From 566fcec60b7458784d4ed9bca974c5a56dacf214 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 15:32:46 -0500 Subject: NFSv4: Fix an atomicity problem in CLOSE If we are to remove the serialisation of OPEN/CLOSE, then we need to ensure that the stateid sent as part of a CLOSE operation does not change after we test the state in nfs4_close_prepare. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 467c84efb596..7e38d641236e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -389,7 +389,7 @@ struct nfs_open_confirmres { struct nfs_closeargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; - nfs4_stateid * stateid; + nfs4_stateid stateid; struct nfs_seqid * seqid; fmode_t fmode; const u32 * bitmask; -- cgit v1.2.3 From 425c1d4e5b6d4bd700eb94ad8318bdb05431fdc7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 14:57:53 -0500 Subject: NFSv4: Fix lock on-wire reordering issues This patch ensures that the server cannot reorder our LOCK/LOCKU requests if they are sent in parallel on the wire. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 29 ++++++++++++++++++++++++----- fs/nfs/nfs4xdr.c | 6 +++--- include/linux/nfs_xdr.h | 6 +++--- 3 files changed, 30 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f12ded041a42..41e7c2fc046e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5393,7 +5393,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->arg.fl = &p->fl; p->arg.seqid = seqid; p->res.seqid = seqid; - p->arg.stateid = &lsp->ls_stateid; p->lsp = lsp; atomic_inc(&lsp->ls_count); /* Ensure we don't close file until we're done freeing locks! */ @@ -5428,6 +5427,9 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: + if (!nfs4_stateid_match(&calldata->arg.stateid, + &calldata->lsp->ls_stateid)) + rpc_restart_call_prepare(task); break; default: if (nfs4_async_handle_error(task, calldata->server, @@ -5443,6 +5445,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data) if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) goto out_wait; + nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid); if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) { /* Note: exit _without_ running nfs4_locku_done */ goto out_no_action; @@ -5584,7 +5587,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid, gfp_mask); if (IS_ERR(p->arg.lock_seqid)) goto out_free_seqid; - p->arg.lock_stateid = &lsp->ls_stateid; p->arg.lock_owner.clientid = server->nfs_client->cl_clientid; p->arg.lock_owner.id = lsp->ls_seqid.owner_id; p->arg.lock_owner.s_dev = server->s_dev; @@ -5615,11 +5617,15 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) { goto out_release_lock_seqid; } - data->arg.open_stateid = &state->open_stateid; + nfs4_stateid_copy(&data->arg.open_stateid, + &state->open_stateid); data->arg.new_lock_owner = 1; data->res.open_seqid = data->arg.open_seqid; - } else + } else { data->arg.new_lock_owner = 0; + nfs4_stateid_copy(&data->arg.lock_stateid, + &data->lsp->ls_stateid); + } if (!nfs4_valid_open_stateid(state)) { data->rpc_status = -EBADF; task->tk_action = NULL; @@ -5651,7 +5657,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) return; data->rpc_status = task->tk_status; - if (task->tk_status == 0) { + switch (task->tk_status) { + case 0: renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp); if (data->arg.new_lock_owner != 0) { @@ -5660,6 +5667,18 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) rpc_restart_call_prepare(task); + break; + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_OLD_STATEID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + if (data->arg.new_lock_owner != 0) { + if (!nfs4_stateid_match(&data->arg.open_stateid, + &lsp->ls_state->open_stateid)) + rpc_restart_call_prepare(task); + } else if (!nfs4_stateid_match(&data->arg.lock_stateid, + &lsp->ls_stateid)) + rpc_restart_call_prepare(task); } dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d05fada4929c..e3018e7a316c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1304,12 +1304,12 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args *p = cpu_to_be32(args->new_lock_owner); if (args->new_lock_owner){ encode_nfs4_seqid(xdr, args->open_seqid); - encode_nfs4_stateid(xdr, args->open_stateid); + encode_nfs4_stateid(xdr, &args->open_stateid); encode_nfs4_seqid(xdr, args->lock_seqid); encode_lockowner(xdr, &args->lock_owner); } else { - encode_nfs4_stateid(xdr, args->lock_stateid); + encode_nfs4_stateid(xdr, &args->lock_stateid); encode_nfs4_seqid(xdr, args->lock_seqid); } } @@ -1333,7 +1333,7 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar encode_op_hdr(xdr, OP_LOCKU, decode_locku_maxsz, hdr); encode_uint32(xdr, nfs4_lock_type(args->fl, 0)); encode_nfs4_seqid(xdr, args->seqid); - encode_nfs4_stateid(xdr, args->stateid); + encode_nfs4_stateid(xdr, &args->stateid); p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, args->fl->fl_start); xdr_encode_hyper(p, nfs4_lock_length(args->fl)); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7e38d641236e..b6a6953c0f09 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -416,9 +416,9 @@ struct nfs_lock_args { struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * lock_seqid; - nfs4_stateid * lock_stateid; + nfs4_stateid lock_stateid; struct nfs_seqid * open_seqid; - nfs4_stateid * open_stateid; + nfs4_stateid open_stateid; struct nfs_lowner lock_owner; unsigned char block : 1; unsigned char reclaim : 1; @@ -437,7 +437,7 @@ struct nfs_locku_args { struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * seqid; - nfs4_stateid * stateid; + nfs4_stateid stateid; }; struct nfs_locku_res { -- cgit v1.2.3 From c69899a17ca4836230720e65493942d9582a0424 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 16:03:52 -0500 Subject: NFSv4: Update of VFS byte range lock must be atomic with the stateid update Ensure that we test the lock stateid remained unchanged while we were updating the VFS tracking of the byte range lock. Have the process replay the lock to the server if we detect that was not the case. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 37 +++++++++++++++---------------------- include/linux/nfs_xdr.h | 1 + 2 files changed, 16 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 41e7c2fc046e..9f6baf98942c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5420,9 +5420,10 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) switch (task->tk_status) { case 0: renew_lease(calldata->server, calldata->timestamp); - nfs4_update_lock_stateid(calldata->lsp, - &calldata->res.stateid); - break; + do_vfs_lock(calldata->fl.fl_file, &calldata->fl); + if (nfs4_update_lock_stateid(calldata->lsp, + &calldata->res.stateid)) + break; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: @@ -5661,6 +5662,13 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) case 0: renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp); + if (data->arg.new_lock) { + data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); + if (do_vfs_lock(data->fl.fl_file, &data->fl) < 0) { + rpc_restart_call_prepare(task); + break; + } + } if (data->arg.new_lock_owner != 0) { nfs_confirm_seqid(&lsp->ls_seqid, 0); nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); @@ -5760,7 +5768,8 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f if (recovery_type == NFS_LOCK_RECLAIM) data->arg.reclaim = NFS_LOCK_RECLAIM; nfs4_set_sequence_privileged(&data->arg.seq_args); - } + } else + data->arg.new_lock = 1; task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); @@ -5884,10 +5893,8 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) { - struct nfs4_state_owner *sp = state->owner; struct nfs_inode *nfsi = NFS_I(state->inode); unsigned char fl_flags = request->fl_flags; - unsigned int seq; int status = -ENOLCK; if ((fl_flags & FL_POSIX) && @@ -5907,25 +5914,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock /* ...but avoid races with delegation recall... */ request->fl_flags = fl_flags & ~FL_SLEEP; status = do_vfs_lock(request->fl_file, request); - goto out_unlock; - } - seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); - up_read(&nfsi->rwsem); - status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW); - if (status != 0) + up_read(&nfsi->rwsem); goto out; - down_read(&nfsi->rwsem); - if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) { - status = -NFS4ERR_DELAY; - goto out_unlock; } - /* Note: we always want to sleep here! */ - request->fl_flags = fl_flags | FL_SLEEP; - if (do_vfs_lock(request->fl_file, request) < 0) - printk(KERN_WARNING "NFS: %s: VFS is out of sync with lock " - "manager!\n", __func__); -out_unlock: up_read(&nfsi->rwsem); + status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW); out: request->fl_flags = fl_flags; return status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b6a6953c0f09..e5c3b620a609 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -422,6 +422,7 @@ struct nfs_lock_args { struct nfs_lowner lock_owner; unsigned char block : 1; unsigned char reclaim : 1; + unsigned char new_lock : 1; unsigned char new_lock_owner : 1; }; -- cgit v1.2.3 From 284f4902a632584e8d73cf7d9363f819adf7240c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 21 Jan 2015 11:02:13 -0500 Subject: xprtrdma: Modernize htonl and ntohl Clean up: Replace htonl and ntohl with the be32 equivalents. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 9 ++++++++ include/linux/sunrpc/svc_rdma.h | 2 -- net/sunrpc/xprtrdma/rpc_rdma.c | 48 ++++++++++++++++++++++------------------- 3 files changed, 35 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index b78f16b1dea3..1578ed241c19 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -42,6 +42,9 @@ #include +#define RPCRDMA_VERSION 1 +#define rpcrdma_version cpu_to_be32(RPCRDMA_VERSION) + struct rpcrdma_segment { __be32 rs_handle; /* Registered memory handle */ __be32 rs_length; /* Length of the chunk in bytes */ @@ -115,4 +118,10 @@ enum rpcrdma_proc { RDMA_ERROR = 4 /* An RPC RDMA encoding error */ }; +#define rdma_msg cpu_to_be32(RDMA_MSG) +#define rdma_nomsg cpu_to_be32(RDMA_NOMSG) +#define rdma_msgp cpu_to_be32(RDMA_MSGP) +#define rdma_done cpu_to_be32(RDMA_DONE) +#define rdma_error cpu_to_be32(RDMA_ERROR) + #endif /* _LINUX_SUNRPC_RPC_RDMA_H */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 975da754c778..ddfe88f52219 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -63,8 +63,6 @@ extern atomic_t rdma_stat_rq_prod; extern atomic_t rdma_stat_sq_poll; extern atomic_t rdma_stat_sq_prod; -#define RPCRDMA_VERSION 1 - /* * Contexts are built when an RDMA request is created and are a * record of the resources that can be recovered when the request diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index df01d124936c..a6fb30b0a8cc 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -209,9 +209,11 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, if (cur_rchunk) { /* read */ cur_rchunk->rc_discrim = xdr_one; /* all read chunks have the same "position" */ - cur_rchunk->rc_position = htonl(pos); - cur_rchunk->rc_target.rs_handle = htonl(seg->mr_rkey); - cur_rchunk->rc_target.rs_length = htonl(seg->mr_len); + cur_rchunk->rc_position = cpu_to_be32(pos); + cur_rchunk->rc_target.rs_handle = + cpu_to_be32(seg->mr_rkey); + cur_rchunk->rc_target.rs_length = + cpu_to_be32(seg->mr_len); xdr_encode_hyper( (__be32 *)&cur_rchunk->rc_target.rs_offset, seg->mr_base); @@ -222,8 +224,10 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, cur_rchunk++; r_xprt->rx_stats.read_chunk_count++; } else { /* write/reply */ - cur_wchunk->wc_target.rs_handle = htonl(seg->mr_rkey); - cur_wchunk->wc_target.rs_length = htonl(seg->mr_len); + cur_wchunk->wc_target.rs_handle = + cpu_to_be32(seg->mr_rkey); + cur_wchunk->wc_target.rs_length = + cpu_to_be32(seg->mr_len); xdr_encode_hyper( (__be32 *)&cur_wchunk->wc_target.rs_offset, seg->mr_base); @@ -257,7 +261,7 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target, *iptr++ = xdr_zero; /* encode a NULL reply chunk */ } else { warray->wc_discrim = xdr_one; - warray->wc_nchunks = htonl(nchunks); + warray->wc_nchunks = cpu_to_be32(nchunks); iptr = (__be32 *) cur_wchunk; if (type == rpcrdma_writech) { *iptr++ = xdr_zero; /* finish the write chunk list */ @@ -404,11 +408,11 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) /* build RDMA header in private area at front */ headerp = (struct rpcrdma_msg *) req->rl_base; - /* don't htonl XID, it's already done in request */ + /* don't byte-swap XID, it's already done in request */ headerp->rm_xid = rqst->rq_xid; - headerp->rm_vers = xdr_one; - headerp->rm_credit = htonl(r_xprt->rx_buf.rb_max_requests); - headerp->rm_type = htonl(RDMA_MSG); + headerp->rm_vers = rpcrdma_version; + headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_max_requests); + headerp->rm_type = rdma_msg; /* * Chunks needed for results? @@ -482,11 +486,11 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) RPCRDMA_INLINE_PAD_VALUE(rqst)); if (padlen) { - headerp->rm_type = htonl(RDMA_MSGP); + headerp->rm_type = rdma_msgp; headerp->rm_body.rm_padded.rm_align = - htonl(RPCRDMA_INLINE_PAD_VALUE(rqst)); + cpu_to_be32(RPCRDMA_INLINE_PAD_VALUE(rqst)); headerp->rm_body.rm_padded.rm_thresh = - htonl(RPCRDMA_INLINE_PAD_THRESH); + cpu_to_be32(RPCRDMA_INLINE_PAD_THRESH); headerp->rm_body.rm_padded.rm_pempty[0] = xdr_zero; headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero; headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero; @@ -570,7 +574,7 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b unsigned int i, total_len; struct rpcrdma_write_chunk *cur_wchunk; - i = ntohl(**iptrp); /* get array count */ + i = be32_to_cpu(**iptrp); if (i > max) return -1; cur_wchunk = (struct rpcrdma_write_chunk *) (*iptrp + 1); @@ -582,11 +586,11 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __b xdr_decode_hyper((__be32 *)&seg->rs_offset, &off); dprintk("RPC: %s: chunk %d@0x%llx:0x%x\n", __func__, - ntohl(seg->rs_length), + be32_to_cpu(seg->rs_length), (unsigned long long)off, - ntohl(seg->rs_handle)); + be32_to_cpu(seg->rs_handle)); } - total_len += ntohl(seg->rs_length); + total_len += be32_to_cpu(seg->rs_length); ++cur_wchunk; } /* check and adjust for properly terminated write chunk */ @@ -749,9 +753,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) goto repost; } headerp = (struct rpcrdma_msg *) rep->rr_base; - if (headerp->rm_vers != xdr_one) { + if (headerp->rm_vers != rpcrdma_version) { dprintk("RPC: %s: invalid version %d\n", - __func__, ntohl(headerp->rm_vers)); + __func__, be32_to_cpu(headerp->rm_vers)); goto repost; } @@ -793,7 +797,7 @@ repost: /* check for expected message types */ /* The order of some of these tests is important. */ switch (headerp->rm_type) { - case htonl(RDMA_MSG): + case rdma_msg: /* never expect read chunks */ /* never expect reply chunks (two ways to check) */ /* never expect write chunks without having offered RDMA */ @@ -832,7 +836,7 @@ repost: rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen); break; - case htonl(RDMA_NOMSG): + case rdma_nomsg: /* never expect read or write chunks, always reply chunks */ if (headerp->rm_body.rm_chunks[0] != xdr_zero || headerp->rm_body.rm_chunks[1] != xdr_zero || @@ -853,7 +857,7 @@ badheader: dprintk("%s: invalid rpcrdma reply header (type %d):" " chunks[012] == %d %d %d" " expected chunks <= %d\n", - __func__, ntohl(headerp->rm_type), + __func__, be32_to_cpu(headerp->rm_type), headerp->rm_body.rm_chunks[0], headerp->rm_body.rm_chunks[1], headerp->rm_body.rm_chunks[2], -- cgit v1.2.3 From f2846481b4bf758cf7c3fe8f24b35950306f1db2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 21 Jan 2015 11:02:29 -0500 Subject: xprtrdma: Clean up hdrlen Clean up: Replace naked integers with a documenting macro. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 5 ++++- net/sunrpc/xprtrdma/rpc_rdma.c | 12 +++++++----- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 1578ed241c19..f33c5a4d6fe4 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -98,7 +98,10 @@ struct rpcrdma_msg { } rm_body; }; -#define RPCRDMA_HDRLEN_MIN 28 +/* + * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks + */ +#define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) enum rpcrdma_errcode { ERR_VERS = 1, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 150dd7641803..dcf5ebc3d373 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -472,7 +472,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) return -EIO; } - hdrlen = 28; /*sizeof *headerp;*/ + hdrlen = RPCRDMA_HDRLEN_MIN; padlen = 0; /* @@ -748,7 +748,7 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) } return; } - if (rep->rr_len < 28) { + if (rep->rr_len < RPCRDMA_HDRLEN_MIN) { dprintk("RPC: %s: short/invalid reply\n", __func__); goto repost; } @@ -830,8 +830,9 @@ repost: } else { /* else ordinary inline */ rdmalen = 0; - iptr = (__be32 *)((unsigned char *)headerp + 28); - rep->rr_len -= 28; /*sizeof *headerp;*/ + iptr = (__be32 *)((unsigned char *)headerp + + RPCRDMA_HDRLEN_MIN); + rep->rr_len -= RPCRDMA_HDRLEN_MIN; status = rep->rr_len; } /* Fix up the rpc results for upper layer */ @@ -845,7 +846,8 @@ repost: headerp->rm_body.rm_chunks[2] != xdr_one || req->rl_nchunks == 0) goto badheader; - iptr = (__be32 *)((unsigned char *)headerp + 28); + iptr = (__be32 *)((unsigned char *)headerp + + RPCRDMA_HDRLEN_MIN); rdmalen = rpcrdma_count_chunks(rep, req->rl_nchunks, 0, &iptr); if (rdmalen < 0) goto badheader; -- cgit v1.2.3 From 1a04c6e1a26a43305fe124a0978a3e4be861af89 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 30 May 2014 18:15:57 +0800 Subject: nfsv3: introduce nfs3_set_ds_client The flexfiles layout wants to create DS connection over NFSv3. Add nfs3_set_ds_client to allow that to happen. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/internal.h | 4 ++++ fs/nfs/nfs3_fs.h | 2 ++ fs/nfs/nfs3client.c | 34 ++++++++++++++++++++++++++++++++++ fs/nfs/nfs3super.c | 2 +- include/linux/nfs_fs_sb.h | 9 +++++---- 5 files changed, 46 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7d7c36ff09fa..7332ba1f693b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -193,6 +193,10 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, rpc_authflavor_t au_flavor); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); +extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, + unsigned int ds_retrans, rpc_authflavor_t au_flavor); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index 333ae4068506..e134d6548ab7 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -30,5 +30,7 @@ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subver struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); +/* nfs3super.c */ +extern struct nfs_subversion nfs_v3; #endif /* __LINUX_FS_NFS_NFS3_FS_H */ diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 8c1b437c5403..52e2344bf9a1 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -64,3 +64,37 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source, nfs_init_server_aclclient(server); return server; } + +/* + * Set up a pNFS Data Server client over NFSv3. + * + * Return any existing nfs_client that matches server address,port,version + * and minorversion. + * + * For a new nfs_client, use a soft mount (default), a low retrans and a + * low timeout interval so that if a connection is lost, we retry through + * the MDS. + */ +struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, + rpc_authflavor_t au_flavor) +{ + struct nfs_client_initdata cl_init = { + .addr = ds_addr, + .addrlen = ds_addrlen, + .nfs_mod = &nfs_v3, + .proto = ds_proto, + .net = mds_clp->cl_net, + }; + struct rpc_timeout ds_timeout; + struct nfs_client *clp; + + /* Use the MDS nfs_client cl_ipaddr. */ + nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); + clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, + au_flavor); + + return clp; +} +EXPORT_SYMBOL_GPL(nfs3_set_ds_client); diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c index 6af29c2da352..5c4394e4656b 100644 --- a/fs/nfs/nfs3super.c +++ b/fs/nfs/nfs3super.c @@ -7,7 +7,7 @@ #include "nfs3_fs.h" #include "nfs.h" -static struct nfs_subversion nfs_v3 = { +struct nfs_subversion nfs_v3 = { .owner = THIS_MODULE, .nfs_fs = &nfs_fs_type, .rpc_vers = &nfs_version3, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ddea982355f3..5e1273d4de14 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -77,10 +77,6 @@ struct nfs_client { /* Client owner identifier */ const char * cl_owner_id; - /* Our own IP address, as a null-terminated string. - * This is used to generate the mv0 callback address. - */ - char cl_ipaddr[48]; u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; unsigned long cl_mig_gen; @@ -108,6 +104,11 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */ #endif /* CONFIG_NFS_V4 */ + /* Our own IP address, as a null-terminated string. + * This is used to generate the mv0 callback address. + */ + char cl_ipaddr[48]; + #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif -- cgit v1.2.3 From abde71f4d3c027a30f8d725e1e22001313b4481a Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Mon, 9 Jun 2014 13:12:20 -0700 Subject: pnfs: Add nfs_rpc_ops in calls to nfs_initiate_pgio Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayout.c | 4 ++-- fs/nfs/internal.h | 1 + fs/nfs/pagelist.c | 6 ++++-- fs/nfs/read.c | 3 ++- fs/nfs/write.c | 6 +++--- include/linux/nfs_page.h | 1 + 6 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index bc36ed350a68..25c4896887ca 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -501,7 +501,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) hdr->mds_offset = offset; /* Perform an asynchronous read to ds */ - nfs_initiate_pgio(ds_clnt, hdr, + nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode), &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; } @@ -542,7 +542,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) hdr->args.offset = filelayout_get_dserver_offset(lseg, offset); /* Perform an asynchronous write */ - nfs_initiate_pgio(ds_clnt, hdr, + nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode), &filelayout_write_call_ops, sync, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5543850268d2..1d15ffa94937 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -251,6 +251,7 @@ void nfs_pgio_header_free(struct nfs_pgio_header *); void nfs_pgio_data_destroy(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *, + const struct nfs_rpc_ops *, const struct rpc_call_ops *, int, int); void nfs_free_request(struct nfs_page *req); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2b5e769beb16..35a2626a6922 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -597,6 +597,7 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) } int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, + const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags) { struct rpc_task *task; @@ -616,7 +617,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, }; int ret = 0; - hdr->rw_ops->rw_initiate(hdr, &msg, &task_setup_data, how); + hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how); dprintk("NFS: %5u initiated pgio call " "(req %s/%llu, %u bytes @ offset %llu)\n", @@ -792,7 +793,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) ret = nfs_generic_pgio(desc, hdr); if (ret == 0) ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode), - hdr, desc->pg_rpc_callops, + hdr, NFS_PROTO(hdr->inode), + desc->pg_rpc_callops, desc->pg_ioflags, 0); return ret; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index c91a4799c562..092ab499f2b6 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -168,13 +168,14 @@ out: static void nfs_initiate_read(struct nfs_pgio_header *hdr, struct rpc_message *msg, + const struct nfs_rpc_ops *rpc_ops, struct rpc_task_setup *task_setup_data, int how) { struct inode *inode = hdr->inode; int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; task_setup_data->flags |= swap_flags; - NFS_PROTO(inode)->read_setup(hdr, msg); + rpc_ops->read_setup(hdr, msg); } static void diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af3af685a9e3..54d4857e0e2b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1240,15 +1240,15 @@ static int flush_task_priority(int how) static void nfs_initiate_write(struct nfs_pgio_header *hdr, struct rpc_message *msg, + const struct nfs_rpc_ops *rpc_ops, struct rpc_task_setup *task_setup_data, int how) { - struct inode *inode = hdr->inode; int priority = flush_task_priority(how); task_setup_data->priority = priority; - NFS_PROTO(inode)->write_setup(hdr, msg); + rpc_ops->write_setup(hdr, msg); - nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client, + nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client, &task_setup_data->rpc_client, msg, hdr); } diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 6c3e06ee2fb7..4c3aa809ab95 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -69,6 +69,7 @@ struct nfs_rw_ops { struct inode *); void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *); void (*rw_initiate)(struct nfs_pgio_header *, struct rpc_message *, + const struct nfs_rpc_ops *, struct rpc_task_setup *, int); }; -- cgit v1.2.3 From 840210fc4872bcbc17ab4f435f28021dce9d0aff Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 24 Jun 2014 10:59:52 -0400 Subject: sunrpc: add rpc_count_iostats_idx Add a call to tally stats for a task under a different statsidx than what's contained in the task structure. This is needed to properly account for pnfs reads/writes when the DS nfs version != the MDS version. Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes --- include/linux/sunrpc/metrics.h | 2 ++ net/sunrpc/stats.c | 26 +++++++++++++++++++------- 2 files changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index eecb5a71e6c0..89f2ca178873 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -79,6 +79,8 @@ struct rpc_clnt; struct rpc_iostats * rpc_alloc_iostats(struct rpc_clnt *); void rpc_count_iostats(const struct rpc_task *, struct rpc_iostats *); +void rpc_count_iostats_metrics(const struct rpc_task *, + struct rpc_iostats *); void rpc_print_iostats(struct seq_file *, struct rpc_clnt *); void rpc_free_iostats(struct rpc_iostats *); diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index 9711a155bc50..2ecb994314c1 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -140,22 +140,20 @@ void rpc_free_iostats(struct rpc_iostats *stats) EXPORT_SYMBOL_GPL(rpc_free_iostats); /** - * rpc_count_iostats - tally up per-task stats + * rpc_count_iostats_metrics - tally up per-task stats * @task: completed rpc_task - * @stats: array of stat structures + * @op_metrics: stat structure for OP that will accumulate stats from @task */ -void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) +void rpc_count_iostats_metrics(const struct rpc_task *task, + struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; - struct rpc_iostats *op_metrics; ktime_t delta, now; - if (!stats || !req) + if (!op_metrics || !req) return; now = ktime_get(); - op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx]; - spin_lock(&op_metrics->om_lock); op_metrics->om_ops++; @@ -175,6 +173,20 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) spin_unlock(&op_metrics->om_lock); } +EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); + +/** + * rpc_count_iostats - tally up per-task stats + * @task: completed rpc_task + * @stats: array of stat structures + * + * Uses the statidx from @task + */ +void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) +{ + rpc_count_iostats_metrics(task, + &stats[task->tk_msg.rpc_proc->p_statidx]); +} EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, -- cgit v1.2.3 From aabff4ddcac0d36dd26546f5b905c27682e7bf89 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 27 Aug 2014 10:47:14 +0800 Subject: nfs: save server READ/WRITE/COMMIT status Flexfiles layout would want to use them to report DS IO status. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs2xdr.c | 10 +++++++--- fs/nfs/nfs3xdr.c | 3 +++ fs/nfs/nfs4xdr.c | 3 +++ include/linux/nfs_xdr.h | 2 ++ 4 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 5f61b83f4a1c..b4e03ed8599d 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -481,7 +481,8 @@ out_overflow: * void; * }; */ -static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result) +static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result, + __u32 *op_status) { enum nfs_stat status; int error; @@ -489,6 +490,8 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result) error = decode_stat(xdr, &status); if (unlikely(error)) goto out; + if (op_status) + *op_status = status; if (status != NFS_OK) goto out_default; error = decode_fattr(xdr, result); @@ -808,7 +811,7 @@ out_default: static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, struct nfs_fattr *result) { - return decode_attrstat(xdr, result); + return decode_attrstat(xdr, result, NULL); } static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, @@ -865,6 +868,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_stat(xdr, &status); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS_OK) goto out_default; error = decode_fattr(xdr, result->fattr); @@ -882,7 +886,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, { /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; - return decode_attrstat(xdr, result->fattr); + return decode_attrstat(xdr, result->fattr, &result->op_status); } /** diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 8f4cbe7f4aa8..2a932fdc57cb 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1636,6 +1636,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_post_op_attr(xdr, result->fattr); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS3_OK) goto out_status; error = decode_read3resok(xdr, result); @@ -1708,6 +1709,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, error = decode_wcc_data(xdr, result->fattr); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS3_OK) goto out_status; error = decode_write3resok(xdr, result); @@ -2323,6 +2325,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, error = decode_wcc_data(xdr, result->fattr); if (unlikely(error)) goto out; + result->op_status = status; if (status != NFS3_OK) goto out_status; error = decode_writeverf3(xdr, &result->verf->verifier); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cb4376b78ed9..7d8d7a47f771 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6567,6 +6567,7 @@ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, int status; status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; if (status) goto out; status = decode_sequence(xdr, &res->seq_res, rqstp); @@ -6592,6 +6593,7 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, int status; status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; if (status) goto out; status = decode_sequence(xdr, &res->seq_res, rqstp); @@ -6621,6 +6623,7 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, int status; status = decode_compound_hdr(xdr, &hdr); + res->op_status = hdr.status; if (status) goto out; status = decode_sequence(xdr, &res->seq_res, rqstp); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 467c84efb596..962f461c065d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -513,6 +513,7 @@ struct nfs_pgio_res { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; __u32 count; + __u32 op_status; int eof; /* used by read */ struct nfs_writeverf * verf; /* used by write */ const struct nfs_server *server; /* used by write */ @@ -532,6 +533,7 @@ struct nfs_commitargs { struct nfs_commitres { struct nfs4_sequence_res seq_res; + __u32 op_status; struct nfs_fattr *fattr; struct nfs_writeverf *verf; const struct nfs_server *server; -- cgit v1.2.3 From 4579d6b897ee1b2557517fd536fb17eeb13481ad Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:21 +0800 Subject: nfs41: pass iomode through layoutreturn args So that it is possible to return a specific iomode layouts. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4xdr.c | 2 +- fs/nfs/pnfs.c | 1 + include/linux/nfs_xdr.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7d8d7a47f771..3c3ff633dd17 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2012,7 +2012,7 @@ encode_layoutreturn(struct xdr_stream *xdr, p = reserve_space(xdr, 16); *p++ = cpu_to_be32(0); /* reclaim. always 0 for now */ *p++ = cpu_to_be32(args->layout_type); - *p++ = cpu_to_be32(IOMODE_ANY); + *p++ = cpu_to_be32(args->iomode); *p = cpu_to_be32(RETURN_FILE); p = reserve_space(xdr, 16); p = xdr_encode_hyper(p, 0); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 7e1bac189d1c..1b544c1a746c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -914,6 +914,7 @@ _pnfs_return_layout(struct inode *ino) lrp->args.stateid = stateid; lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; lrp->args.inode = ino; + lrp->args.iomode = IOMODE_ANY; lrp->args.layout = lo; lrp->clp = NFS_SERVER(ino)->nfs_client; lrp->cred = lo->plh_lc_cred; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 962f461c065d..4fd7793d45d1 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -293,6 +293,7 @@ struct nfs4_layoutreturn_args { struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; + enum pnfs_iomode iomode; nfs4_stateid stateid; __u32 layout_type; }; -- cgit v1.2.3 From 2176bf4269a37a7742230ed6c91668241bfe1b2b Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 10 Sep 2014 15:44:18 -0400 Subject: nfs: introduce pg_cleanup op for pgio descriptors Add a new operation to nfs_pageio_ops that is called on nfs_pageio_complete. Signed-off-by: Weston Andros Adamson --- fs/nfs/pagelist.c | 5 ++++- include/linux/nfs_page.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index c4d175829880..1c031878c752 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1050,7 +1050,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, EXPORT_SYMBOL_GPL(nfs_pageio_resend); /** - * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor + * nfs_pageio_complete - Complete I/O then cleanup an nfs_pageio_descriptor * @desc: pointer to io descriptor */ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) @@ -1062,6 +1062,9 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) if (!nfs_do_recoalesce(desc)) break; } + + if (desc->pg_ops->pg_cleanup) + desc->pg_ops->pg_cleanup(desc); } /** diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 4c3aa809ab95..479c566c4ddc 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -58,6 +58,7 @@ struct nfs_pageio_ops { size_t (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); + void (*pg_cleanup)(struct nfs_pageio_descriptor *); }; struct nfs_rw_ops { -- cgit v1.2.3 From 6cccbb6f52dceec5f4faed8846ac05ae830640e6 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 16 Sep 2014 17:35:51 -0400 Subject: nfs: rename pgio header ds_idx to ds_commit_idx 'ds_commit_idx' is a better name - it is used to select the right commit bucket for pnfs. Signed-off-by: Weston Andros Adamson --- fs/nfs/direct.c | 14 ++++++-------- fs/nfs/filelayout/filelayout.c | 4 ++-- include/linux/nfs_xdr.h | 2 +- 3 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e84f764b9dcd..d7c2d430b04d 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -112,22 +112,22 @@ static inline int put_dreq(struct nfs_direct_req *dreq) * nfs_direct_select_verf - select the right verifier * @dreq - direct request possibly spanning multiple servers * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs - * @ds_idx - index of data server in data server list, only valid if ds_clp set + * @commit_idx - commit bucket index for the DS * * returns the correct verifier to use given the role of the server */ static struct nfs_writeverf * nfs_direct_select_verf(struct nfs_direct_req *dreq, struct nfs_client *ds_clp, - int ds_idx) + int commit_idx) { struct nfs_writeverf *verfp = &dreq->verf; #ifdef CONFIG_NFS_V4_1 if (ds_clp) { /* pNFS is in use, use the DS verf */ - if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets) - verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf; + if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets) + verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf; else WARN_ON_ONCE(1); } @@ -148,8 +148,7 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq, { struct nfs_writeverf *verfp; - verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, - hdr->ds_idx); + verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx); WARN_ON_ONCE(verfp->committed >= 0); memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf)); WARN_ON_ONCE(verfp->committed < 0); @@ -169,8 +168,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq, { struct nfs_writeverf *verfp; - verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, - hdr->ds_idx); + verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx); if (verfp->committed < 0) { nfs_direct_set_hdr_verf(dreq, hdr); return 0; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 2af32fc39d60..520cbc53e035 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -492,7 +492,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr) /* No multipath support. Use first DS */ atomic_inc(&ds->ds_clp->cl_count); hdr->ds_clp = ds->ds_clp; - hdr->ds_idx = idx; + hdr->ds_commit_idx = idx; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) hdr->args.fh = fh; @@ -536,7 +536,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync) hdr->pgio_done_cb = filelayout_write_done_cb; atomic_inc(&ds->ds_clp->cl_count); hdr->ds_clp = ds->ds_clp; - hdr->ds_idx = idx; + hdr->ds_commit_idx = idx; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) hdr->args.fh = fh; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4fd7793d45d1..5bc99f04a550 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1328,7 +1328,7 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_idx; /* ds index if ds_clp is set */ + int ds_commit_idx; /* ds index if ds_clp is set */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From a7d42ddb3099727f58366fa006f850a219cce6c8 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 19 Sep 2014 10:55:07 -0400 Subject: nfs: add mirroring support to pgio layer This patch adds mirrored write support to the pgio layer. The default is to use one mirror, but pgio callers may define callbacks to change this to any value up to the (arbitrarily selected) limit of 16. The basic idea is to break out members of nfs_pageio_descriptor that cannot be shared between mirrored DSes and put them in a new structure. Signed-off-by: Weston Andros Adamson --- fs/nfs/direct.c | 17 ++- fs/nfs/internal.h | 1 + fs/nfs/objlayout/objio_osd.c | 3 +- fs/nfs/pagelist.c | 270 +++++++++++++++++++++++++++++++++++-------- fs/nfs/pnfs.c | 26 +++-- fs/nfs/read.c | 30 ++++- fs/nfs/write.c | 10 +- include/linux/nfs_page.h | 20 +++- include/linux/nfs_xdr.h | 1 + 9 files changed, 311 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1ee41d74c31c..0178d4fe8ab7 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -360,8 +360,14 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) spin_lock(&dreq->lock); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) dreq->error = hdr->error; - else - dreq->count += hdr->good_bytes; + else { + /* + * FIXME: right now this only accounts for bytes written + * to the first mirror + */ + if (hdr->pgio_mirror_idx == 0) + dreq->count += hdr->good_bytes; + } spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { @@ -724,7 +730,12 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) dreq->error = hdr->error; } if (dreq->error == 0) { - dreq->count += hdr->good_bytes; + /* + * FIXME: right now this only accounts for bytes written + * to the first mirror + */ + if (hdr->pgio_mirror_idx == 0) + dreq->count += hdr->good_bytes; if (nfs_write_need_commit(hdr)) { if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) request_commit = true; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 05f9a87cdab4..ef1c703e487b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -469,6 +469,7 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo, struct nfs_direct_req *dreq); int nfs_key_timeout_notify(struct file *filp, struct inode *inode); bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx); +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index d00778077df1..9a5f2ee6001f 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -537,11 +537,12 @@ int objio_write_pagelist(struct nfs_pgio_header *hdr, int how) static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req) { + struct nfs_pgio_mirror *mirror = &pgio->pg_mirrors[pgio->pg_mirror_idx]; unsigned int size; size = pnfs_generic_pg_test(pgio, prev, req); - if (!size || pgio->pg_count + req->wb_bytes > + if (!size || mirror->pg_count + req->wb_bytes > (unsigned long)pgio->pg_layout_private) return 0; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1c031878c752..eec12b75c232 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -46,17 +46,22 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)) { - hdr->req = nfs_list_entry(desc->pg_list.next); + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + + hdr->req = nfs_list_entry(mirror->pg_list.next); hdr->inode = desc->pg_inode; hdr->cred = hdr->req->wb_context->cred; hdr->io_start = req_offset(hdr->req); - hdr->good_bytes = desc->pg_count; + hdr->good_bytes = mirror->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) hdr->completion_ops->init_hdr(hdr); + + hdr->pgio_mirror_idx = desc->pg_mirror_idx; } EXPORT_SYMBOL_GPL(nfs_pgheader_init); @@ -480,7 +485,10 @@ nfs_wait_on_request(struct nfs_page *req) size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) { - if (desc->pg_count > desc->pg_bsize) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + + if (mirror->pg_count > mirror->pg_bsize) { /* should never happen */ WARN_ON_ONCE(1); return 0; @@ -490,11 +498,11 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, * Limit the request size so that we can still allocate a page array * for it without upsetting the slab allocator. */ - if (((desc->pg_count + req->wb_bytes) >> PAGE_SHIFT) * + if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) * sizeof(struct page) > PAGE_SIZE) return 0; - return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes); + return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes); } EXPORT_SYMBOL_GPL(nfs_generic_pg_test); @@ -651,10 +659,18 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); static int nfs_pgio_error(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror; + u32 midx; + set_bit(NFS_IOHDR_REDO, &hdr->flags); nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + /* TODO: Make sure it's right to clean up all mirrors here + * and not just hdr->pgio_mirror_idx */ + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + } return -ENOMEM; } @@ -671,6 +687,17 @@ static void nfs_pgio_release(void *calldata) hdr->completion_ops->completion(hdr); } +static void nfs_pageio_mirror_init(struct nfs_pgio_mirror *mirror, + unsigned int bsize) +{ + INIT_LIST_HEAD(&mirror->pg_list); + mirror->pg_bytes_written = 0; + mirror->pg_count = 0; + mirror->pg_bsize = bsize; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; +} + /** * nfs_pageio_init - initialise a page io descriptor * @desc: pointer to descriptor @@ -687,13 +714,10 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, size_t bsize, int io_flags) { - INIT_LIST_HEAD(&desc->pg_list); - desc->pg_bytes_written = 0; - desc->pg_count = 0; - desc->pg_bsize = bsize; - desc->pg_base = 0; + struct nfs_pgio_mirror *new; + int i; + desc->pg_moreio = 0; - desc->pg_recoalesce = 0; desc->pg_inode = inode; desc->pg_ops = pg_ops; desc->pg_completion_ops = compl_ops; @@ -703,6 +727,26 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_lseg = NULL; desc->pg_dreq = NULL; desc->pg_layout_private = NULL; + desc->pg_bsize = bsize; + + desc->pg_mirror_count = 1; + desc->pg_mirror_idx = 0; + + if (pg_ops->pg_get_mirror_count) { + /* until we have a request, we don't have an lseg and no + * idea how many mirrors there will be */ + new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX, + sizeof(struct nfs_pgio_mirror), GFP_KERNEL); + desc->pg_mirrors_dynamic = new; + desc->pg_mirrors = new; + + for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++) + nfs_pageio_mirror_init(&desc->pg_mirrors[i], bsize); + } else { + desc->pg_mirrors_dynamic = NULL; + desc->pg_mirrors = desc->pg_mirrors_static; + nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize); + } } EXPORT_SYMBOL_GPL(nfs_pageio_init); @@ -738,14 +782,16 @@ static void nfs_pgio_result(struct rpc_task *task, void *calldata) int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_page *req; struct page **pages, *last_page; - struct list_head *head = &desc->pg_list; + struct list_head *head = &mirror->pg_list; struct nfs_commit_info cinfo; unsigned int pagecount, pageused; - pagecount = nfs_page_array_len(desc->pg_base, desc->pg_count); + pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); if (!nfs_pgarray_set(&hdr->page_array, pagecount)) return nfs_pgio_error(desc, hdr); @@ -773,7 +819,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, desc->pg_ioflags &= ~FLUSH_COND_STABLE; /* Set up the argument struct */ - nfs_pgio_rpcsetup(hdr, desc->pg_count, 0, desc->pg_ioflags, &cinfo); + nfs_pgio_rpcsetup(hdr, mirror->pg_count, 0, desc->pg_ioflags, &cinfo); desc->pg_rpc_callops = &nfs_pgio_common_ops; return 0; } @@ -781,12 +827,17 @@ EXPORT_SYMBOL_GPL(nfs_generic_pgio); static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror; struct nfs_pgio_header *hdr; int ret; + mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + /* TODO: make sure this is right with mirroring - or + * should it back out all mirrors? */ + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); return -ENOMEM; } nfs_pgheader_init(desc, hdr, nfs_pgio_header_free); @@ -801,6 +852,49 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) return ret; } +/* + * nfs_pageio_setup_mirroring - determine if mirroring is to be used + * by calling the pg_get_mirror_count op + */ +static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + int mirror_count = 1; + + if (!pgio->pg_ops->pg_get_mirror_count) + return 0; + + mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + + if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) + return -EINVAL; + + if (WARN_ON_ONCE(!pgio->pg_mirrors_dynamic)) + return -EINVAL; + + pgio->pg_mirror_count = mirror_count; + + return 0; +} + +/* + * nfs_pageio_stop_mirroring - stop using mirroring (set mirror count to 1) + */ +void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio) +{ + pgio->pg_mirror_count = 1; + pgio->pg_mirror_idx = 0; +} + +static void nfs_pageio_cleanup_mirroring(struct nfs_pageio_descriptor *pgio) +{ + pgio->pg_mirror_count = 1; + pgio->pg_mirror_idx = 0; + pgio->pg_mirrors = pgio->pg_mirrors_static; + kfree(pgio->pg_mirrors_dynamic); + pgio->pg_mirrors_dynamic = NULL; +} + static bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { @@ -867,19 +961,22 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_page *prev = NULL; - if (desc->pg_count != 0) { - prev = nfs_list_entry(desc->pg_list.prev); + + if (mirror->pg_count != 0) { + prev = nfs_list_entry(mirror->pg_list.prev); } else { if (desc->pg_ops->pg_init) desc->pg_ops->pg_init(desc, req); - desc->pg_base = req->wb_pgbase; + mirror->pg_base = req->wb_pgbase; } if (!nfs_can_coalesce_requests(prev, req, desc)) return 0; nfs_list_remove_request(req); - nfs_list_add_request(req, &desc->pg_list); - desc->pg_count += req->wb_bytes; + nfs_list_add_request(req, &mirror->pg_list); + mirror->pg_count += req->wb_bytes; return 1; } @@ -888,16 +985,19 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, */ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) { - if (!list_empty(&desc->pg_list)) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + + if (!list_empty(&mirror->pg_list)) { int error = desc->pg_ops->pg_doio(desc); if (error < 0) desc->pg_error = error; else - desc->pg_bytes_written += desc->pg_count; + mirror->pg_bytes_written += mirror->pg_count; } - if (list_empty(&desc->pg_list)) { - desc->pg_count = 0; - desc->pg_base = 0; + if (list_empty(&mirror->pg_list)) { + mirror->pg_count = 0; + mirror->pg_base = 0; } } @@ -915,10 +1015,14 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_page *subreq; unsigned int bytes_left = 0; unsigned int offset, pgbase; + WARN_ON_ONCE(desc->pg_mirror_idx >= desc->pg_mirror_count); + nfs_page_group_lock(req, false); subreq = req; @@ -938,7 +1042,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_pageio_doio(desc); if (desc->pg_error < 0) return 0; - if (desc->pg_recoalesce) + if (mirror->pg_recoalesce) return 0; /* retry add_request for this subreq */ nfs_page_group_lock(req, false); @@ -976,14 +1080,16 @@ err_ptr: static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; LIST_HEAD(head); do { - list_splice_init(&desc->pg_list, &head); - desc->pg_bytes_written -= desc->pg_count; - desc->pg_count = 0; - desc->pg_base = 0; - desc->pg_recoalesce = 0; + list_splice_init(&mirror->pg_list, &head); + mirror->pg_bytes_written -= mirror->pg_count; + mirror->pg_count = 0; + mirror->pg_base = 0; + mirror->pg_recoalesce = 0; + desc->pg_moreio = 0; while (!list_empty(&head)) { @@ -997,11 +1103,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) return 0; break; } - } while (desc->pg_recoalesce); + } while (mirror->pg_recoalesce); return 1; } -int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, +static int nfs_pageio_add_request_mirror(struct nfs_pageio_descriptor *desc, struct nfs_page *req) { int ret; @@ -1014,9 +1120,78 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, break; ret = nfs_do_recoalesce(desc); } while (ret); + return ret; } +int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + u32 midx; + unsigned int pgbase, offset, bytes; + struct nfs_page *dupreq, *lastreq; + + pgbase = req->wb_pgbase; + offset = req->wb_offset; + bytes = req->wb_bytes; + + nfs_pageio_setup_mirroring(desc, req); + + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + if (midx) { + nfs_page_group_lock(req, false); + + /* find the last request */ + for (lastreq = req->wb_head; + lastreq->wb_this_page != req->wb_head; + lastreq = lastreq->wb_this_page) + ; + + dupreq = nfs_create_request(req->wb_context, + req->wb_page, lastreq, pgbase, bytes); + + if (IS_ERR(dupreq)) { + nfs_page_group_unlock(req); + return 0; + } + + nfs_lock_request(dupreq); + nfs_page_group_unlock(req); + dupreq->wb_offset = offset; + dupreq->wb_index = req->wb_index; + } else + dupreq = req; + + desc->pg_mirror_idx = midx; + if (!nfs_pageio_add_request_mirror(desc, dupreq)) + return 0; + } + + return 1; +} + +/* + * nfs_pageio_complete_mirror - Complete I/O on the current mirror of an + * nfs_pageio_descriptor + * @desc: pointer to io descriptor + */ +static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, + u32 mirror_idx) +{ + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; + u32 restore_idx = desc->pg_mirror_idx; + + desc->pg_mirror_idx = mirror_idx; + for (;;) { + nfs_pageio_doio(desc); + if (!mirror->pg_recoalesce) + break; + if (!nfs_do_recoalesce(desc)) + break; + } + desc->pg_mirror_idx = restore_idx; +} + /* * nfs_pageio_resend - Transfer requests to new descriptor and resend * @hdr - the pgio header to move request from @@ -1055,16 +1230,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_resend); */ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) { - for (;;) { - nfs_pageio_doio(desc); - if (!desc->pg_recoalesce) - break; - if (!nfs_do_recoalesce(desc)) - break; - } + u32 midx; + + for (midx = 0; midx < desc->pg_mirror_count; midx++) + nfs_pageio_complete_mirror(desc, midx); if (desc->pg_ops->pg_cleanup) desc->pg_ops->pg_cleanup(desc); + nfs_pageio_cleanup_mirroring(desc); } /** @@ -1080,10 +1253,17 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) */ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) { - if (!list_empty(&desc->pg_list)) { - struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev); - if (index != prev->wb_index + 1) - nfs_pageio_complete(desc); + struct nfs_pgio_mirror *mirror; + struct nfs_page *prev; + u32 midx; + + for (midx = 0; midx < desc->pg_mirror_count; midx++) { + mirror = &desc->pg_mirrors[midx]; + if (!list_empty(&mirror->pg_list)) { + prev = nfs_list_entry(mirror->pg_list.prev); + if (index != prev->wb_index + 1) + nfs_pageio_complete_mirror(desc, midx); + } } } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 2da2e771fefe..5f7c422ebb5d 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1646,8 +1646,8 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup); * of bytes (maximum @req->wb_bytes) that can be coalesced. */ size_t -pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, - struct nfs_page *req) +pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, + struct nfs_page *prev, struct nfs_page *req) { unsigned int size; u64 seg_end, req_start, seg_left; @@ -1729,10 +1729,12 @@ static void pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { - list_splice_tail_init(&hdr->pages, &desc->pg_list); + list_splice_tail_init(&hdr->pages, &mirror->pg_list); nfs_pageio_reset_write_mds(desc); - desc->pg_recoalesce = 1; + mirror->pg_recoalesce = 1; } nfs_pgio_data_destroy(hdr); } @@ -1781,12 +1783,14 @@ EXPORT_SYMBOL_GPL(pnfs_writehdr_free); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); return -ENOMEM; } nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); @@ -1795,6 +1799,7 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) ret = nfs_generic_pgio(desc, hdr); if (!ret) pnfs_do_write(desc, hdr, desc->pg_ioflags); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); @@ -1839,10 +1844,13 @@ static void pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { - list_splice_tail_init(&hdr->pages, &desc->pg_list); + list_splice_tail_init(&hdr->pages, &mirror->pg_list); nfs_pageio_reset_read_mds(desc); - desc->pg_recoalesce = 1; + mirror->pg_recoalesce = 1; } nfs_pgio_data_destroy(hdr); } @@ -1893,12 +1901,14 @@ EXPORT_SYMBOL_GPL(pnfs_readhdr_free); int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { + struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_header *hdr; int ret; hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { - desc->pg_completion_ops->error_cleanup(&desc->pg_list); + desc->pg_completion_ops->error_cleanup(&mirror->pg_list); return -ENOMEM; } nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 092ab499f2b6..568ecf0a880f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -70,8 +70,15 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_read); void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { + struct nfs_pgio_mirror *mirror; + pgio->pg_ops = &nfs_pgio_rw_ops; - pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize; + + /* read path should never have more than one mirror */ + WARN_ON_ONCE(pgio->pg_mirror_count != 1); + + mirror = &pgio->pg_mirrors[0]; + mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize; } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); @@ -81,6 +88,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, struct nfs_page *new; unsigned int len; struct nfs_pageio_descriptor pgio; + struct nfs_pgio_mirror *pgm; len = nfs_page_length(page); if (len == 0) @@ -97,7 +105,13 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); - NFS_I(inode)->read_io += pgio.pg_bytes_written; + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio.pg_mirror_count != 1); + + pgm = &pgio.pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + return 0; } @@ -352,6 +366,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { struct nfs_pageio_descriptor pgio; + struct nfs_pgio_mirror *pgm; struct nfs_readdesc desc = { .pgio = &pgio, }; @@ -387,10 +402,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&pgio); - NFS_I(inode)->read_io += pgio.pg_bytes_written; - npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio.pg_mirror_count != 1); + + pgm = &pgio.pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + npages = (pgm->pg_bytes_written + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: put_nfs_open_context(desc.ctx); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2bee165fddcf..ceacfeeb28c2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -906,7 +906,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) if (nfs_write_need_commit(hdr)) { memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo, - 0); + hdr->pgio_mirror_idx); goto next; } remove_req: @@ -1304,8 +1304,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_init_write); void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) { + struct nfs_pgio_mirror *mirror; + pgio->pg_ops = &nfs_pgio_rw_ops; - pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; + + nfs_pageio_stop_mirroring(pgio); + + mirror = &pgio->pg_mirrors[0]; + mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; } EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 479c566c4ddc..3eb072dbce83 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -58,6 +58,8 @@ struct nfs_pageio_ops { size_t (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); + unsigned int (*pg_get_mirror_count)(struct nfs_pageio_descriptor *, + struct nfs_page *); void (*pg_cleanup)(struct nfs_pageio_descriptor *); }; @@ -74,15 +76,17 @@ struct nfs_rw_ops { struct rpc_task_setup *, int); }; -struct nfs_pageio_descriptor { +struct nfs_pgio_mirror { struct list_head pg_list; unsigned long pg_bytes_written; size_t pg_count; size_t pg_bsize; unsigned int pg_base; - unsigned char pg_moreio : 1, - pg_recoalesce : 1; + unsigned char pg_recoalesce : 1; +}; +struct nfs_pageio_descriptor { + unsigned char pg_moreio : 1; struct inode *pg_inode; const struct nfs_pageio_ops *pg_ops; const struct nfs_rw_ops *pg_rw_ops; @@ -93,8 +97,18 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_direct_req *pg_dreq; void *pg_layout_private; + unsigned int pg_bsize; /* default bsize for mirrors */ + + u32 pg_mirror_count; + struct nfs_pgio_mirror *pg_mirrors; + struct nfs_pgio_mirror pg_mirrors_static[1]; + struct nfs_pgio_mirror *pg_mirrors_dynamic; + u32 pg_mirror_idx; /* current mirror */ }; +/* arbitrarily selected limit to number of mirrors */ +#define NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX 16 + #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) extern struct nfs_page *nfs_create_request(struct nfs_open_context *ctx, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5bc99f04a550..6400a1e01aa4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1329,6 +1329,7 @@ struct nfs_pgio_header { struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ int ds_commit_idx; /* ds index if ds_clp is set */ + int pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From 15eb67c15342d212b0c8a540b6d6bd2dfad52a63 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 17 Nov 2014 09:30:36 +0800 Subject: nfs41: add range to layoutreturn args So that callers can specify which range to return. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4xdr.c | 6 +++--- fs/nfs/pnfs.c | 4 +++- include/linux/nfs_xdr.h | 2 +- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3c3ff633dd17..56d4c91a48f3 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2012,11 +2012,11 @@ encode_layoutreturn(struct xdr_stream *xdr, p = reserve_space(xdr, 16); *p++ = cpu_to_be32(0); /* reclaim. always 0 for now */ *p++ = cpu_to_be32(args->layout_type); - *p++ = cpu_to_be32(args->iomode); + *p++ = cpu_to_be32(args->range.iomode); *p = cpu_to_be32(RETURN_FILE); p = reserve_space(xdr, 16); - p = xdr_encode_hyper(p, 0); - p = xdr_encode_hyper(p, NFS4_MAX_UINT64); + p = xdr_encode_hyper(p, args->range.offset); + p = xdr_encode_hyper(p, args->range.length); spin_lock(&args->inode->i_lock); encode_nfs4_stateid(xdr, &args->stateid); spin_unlock(&args->inode->i_lock); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 685af4fb39ca..9549b89e494b 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -916,7 +916,9 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, lrp->args.stateid = stateid; lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id; lrp->args.inode = ino; - lrp->args.iomode = iomode; + lrp->args.range.iomode = iomode; + lrp->args.range.offset = 0; + lrp->args.range.length = NFS4_MAX_UINT64; lrp->args.layout = lo; lrp->clp = NFS_SERVER(ino)->nfs_client; lrp->cred = lo->plh_lc_cred; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6400a1e01aa4..363792356d25 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -293,7 +293,7 @@ struct nfs4_layoutreturn_args { struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; - enum pnfs_iomode iomode; + struct pnfs_layout_range range; nfs4_stateid stateid; __u32 layout_type; }; -- cgit v1.2.3 From d67ae825a59d639e4d8b82413af84d854617a87e Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Thu, 11 Dec 2014 17:02:04 -0500 Subject: pnfs/flexfiles: Add the FlexFile Layout Driver The flexfile layout is a new layout that extends the file layout. It is currently being drafted as a specification at https://datatracker.ietf.org/doc/draft-ietf-nfsv4-layout-types/ Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes Signed-off-by: Tao Peng --- fs/nfs/Kconfig | 5 + fs/nfs/Makefile | 1 + fs/nfs/flexfilelayout/Makefile | 5 + fs/nfs/flexfilelayout/flexfilelayout.c | 1574 +++++++++++++++++++++++++++++ fs/nfs/flexfilelayout/flexfilelayout.h | 155 +++ fs/nfs/flexfilelayout/flexfilelayoutdev.c | 552 ++++++++++ fs/nfs/idmap.c | 3 +- fs/nfs/nfs4proc.c | 4 +- fs/nfs/pnfs.c | 32 +- fs/nfs/pnfs.h | 1 + include/linux/nfs4.h | 1 + include/linux/nfs_idmap.h | 2 + include/linux/sunrpc/metrics.h | 2 + 13 files changed, 2325 insertions(+), 12 deletions(-) create mode 100644 fs/nfs/flexfilelayout/Makefile create mode 100644 fs/nfs/flexfilelayout/flexfilelayout.c create mode 100644 fs/nfs/flexfilelayout/flexfilelayout.h create mode 100644 fs/nfs/flexfilelayout/flexfilelayoutdev.c (limited to 'include/linux') diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 3dece03f2fc8..c7abc10279af 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT depends on NFS_V4_1 && SCSI_OSD_ULD default NFS_V4 +config PNFS_FLEXFILE_LAYOUT + tristate + depends on NFS_V4_1 && NFS_V3 + default m + config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN string "NFSv4.1 Implementation ID Domain" depends on NFS_V4_1 diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 23abffa8a4ce..1e987acf20c9 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -33,3 +33,4 @@ nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/ obj-$(CONFIG_PNFS_BLOCK) += blocklayout/ +obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ diff --git a/fs/nfs/flexfilelayout/Makefile b/fs/nfs/flexfilelayout/Makefile new file mode 100644 index 000000000000..1d2c9f6bbcd4 --- /dev/null +++ b/fs/nfs/flexfilelayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Flexfile Layout Driver kernel module +# +obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += nfs_layout_flexfiles.o +nfs_layout_flexfiles-y := flexfilelayout.o flexfilelayoutdev.o diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c new file mode 100644 index 000000000000..f29fb7d7e8f8 --- /dev/null +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -0,0 +1,1574 @@ +/* + * Module for pnfs flexfile layout driver. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ + +#include +#include +#include + +#include +#include + +#include "flexfilelayout.h" +#include "../nfs4session.h" +#include "../internal.h" +#include "../delegation.h" +#include "../nfs4trace.h" +#include "../iostat.h" +#include "../nfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ) + +static struct pnfs_layout_hdr * +ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) +{ + struct nfs4_flexfile_layout *ffl; + + ffl = kzalloc(sizeof(*ffl), gfp_flags); + if (ffl) { + INIT_LIST_HEAD(&ffl->error_list); + return &ffl->generic_hdr; + } else + return NULL; +} + +static void +ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct nfs4_ff_layout_ds_err *err, *n; + + list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list, + list) { + list_del(&err->list); + kfree(err); + } + kfree(FF_LAYOUT_FROM_HDR(lo)); +} + +static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE); + if (unlikely(p == NULL)) + return -ENOBUFS; + memcpy(stateid, p, NFS4_STATEID_SIZE); + dprintk("%s: stateid id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); + return 0; +} + +static int decode_deviceid(struct xdr_stream *xdr, struct nfs4_deviceid *devid) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE); + if (unlikely(!p)) + return -ENOBUFS; + memcpy(devid, p, NFS4_DEVICEID4_SIZE); + nfs4_print_deviceid(devid); + return 0; +} + +static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -ENOBUFS; + fh->size = be32_to_cpup(p++); + if (fh->size > sizeof(struct nfs_fh)) { + printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n", + fh->size); + return -EOVERFLOW; + } + /* fh.data */ + p = xdr_inline_decode(xdr, fh->size); + if (unlikely(!p)) + return -ENOBUFS; + memcpy(&fh->data, p, fh->size); + dprintk("%s: fh len %d\n", __func__, fh->size); + + return 0; +} + +/* + * Currently only stringified uids and gids are accepted. + * I.e., kerberos is not supported to the DSes, so no pricipals. + * + * That means that one common function will suffice, but when + * principals are added, this should be split to accomodate + * calls to both nfs_map_name_to_uid() and nfs_map_group_to_gid(). + */ +static int +decode_name(struct xdr_stream *xdr, u32 *id) +{ + __be32 *p; + int len; + + /* opaque_length(4)*/ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -ENOBUFS; + len = be32_to_cpup(p++); + if (len < 0) + return -EINVAL; + + dprintk("%s: len %u\n", __func__, len); + + /* opaque body */ + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + return -ENOBUFS; + + if (!nfs_map_string_to_numeric((char *)p, len, id)) + return -EINVAL; + + return 0; +} + +static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls) +{ + int i; + + if (fls->mirror_array) { + for (i = 0; i < fls->mirror_array_cnt; i++) { + /* normally mirror_ds is freed in + * .free_deviceid_node but we still do it here + * for .alloc_lseg error path */ + if (fls->mirror_array[i]) { + kfree(fls->mirror_array[i]->fh_versions); + nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds); + kfree(fls->mirror_array[i]); + } + } + kfree(fls->mirror_array); + fls->mirror_array = NULL; + } +} + +static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr) +{ + int ret = 0; + + dprintk("--> %s\n", __func__); + + /* FIXME: remove this check when layout segment support is added */ + if (lgr->range.offset != 0 || + lgr->range.length != NFS4_MAX_UINT64) { + dprintk("%s Only whole file layouts supported. Use MDS i/o\n", + __func__); + ret = -EINVAL; + } + + dprintk("--> %s returns %d\n", __func__, ret); + return ret; +} + +static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls) +{ + if (fls) { + ff_layout_free_mirror_array(fls); + kfree(fls); + } +} + +static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls) +{ + struct nfs4_ff_layout_mirror *tmp; + int i, j; + + for (i = 0; i < fls->mirror_array_cnt - 1; i++) { + for (j = i + 1; j < fls->mirror_array_cnt; j++) + if (fls->mirror_array[i]->efficiency < + fls->mirror_array[j]->efficiency) { + tmp = fls->mirror_array[i]; + fls->mirror_array[i] = fls->mirror_array[j]; + fls->mirror_array[j] = tmp; + } + } +} + +static struct pnfs_layout_segment * +ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, + struct nfs4_layoutget_res *lgr, + gfp_t gfp_flags) +{ + struct pnfs_layout_segment *ret; + struct nfs4_ff_layout_segment *fls = NULL; + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + u64 stripe_unit; + u32 mirror_array_cnt; + __be32 *p; + int i, rc; + + dprintk("--> %s\n", __func__); + scratch = alloc_page(gfp_flags); + if (!scratch) + return ERR_PTR(-ENOMEM); + + xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, + lgr->layoutp->len); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* stripe unit and mirror_array_cnt */ + rc = -EIO; + p = xdr_inline_decode(&stream, 8 + 4); + if (!p) + goto out_err_free; + + p = xdr_decode_hyper(p, &stripe_unit); + mirror_array_cnt = be32_to_cpup(p++); + dprintk("%s: stripe_unit=%llu mirror_array_cnt=%u\n", __func__, + stripe_unit, mirror_array_cnt); + + if (mirror_array_cnt > NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT || + mirror_array_cnt == 0) + goto out_err_free; + + rc = -ENOMEM; + fls = kzalloc(sizeof(*fls), gfp_flags); + if (!fls) + goto out_err_free; + + fls->mirror_array_cnt = mirror_array_cnt; + fls->stripe_unit = stripe_unit; + fls->mirror_array = kcalloc(fls->mirror_array_cnt, + sizeof(fls->mirror_array[0]), gfp_flags); + if (fls->mirror_array == NULL) + goto out_err_free; + + for (i = 0; i < fls->mirror_array_cnt; i++) { + struct nfs4_deviceid devid; + struct nfs4_deviceid_node *idnode; + u32 ds_count; + u32 fh_count; + int j; + + rc = -EIO; + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + ds_count = be32_to_cpup(p); + + /* FIXME: allow for striping? */ + if (ds_count != 1) + goto out_err_free; + + fls->mirror_array[i] = + kzalloc(sizeof(struct nfs4_ff_layout_mirror), + gfp_flags); + if (fls->mirror_array[i] == NULL) { + rc = -ENOMEM; + goto out_err_free; + } + + spin_lock_init(&fls->mirror_array[i]->lock); + fls->mirror_array[i]->ds_count = ds_count; + + /* deviceid */ + rc = decode_deviceid(&stream, &devid); + if (rc) + goto out_err_free; + + idnode = nfs4_find_get_deviceid(NFS_SERVER(lh->plh_inode), + &devid, lh->plh_lc_cred, + gfp_flags); + /* + * upon success, mirror_ds is allocated by previous + * getdeviceinfo, or newly by .alloc_deviceid_node + * nfs4_find_get_deviceid failure is indeed getdeviceinfo falure + */ + if (idnode) + fls->mirror_array[i]->mirror_ds = + FF_LAYOUT_MIRROR_DS(idnode); + else + goto out_err_free; + + /* efficiency */ + rc = -EIO; + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + fls->mirror_array[i]->efficiency = be32_to_cpup(p); + + /* stateid */ + rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid); + if (rc) + goto out_err_free; + + /* fh */ + p = xdr_inline_decode(&stream, 4); + if (!p) + goto out_err_free; + fh_count = be32_to_cpup(p); + + fls->mirror_array[i]->fh_versions = + kzalloc(fh_count * sizeof(struct nfs_fh), + gfp_flags); + if (fls->mirror_array[i]->fh_versions == NULL) { + rc = -ENOMEM; + goto out_err_free; + } + + for (j = 0; j < fh_count; j++) { + rc = decode_nfs_fh(&stream, + &fls->mirror_array[i]->fh_versions[j]); + if (rc) + goto out_err_free; + } + + fls->mirror_array[i]->fh_versions_cnt = fh_count; + + /* user */ + rc = decode_name(&stream, &fls->mirror_array[i]->uid); + if (rc) + goto out_err_free; + + /* group */ + rc = decode_name(&stream, &fls->mirror_array[i]->gid); + if (rc) + goto out_err_free; + + dprintk("%s: uid %d gid %d\n", __func__, + fls->mirror_array[i]->uid, + fls->mirror_array[i]->gid); + } + + ff_layout_sort_mirrors(fls); + rc = ff_layout_check_layout(lgr); + if (rc) + goto out_err_free; + + ret = &fls->generic_hdr; + dprintk("<-- %s (success)\n", __func__); +out_free_page: + __free_page(scratch); + return ret; +out_err_free: + _ff_layout_free_lseg(fls); + ret = ERR_PTR(rc); + dprintk("<-- %s (%d)\n", __func__, rc); + goto out_free_page; +} + +static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &layout->plh_segs, pls_list) + if (lseg->pls_range.iomode == IOMODE_RW) + return true; + + return false; +} + +static void +ff_layout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); + int i; + + dprintk("--> %s\n", __func__); + + for (i = 0; i < fls->mirror_array_cnt; i++) { + if (fls->mirror_array[i]) { + nfs4_ff_layout_put_deviceid(fls->mirror_array[i]->mirror_ds); + fls->mirror_array[i]->mirror_ds = NULL; + if (fls->mirror_array[i]->cred) { + put_rpccred(fls->mirror_array[i]->cred); + fls->mirror_array[i]->cred = NULL; + } + } + } + + if (lseg->pls_range.iomode == IOMODE_RW) { + struct nfs4_flexfile_layout *ffl; + struct inode *inode; + + ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout); + inode = ffl->generic_hdr.plh_inode; + spin_lock(&inode->i_lock); + if (!ff_layout_has_rw_segments(lseg->pls_layout)) { + ffl->commit_info.nbuckets = 0; + kfree(ffl->commit_info.buckets); + ffl->commit_info.buckets = NULL; + } + spin_unlock(&inode->i_lock); + } + _ff_layout_free_lseg(fls); +} + +/* Return 1 until we have multiple lsegs support */ +static int +ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls) +{ + return 1; +} + +static int +ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + gfp_t gfp_flags) +{ + struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); + struct pnfs_commit_bucket *buckets; + int size; + + if (cinfo->ds->nbuckets != 0) { + /* This assumes there is only one RW lseg per file. + * To support multiple lseg per file, we need to + * change struct pnfs_commit_bucket to allow dynamic + * increasing nbuckets. + */ + return 0; + } + + size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg); + + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), + gfp_flags); + if (!buckets) + return -ENOMEM; + else { + int i; + + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets != 0) + kfree(buckets); + else { + cinfo->ds->buckets = buckets; + cinfo->ds->nbuckets = size; + for (i = 0; i < size; i++) { + INIT_LIST_HEAD(&buckets[i].written); + INIT_LIST_HEAD(&buckets[i].committing); + /* mark direct verifier as unset */ + buckets[i].direct_verf.committed = + NFS_INVALID_STABLE_HOW; + } + } + spin_unlock(cinfo->lock); + return 0; + } +} + +static struct nfs4_pnfs_ds * +ff_layout_choose_best_ds_for_read(struct nfs_pageio_descriptor *pgio, + int *best_idx) +{ + struct nfs4_ff_layout_segment *fls; + struct nfs4_pnfs_ds *ds; + int idx; + + fls = FF_LAYOUT_LSEG(pgio->pg_lseg); + /* mirrors are sorted by efficiency */ + for (idx = 0; idx < fls->mirror_array_cnt; idx++) { + ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, idx, false); + if (ds) { + *best_idx = idx; + return ds; + } + } + + return NULL; +} + +static void +ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs_pgio_mirror *pgm; + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_pnfs_ds *ds; + int ds_idx; + + /* Use full layout for now */ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_READ, + GFP_KERNEL); + /* If no lseg, fall back to read through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + + ds = ff_layout_choose_best_ds_for_read(pgio, &ds_idx); + if (!ds) + goto out_mds; + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + + pgio->pg_mirror_idx = ds_idx; + + /* read always uses only one mirror - idx 0 for pgio layer */ + pgm = &pgio->pg_mirrors[0]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; + + return; +out_mds: + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_read_mds(pgio); +} + +static void +ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + struct nfs4_ff_layout_mirror *mirror; + struct nfs_pgio_mirror *pgm; + struct nfs_commit_info cinfo; + struct nfs4_pnfs_ds *ds; + int i; + int status; + + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + /* If no lseg, fall back to write through mds */ + if (pgio->pg_lseg == NULL) + goto out_mds; + + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); + if (status < 0) + goto out_mds; + + /* Use a direct mapping of ds_idx to pgio mirror_idx */ + if (WARN_ON_ONCE(pgio->pg_mirror_count != + FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))) + goto out_mds; + + for (i = 0; i < pgio->pg_mirror_count; i++) { + ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true); + if (!ds) + goto out_mds; + pgm = &pgio->pg_mirrors[i]; + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize; + } + + return; + +out_mds: + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_write_mds(pgio); +} + +static unsigned int +ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + if (!pgio->pg_lseg) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + 0, + NFS4_MAX_UINT64, + IOMODE_RW, + GFP_NOFS); + if (pgio->pg_lseg) + return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg); + + /* no lseg means that pnfs is not in use, so no mirroring here */ + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + nfs_pageio_reset_write_mds(pgio); + return 1; +} + +static const struct nfs_pageio_ops ff_layout_pg_read_ops = { + .pg_init = ff_layout_pg_init_read, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static const struct nfs_pageio_ops ff_layout_pg_write_ops = { + .pg_init = ff_layout_pg_init_write, + .pg_test = pnfs_generic_pg_test, + .pg_doio = pnfs_generic_pg_writepages, + .pg_get_mirror_count = ff_layout_pg_get_mirror_count_write, + .pg_cleanup = pnfs_generic_pg_cleanup, +}; + +static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) +{ + struct rpc_task *task = &hdr->task; + + pnfs_layoutcommit_inode(hdr->inode, false); + + if (retry_pnfs) { + dprintk("%s Reset task %5u for i/o through pNFS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + if (!hdr->dreq) { + struct nfs_open_context *ctx; + + ctx = nfs_list_entry(hdr->pages.next)->wb_context; + set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); + hdr->completion_ops->error_cleanup(&hdr->pages); + } else { + nfs_direct_set_resched_writes(hdr->dreq); + /* fake unstable write to let common nfs resend pages */ + hdr->verf.committed = NFS_UNSTABLE; + hdr->good_bytes = 0; + } + return; + } + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_write_done_resend_to_mds(hdr); + } +} + +static void ff_layout_reset_read(struct nfs_pgio_header *hdr) +{ + struct rpc_task *task = &hdr->task; + + pnfs_layoutcommit_inode(hdr->inode, false); + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%llu, %u bytes @ offset %llu)\n", __func__, + hdr->task.tk_pid, + hdr->inode->i_sb->s_id, + (unsigned long long)NFS_FILEID(hdr->inode), + hdr->args.count, + (unsigned long long)hdr->args.offset); + + task->tk_status = pnfs_read_done_resend_to_mds(hdr); + } +} + +static int ff_layout_async_handle_error_v4(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg, + int idx) +{ + struct pnfs_layout_hdr *lo = lseg->pls_layout; + struct inode *inode = lo->plh_inode; + struct nfs_server *mds_server = NFS_SERVER(inode); + + struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + struct nfs_client *mds_client = mds_server->nfs_client; + struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; + + if (task->tk_status >= 0) + return 0; + + switch (task->tk_status) { + /* MDS state errors */ + case -NFS4ERR_DELEG_REVOKED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_BAD_STATEID: + if (state == NULL) + break; + nfs_remove_bad_delegation(state->inode); + case -NFS4ERR_OPENMODE: + if (state == NULL) + break; + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + goto wait_on_recovery; + case -NFS4ERR_EXPIRED: + if (state != NULL) { + if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) + goto out_bad_stateid; + } + nfs4_schedule_lease_recovery(mds_client); + goto wait_on_recovery; + /* DS session errors */ + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_DEADSESSION: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + case -NFS4ERR_SEQ_FALSE_RETRY: + case -NFS4ERR_SEQ_MISORDERED: + dprintk("%s ERROR %d, Reset session. Exchangeid " + "flags 0x%x\n", __func__, task->tk_status, + clp->cl_exchange_flags); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + break; + case -NFS4ERR_DELAY: + case -NFS4ERR_GRACE: + rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX); + break; + case -NFS4ERR_RETRY_UNCACHED_REP: + break; + /* Invalidate Layout errors */ + case -NFS4ERR_PNFS_NO_LAYOUT: + case -ESTALE: /* mapped NFS4ERR_STALE */ + case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ + case -EISDIR: /* mapped NFS4ERR_ISDIR */ + case -NFS4ERR_FHEXPIRED: + case -NFS4ERR_WRONG_TYPE: + dprintk("%s Invalid layout error %d\n", __func__, + task->tk_status); + /* + * Destroy layout so new i/o will get a new layout. + * Layout will not be destroyed until all current lseg + * references are put. Mark layout as invalid to resend failed + * i/o and all i/o waiting on the slot table to the MDS until + * layout is destroyed and a new valid layout is obtained. + */ + pnfs_destroy_layout(NFS_I(inode)); + rpc_wake_up(&tbl->slot_tbl_waitq); + goto reset; + /* RPC connection errors */ + case -ECONNREFUSED: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EIO: + case -ETIMEDOUT: + case -EPIPE: + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + rpc_wake_up(&tbl->slot_tbl_waitq); + /* fall through */ + default: + if (ff_layout_has_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, + task->tk_status); + return -NFS4ERR_RESET_TO_MDS; + } +out: + task->tk_status = 0; + return -EAGAIN; +out_bad_stateid: + task->tk_status = -EIO; + return 0; +wait_on_recovery: + rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); + if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) + rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); + goto out; +} + +/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ +static int ff_layout_async_handle_error_v3(struct rpc_task *task, + struct pnfs_layout_segment *lseg, + int idx) +{ + struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); + + if (task->tk_status >= 0) + return 0; + + if (task->tk_status != -EJUKEBOX) { + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + nfs4_mark_deviceid_unavailable(devid); + if (ff_layout_has_available_ds(lseg)) + return -NFS4ERR_RESET_TO_PNFS; + else + return -NFS4ERR_RESET_TO_MDS; + } + + if (task->tk_status == -EJUKEBOX) + nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY); + task->tk_status = 0; + rpc_restart_call(task); + rpc_delay(task, NFS_JUKEBOX_RETRY_TIME); + return -EAGAIN; +} + +static int ff_layout_async_handle_error(struct rpc_task *task, + struct nfs4_state *state, + struct nfs_client *clp, + struct pnfs_layout_segment *lseg, + int idx) +{ + int vers = clp->cl_nfs_mod->rpc_vers->number; + + switch (vers) { + case 3: + return ff_layout_async_handle_error_v3(task, lseg, idx); + case 4: + return ff_layout_async_handle_error_v4(task, state, clp, + lseg, idx); + default: + /* should never happen */ + WARN_ON_ONCE(1); + return 0; + } +} + +static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, + int idx, u64 offset, u64 length, + u32 status, int opnum) +{ + struct nfs4_ff_layout_mirror *mirror; + int err; + + mirror = FF_LAYOUT_COMP(lseg, idx); + err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, offset, length, status, opnum, + GFP_NOIO); + dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status); +} + +/* NFS_PROTO call done callback routines */ + +static int ff_layout_read_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_read(hdr, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status) + hdr->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && hdr->res.op_status) + ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, + hdr->args.offset, hdr->args.count, + hdr->res.op_status, OP_READ); + err = ff_layout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg, + hdr->pgio_mirror_idx); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &hdr->lseg->pls_layout->plh_flags); + pnfs_read_resend_pnfs(hdr); + return task->tk_status; + case -NFS4ERR_RESET_TO_MDS: + inode = hdr->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, hdr->lseg); + ff_layout_reset_read(hdr); + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + return 0; +} + +/* + * We reference the rpc_cred of the first WRITE that triggers the need for + * a LAYOUTCOMMIT, and use it to send the layoutcommit compound. + * rfc5661 is not clear about which credential should be used. + * + * Flexlayout client should treat DS replied FILE_SYNC as DATA_SYNC, so + * to follow http://www.rfc-editor.org/errata_search.php?rfc=5661&eid=2751 + * we always send layoutcommit after DS writes. + */ +static void +ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr) +{ + pnfs_set_layoutcommit(hdr); + dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); +} + +static bool +ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) +{ + /* No mirroring for now */ + struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx); + + return ff_layout_test_devid_unavailable(node); +} + +static int ff_layout_read_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return -EIO; + } + if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + if (ff_layout_has_available_ds(hdr->lseg)) + pnfs_read_resend_pnfs(hdr); + else + ff_layout_reset_read(hdr); + rpc_exit(task, 0); + return -EAGAIN; + } + hdr->pgio_done_cb = ff_layout_read_done_cb; + + return 0; +} + +/* + * Call ops for the async read/write cases + * In the case of dense layouts, the offset needs to be reset to its + * original value. + */ +static void ff_layout_read_prepare_v3(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_read_prepare_common(task, hdr)) + return; + + rpc_call_start(task); +} + +static int ff_layout_setup_sequence(struct nfs_client *ds_clp, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) +{ + if (ds_clp->cl_session) + return nfs41_setup_sequence(ds_clp->cl_session, + args, + res, + task); + return nfs40_setup_sequence(ds_clp->cl_slot_tbl, + args, + res, + task); +} + +static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_read_prepare_common(task, hdr)) + return; + + if (ff_layout_setup_sequence(hdr->ds_clp, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_READ) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void ff_layout_read_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs4_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, hdr); +} + +static void ff_layout_read_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]); +} + +static int ff_layout_write_done_cb(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_write(hdr, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !hdr->res.op_status) + hdr->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && hdr->res.op_status) + ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx, + hdr->args.offset, hdr->args.count, + hdr->res.op_status, OP_WRITE); + err = ff_layout_async_handle_error(task, hdr->args.context->state, + hdr->ds_clp, hdr->lseg, + hdr->pgio_mirror_idx); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + case -NFS4ERR_RESET_TO_MDS: + inode = hdr->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, hdr->lseg); + if (err == -NFS4ERR_RESET_TO_PNFS) { + pnfs_set_retry_layoutget(hdr->lseg->pls_layout); + ff_layout_reset_write(hdr, true); + } else { + pnfs_clear_retry_layoutget(hdr->lseg->pls_layout); + ff_layout_reset_write(hdr, false); + } + return task->tk_status; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (hdr->res.verf->committed == NFS_FILE_SYNC || + hdr->res.verf->committed == NFS_DATA_SYNC) + ff_layout_set_layoutcommit(hdr); + + return 0; +} + +static int ff_layout_commit_done_cb(struct rpc_task *task, + struct nfs_commit_data *data) +{ + struct inode *inode; + int err; + + trace_nfs4_pnfs_commit_ds(data, task->tk_status); + if (task->tk_status == -ETIMEDOUT && !data->res.op_status) + data->res.op_status = NFS4ERR_NXIO; + if (task->tk_status < 0 && data->res.op_status) + ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index, + data->args.offset, data->args.count, + data->res.op_status, OP_COMMIT); + err = ff_layout_async_handle_error(task, NULL, data->ds_clp, + data->lseg, data->ds_commit_index); + + switch (err) { + case -NFS4ERR_RESET_TO_PNFS: + case -NFS4ERR_RESET_TO_MDS: + inode = data->lseg->pls_layout->plh_inode; + pnfs_error_mark_layout_for_return(inode, data->lseg); + if (err == -NFS4ERR_RESET_TO_PNFS) + pnfs_set_retry_layoutget(data->lseg->pls_layout); + else + pnfs_clear_retry_layoutget(data->lseg->pls_layout); + pnfs_generic_prepare_to_resend_writes(data); + return -EAGAIN; + case -EAGAIN: + rpc_restart_call_prepare(task); + return -EAGAIN; + } + + if (data->verf.committed == NFS_UNSTABLE) + pnfs_commit_set_layoutcommit(data); + + return 0; +} + +static int ff_layout_write_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { + rpc_exit(task, -EIO); + return -EIO; + } + + if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) { + bool retry_pnfs; + + retry_pnfs = ff_layout_has_available_ds(hdr->lseg); + dprintk("%s task %u reset io to %s\n", __func__, + task->tk_pid, retry_pnfs ? "pNFS" : "MDS"); + ff_layout_reset_write(hdr, retry_pnfs); + rpc_exit(task, 0); + return -EAGAIN; + } + + return 0; +} + +static void ff_layout_write_prepare_v3(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_write_prepare_common(task, hdr)) + return; + + rpc_call_start(task); +} + +static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (ff_layout_write_prepare_common(task, hdr)) + return; + + if (ff_layout_setup_sequence(hdr->ds_clp, + &hdr->args.seq_args, + &hdr->res.seq_res, + task)) + return; + + if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, + hdr->args.lock_context, FMODE_WRITE) == -EIO) + rpc_exit(task, -EIO); /* lost lock, terminate I/O */ +} + +static void ff_layout_write_call_done(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && + task->tk_status == 0) { + nfs4_sequence_done(task, &hdr->res.seq_res); + return; + } + + /* Note this may cause RPC to be resent */ + hdr->mds_ops->rpc_call_done(task, hdr); +} + +static void ff_layout_write_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_pgio_header *hdr = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]); +} + +static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) +{ + rpc_call_start(task); +} + +static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + ff_layout_setup_sequence(wdata->ds_clp, + &wdata->args.seq_args, + &wdata->res.seq_res, + task); +} + +static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *cdata = data; + + rpc_count_iostats_metrics(task, + &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]); +} + +static const struct rpc_call_ops ff_layout_read_call_ops_v3 = { + .rpc_call_prepare = ff_layout_read_prepare_v3, + .rpc_call_done = ff_layout_read_call_done, + .rpc_count_stats = ff_layout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_read_call_ops_v4 = { + .rpc_call_prepare = ff_layout_read_prepare_v4, + .rpc_call_done = ff_layout_read_call_done, + .rpc_count_stats = ff_layout_read_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_write_call_ops_v3 = { + .rpc_call_prepare = ff_layout_write_prepare_v3, + .rpc_call_done = ff_layout_write_call_done, + .rpc_count_stats = ff_layout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_write_call_ops_v4 = { + .rpc_call_prepare = ff_layout_write_prepare_v4, + .rpc_call_done = ff_layout_write_call_done, + .rpc_count_stats = ff_layout_write_count_stats, + .rpc_release = pnfs_generic_rw_release, +}; + +static const struct rpc_call_ops ff_layout_commit_call_ops_v3 = { + .rpc_call_prepare = ff_layout_commit_prepare_v3, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = ff_layout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static const struct rpc_call_ops ff_layout_commit_call_ops_v4 = { + .rpc_call_prepare = ff_layout_commit_prepare_v4, + .rpc_call_done = pnfs_generic_write_commit_done, + .rpc_count_stats = ff_layout_commit_count_stats, + .rpc_release = pnfs_generic_commit_release, +}; + +static enum pnfs_try_status +ff_layout_read_pagelist(struct nfs_pgio_header *hdr) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + loff_t offset = hdr->args.offset; + u32 idx = hdr->pgio_mirror_idx; + int vers; + struct nfs_fh *fh; + + dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", + __func__, hdr->inode->i_ino, + hdr->args.pgbase, (size_t)hdr->args.count, offset); + + ds = nfs4_ff_layout_prepare_ds(lseg, idx, false); + if (!ds) + goto out_failed; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + hdr->inode); + if (IS_ERR(ds_clnt)) + goto out_failed; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred); + if (IS_ERR(ds_cred)) + goto out_failed; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__, + ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers); + + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + fh = nfs4_ff_layout_select_ds_fh(lseg, idx); + if (fh) + hdr->args.fh = fh; + + /* + * Note that if we ever decide to split across DSes, + * then we may need to handle dense-like offsets. + */ + hdr->args.offset = offset; + hdr->mds_offset = offset; + + /* Perform an asynchronous read to ds */ + nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_read_call_ops_v3 : + &ff_layout_read_call_ops_v4, + 0, RPC_TASK_SOFTCONN); + + return PNFS_ATTEMPTED; + +out_failed: + if (ff_layout_has_available_ds(lseg)) + return PNFS_TRY_AGAIN; + return PNFS_NOT_ATTEMPTED; +} + +/* Perform async writes. */ +static enum pnfs_try_status +ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) +{ + struct pnfs_layout_segment *lseg = hdr->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + loff_t offset = hdr->args.offset; + int vers; + struct nfs_fh *fh; + int idx = hdr->pgio_mirror_idx; + + ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); + if (!ds) + return PNFS_NOT_ATTEMPTED; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + hdr->inode); + if (IS_ERR(ds_clnt)) + return PNFS_NOT_ATTEMPTED; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred); + if (IS_ERR(ds_cred)) + return PNFS_NOT_ATTEMPTED; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n", + __func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count, + offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), + vers); + + hdr->pgio_done_cb = ff_layout_write_done_cb; + atomic_inc(&ds->ds_clp->cl_count); + hdr->ds_clp = ds->ds_clp; + hdr->ds_commit_idx = idx; + fh = nfs4_ff_layout_select_ds_fh(lseg, idx); + if (fh) + hdr->args.fh = fh; + + /* + * Note that if we ever decide to split across DSes, + * then we may need to handle dense-like offsets. + */ + hdr->args.offset = offset; + + /* Perform an asynchronous write */ + nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_write_call_ops_v3 : + &ff_layout_write_call_ops_v4, + sync, RPC_TASK_SOFTCONN); + return PNFS_ATTEMPTED; +} + +static void +ff_layout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) +{ + struct list_head *list; + struct pnfs_commit_bucket *buckets; + + spin_lock(cinfo->lock); + buckets = cinfo->ds->buckets; + list = &buckets[ds_commit_idx].written; + if (list_empty(list)) { + /* Non-empty buckets hold a reference on the lseg. That ref + * is normally transferred to the COMMIT call and released + * there. It could also be released if the last req is pulled + * off due to a rewrite, in which case it will be done in + * pnfs_common_clear_request_commit + */ + WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL); + buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg); + } + set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; + + /* nfs_request_add_commit_list(). We need to add req to list without + * dropping cinfo lock. + */ + set_bit(PG_CLEAN, &(req)->wb_flags); + nfs_list_add_request(req, list); + cinfo->mds->ncommit++; + spin_unlock(cinfo->lock); + if (!cinfo->dreq) { + inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); + inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, + BDI_RECLAIMABLE); + __mark_inode_dirty(req->wb_context->dentry->d_inode, + I_DIRTY_DATASYNC); + } +} + +static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + return i; +} + +static struct nfs_fh * +select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i) +{ + struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg); + + /* FIXME: Assume that there is only one NFS version available + * for the DS. + */ + return &flseg->mirror_array[i]->fh_versions[0]; +} + +static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) +{ + struct pnfs_layout_segment *lseg = data->lseg; + struct nfs4_pnfs_ds *ds; + struct rpc_clnt *ds_clnt; + struct rpc_cred *ds_cred; + u32 idx; + int vers; + struct nfs_fh *fh; + + idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); + ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); + if (!ds) + goto out_err; + + ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp, + data->inode); + if (IS_ERR(ds_clnt)) + goto out_err; + + ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred); + if (IS_ERR(ds_cred)) + goto out_err; + + vers = nfs4_ff_layout_ds_version(lseg, idx); + + dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__, + data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count), + vers); + data->commit_done_cb = ff_layout_commit_done_cb; + data->cred = ds_cred; + atomic_inc(&ds->ds_clp->cl_count); + data->ds_clp = ds->ds_clp; + fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); + if (fh) + data->args.fh = fh; + return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops, + vers == 3 ? &ff_layout_commit_call_ops_v3 : + &ff_layout_commit_call_ops_v4, + how, RPC_TASK_SOFTCONN); +out_err: + pnfs_generic_prepare_to_resend_writes(data); + pnfs_generic_commit_release(data); + return -EAGAIN; +} + +static int +ff_layout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how, struct nfs_commit_info *cinfo) +{ + return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo, + ff_layout_initiate_commit); +} + +static struct pnfs_ds_commit_info * +ff_layout_get_ds_info(struct inode *inode) +{ + struct pnfs_layout_hdr *layout = NFS_I(inode)->layout; + + if (layout == NULL) + return NULL; + + return &FF_LAYOUT_FROM_HDR(layout)->commit_info; +} + +static void +ff_layout_free_deveiceid_node(struct nfs4_deviceid_node *d) +{ + nfs4_ff_layout_free_deviceid(container_of(d, struct nfs4_ff_layout_ds, + id_node)); +} + +static int ff_layout_encode_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct pnfs_layout_hdr *hdr = &flo->generic_hdr; + __be32 *start; + int count = 0, ret = 0; + + start = xdr_reserve_space(xdr, 4); + if (unlikely(!start)) + return -E2BIG; + + /* This assume we always return _ALL_ layouts */ + spin_lock(&hdr->plh_inode->i_lock); + ret = ff_layout_encode_ds_ioerr(flo, xdr, &count, &args->range); + spin_unlock(&hdr->plh_inode->i_lock); + + *start = cpu_to_be32(count); + + return ret; +} + +/* report nothing for now */ +static void ff_layout_encode_iostats(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4); + if (likely(p)) + *p = cpu_to_be32(0); +} + +static struct nfs4_deviceid_node * +ff_layout_alloc_deviceid_node(struct nfs_server *server, + struct pnfs_device *pdev, gfp_t gfp_flags) +{ + struct nfs4_ff_layout_ds *dsaddr; + + dsaddr = nfs4_ff_alloc_deviceid_node(server, pdev, gfp_flags); + if (!dsaddr) + return NULL; + return &dsaddr->id_node; +} + +static void +ff_layout_encode_layoutreturn(struct pnfs_layout_hdr *lo, + struct xdr_stream *xdr, + const struct nfs4_layoutreturn_args *args) +{ + struct nfs4_flexfile_layout *flo = FF_LAYOUT_FROM_HDR(lo); + __be32 *start; + + dprintk("%s: Begin\n", __func__); + start = xdr_reserve_space(xdr, 4); + BUG_ON(!start); + + if (ff_layout_encode_ioerr(flo, xdr, args)) + goto out; + + ff_layout_encode_iostats(flo, xdr, args); +out: + *start = cpu_to_be32((xdr->p - start - 1) * 4); + dprintk("%s: Return\n", __func__); +} + +static struct pnfs_layoutdriver_type flexfilelayout_type = { + .id = LAYOUT_FLEX_FILES, + .name = "LAYOUT_FLEX_FILES", + .owner = THIS_MODULE, + .alloc_layout_hdr = ff_layout_alloc_layout_hdr, + .free_layout_hdr = ff_layout_free_layout_hdr, + .alloc_lseg = ff_layout_alloc_lseg, + .free_lseg = ff_layout_free_lseg, + .pg_read_ops = &ff_layout_pg_read_ops, + .pg_write_ops = &ff_layout_pg_write_ops, + .get_ds_info = ff_layout_get_ds_info, + .free_deviceid_node = ff_layout_free_deveiceid_node, + .mark_request_commit = ff_layout_mark_request_commit, + .clear_request_commit = pnfs_generic_clear_request_commit, + .scan_commit_lists = pnfs_generic_scan_commit_lists, + .recover_commit_reqs = pnfs_generic_recover_commit_reqs, + .commit_pagelist = ff_layout_commit_pagelist, + .read_pagelist = ff_layout_read_pagelist, + .write_pagelist = ff_layout_write_pagelist, + .alloc_deviceid_node = ff_layout_alloc_deviceid_node, + .encode_layoutreturn = ff_layout_encode_layoutreturn, +}; + +static int __init nfs4flexfilelayout_init(void) +{ + printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n", + __func__); + return pnfs_register_layoutdriver(&flexfilelayout_type); +} + +static void __exit nfs4flexfilelayout_exit(void) +{ + printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n", + __func__); + pnfs_unregister_layoutdriver(&flexfilelayout_type); +} + +MODULE_ALIAS("nfs-layouttype4-4"); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("The NFSv4 flexfile layout driver"); + +module_init(nfs4flexfilelayout_init); +module_exit(nfs4flexfilelayout_exit); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h new file mode 100644 index 000000000000..070f20445b2d --- /dev/null +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -0,0 +1,155 @@ +/* + * NFSv4 flexfile layout driver data structures. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ + +#ifndef FS_NFS_NFS4FLEXFILELAYOUT_H +#define FS_NFS_NFS4FLEXFILELAYOUT_H + +#include "../pnfs.h" + +/* XXX: Let's filter out insanely large mirror count for now to avoid oom + * due to network error etc. */ +#define NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT 4096 + +struct nfs4_ff_ds_version { + u32 version; + u32 minor_version; + u32 rsize; + u32 wsize; + bool tightly_coupled; +}; + +/* chained in global deviceid hlist */ +struct nfs4_ff_layout_ds { + struct nfs4_deviceid_node id_node; + u32 ds_versions_cnt; + struct nfs4_ff_ds_version *ds_versions; + struct nfs4_pnfs_ds *ds; +}; + +struct nfs4_ff_layout_ds_err { + struct list_head list; /* linked in mirror error_list */ + u64 offset; + u64 length; + int status; + enum nfs_opnum4 opnum; + nfs4_stateid stateid; + struct nfs4_deviceid deviceid; +}; + +struct nfs4_ff_layout_mirror { + u32 ds_count; + u32 efficiency; + struct nfs4_ff_layout_ds *mirror_ds; + u32 fh_versions_cnt; + struct nfs_fh *fh_versions; + nfs4_stateid stateid; + struct nfs4_string user_name; + struct nfs4_string group_name; + u32 uid; + u32 gid; + struct rpc_cred *cred; + spinlock_t lock; +}; + +struct nfs4_ff_layout_segment { + struct pnfs_layout_segment generic_hdr; + u64 stripe_unit; + u32 mirror_array_cnt; + struct nfs4_ff_layout_mirror **mirror_array; +}; + +struct nfs4_flexfile_layout { + struct pnfs_layout_hdr generic_hdr; + struct pnfs_ds_commit_info commit_info; + struct list_head error_list; /* nfs4_ff_layout_ds_err */ +}; + +static inline struct nfs4_flexfile_layout * +FF_LAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct nfs4_flexfile_layout, generic_hdr); +} + +static inline struct nfs4_ff_layout_segment * +FF_LAYOUT_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, + struct nfs4_ff_layout_segment, + generic_hdr); +} + +static inline struct nfs4_deviceid_node * +FF_LAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg, u32 idx) +{ + if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt || + FF_LAYOUT_LSEG(lseg)->mirror_array[idx] == NULL || + FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds == NULL) + return NULL; + return &FF_LAYOUT_LSEG(lseg)->mirror_array[idx]->mirror_ds->id_node; +} + +static inline struct nfs4_ff_layout_ds * +FF_LAYOUT_MIRROR_DS(struct nfs4_deviceid_node *node) +{ + return container_of(node, struct nfs4_ff_layout_ds, id_node); +} + +static inline struct nfs4_ff_layout_mirror * +FF_LAYOUT_COMP(struct pnfs_layout_segment *lseg, u32 idx) +{ + if (idx >= FF_LAYOUT_LSEG(lseg)->mirror_array_cnt) + return NULL; + return FF_LAYOUT_LSEG(lseg)->mirror_array[idx]; +} + +static inline u32 +FF_LAYOUT_MIRROR_COUNT(struct pnfs_layout_segment *lseg) +{ + return FF_LAYOUT_LSEG(lseg)->mirror_array_cnt; +} + +static inline bool +ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node) +{ + return nfs4_test_deviceid_unavailable(node); +} + +static inline int +nfs4_ff_layout_ds_version(struct pnfs_layout_segment *lseg, u32 ds_idx) +{ + return FF_LAYOUT_COMP(lseg, ds_idx)->mirror_ds->ds_versions[0].version; +} + +struct nfs4_ff_layout_ds * +nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags); +void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds); +void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds); +int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_mirror *mirror, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + gfp_t gfp_flags); +int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, int *count, + const struct pnfs_layout_range *range); +struct nfs_fh * +nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx); + +struct nfs4_pnfs_ds * +nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, + bool fail_return); + +struct rpc_clnt * +nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, + u32 ds_idx, + struct nfs_client *ds_clp, + struct inode *inode); +struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, + u32 ds_idx, struct rpc_cred *mdscred); +bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg); +#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */ diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c new file mode 100644 index 000000000000..3bbb16b3066f --- /dev/null +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -0,0 +1,552 @@ +/* + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tao Peng + */ + +#include +#include +#include +#include + +#include "../internal.h" +#include "../nfs4session.h" +#include "flexfilelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; +static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; + +void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds) +{ + if (mirror_ds) + nfs4_put_deviceid_node(&mirror_ds->id_node); +} + +void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) +{ + nfs4_print_deviceid(&mirror_ds->id_node.deviceid); + nfs4_pnfs_ds_put(mirror_ds->ds); + kfree(mirror_ds); +} + +/* Decode opaque device data and construct new_ds using it */ +struct nfs4_ff_layout_ds * +nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, + gfp_t gfp_flags) +{ + struct xdr_stream stream; + struct xdr_buf buf; + struct page *scratch; + struct list_head dsaddrs; + struct nfs4_pnfs_ds_addr *da; + struct nfs4_ff_layout_ds *new_ds = NULL; + struct nfs4_ff_ds_version *ds_versions = NULL; + u32 mp_count; + u32 version_count; + __be32 *p; + int i, ret = -ENOMEM; + + /* set up xdr stream */ + scratch = alloc_page(gfp_flags); + if (!scratch) + goto out_err; + + new_ds = kzalloc(sizeof(struct nfs4_ff_layout_ds), gfp_flags); + if (!new_ds) + goto out_scratch; + + nfs4_init_deviceid_node(&new_ds->id_node, + server, + &pdev->dev_id); + INIT_LIST_HEAD(&dsaddrs); + + xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen); + xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); + + /* multipath count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + mp_count = be32_to_cpup(p); + dprintk("%s: multipath ds count %d\n", __func__, mp_count); + + for (i = 0; i < mp_count; i++) { + /* multipath ds */ + da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, + &stream, gfp_flags); + if (da) + list_add_tail(&da->da_node, &dsaddrs); + } + if (list_empty(&dsaddrs)) { + dprintk("%s: no suitable DS addresses found\n", + __func__); + ret = -ENOMEDIUM; + goto out_err_drain_dsaddrs; + } + + /* version count */ + p = xdr_inline_decode(&stream, 4); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + version_count = be32_to_cpup(p); + dprintk("%s: version count %d\n", __func__, version_count); + + ds_versions = kzalloc(version_count * sizeof(struct nfs4_ff_ds_version), + gfp_flags); + if (!ds_versions) + goto out_scratch; + + for (i = 0; i < version_count; i++) { + /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + + * tightly_coupled(4) */ + p = xdr_inline_decode(&stream, 20); + if (unlikely(!p)) + goto out_err_drain_dsaddrs; + ds_versions[i].version = be32_to_cpup(p++); + ds_versions[i].minor_version = be32_to_cpup(p++); + ds_versions[i].rsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].wsize = nfs_block_size(be32_to_cpup(p++), NULL); + ds_versions[i].tightly_coupled = be32_to_cpup(p); + + if (ds_versions[i].rsize > NFS_MAX_FILE_IO_SIZE) + ds_versions[i].rsize = NFS_MAX_FILE_IO_SIZE; + if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE) + ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE; + + if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) { + dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__, + i, ds_versions[i].version, + ds_versions[i].minor_version); + ret = -EPROTONOSUPPORT; + goto out_err_drain_dsaddrs; + } + + dprintk("%s: [%d] vers %u minor_ver %u rsize %u wsize %u coupled %d\n", + __func__, i, ds_versions[i].version, + ds_versions[i].minor_version, + ds_versions[i].rsize, + ds_versions[i].wsize, + ds_versions[i].tightly_coupled); + } + + new_ds->ds_versions = ds_versions; + new_ds->ds_versions_cnt = version_count; + + new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + if (!new_ds->ds) + goto out_err_drain_dsaddrs; + + /* If DS was already in cache, free ds addrs */ + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, + struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + __free_page(scratch); + return new_ds; + +out_err_drain_dsaddrs: + while (!list_empty(&dsaddrs)) { + da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + kfree(ds_versions); +out_scratch: + __free_page(scratch); +out_err: + kfree(new_ds); + + dprintk("%s ERROR: returning %d\n", __func__, ret); + return NULL; +} + +static u64 +end_offset(u64 start, u64 len) +{ + u64 end; + + end = start + len; + return end >= start ? end : NFS4_MAX_UINT64; +} + +static void extend_ds_error(struct nfs4_ff_layout_ds_err *err, + u64 offset, u64 length) +{ + u64 end; + + end = max_t(u64, end_offset(err->offset, err->length), + end_offset(offset, length)); + err->offset = min_t(u64, err->offset, offset); + err->length = end - err->offset; +} + +static bool ds_error_can_merge(struct nfs4_ff_layout_ds_err *err, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + nfs4_stateid *stateid, + struct nfs4_deviceid *deviceid) +{ + return err->status == status && err->opnum == opnum && + nfs4_stateid_match(&err->stateid, stateid) && + !memcmp(&err->deviceid, deviceid, sizeof(*deviceid)) && + end_offset(err->offset, err->length) >= offset && + err->offset <= end_offset(offset, length); +} + +static bool merge_ds_error(struct nfs4_ff_layout_ds_err *old, + struct nfs4_ff_layout_ds_err *new) +{ + if (!ds_error_can_merge(old, new->offset, new->length, new->status, + new->opnum, &new->stateid, &new->deviceid)) + return false; + + extend_ds_error(old, new->offset, new->length); + return true; +} + +static bool +ff_layout_add_ds_error_locked(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_ds_err *dserr) +{ + struct nfs4_ff_layout_ds_err *err; + + list_for_each_entry(err, &flo->error_list, list) { + if (merge_ds_error(err, dserr)) { + return true; + } + } + + list_add(&dserr->list, &flo->error_list); + return false; +} + +static bool +ff_layout_update_ds_error(struct nfs4_flexfile_layout *flo, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + nfs4_stateid *stateid, struct nfs4_deviceid *deviceid) +{ + bool found = false; + struct nfs4_ff_layout_ds_err *err; + + list_for_each_entry(err, &flo->error_list, list) { + if (ds_error_can_merge(err, offset, length, status, opnum, + stateid, deviceid)) { + found = true; + extend_ds_error(err, offset, length); + break; + } + } + + return found; +} + +int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, + struct nfs4_ff_layout_mirror *mirror, u64 offset, + u64 length, int status, enum nfs_opnum4 opnum, + gfp_t gfp_flags) +{ + struct nfs4_ff_layout_ds_err *dserr; + bool needfree; + + if (status == 0) + return 0; + + if (mirror->mirror_ds == NULL) + return -EINVAL; + + spin_lock(&flo->generic_hdr.plh_inode->i_lock); + if (ff_layout_update_ds_error(flo, offset, length, status, opnum, + &mirror->stateid, + &mirror->mirror_ds->id_node.deviceid)) { + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + return 0; + } + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + dserr = kmalloc(sizeof(*dserr), gfp_flags); + if (!dserr) + return -ENOMEM; + + INIT_LIST_HEAD(&dserr->list); + dserr->offset = offset; + dserr->length = length; + dserr->status = status; + dserr->opnum = opnum; + nfs4_stateid_copy(&dserr->stateid, &mirror->stateid); + memcpy(&dserr->deviceid, &mirror->mirror_ds->id_node.deviceid, + NFS4_DEVICEID4_SIZE); + + spin_lock(&flo->generic_hdr.plh_inode->i_lock); + needfree = ff_layout_add_ds_error_locked(flo, dserr); + spin_unlock(&flo->generic_hdr.plh_inode->i_lock); + if (needfree) + kfree(dserr); + + return 0; +} + +/* currently we only support AUTH_NONE and AUTH_SYS */ +static rpc_authflavor_t +nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror) +{ + if (mirror->uid == (u32)-1) + return RPC_AUTH_NULL; + return RPC_AUTH_UNIX; +} + +/* fetch cred for NFSv3 DS */ +static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror, + struct nfs4_pnfs_ds *ds) +{ + if (ds->ds_clp && !mirror->cred && + mirror->mirror_ds->ds_versions[0].version == 3) { + struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth; + struct rpc_cred *cred; + struct auth_cred acred = { + .uid = make_kuid(&init_user_ns, mirror->uid), + .gid = make_kgid(&init_user_ns, mirror->gid), + }; + + /* AUTH_NULL ignores acred */ + cred = auth->au_ops->lookup_cred(auth, &acred, 0); + if (IS_ERR(cred)) { + dprintk("%s: lookup_cred failed with %ld\n", + __func__, PTR_ERR(cred)); + return PTR_ERR(cred); + } else { + mirror->cred = cred; + } + } + return 0; +} + +struct nfs_fh * +nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx); + struct nfs_fh *fh = NULL; + struct nfs4_deviceid_node *devid; + + if (mirror == NULL || mirror->mirror_ds == NULL || + mirror->mirror_ds->ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for mirror offset index %d\n", + __func__, mirror_idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + pnfs_generic_mark_devid_invalid(devid); + } + goto out; + } + + /* FIXME: For now assume there is only 1 version available for the DS */ + fh = &mirror->fh_versions[0]; +out: + return fh; +} + +/* Upon return, either ds is connected, or ds is NULL */ +struct nfs4_pnfs_ds * +nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, + bool fail_return) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + struct nfs4_pnfs_ds *ds = NULL; + struct nfs4_deviceid_node *devid; + struct inode *ino = lseg->pls_layout->plh_inode; + struct nfs_server *s = NFS_SERVER(ino); + unsigned int max_payload; + rpc_authflavor_t flavor; + + if (mirror == NULL || mirror->mirror_ds == NULL || + mirror->mirror_ds->ds == NULL) { + printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", + __func__, ds_idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + pnfs_generic_mark_devid_invalid(devid); + } + goto out; + } + + devid = &mirror->mirror_ds->id_node; + if (ff_layout_test_devid_unavailable(devid)) + goto out; + + ds = mirror->mirror_ds->ds; + /* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */ + smp_rmb(); + if (ds->ds_clp) + goto out; + + flavor = nfs4_ff_layout_choose_authflavor(mirror); + + /* FIXME: For now we assume the server sent only one version of NFS + * to use for the DS. + */ + nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + dataserver_retrans, + mirror->mirror_ds->ds_versions[0].version, + mirror->mirror_ds->ds_versions[0].minor_version, + flavor); + + /* connect success, check rsize/wsize limit */ + if (ds->ds_clp) { + max_payload = + nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient), + NULL); + if (mirror->mirror_ds->ds_versions[0].rsize > max_payload) + mirror->mirror_ds->ds_versions[0].rsize = max_payload; + if (mirror->mirror_ds->ds_versions[0].wsize > max_payload) + mirror->mirror_ds->ds_versions[0].wsize = max_payload; + } else { + ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), + mirror, lseg->pls_range.offset, + lseg->pls_range.length, NFS4ERR_NXIO, + OP_ILLEGAL, GFP_NOIO); + if (fail_return) { + pnfs_error_mark_layout_for_return(ino, lseg); + if (ff_layout_has_available_ds(lseg)) + pnfs_set_retry_layoutget(lseg->pls_layout); + else + pnfs_clear_retry_layoutget(lseg->pls_layout); + + } else { + if (ff_layout_has_available_ds(lseg)) + set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lseg->pls_layout->plh_flags); + else { + pnfs_error_mark_layout_for_return(ino, lseg); + pnfs_clear_retry_layoutget(lseg->pls_layout); + } + } + } + + if (ff_layout_update_mirror_cred(mirror, ds)) + ds = NULL; +out: + return ds; +} + +struct rpc_cred * +ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct rpc_cred *mdscred) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + struct rpc_cred *cred = ERR_PTR(-EINVAL); + + if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true)) + goto out; + + if (mirror && mirror->cred) + cred = mirror->cred; + else + cred = mdscred; +out: + return cred; +} + +/** +* Find or create a DS rpc client with th MDS server rpc client auth flavor +* in the nfs_client cl_ds_clients list. +*/ +struct rpc_clnt * +nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx, + struct nfs_client *ds_clp, struct inode *inode) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); + + switch (mirror->mirror_ds->ds_versions[0].version) { + case 3: + /* For NFSv3 DS, flavor is set when creating DS connections */ + return ds_clp->cl_rpcclient; + case 4: + return nfs4_find_or_create_ds_client(ds_clp, inode); + default: + BUG(); + } +} + +static bool is_range_intersecting(u64 offset1, u64 length1, + u64 offset2, u64 length2) +{ + u64 end1 = end_offset(offset1, length1); + u64 end2 = end_offset(offset2, length2); + + return (end1 == NFS4_MAX_UINT64 || end1 > offset2) && + (end2 == NFS4_MAX_UINT64 || end2 > offset1); +} + +/* called with inode i_lock held */ +int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, + struct xdr_stream *xdr, int *count, + const struct pnfs_layout_range *range) +{ + struct nfs4_ff_layout_ds_err *err, *n; + __be32 *p; + + list_for_each_entry_safe(err, n, &flo->error_list, list) { + if (!is_range_intersecting(err->offset, err->length, + range->offset, range->length)) + continue; + /* offset(8) + length(8) + stateid(NFS4_STATEID_SIZE) + * + deviceid(NFS4_DEVICEID4_SIZE) + status(4) + opnum(4) + */ + p = xdr_reserve_space(xdr, + 24 + NFS4_STATEID_SIZE + NFS4_DEVICEID4_SIZE); + if (unlikely(!p)) + return -ENOBUFS; + p = xdr_encode_hyper(p, err->offset); + p = xdr_encode_hyper(p, err->length); + p = xdr_encode_opaque_fixed(p, &err->stateid, + NFS4_STATEID_SIZE); + p = xdr_encode_opaque_fixed(p, &err->deviceid, + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(err->status); + *p++ = cpu_to_be32(err->opnum); + *count += 1; + list_del(&err->list); + kfree(err); + dprintk("%s: offset %llu length %llu status %d op %d count %d\n", + __func__, err->offset, err->length, err->status, + err->opnum, *count); + } + + return 0; +} + +bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg) +{ + struct nfs4_ff_layout_mirror *mirror; + struct nfs4_deviceid_node *devid; + int idx; + + for (idx = 0; idx < FF_LAYOUT_MIRROR_COUNT(lseg); idx++) { + mirror = FF_LAYOUT_COMP(lseg, idx); + if (mirror && mirror->mirror_ds) { + devid = &mirror->mirror_ds->id_node; + if (!ff_layout_test_devid_unavailable(devid)) + return true; + } + } + + return false; +} + +module_param(dataserver_retrans, uint, 0644); +MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client " + "retries a request before it attempts further " + " recovery action."); +module_param(dataserver_timeo, uint, 0644); +MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the " + "NFSv4.1 client waits for a response from a " + " data server before it retries an NFS request."); diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 2f5db844c172..857e2a99acc8 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -152,7 +152,7 @@ void nfs_fattr_map_and_free_names(struct nfs_server *server, struct nfs_fattr *f nfs_fattr_free_group_name(fattr); } -static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res) +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res) { unsigned long val; char buf[16]; @@ -166,6 +166,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re *res = val; return 1; } +EXPORT_SYMBOL_GPL(nfs_map_string_to_numeric); static int nfs_map_numeric_to_string(__u32 id, char *buf, size_t buflen) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 44c600aac907..ca6dda0f68bb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7796,9 +7796,7 @@ static void nfs4_layoutreturn_release(void *calldata) spin_lock(&lo->plh_inode->i_lock); if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); - smp_mb__after_atomic(); - wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); + pnfs_clear_layoutreturn_waitbit(lo); clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); lo->plh_block_lgets--; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c4c9fe606ae6..0fb0f1920a1f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -910,7 +910,9 @@ send_layoutget(struct pnfs_layout_hdr *lo, pnfs_layout_io_set_failed(lo, range->iomode); } return NULL; - } + } else + pnfs_layout_clear_fail_bit(lo, + pnfs_iomode_to_fail_bit(range->iomode)); return lseg; } @@ -930,6 +932,13 @@ static void pnfs_clear_layoutcommit(struct inode *inode, } } +void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) +{ + clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); + smp_mb__after_atomic(); + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); +} + static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, enum pnfs_iomode iomode, bool sync) @@ -943,6 +952,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, status = -ENOMEM; spin_lock(&ino->i_lock); lo->plh_block_lgets--; + pnfs_clear_layoutreturn_waitbit(lo); rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq); spin_unlock(&ino->i_lock); pnfs_put_layout_hdr(lo); @@ -1418,6 +1428,15 @@ static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) TASK_UNINTERRUPTIBLE); } +static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo) +{ + unsigned long *bitlock = &lo->plh_flags; + + clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock); + smp_mb__after_atomic(); + wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET); +} + /* * Layout segment is retreived from the server if not cached. * The appropriate layout segment is referenced and returned to the caller. @@ -1499,6 +1518,8 @@ lookup_again: spin_unlock(&ino->i_lock); dprintk("%s wait for layoutreturn\n", __func__); if (pnfs_prepare_to_retry_layoutget(lo)) { + if (first) + pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); goto lookup_again; @@ -1533,13 +1554,8 @@ lookup_again: pnfs_clear_retry_layoutget(lo); atomic_dec(&lo->plh_outstanding); out_put_layout_hdr: - if (first) { - unsigned long *bitlock = &lo->plh_flags; - - clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock); - smp_mb__after_atomic(); - wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET); - } + if (first) + pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); out: dprintk("%s: inode %s/%llu pNFS layout segment %s for " diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 49a466708400..7642021484bf 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -278,6 +278,7 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, u64 count, enum pnfs_iomode iomode, gfp_t gfp_flags); +void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo); void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp); int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 022b761dbf0a..de7c91ca427e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -516,6 +516,7 @@ enum pnfs_layouttype { LAYOUT_NFSV4_1_FILES = 1, LAYOUT_OSD2_OBJECTS = 2, LAYOUT_BLOCK_VOLUME = 3, + LAYOUT_FLEX_FILES = 4, }; /* used for both layout return and recall */ diff --git a/include/linux/nfs_idmap.h b/include/linux/nfs_idmap.h index 0f4b79da6584..333844e38f66 100644 --- a/include/linux/nfs_idmap.h +++ b/include/linux/nfs_idmap.h @@ -73,5 +73,7 @@ int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t); int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t); +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res); + extern unsigned int nfs_idmap_cache_timeout; #endif /* NFS_IDMAP_H */ diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 89f2ca178873..7e61a17030a4 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -89,6 +89,8 @@ void rpc_free_iostats(struct rpc_iostats *); static inline struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { return NULL; } static inline void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) {} +static inline void rpc_count_iostats_metrics(const struct rpc_task *, + struct rpc_iostats *) {} static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {} static inline void rpc_free_iostats(struct rpc_iostats *stats) {} -- cgit v1.2.3 From 03a9a42a1a7e5b3e7919ddfacc1d1cc81882a955 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Jan 2015 18:12:28 -0500 Subject: SUNRPC: NULL utsname dereference on NFS umount during namespace cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix an Oopsable condition when nsm_mon_unmon is called as part of the namespace cleanup, which now apparently happens after the utsname has been freed. Link: http://lkml.kernel.org/r/20150125220604.090121ae@neptune.home Reported-by: Bruno Prémont Cc: stable@vger.kernel.org # 3.18 Signed-off-by: Trond Myklebust --- fs/lockd/mon.c | 13 +++++++++---- include/linux/sunrpc/clnt.h | 3 ++- net/sunrpc/clnt.c | 12 +++++++----- net/sunrpc/rpcb_clnt.c | 8 ++++++-- 4 files changed, 24 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 1cc6ec51e6b1..47a32b6d9b90 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -65,7 +65,7 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm) return (struct sockaddr *)&nsm->sm_addr; } -static struct rpc_clnt *nsm_create(struct net *net) +static struct rpc_clnt *nsm_create(struct net *net, const char *nodename) { struct sockaddr_in sin = { .sin_family = AF_INET, @@ -77,6 +77,7 @@ static struct rpc_clnt *nsm_create(struct net *net) .address = (struct sockaddr *)&sin, .addrsize = sizeof(sin), .servername = "rpc.statd", + .nodename = nodename, .program = &nsm_program, .version = NSM_VERSION, .authflavor = RPC_AUTH_NULL, @@ -102,7 +103,7 @@ out: return clnt; } -static struct rpc_clnt *nsm_client_get(struct net *net) +static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename) { struct rpc_clnt *clnt, *new; struct lockd_net *ln = net_generic(net, lockd_net_id); @@ -111,7 +112,7 @@ static struct rpc_clnt *nsm_client_get(struct net *net) if (clnt != NULL) goto out; - clnt = new = nsm_create(net); + clnt = new = nsm_create(net, nodename); if (IS_ERR(clnt)) goto out; @@ -190,19 +191,23 @@ int nsm_monitor(const struct nlm_host *host) struct nsm_res res; int status; struct rpc_clnt *clnt; + const char *nodename = NULL; dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name); if (nsm->sm_monitored) return 0; + if (host->h_rpcclnt) + nodename = host->h_rpcclnt->cl_nodename; + /* * Choose whether to record the caller_name or IP address of * this peer in the local rpc.statd's database. */ nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf; - clnt = nsm_client_get(host->net); + clnt = nsm_client_get(host->net, nodename); if (IS_ERR(clnt)) { status = PTR_ERR(clnt); dprintk("lockd: failed to create NSM upcall transport, " diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index d86acc63b25f..598ba80ec30c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -57,7 +57,7 @@ struct rpc_clnt { const struct rpc_timeout *cl_timeout; /* Timeout strategy */ int cl_nodelen; /* nodename length */ - char cl_nodename[UNX_MAXNODENAME]; + char cl_nodename[UNX_MAXNODENAME+1]; struct rpc_pipe_dir_head cl_pipedir_objects; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; @@ -112,6 +112,7 @@ struct rpc_create_args { struct sockaddr *saddress; const struct rpc_timeout *timeout; const char *servername; + const char *nodename; const struct rpc_program *program; u32 prognumber; /* overrides program->number */ u32 version; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 05da12a33945..3f5d4d48f0cb 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -286,10 +286,8 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) { - clnt->cl_nodelen = strlen(nodename); - if (clnt->cl_nodelen > UNX_MAXNODENAME) - clnt->cl_nodelen = UNX_MAXNODENAME; - memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen); + clnt->cl_nodelen = strlcpy(clnt->cl_nodename, + nodename, sizeof(clnt->cl_nodename)); } static int rpc_client_register(struct rpc_clnt *clnt, @@ -365,6 +363,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, const struct rpc_version *version; struct rpc_clnt *clnt = NULL; const struct rpc_timeout *timeout; + const char *nodename = args->nodename; int err; /* sanity check the name before trying to print it */ @@ -420,8 +419,10 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, atomic_set(&clnt->cl_count, 1); + if (nodename == NULL) + nodename = utsname()->nodename; /* save the nodename */ - rpc_clnt_set_nodename(clnt, utsname()->nodename); + rpc_clnt_set_nodename(clnt, nodename); err = rpc_client_register(clnt, args->authflavor, args->client_name); if (err) @@ -576,6 +577,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, if (xprt == NULL) goto out_err; args->servername = xprt->servername; + args->nodename = clnt->cl_nodename; new = rpc_new_client(args, xprt, clnt); if (IS_ERR(new)) { diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 05202012bcfc..cf5770d8f49a 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -355,7 +355,8 @@ out: return result; } -static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, +static struct rpc_clnt *rpcb_create(struct net *net, const char *nodename, + const char *hostname, struct sockaddr *srvaddr, size_t salen, int proto, u32 version) { @@ -365,6 +366,7 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *hostname, .address = srvaddr, .addrsize = salen, .servername = hostname, + .nodename = nodename, .program = &rpcb_program, .version = version, .authflavor = RPC_AUTH_UNIX, @@ -740,7 +742,9 @@ void rpcb_getport_async(struct rpc_task *task) dprintk("RPC: %5u %s: trying rpcbind version %u\n", task->tk_pid, __func__, bind_version); - rpcb_clnt = rpcb_create(xprt->xprt_net, xprt->servername, sap, salen, + rpcb_clnt = rpcb_create(xprt->xprt_net, + clnt->cl_nodename, + xprt->servername, sap, salen, xprt->prot, bind_version); if (IS_ERR(rpcb_clnt)) { status = PTR_ERR(rpcb_clnt); -- cgit v1.2.3 From 6ae373394c4257bad562817aa60464ff7fe8f9c4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Jan 2015 14:21:14 -0500 Subject: NFSv4.1: Ask for no delegation on OPEN if using O_DIRECT If we're using NFSv4.1, then we have the ability to let the server know whether or not we believe that returning a delegation as part of our OPEN request would be useful. The feature needs to be used with care, since the client sending the request doesn't necessarily know how other clients are using that file, and how they may be affected by the delegation. For this reason, our initial use of the feature will be to let the server know when the client believes that handing out a delegation would not be useful. The first application for this function is when opening the file using O_DIRECT. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 30 +++++++++++++++++++ fs/nfs/nfs4xdr.c | 79 +++++++++++++++++++++++++++++++++---------------- include/linux/nfs_xdr.h | 2 ++ 3 files changed, 85 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6e1c9b2d92c5..cd4295d84d54 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -940,6 +940,31 @@ static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, return true; } +static u32 +nfs4_map_atomic_open_share(struct nfs_server *server, + fmode_t fmode, int openflags) +{ + u32 res = 0; + + switch (fmode & (FMODE_READ | FMODE_WRITE)) { + case FMODE_READ: + res = NFS4_SHARE_ACCESS_READ; + break; + case FMODE_WRITE: + res = NFS4_SHARE_ACCESS_WRITE; + break; + case FMODE_READ|FMODE_WRITE: + res = NFS4_SHARE_ACCESS_BOTH; + } + if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1)) + goto out; + /* Want no delegation if we're using O_DIRECT */ + if (openflags & O_DIRECT) + res |= NFS4_SHARE_WANT_NO_DELEG; +out: + return res; +} + static enum open_claim_type4 nfs4_map_atomic_open_claim(struct nfs_server *server, enum open_claim_type4 claim) @@ -1002,6 +1027,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, atomic_inc(&sp->so_count); p->o_arg.open_flags = flags; p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); + p->o_arg.share_access = nfs4_map_atomic_open_share(server, + fmode, flags); /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS * will return permission denied for all bits until close */ if (!(flags & O_EXCL)) { @@ -2695,6 +2722,9 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) goto out_wait; } } + calldata->arg.share_access = + nfs4_map_atomic_open_share(NFS_SERVER(inode), + calldata->arg.fmode, 0); nfs_fattr_init(calldata->res.fattr); calldata->timestamp = jiffies; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index a2329d69502b..e23a0a664e12 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1351,24 +1351,12 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc encode_string(xdr, name->len, name->name); } -static void encode_share_access(struct xdr_stream *xdr, fmode_t fmode) +static void encode_share_access(struct xdr_stream *xdr, u32 share_access) { __be32 *p; p = reserve_space(xdr, 8); - switch (fmode & (FMODE_READ|FMODE_WRITE)) { - case FMODE_READ: - *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_READ); - break; - case FMODE_WRITE: - *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_WRITE); - break; - case FMODE_READ|FMODE_WRITE: - *p++ = cpu_to_be32(NFS4_SHARE_ACCESS_BOTH); - break; - default: - *p++ = cpu_to_be32(0); - } + *p++ = cpu_to_be32(share_access); *p = cpu_to_be32(0); /* for linux, share_deny = 0 always */ } @@ -1380,7 +1368,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena * owner 4 = 32 */ encode_nfs4_seqid(xdr, arg->seqid); - encode_share_access(xdr, arg->fmode); + encode_share_access(xdr, arg->share_access); p = reserve_space(xdr, 36); p = xdr_encode_hyper(p, arg->clientid); *p++ = cpu_to_be32(24); @@ -1535,7 +1523,7 @@ static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_close encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr); encode_nfs4_stateid(xdr, &arg->stateid); encode_nfs4_seqid(xdr, arg->seqid); - encode_share_access(xdr, arg->fmode); + encode_share_access(xdr, arg->share_access); } static void @@ -4935,20 +4923,13 @@ out_overflow: return -EIO; } -static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +static int decode_rw_delegation(struct xdr_stream *xdr, + uint32_t delegation_type, + struct nfs_openres *res) { __be32 *p; - uint32_t delegation_type; int status; - p = xdr_inline_decode(xdr, 4); - if (unlikely(!p)) - goto out_overflow; - delegation_type = be32_to_cpup(p); - if (delegation_type == NFS4_OPEN_DELEGATE_NONE) { - res->delegation_type = 0; - return 0; - } status = decode_stateid(xdr, &res->delegation); if (unlikely(status)) return status; @@ -4972,6 +4953,52 @@ out_overflow: return -EIO; } +static int decode_no_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t why_no_delegation; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + why_no_delegation = be32_to_cpup(p); + switch (why_no_delegation) { + case WND4_CONTENTION: + case WND4_RESOURCE: + xdr_inline_decode(xdr, 4); + /* Ignore for now */ + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_delegation(struct xdr_stream *xdr, struct nfs_openres *res) +{ + __be32 *p; + uint32_t delegation_type; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + delegation_type = be32_to_cpup(p); + res->delegation_type = 0; + switch (delegation_type) { + case NFS4_OPEN_DELEGATE_NONE: + return 0; + case NFS4_OPEN_DELEGATE_READ: + case NFS4_OPEN_DELEGATE_WRITE: + return decode_rw_delegation(xdr, delegation_type, res); + case NFS4_OPEN_DELEGATE_NONE_EXT: + return decode_no_delegation(xdr, res); + } + return -EIO; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res) { __be32 *p; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 81401125ab2d..2c35e2affa6f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -326,6 +326,7 @@ struct nfs_openargs { struct nfs_seqid * seqid; int open_flags; fmode_t fmode; + u32 share_access; u32 access; __u64 clientid; struct stateowner_id id; @@ -393,6 +394,7 @@ struct nfs_closeargs { nfs4_stateid stateid; struct nfs_seqid * seqid; fmode_t fmode; + u32 share_access; const u32 * bitmask; }; -- cgit v1.2.3 From 472e259449819d939b5a5188b6f4c7d59aa4304c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 16:50:30 -0500 Subject: NFSv4.1: Pin the inode and super block in asynchronous layoutcommit If we're sending an asynchronous layoutcommit, then we need to ensure that the inode and the super block remain pinned. Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- fs/nfs/nfs4proc.c | 19 +++++++++++-------- include/linux/nfs_xdr.h | 1 + 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index dd892a4e7eb3..e092b8540e2e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7989,6 +7989,7 @@ static void nfs4_layoutcommit_release(void *calldata) nfs_post_op_update_inode_force_wcc(data->args.inode, data->res.fattr); put_rpccred(data->cred); + nfs_iput_and_deactive(data->inode); kfree(data); } @@ -8013,7 +8014,6 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) .rpc_message = &msg, .callback_ops = &nfs4_layoutcommit_ops, .callback_data = data, - .flags = RPC_TASK_ASYNC, }; struct rpc_task *task; int status = 0; @@ -8024,18 +8024,21 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) data->args.lastbytewritten, data->args.inode->i_ino); + if (!sync) { + data->inode = nfs_igrab_and_active(data->args.inode); + if (data->inode == NULL) { + nfs4_layoutcommit_release(data); + return -EAGAIN; + } + task_setup_data.flags = RPC_TASK_ASYNC; + } nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); - if (sync == false) - goto out; - status = nfs4_wait_for_completion_rpc_task(task); - if (status != 0) - goto out; - status = task->tk_status; + if (sync) + status = task->tk_status; trace_nfs4_layoutcommit(data->args.inode, status); -out: dprintk("%s: status %d\n", __func__, status); rpc_put_task(task); return status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2c35e2affa6f..bb0d56f737e0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -285,6 +285,7 @@ struct nfs4_layoutcommit_data { struct nfs_fattr fattr; struct list_head lseg_list; struct rpc_cred *cred; + struct inode *inode; struct nfs4_layoutcommit_args args; struct nfs4_layoutcommit_res res; }; -- cgit v1.2.3 From 5a0ec8acb945e302ce819b4a9787796ccf284548 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 16:35:16 -0500 Subject: NFSv4.1: Pin the inode and super block in asynchronous layoutreturns If we're sending an asynchronous layoutreturn, then we need to ensure that the inode and the super block remain pinned. Cc: Peng Tao Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- fs/nfs/nfs4proc.c | 19 +++++++++++-------- include/linux/nfs_xdr.h | 1 + 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e092b8540e2e..2e7c9f7a6f7c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7856,6 +7856,7 @@ static void nfs4_layoutreturn_release(void *calldata) lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_put_layout_hdr(lrp->args.layout); + nfs_iput_and_deactive(lrp->inode); kfree(calldata); dprintk("<-- %s\n", __func__); } @@ -7880,23 +7881,25 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) .rpc_message = &msg, .callback_ops = &nfs4_layoutreturn_call_ops, .callback_data = lrp, - .flags = RPC_TASK_ASYNC, }; int status = 0; dprintk("--> %s\n", __func__); + if (!sync) { + lrp->inode = nfs_igrab_and_active(lrp->args.inode); + if (!lrp->inode) { + nfs4_layoutreturn_release(lrp); + return -EAGAIN; + } + task_setup_data.flags |= RPC_TASK_ASYNC; + } nfs4_init_sequence(&lrp->args.seq_args, &lrp->res.seq_res, 1); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); - if (sync == false) - goto out; - status = nfs4_wait_for_completion_rpc_task(task); - if (status != 0) - goto out; - status = task->tk_status; + if (sync) + status = task->tk_status; trace_nfs4_layoutreturn(lrp->args.inode, status); -out: dprintk("<-- %s status=%d\n", __func__, status); rpc_put_task(task); return status; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bb0d56f737e0..38d96ba935c2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -310,6 +310,7 @@ struct nfs4_layoutreturn { struct nfs4_layoutreturn_res res; struct rpc_cred *cred; struct nfs_client *clp; + struct inode *inode; int rpc_status; }; -- cgit v1.2.3 From 718ba5b87343df303017585200ee182e937eabfc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 18:19:25 -0500 Subject: SUNRPC: Add helpers to prevent socket create from racing The socket lock is currently held by the task that is requesting the connection be established. While that is efficient in the case where the connection happens quickly, it is racy in the case where it doesn't. What we really want is for the connect helper to be able to block access to the socket while it is being set up. This patch does so by arranging to transfer the socket lock from the task that is requesting the connect attempt, and then releasing that lock once everything is done. This scheme also gives us automatic protection against collisions with the RPC close code, so we can kill the cancel_delayed_work_sync() call in xs_close(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ net/sunrpc/xprt.c | 37 +++++++++++++++++++++++++++++++++---- net/sunrpc/xprtsock.c | 7 +++++-- 3 files changed, 41 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9d27ac45b909..2926e618dbc6 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -347,6 +347,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); int xs_swapper(struct rpc_xprt *xprt, int enable); +bool xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *); +void xprt_unlock_connect(struct rpc_xprt *, void *); + /* * Reserved bit positions in xprt->state */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ebbefad21a37..ff3574df8344 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -690,6 +690,37 @@ out_abort: spin_unlock(&xprt->transport_lock); } +bool xprt_lock_connect(struct rpc_xprt *xprt, + struct rpc_task *task, + void *cookie) +{ + bool ret = false; + + spin_lock_bh(&xprt->transport_lock); + if (!test_bit(XPRT_LOCKED, &xprt->state)) + goto out; + if (xprt->snd_task != task) + goto out; + xprt->snd_task = cookie; + ret = true; +out: + spin_unlock_bh(&xprt->transport_lock); + return ret; +} + +void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) +{ + spin_lock_bh(&xprt->transport_lock); + if (xprt->snd_task != cookie) + goto out; + if (!test_bit(XPRT_LOCKED, &xprt->state)) + goto out; + xprt->snd_task =NULL; + xprt->ops->release_xprt(xprt, NULL); +out: + spin_unlock_bh(&xprt->transport_lock); +} + /** * xprt_connect - schedule a transport connect operation * @task: RPC task that is requesting the connect @@ -712,9 +743,7 @@ void xprt_connect(struct rpc_task *task) if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) xprt->ops->close(xprt); - if (xprt_connected(xprt)) - xprt_release_write(xprt, task); - else { + if (!xprt_connected(xprt)) { task->tk_rqstp->rq_bytes_sent = 0; task->tk_timeout = task->tk_rqstp->rq_timeout; rpc_sleep_on(&xprt->pending, task, xprt_connect_status); @@ -726,6 +755,7 @@ void xprt_connect(struct rpc_task *task) xprt->stat.connect_start = jiffies; xprt->ops->connect(xprt, task); } + xprt_release_write(xprt, task); } static void xprt_connect_status(struct rpc_task *task) @@ -758,7 +788,6 @@ static void xprt_connect_status(struct rpc_task *task) dprintk("RPC: %5u xprt_connect_status: error %d connecting to " "server %s\n", task->tk_pid, -task->tk_status, xprt->servername); - xprt_release_write(xprt, task); task->tk_status = -EIO; } } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0fa7ed93dc20..e57d8ed2c4d8 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -852,8 +852,6 @@ static void xs_close(struct rpc_xprt *xprt) dprintk("RPC: xs_close xprt %p\n", xprt); - cancel_delayed_work_sync(&transport->connect_worker); - xs_reset_transport(transport); xprt->reestablish_timeout = 0; @@ -2101,6 +2099,7 @@ static void xs_udp_setup_socket(struct work_struct *work) trace_rpc_socket_connect(xprt, sock, 0); status = 0; out: + xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); } @@ -2286,6 +2285,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case 0: case -EINPROGRESS: case -EALREADY: + xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); return; case -EINVAL: @@ -2303,6 +2303,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) out_eagain: status = -EAGAIN; out: + xprt_unlock_connect(xprt, transport); xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); } @@ -2325,6 +2326,8 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); + if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) { dprintk("RPC: xs_connect delayed xprt %p for %lu " "seconds\n", -- cgit v1.2.3 From 4efdd92c921135175a85452cd41273d9e2788db3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 15:34:28 -0500 Subject: SUNRPC: Remove TCP client connection reset hack Instead we rely on SO_REUSEPORT to provide the reconnection semantics that we need for NFSv2/v3. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprtsock.c | 67 +-------------------------------------------- 2 files changed, 1 insertion(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2926e618dbc6..86af854338b5 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -363,7 +363,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #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 e53a5ca03daf..dbf279cd4494 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -796,8 +796,6 @@ 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); @@ -2102,57 +2100,6 @@ out: xprt_wake_pending_tasks(xprt, status); } -/* - * We need to preserve the port number so the reply cache on the server can - * find our cached RPC replies when we get around to reconnecting. - */ -static void xs_abort_connection(struct sock_xprt *transport) -{ - int result; - struct sockaddr any; - - dprintk("RPC: disconnecting xprt %p to reuse port\n", transport); - - /* - * Disconnect the transport socket by doing a connect operation - * with AF_UNSPEC. This should return immediately... - */ - memset(&any, 0, sizeof(any)); - any.sa_family = AF_UNSPEC; - result = kernel_connect(transport->sock, &any, sizeof(any), 0); - trace_rpc_socket_reset_connection(&transport->xprt, - transport->sock, result); - if (!result) - xs_sock_reset_connection_flags(&transport->xprt); - dprintk("RPC: AF_UNSPEC connect return code %d\n", result); -} - -static void xs_tcp_reuse_connection(struct sock_xprt *transport) -{ - unsigned int state = transport->inet->sk_state; - - if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) { - /* we don't need to abort the connection if the socket - * hasn't undergone a shutdown - */ - if (transport->inet->sk_shutdown == 0) - return; - dprintk("RPC: %s: TCP_CLOSEd and sk_shutdown set to %d\n", - __func__, transport->inet->sk_shutdown); - } - if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) { - /* we don't need to abort the connection if the socket - * hasn't undergone a shutdown - */ - if (transport->inet->sk_shutdown == 0) - return; - dprintk("RPC: %s: ESTABLISHED/SYN_SENT " - "sk_shutdown set to %d\n", - __func__, transport->inet->sk_shutdown); - } - xs_abort_connection(transport); -} - static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -2245,18 +2192,6 @@ static void xs_tcp_setup_socket(struct work_struct *work) status = PTR_ERR(sock); goto out; } - } else { - int abort_and_exit; - - 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; } dprintk("RPC: worker connecting xprt %p via %s to " @@ -2296,9 +2231,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EADDRINUSE: case -ENOBUFS: /* retry with existing socket, after a delay */ + xs_tcp_force_close(xprt); goto out; } -out_eagain: status = -EAGAIN; out: xprt_unlock_connect(xprt, transport); -- cgit v1.2.3 From 505936f59f1e4cd0ff92ae5abc7aae64fb74dbdb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 16:00:01 -0500 Subject: SUNRPC: Cleanup to remove remaining uses of XPRT_CONNECTION_ABORT Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprtsock.c | 3 --- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 86af854338b5..ae39d478a272 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -360,7 +360,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) -#define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c65f74019288..2f8db3499a17 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -804,7 +804,6 @@ static void xs_error_report(struct sock *sk) static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { smp_mb__before_atomic(); - clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); @@ -1904,7 +1903,6 @@ static int xs_local_setup_socket(struct sock_xprt *transport) struct socket *sock; int status = -EIO; - clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); status = __sock_create(xprt->xprt_net, AF_LOCAL, SOCK_STREAM, 0, &sock, 1); if (status < 0) { @@ -2149,7 +2147,6 @@ static void xs_tcp_setup_socket(struct work_struct *work) int status = -EIO; if (!sock) { - clear_bit(XPRT_CONNECTION_ABORT, &xprt->state); sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP, true); -- cgit v1.2.3 From 9e2b9f37760e129cee053cc7b6e7288acc2a7134 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 19:21:27 -0500 Subject: SUNRPC: Remove the redundant XPRT_CONNECTION_CLOSE flag Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprt.c | 1 - net/sunrpc/xprtsock.c | 1 - 3 files changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ae39d478a272..8b93ef53df3c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -360,7 +360,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) -#define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) static inline void xprt_set_connected(struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index ff3574df8344..e3015aede0d9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -683,7 +683,6 @@ xprt_init_autodisconnect(unsigned long data) if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); - set_bit(XPRT_CONNECTION_CLOSE, &xprt->state); queue_work(rpciod_workqueue, &xprt->task_cleanup); return; out_abort: diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0279e8ffb14a..c72b13e2bdf5 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -804,7 +804,6 @@ static void xs_error_report(struct sock *sk) static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) { smp_mb__before_atomic(); - clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); clear_bit(XPRT_CLOSING, &xprt->state); smp_mb__after_atomic(); -- cgit v1.2.3