diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index b6fc169be1b1..7df2503cef6c 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -209,8 +209,6 @@ config NFS_DISABLE_UDP_SUPPORT config NFS_V4_2_READ_PLUS bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation" depends on NFS_V4_2 - default n + default y help - This is intended for developers only. The READ_PLUS operation has - been shown to have issues under specific conditions and should not - be used in production. + Choose Y here to enable use of the NFS v4.2 READ_PLUS operation. diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index 70f5563a8e81..65cbb5607a5f 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -404,7 +404,7 @@ bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->concat.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; @@ -433,7 +433,7 @@ bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->stripe.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index e4c5f193ed5e..44eca51b2808 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -517,6 +517,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, .authflavor = flavor, .cred = cl_init->cred, .xprtsec = cl_init->xprtsec, + .connect_timeout = cl_init->connect_timeout, + .reconnect_timeout = cl_init->reconnect_timeout, }; if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8f3112e71a6a..e6a51fd94fea 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1089,6 +1089,17 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, for (i = desc->cache_entry_index; i < array->size; i++) { struct nfs_cache_array_entry *ent; + /* + * nfs_readdir_handle_cache_misses return force clear at + * (cache_misses > NFS_READDIR_CACHE_MISS_THRESHOLD) for + * readdir heuristic, NFS_READDIR_CACHE_MISS_THRESHOLD + 1 + * entries need be emitted here. + */ + if (first_emit && i > NFS_READDIR_CACHE_MISS_THRESHOLD + 2) { + desc->eob = true; + break; + } + ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->name, ent->name_len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { @@ -1107,10 +1118,6 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, desc->ctx->pos = desc->dir_cookie; else desc->ctx->pos++; - if (first_emit && i > NFS_READDIR_CACHE_MISS_THRESHOLD + 1) { - desc->eob = true; - break; - } } if (array->folio_is_eof) desc->eof = !desc->eob; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index aaffaaa336cc..47d892a1d363 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -472,13 +472,31 @@ out: return result; } +static void nfs_direct_add_page_head(struct list_head *list, + struct nfs_page *req) +{ + struct nfs_page *head = req->wb_head; + + if (!list_empty(&head->wb_list) || !nfs_lock_request(head)) + return; + if (!list_empty(&head->wb_list)) { + nfs_unlock_request(head); + return; + } + list_add(&head->wb_list, list); + kref_get(&head->wb_kref); + kref_get(&head->wb_kref); +} + static void nfs_direct_join_group(struct list_head *list, struct inode *inode) { struct nfs_page *req, *subreq; list_for_each_entry(req, list, wb_list) { - if (req->wb_head != req) + if (req->wb_head != req) { + nfs_direct_add_page_head(&req->wb_list, req); continue; + } subreq = req->wb_this_page; if (subreq == req) continue; diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index 6603b5cee029..714975e5c0db 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -7,14 +7,16 @@ * Resolves DNS hostnames into valid ip addresses */ -#ifdef CONFIG_NFS_USE_KERNEL_DNS - #include #include #include -#include + #include "dns_resolve.h" +#ifdef CONFIG_NFS_USE_KERNEL_DNS + +#include + ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, struct sockaddr_storage *ss, size_t salen) { @@ -35,7 +37,6 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, #else -#include #include #include #include @@ -43,15 +44,12 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, #include #include #include -#include -#include #include #include #include #include #include "nfs4_fs.h" -#include "dns_resolve.h" #include "cache_lib.h" #include "netns.h" diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 79b1b3fcd3fc..3f9768810427 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -200,7 +200,7 @@ nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe EXPORT_SYMBOL_GPL(nfs_file_splice_read); int -nfs_file_mmap(struct file * file, struct vm_area_struct * vma) +nfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); int status; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 913c09806c7f..9c9cf764f600 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -82,6 +82,8 @@ struct nfs_client_initdata { const struct rpc_timeout *timeparms; const struct cred *cred; struct xprtsec_parms xprtsec; + unsigned long connect_timeout; + unsigned long reconnect_timeout; }; /* @@ -493,6 +495,7 @@ extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); +extern bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size); extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, struct nfs_open_context *ctx, struct folio *folio); diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 05c3b4b2b3dd..c19093814296 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -949,7 +949,7 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_filename_inline(xdr, &entry->name, &entry->len); if (unlikely(error)) - return -EAGAIN; + return error == -ENAMETOOLONG ? -ENAMETOOLONG : -EAGAIN; /* * The type (size and byte order) of nfscookie isn't defined in diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index eff3802c5e03..674c012868b1 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -86,6 +86,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans) { struct rpc_timeout ds_timeout; + unsigned long connect_timeout = ds_timeo * (ds_retrans + 1) * HZ / 10; struct nfs_client *mds_clp = mds_srv->nfs_client; struct nfs_client_initdata cl_init = { .addr = ds_addr, @@ -98,6 +99,8 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, .timeparms = &ds_timeout, .cred = mds_srv->cred, .xprtsec = mds_clp->cl_xprtsec, + .connect_timeout = connect_timeout, + .reconnect_timeout = connect_timeout, }; struct nfs_client *clp; char buf[INET6_ADDRSTRLEN + 1]; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 3b0b650c9c5a..60f032be805a 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1991,7 +1991,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_inline_filename3(xdr, &entry->name, &entry->len); if (unlikely(error)) - return -EAGAIN; + return error == -ENAMETOOLONG ? -ENAMETOOLONG : -EAGAIN; error = decode_cookie3(xdr, &new_cookie); if (unlikely(error)) diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 0fe5aacbcfdf..b59876b01a1e 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -13,6 +13,7 @@ * more? Need to consider not to pre-alloc too much for a compound. */ #define PNFS_LAYOUTSTATS_MAXDEV (4) +#define READ_PLUS_SCRATCH_SIZE (16) /* nfs4.2proc.c */ #ifdef CONFIG_NFS_V4_2 diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 49f78e23b34c..063e00aff87e 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -471,8 +471,9 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, continue; } break; - } else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) { - args.sync = true; + } else if (err == -NFS4ERR_OFFLOAD_NO_REQS && + args.sync != res.synchronous) { + args.sync = res.synchronous; dst_exception.retry = 1; continue; } else if ((err == -ESTALE || diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 95234208dc9e..9e3ae53e2205 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -54,10 +54,16 @@ (1 /* data_content4 */ + \ 2 /* data_info4.di_offset */ + \ 1 /* data_info4.di_length */) +#define NFS42_READ_PLUS_HOLE_SEGMENT_SIZE \ + (1 /* data_content4 */ + \ + 2 /* data_info4.di_offset */ + \ + 2 /* data_info4.di_length */) +#define READ_PLUS_SEGMENT_SIZE_DIFF (NFS42_READ_PLUS_HOLE_SEGMENT_SIZE - \ + NFS42_READ_PLUS_DATA_SEGMENT_SIZE) #define decode_read_plus_maxsz (op_decode_hdr_maxsz + \ 1 /* rpr_eof */ + \ 1 /* rpr_contents count */ + \ - NFS42_READ_PLUS_DATA_SEGMENT_SIZE) + NFS42_READ_PLUS_HOLE_SEGMENT_SIZE) #define encode_seek_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + \ 2 /* offset */ + \ @@ -617,8 +623,8 @@ static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req, encode_putfh(xdr, args->fh, &hdr); encode_read_plus(xdr, args, &hdr); - rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->count, hdr.replen); + rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->count, + hdr.replen - READ_PLUS_SEGMENT_SIZE_DIFF); encode_nops(&hdr); } @@ -1056,13 +1062,12 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) res->eof = be32_to_cpup(p++); segments = be32_to_cpup(p++); if (segments == 0) - return status; + return 0; segs = kmalloc_array(segments, sizeof(*segs), GFP_KERNEL); if (!segs) return -ENOMEM; - status = -EIO; for (i = 0; i < segments; i++) { status = decode_read_plus_segment(xdr, &segs[i]); if (status < 0) @@ -1428,7 +1433,7 @@ static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp, struct compound_hdr hdr; int status; - xdr_set_scratch_buffer(xdr, res->scratch, sizeof(res->scratch)); + xdr_set_scratch_buffer(xdr, res->scratch, READ_PLUS_SCRATCH_SIZE); status = decode_compound_hdr(xdr, &hdr); if (status) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d9114a754db7..27fb25567ce7 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -232,6 +232,8 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); + if (test_bit(NFS_CS_DS, &cl_init->init_flags)) + __set_bit(NFS_CS_DS, &clp->cl_flags); /* * Set up the connection to the server before we add add to the * global list. @@ -1007,6 +1009,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, if (mds_srv->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + __set_bit(NFS_CS_DS, &cl_init.init_flags); /* * Set an authflavor equual to the MDS value. Use the MDS nfs_client * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d57aaf0cc577..794343790ea8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5438,18 +5438,8 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, return false; } -static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr) -{ - if (hdr->res.scratch) { - kfree(hdr->res.scratch); - hdr->res.scratch = NULL; - } -} - static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { - nfs4_read_plus_scratch_free(hdr); - if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) @@ -5469,8 +5459,7 @@ static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr, /* Note: We don't use READ_PLUS with pNFS yet */ if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) { msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS]; - hdr->res.scratch = kmalloc(32, GFP_KERNEL); - return hdr->res.scratch != NULL; + return nfs_read_alloc_scratch(hdr, READ_PLUS_SCRATCH_SIZE); } return false; } @@ -8798,6 +8787,8 @@ nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred, #ifdef CONFIG_NFS_V4_1_MIGRATION calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR; #endif + if (test_bit(NFS_CS_DS, &clp->cl_flags)) + calldata->args.flags |= EXCHGID4_FLAG_USE_PNFS_DS; msg.rpc_argp = &calldata->args; msg.rpc_resp = &calldata->res; task_setup_data.callback_data = calldata; @@ -8875,6 +8866,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre /* Save the EXCHANGE_ID verifier session trunk tests */ memcpy(clp->cl_confirm.data, argp->verifier.data, sizeof(clp->cl_confirm.data)); + if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS) + set_bit(NFS_CS_DS, &clp->cl_flags); out: trace_nfs4_exchange_id(clp, status); rpc_put_task(task); diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index ddbbf4fcda86..178001c90156 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -154,7 +154,7 @@ nfs4_get_device_info(struct nfs_server *server, set_bit(NFS_DEVICEID_NOCACHE, &d->flags); out_free_pages: - for (i = 0; i < max_pages; i++) + while (--i >= 0) __free_page(pages[i]); kfree(pages); out_free_pdev: diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index a0112ad4937a..afd23910f3bf 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -852,6 +852,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, { struct nfs_client *clp = ERR_PTR(-EIO); struct nfs4_pnfs_ds_addr *da; + unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10; int status = 0; dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -870,6 +871,8 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, .dstaddr = (struct sockaddr *)&da->da_addr, .addrlen = da->da_addrlen, .servername = clp->cl_hostname, + .connect_timeout = connect_timeout, + .reconnect_timeout = connect_timeout, }; if (da->da_transport != clp->cl_proto) @@ -943,7 +946,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, * Test this address for session trunking and * add as an alias */ - xprtdata.cred = nfs4_get_clid_cred(clp), + xprtdata.cred = nfs4_get_clid_cred(clp); rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, rpc_clnt_setup_test_and_add_xprt, &rpcdata); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index f71eeee67e20..7dc21a48e3e7 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -47,6 +47,8 @@ static struct nfs_pgio_header *nfs_readhdr_alloc(void) static void nfs_readhdr_free(struct nfs_pgio_header *rhdr) { + if (rhdr->res.scratch != NULL) + kfree(rhdr->res.scratch); kmem_cache_free(nfs_rdata_cachep, rhdr); } @@ -108,6 +110,14 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); +bool nfs_read_alloc_scratch(struct nfs_pgio_header *hdr, size_t size) +{ + WARN_ON(hdr->res.scratch != NULL); + hdr->res.scratch = kmalloc(size, GFP_KERNEL); + return hdr->res.scratch != NULL; +} +EXPORT_SYMBOL_GPL(nfs_read_alloc_scratch); + static void nfs_readpage_release(struct nfs_page *req, int error) { struct folio *folio = nfs_page_to_folio(req); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 4f41d839face..af7358277f1c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -148,6 +148,8 @@ struct rpc_create_args { const struct cred *cred; unsigned int max_connect; struct xprtsec_parms xprtsec; + unsigned long connect_timeout; + unsigned long reconnect_timeout; }; struct rpc_add_xprt_test { diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 42f9d7eb9a1a..5b4fb3c791bc 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -226,6 +226,7 @@ struct xdr_stream { struct kvec *iov; /* pointer to the current kvec */ struct kvec scratch; /* Scratch buffer */ struct page **page_ptr; /* pointer to the current page */ + void *page_kaddr; /* kmapped address of the current page */ unsigned int nwords; /* Remaining decode buffer length */ struct rpc_rqst *rqst; /* For debugging */ @@ -257,6 +258,7 @@ extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, struct page **pages, unsigned int len); +extern void xdr_finish_decode(struct xdr_stream *xdr); extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); @@ -777,9 +779,7 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; - if (len > SIZE_MAX / sizeof(*p)) - return -EBADMSG; - p = xdr_inline_decode(xdr, len * sizeof(*p)); + p = xdr_inline_decode(xdr, size_mul(len, sizeof(*p))); if (unlikely(!p)) return -EBADMSG; if (array == NULL) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index b52411bcfe4e..4ecc89301eb7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -351,6 +351,8 @@ struct xprt_create { struct rpc_xprt_switch *bc_xps; unsigned int flags; struct xprtsec_parms xprtsec; + unsigned long connect_timeout; + unsigned long reconnect_timeout; }; struct xprt_class { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d7c697af3762..8d75290f1a31 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -534,6 +534,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .servername = args->servername, .bc_xprt = args->bc_xprt, .xprtsec = args->xprtsec, + .connect_timeout = args->connect_timeout, + .reconnect_timeout = args->reconnect_timeout, }; char servername[48]; struct rpc_clnt *clnt; @@ -2602,6 +2604,7 @@ out: case 0: task->tk_action = rpc_exit_task; task->tk_status = rpcauth_unwrap_resp(task, &xdr); + xdr_finish_decode(&xdr); return; case -EAGAIN: task->tk_status = 0; @@ -3069,6 +3072,11 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, } xprt->resvport = resvport; xprt->reuseport = reuseport; + + if (xprtargs->connect_timeout) + connect_timeout = xprtargs->connect_timeout; + if (xprtargs->reconnect_timeout) + reconnect_timeout = xprtargs->reconnect_timeout; if (xprt->ops->set_connect_timeout != NULL) xprt->ops->set_connect_timeout(xprt, connect_timeout, diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index dc21e6c732db..812fda9d45dd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1394,6 +1394,8 @@ svc_process_common(struct svc_rqst *rqstp) rc = process.dispatch(rqstp); if (procp->pc_release) procp->pc_release(rqstp); + xdr_finish_decode(xdr); + if (!rc) goto dropit; if (rqstp->rq_auth_stat != rpc_auth_ok) diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 358e6de91775..62e07c330a66 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1338,6 +1338,14 @@ static unsigned int xdr_set_tail_base(struct xdr_stream *xdr, return xdr_set_iov(xdr, buf->tail, base, len); } +static void xdr_stream_unmap_current_page(struct xdr_stream *xdr) +{ + if (xdr->page_kaddr) { + kunmap_local(xdr->page_kaddr); + xdr->page_kaddr = NULL; + } +} + static unsigned int xdr_set_page_base(struct xdr_stream *xdr, unsigned int base, unsigned int len) { @@ -1355,12 +1363,18 @@ static unsigned int xdr_set_page_base(struct xdr_stream *xdr, if (len > maxlen) len = maxlen; + xdr_stream_unmap_current_page(xdr); xdr_stream_page_set_pos(xdr, base); base += xdr->buf->page_base; pgnr = base >> PAGE_SHIFT; xdr->page_ptr = &xdr->buf->pages[pgnr]; - kaddr = page_address(*xdr->page_ptr); + + if (PageHighMem(*xdr->page_ptr)) { + xdr->page_kaddr = kmap_local_page(*xdr->page_ptr); + kaddr = xdr->page_kaddr; + } else + kaddr = page_address(*xdr->page_ptr); pgoff = base & ~PAGE_MASK; xdr->p = (__be32*)(kaddr + pgoff); @@ -1414,6 +1428,7 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst) { xdr->buf = buf; + xdr->page_kaddr = NULL; xdr_reset_scratch_buffer(xdr); xdr->nwords = XDR_QUADLEN(buf->len); if (xdr_set_iov(xdr, buf->head, 0, buf->len) == 0 && @@ -1446,6 +1461,16 @@ void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, } EXPORT_SYMBOL_GPL(xdr_init_decode_pages); +/** + * xdr_finish_decode - Clean up the xdr_stream after decoding data. + * @xdr: pointer to xdr_stream struct + */ +void xdr_finish_decode(struct xdr_stream *xdr) +{ + xdr_stream_unmap_current_page(xdr); +} +EXPORT_SYMBOL(xdr_finish_decode); + static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes) { unsigned int nwords = XDR_QUADLEN(nbytes); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 5e5ff6784ef5..da409450dfc0 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -593,7 +593,6 @@ void xprt_rdma_cleanup(void); int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int); size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *); unsigned int xprt_rdma_bc_max_slots(struct rpc_xprt *); -int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int); void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *); int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst); void xprt_rdma_bc_free_rqst(struct rpc_rqst *); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 268a2cc61acd..71cd916e384f 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2237,9 +2237,13 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct net *net = sock_net(sock->sk); + unsigned long connect_timeout; + unsigned long syn_retries; unsigned int keepidle; unsigned int keepcnt; unsigned int timeo; + unsigned long t; spin_lock(&xprt->transport_lock); keepidle = DIV_ROUND_UP(xprt->timeout->to_initval, HZ); @@ -2257,6 +2261,35 @@ static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, /* TCP user timeout (see RFC5482) */ tcp_sock_set_user_timeout(sock->sk, timeo); + + /* Connect timeout */ + connect_timeout = max_t(unsigned long, + DIV_ROUND_UP(xprt->connect_timeout, HZ), 1); + syn_retries = max_t(unsigned long, + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries), 1); + for (t = 0; t <= syn_retries && (1UL << t) < connect_timeout; t++) + ; + if (t <= syn_retries) + tcp_sock_set_syncnt(sock->sk, t - 1); +} + +static void xs_tcp_do_set_connect_timeout(struct rpc_xprt *xprt, + unsigned long connect_timeout) +{ + struct sock_xprt *transport = + container_of(xprt, struct sock_xprt, xprt); + struct rpc_timeout to; + unsigned long initval; + + memcpy(&to, xprt->timeout, sizeof(to)); + /* Arbitrary lower limit */ + initval = max_t(unsigned long, connect_timeout, XS_TCP_INIT_REEST_TO); + to.to_initval = initval; + to.to_maxval = initval; + to.to_retries = 0; + memcpy(&transport->tcp_timeout, &to, sizeof(transport->tcp_timeout)); + xprt->timeout = &transport->tcp_timeout; + xprt->connect_timeout = connect_timeout; } static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt, @@ -2264,25 +2297,12 @@ static void xs_tcp_set_connect_timeout(struct rpc_xprt *xprt, unsigned long reconnect_timeout) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - struct rpc_timeout to; - unsigned long initval; spin_lock(&xprt->transport_lock); if (reconnect_timeout < xprt->max_reconnect_timeout) xprt->max_reconnect_timeout = reconnect_timeout; - if (connect_timeout < xprt->connect_timeout) { - memcpy(&to, xprt->timeout, sizeof(to)); - initval = DIV_ROUND_UP(connect_timeout, to.to_retries + 1); - /* Arbitrary lower limit */ - if (initval < XS_TCP_INIT_REEST_TO << 1) - initval = XS_TCP_INIT_REEST_TO << 1; - to.to_initval = initval; - to.to_maxval = initval; - memcpy(&transport->tcp_timeout, &to, - sizeof(transport->tcp_timeout)); - xprt->timeout = &transport->tcp_timeout; - xprt->connect_timeout = connect_timeout; - } + if (connect_timeout < xprt->connect_timeout) + xs_tcp_do_set_connect_timeout(xprt, connect_timeout); set_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state); spin_unlock(&xprt->transport_lock); } @@ -3335,8 +3355,13 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->timeout = &xs_tcp_default_timeout; xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + if (args->reconnect_timeout) + xprt->max_reconnect_timeout = args->reconnect_timeout; + xprt->connect_timeout = xprt->timeout->to_initval * (xprt->timeout->to_retries + 1); + if (args->connect_timeout) + xs_tcp_do_set_connect_timeout(xprt, args->connect_timeout); INIT_WORK(&transport->recv_worker, xs_stream_data_receive_workfn); INIT_WORK(&transport->error_worker, xs_error_handle);