /* * nfs_page_search_commits_for_head_request_locked * @@ -870,43 +869,6 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr) return hdr->verf.committed != NFS_FILE_SYNC; } -#else -static struct nfs_page * -nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, - struct page *page) -{ - return NULL; -} - -static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, - struct inode *inode) -{ -} - -void nfs_init_cinfo(struct nfs_commit_info *cinfo, - struct inode *inode, - struct nfs_direct_req *dreq) -{ -} - -void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo) -{ -} - -static void -nfs_clear_request_commit(struct nfs_page *req) -{ -} - -int nfs_write_need_commit(struct nfs_pgio_header *hdr) -{ - return 0; -} - -#endif - static void nfs_write_completion(struct nfs_pgio_header *hdr) { struct nfs_commit_info cinfo; @@ -942,7 +904,6 @@ out: hdr->release(hdr); } -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { @@ -999,19 +960,6 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, return ret; } -#else -unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) -{ - return 0; -} - -int nfs_scan_commit(struct inode *inode, struct list_head *dst, - struct nfs_commit_info *cinfo) -{ - return 0; -} -#endif - /* * Search for an existing write request, and attempt to update * it to reflect a new dirty region on a given page. @@ -1404,7 +1352,6 @@ static int nfs_writeback_done(struct rpc_task *task, return status; nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) if (hdr->res.verf->committed < hdr->args.stable && task->tk_status >= 0) { /* We tried a write call, but the server did not @@ -1426,7 +1373,6 @@ static int nfs_writeback_done(struct rpc_task *task, complain = jiffies + 300 * HZ; } } -#endif /* Deal with the suid/sgid bit corner case */ if (nfs_should_remove_suid(inode)) @@ -1479,7 +1425,6 @@ static void nfs_writeback_result(struct rpc_task *task, } -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) { int ret; @@ -1803,12 +1748,6 @@ out_mark_dirty: __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return ret; } -#else -static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_control *wbc) -{ - return 0; -} -#endif int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 5180a7ededec..fd334d4b0d41 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -529,17 +529,9 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned 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); -#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); -#else -static inline int -nfs_commit_inode(struct inode *inode, int how) -{ - return 0; -} -#endif static inline int nfs_have_writebacks(struct inode *inode) -- cgit v1.2.3-59-g8ed1b From cb8c20fa53ec28602793ee43ddc7e8883be62e69 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 3 Sep 2014 12:19:10 -0400 Subject: NFS: Move NFS v3 acl functions to nfs3_fs.h This code is internal to the v3 module, so other parts of the client shouldn't have any knowledge of it. nfs3_getxattr(), nfs3_setxattr(), and nfs3_removexattr() no longer exist anywhere so I remove the declarations while I'm here. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/nfs3_fs.h | 19 +++++++++++++++++++ fs/nfs/nfs3super.c | 1 + include/linux/nfs_fs.h | 33 --------------------------------- 3 files changed, 20 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index 6599e0dcd69f..333ae4068506 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -6,6 +6,25 @@ #ifndef __LINUX_FS_NFS_NFS3_FS_H #define __LINUX_FS_NFS_NFS3_FS_H +/* + * nfs3acl.c + */ +#ifdef CONFIG_NFS_V3_ACL +extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type); +extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl); +extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t); +extern const struct xattr_handler *nfs3_xattr_handlers[]; +#else +static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) +{ + return 0; +} +#define nfs3_listxattr NULL +#endif /* CONFIG_NFS_V3_ACL */ + /* nfs3client.c */ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *); struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *, diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c index d6a98949af19..6af29c2da352 100644 --- a/fs/nfs/nfs3super.c +++ b/fs/nfs/nfs3super.c @@ -4,6 +4,7 @@ #include #include #include "internal.h" +#include "nfs3_fs.h" #include "nfs.h" static struct nfs_subversion nfs_v3 = { diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fd334d4b0d41..28d649054d5f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -442,22 +442,6 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file) return NULL; } -/* - * linux/fs/nfs/xattr.c - */ -#ifdef CONFIG_NFS_V3_ACL -extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t); -extern ssize_t nfs3_getxattr(struct dentry *, const char *, void *, size_t); -extern int nfs3_setxattr(struct dentry *, const char *, - const void *, size_t, int); -extern int nfs3_removexattr (struct dentry *, const char *name); -#else -# define nfs3_listxattr NULL -# define nfs3_getxattr NULL -# define nfs3_setxattr NULL -# define nfs3_removexattr NULL -#endif - /* * linux/fs/nfs/direct.c */ @@ -548,23 +532,6 @@ extern int nfs_readpages(struct file *, struct address_space *, extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, struct page *); -/* - * linux/fs/nfs3proc.c - */ -#ifdef CONFIG_NFS_V3_ACL -extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type); -extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, - struct posix_acl *dfacl); -extern const struct xattr_handler *nfs3_xattr_handlers[]; -#else -static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, - struct posix_acl *dfacl) -{ - return 0; -} -#endif /* CONFIG_NFS_V3_ACL */ - /* * inline functions */ -- cgit v1.2.3-59-g8ed1b From a743419f420a64d442280845c0377a915b76644f Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 23 Sep 2014 12:26:19 -0400 Subject: SUNRPC: Don't wake tasks during connection abort When aborting a connection to preserve source ports, don't wake the task in xs_error_report. This allows tasks with RPC_TASK_SOFTCONN to succeed if the connection needs to be re-established since it preserves the task's status instead of setting it to the status of the aborting kernel_connect(). This may also avoid a potential conflict on the socket's lock. Signed-off-by: Benjamin Coddington Cc: stable@vger.kernel.org # 3.14+ Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/xprtsock.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index fcbfe8783243..cf391eef2e6d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -357,6 +357,7 @@ int xs_swapper(struct rpc_xprt *xprt, int enable); #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) +#define XPRT_CONNECTION_REUSE (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 7ed47b4943da..bffba4e4bfc6 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -845,6 +845,8 @@ static void xs_error_report(struct sock *sk) dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -err); trace_rpc_socket_error(xprt, sk->sk_socket, err); + if (test_bit(XPRT_CONNECTION_REUSE, &xprt->state)) + goto out; xprt_wake_pending_tasks(xprt, err); out: read_unlock_bh(&sk->sk_callback_lock); @@ -2261,7 +2263,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); /* "close" the socket, preserving the local port */ + set_bit(XPRT_CONNECTION_REUSE, &xprt->state); xs_tcp_reuse_connection(transport); + clear_bit(XPRT_CONNECTION_REUSE, &xprt->state); if (abort_and_exit) goto out_eagain; -- cgit v1.2.3-59-g8ed1b From 8478eaa16e701ecfe054b62ec764bc1291b79e19 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 18 Sep 2014 16:09:27 +1000 Subject: NFSv4: use exponential retry on NFS4ERR_DELAY for async requests. Currently asynchronous NFSv4 request will be retried with exponential timeout (from 1/10 to 15 seconds), but async requests will always use a 15second retry. Some "async" requests are really synchronous though. The async mechanism is used to allow the request to continue if the requesting process is killed. In those cases, an exponential retry is appropriate. For example, if two different clients both open a file and get a READ delegation, and one client then unlinks the file (while still holding an open file descriptor), that unlink will used the "silly-rename" handling which is async. The first rename will result in NFS4ERR_DELAY while the delegation is reclaimed from the other client. The rename will not be retried for 15 seconds, causing an unlink to take 15 seconds rather than 100msec. This patch only added exponential timeout for async unlink and async rename. Other async calls, such as 'close' are sometimes waited for so they might benefit from exponential timeout too. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 65 ++++++++++++++++++++++++++++++++----------------- include/linux/nfs_xdr.h | 2 ++ 2 files changed, 44 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 288be08bda95..45bce9ed6791 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -77,7 +77,7 @@ struct nfs4_opendata; static int _nfs4_proc_open(struct nfs4_opendata *data); static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); -static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *); +static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *); static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label); @@ -314,20 +314,30 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent kunmap_atomic(start); } +static long nfs4_update_delay(long *timeout) +{ + long ret; + if (!timeout) + return NFS4_POLL_RETRY_MAX; + if (*timeout <= 0) + *timeout = NFS4_POLL_RETRY_MIN; + if (*timeout > NFS4_POLL_RETRY_MAX) + *timeout = NFS4_POLL_RETRY_MAX; + ret = *timeout; + *timeout <<= 1; + return ret; +} + static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) { int res = 0; might_sleep(); - if (*timeout <= 0) - *timeout = NFS4_POLL_RETRY_MIN; - if (*timeout > NFS4_POLL_RETRY_MAX) - *timeout = NFS4_POLL_RETRY_MAX; - freezable_schedule_timeout_killable_unsafe(*timeout); + freezable_schedule_timeout_killable_unsafe( + nfs4_update_delay(timeout)); if (fatal_signal_pending(current)) res = -ERESTARTSYS; - *timeout <<= 1; return res; } @@ -2583,7 +2593,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data) if (calldata->arg.fmode == 0) break; default: - if (nfs4_async_handle_error(task, server, state) == -EAGAIN) { + if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) { rpc_restart_call_prepare(task); goto out_release; } @@ -3572,7 +3582,8 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) if (!nfs4_sequence_done(task, &res->seq_res)) return 0; - if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN) + if (nfs4_async_handle_error(task, res->server, NULL, + &data->timeout) == -EAGAIN) return 0; update_changeattr(dir, &res->cinfo); return 1; @@ -3605,7 +3616,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, if (!nfs4_sequence_done(task, &res->seq_res)) return 0; - if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN) + if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN) return 0; update_changeattr(old_dir, &res->old_cinfo); @@ -4109,7 +4120,8 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) trace_nfs4_read(hdr, task->tk_status); if (nfs4_async_handle_error(task, server, - hdr->args.context->state) == -EAGAIN) { + hdr->args.context->state, + NULL) == -EAGAIN) { rpc_restart_call_prepare(task); return -EAGAIN; } @@ -4177,10 +4189,11 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { struct inode *inode = hdr->inode; - + trace_nfs4_write(hdr, task->tk_status); if (nfs4_async_handle_error(task, NFS_SERVER(inode), - hdr->args.context->state) == -EAGAIN) { + hdr->args.context->state, + NULL) == -EAGAIN) { rpc_restart_call_prepare(task); return -EAGAIN; } @@ -4260,7 +4273,8 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *da struct inode *inode = data->inode; trace_nfs4_commit(data, task->tk_status); - if (nfs4_async_handle_error(task, NFS_SERVER(inode), NULL) == -EAGAIN) { + if (nfs4_async_handle_error(task, NFS_SERVER(inode), + NULL, NULL) == -EAGAIN) { rpc_restart_call_prepare(task); return -EAGAIN; } @@ -4813,7 +4827,8 @@ out: static int -nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, struct nfs4_state *state) +nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, + struct nfs4_state *state, long *timeout) { struct nfs_client *clp = server->nfs_client; @@ -4863,6 +4878,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, #endif /* CONFIG_NFS_V4_1 */ case -NFS4ERR_DELAY: nfs_inc_server_stats(server, NFSIOS_DELAY); + rpc_delay(task, nfs4_update_delay(timeout)); + goto restart_call; case -NFS4ERR_GRACE: rpc_delay(task, NFS4_POLL_RETRY_MAX); case -NFS4ERR_RETRY_UNCACHED_REP: @@ -5103,8 +5120,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) pnfs_roc_set_barrier(data->inode, data->roc_barrier); break; default: - if (nfs4_async_handle_error(task, data->res.server, NULL) == - -EAGAIN) { + if (nfs4_async_handle_error(task, data->res.server, + NULL, NULL) == -EAGAIN) { rpc_restart_call_prepare(task); return; } @@ -5368,7 +5385,8 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) case -NFS4ERR_EXPIRED: break; default: - if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN) + if (nfs4_async_handle_error(task, calldata->server, + NULL, NULL) == -EAGAIN) rpc_restart_call_prepare(task); } nfs_release_seqid(calldata->arg.seqid); @@ -5974,7 +5992,8 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) break; case -NFS4ERR_LEASE_MOVED: case -NFS4ERR_DELAY: - if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) + if (nfs4_async_handle_error(task, server, + NULL, NULL) == -EAGAIN) rpc_restart_call_prepare(task); } } @@ -7591,7 +7610,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); } } - if (nfs4_async_handle_error(task, server, state) == -EAGAIN) + if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) rpc_restart_call_prepare(task); out: dprintk("<-- %s\n", __func__); @@ -7751,7 +7770,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) case 0: break; case -NFS4ERR_DELAY: - if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN) + if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN) break; rpc_restart_call_prepare(task); return; @@ -7882,7 +7901,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) case 0: break; default: - if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { + if (nfs4_async_handle_error(task, server, NULL, NULL) == -EAGAIN) { rpc_restart_call_prepare(task); return; } @@ -8178,7 +8197,7 @@ static void nfs41_free_stateid_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case -NFS4ERR_DELAY: - if (nfs4_async_handle_error(task, data->server, NULL) == -EAGAIN) + if (nfs4_async_handle_error(task, data->server, NULL, NULL) == -EAGAIN) rpc_restart_call_prepare(task); } } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7ae249ccb78d..6951c7d9097d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1339,6 +1339,7 @@ struct nfs_unlinkdata { struct inode *dir; struct rpc_cred *cred; struct nfs_fattr dir_attr; + long timeout; }; struct nfs_renamedata { @@ -1352,6 +1353,7 @@ struct nfs_renamedata { struct dentry *new_dentry; struct nfs_fattr new_fattr; void (*complete)(struct rpc_task *, struct nfs_renamedata *); + long timeout; }; struct nfs_access_entry; -- cgit v1.2.3-59-g8ed1b From cbbce82209490df8b68da9aec0d642451fe0a668 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 25 Sep 2014 13:55:19 +1000 Subject: SCHED: add some "wait..on_bit...timeout()" interfaces. In commit c1221321b7c25b53204447cff9949a6d5a7ddddc sched: Allow wait_on_bit_action() functions to support a timeout I suggested that a "wait_on_bit_timeout()" interface would not meet my need. This isn't true - I was just over-engineering. Including a 'private' field in wait_bit_key instead of a focused "timeout" field was just premature generalization. If some other use is ever found, it can be generalized or added later. So this patch renames "private" to "timeout" with a meaning "stop waiting when "jiffies" reaches or passes "timeout", and adds two of the many possible wait..bit..timeout() interfaces: wait_on_page_bit_killable_timeout(), which is the one I want to use, and out_of_line_wait_on_bit_timeout() which is a reasonably general example. Others can be added as needed. Acked-by: Peter Zijlstra (Intel) Signed-off-by: NeilBrown Acked-by: Ingo Molnar Signed-off-by: Trond Myklebust --- include/linux/pagemap.h | 2 ++ include/linux/wait.h | 5 ++++- kernel/sched/wait.c | 36 ++++++++++++++++++++++++++++++++++++ mm/filemap.c | 13 +++++++++++++ 4 files changed, 55 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3df8c7db7a4e..87f9e4230d3a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -502,6 +502,8 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, extern void wait_on_page_bit(struct page *page, int bit_nr); extern int wait_on_page_bit_killable(struct page *page, int bit_nr); +extern int wait_on_page_bit_killable_timeout(struct page *page, + int bit_nr, unsigned long timeout); static inline int wait_on_page_locked_killable(struct page *page) { diff --git a/include/linux/wait.h b/include/linux/wait.h index 6fb1ba5f9b2f..80115bf88671 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -25,7 +25,7 @@ struct wait_bit_key { void *flags; int bit_nr; #define WAIT_ATOMIC_T_BIT_NR -1 - unsigned long private; + unsigned long timeout; }; struct wait_bit_queue { @@ -154,6 +154,7 @@ int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_ac void wake_up_bit(void *, int); void wake_up_atomic_t(atomic_t *); int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned); +int out_of_line_wait_on_bit_timeout(void *, int, wait_bit_action_f *, unsigned, unsigned long); int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned); int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned); wait_queue_head_t *bit_waitqueue(void *, int); @@ -859,6 +860,8 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); extern int bit_wait(struct wait_bit_key *); extern int bit_wait_io(struct wait_bit_key *); +extern int bit_wait_timeout(struct wait_bit_key *); +extern int bit_wait_io_timeout(struct wait_bit_key *); /** * wait_on_bit - wait for a bit to be cleared diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 15cab1a4f84e..5a62915f47a8 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -343,6 +343,18 @@ int __sched out_of_line_wait_on_bit(void *word, int bit, } EXPORT_SYMBOL(out_of_line_wait_on_bit); +int __sched out_of_line_wait_on_bit_timeout( + void *word, int bit, wait_bit_action_f *action, + unsigned mode, unsigned long timeout) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + wait.key.timeout = jiffies + timeout; + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout); + int __sched __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, wait_bit_action_f *action, unsigned mode) @@ -520,3 +532,27 @@ __sched int bit_wait_io(struct wait_bit_key *word) return 0; } EXPORT_SYMBOL(bit_wait_io); + +__sched int bit_wait_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_timeout); + +__sched int bit_wait_io_timeout(struct wait_bit_key *word) +{ + unsigned long now = ACCESS_ONCE(jiffies); + if (signal_pending_state(current->state, current)) + return 1; + if (time_after_eq(now, word->timeout)) + return -EAGAIN; + io_schedule_timeout(word->timeout - now); + return 0; +} +EXPORT_SYMBOL_GPL(bit_wait_io_timeout); diff --git a/mm/filemap.c b/mm/filemap.c index 90effcdf948d..cbe5a9013f70 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -703,6 +703,19 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr) bit_wait_io, TASK_KILLABLE); } +int wait_on_page_bit_killable_timeout(struct page *page, + int bit_nr, unsigned long timeout) +{ + DEFINE_WAIT_BIT(wait, &page->flags, bit_nr); + + wait.key.timeout = jiffies + timeout; + if (!test_bit(bit_nr, &page->flags)) + return 0; + return __wait_on_bit(page_waitqueue(page), &wait, + bit_wait_io_timeout, TASK_KILLABLE); +} +EXPORT_SYMBOL_GPL(wait_on_page_bit_killable_timeout); + /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue * @page: Page defining the wait queue of interest -- cgit v1.2.3-59-g8ed1b From a4796e37c12e177572b80864cbab9c907ea250b0 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 24 Sep 2014 11:28:32 +1000 Subject: MM: export page_wakeup functions This will allow NFS to wait for PG_private to be cleared and, particularly, to send a wake-up when it is. Signed-off-by: NeilBrown Acked-by: Andrew Morton Signed-off-by: Trond Myklebust --- include/linux/pagemap.h | 10 ++++++++-- mm/filemap.c | 8 ++------ 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 87f9e4230d3a..2dca0cef3506 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -496,8 +496,8 @@ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, } /* - * This is exported only for wait_on_page_locked/wait_on_page_writeback. - * Never use this directly! + * This is exported only for wait_on_page_locked/wait_on_page_writeback, + * and for filesystems which need to wait on PG_private. */ extern void wait_on_page_bit(struct page *page, int bit_nr); @@ -512,6 +512,12 @@ static inline int wait_on_page_locked_killable(struct page *page) return 0; } +extern wait_queue_head_t *page_waitqueue(struct page *page); +static inline void wake_up_page(struct page *page, int bit) +{ + __wake_up_bit(page_waitqueue(page), &page->flags, bit); +} + /* * Wait for a page to be unlocked. * diff --git a/mm/filemap.c b/mm/filemap.c index cbe5a9013f70..b9b1413080be 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -670,17 +670,13 @@ EXPORT_SYMBOL(__page_cache_alloc); * at a cost of "thundering herd" phenomena during rare hash * collisions. */ -static wait_queue_head_t *page_waitqueue(struct page *page) +wait_queue_head_t *page_waitqueue(struct page *page) { const struct zone *zone = page_zone(page); return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)]; } - -static inline void wake_up_page(struct page *page, int bit) -{ - __wake_up_bit(page_waitqueue(page), &page->flags, bit); -} +EXPORT_SYMBOL(page_waitqueue); void wait_on_page_bit(struct page *page, int bit_nr) { -- cgit v1.2.3-59-g8ed1b