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 --- fs/nfs/nfs4proc.c | 7 ++++++- fs/nfs/nfs4xdr.c | 4 ++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c347705..4863dec 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2587,6 +2587,11 @@ static void nfs4_close_done(struct rpc_task *task, void *data) case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: case -NFS4ERR_EXPIRED: + if (!nfs4_stateid_match(&calldata->arg.stateid, + &state->stateid)) { + rpc_restart_call_prepare(task); + goto out_release; + } if (calldata->arg.fmode == 0) break; default: @@ -2619,6 +2624,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); + nfs4_stateid_copy(&calldata->arg.stateid, &state->stateid); /* Calculate the change in open mode */ calldata->arg.fmode = 0; if (state->n_rdwr == 0) { @@ -2757,7 +2763,6 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->inode = state->inode; calldata->state = state; calldata->arg.fh = NFS_FH(state->inode); - calldata->arg.stateid = &state->open_stateid; /* Serialization for the sequence id */ calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask); if (calldata->arg.seqid == NULL) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cb4376b..7e7be5a 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1125,7 +1125,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg { encode_op_hdr(xdr, OP_CLOSE, decode_close_maxsz, hdr); encode_nfs4_seqid(xdr, arg->seqid); - encode_nfs4_stateid(xdr, arg->stateid); + encode_nfs4_stateid(xdr, &arg->stateid); } static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr) @@ -1530,7 +1530,7 @@ static void encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_co static void encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closeargs *arg, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_OPEN_DOWNGRADE, decode_open_downgrade_maxsz, hdr); - encode_nfs4_stateid(xdr, arg->stateid); + encode_nfs4_stateid(xdr, &arg->stateid); encode_nfs4_seqid(xdr, arg->seqid); encode_share_access(xdr, arg->fmode); } -- cgit v1.1 From f95549cf24660255c880b3ea7ee2d7d08de1f5c5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 18:06:09 -0500 Subject: NFSv4: More CLOSE/OPEN races If an OPEN RPC call races with a CLOSE or OPEN_DOWNGRADE so that it updates the nfs_state structure before the CLOSE/OPEN_DOWNGRADE has a chance to do so, then we know that the state->flags need to be recalculated from scratch. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4863dec..a6c04a5 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1167,6 +1167,16 @@ static bool nfs_need_update_open_stateid(struct nfs4_state *state, return false; } +static void nfs_resync_open_stateid_locked(struct nfs4_state *state) +{ + if (state->n_wronly) + set_bit(NFS_O_WRONLY_STATE, &state->flags); + if (state->n_rdonly) + set_bit(NFS_O_RDONLY_STATE, &state->flags); + if (state->n_rdwr) + set_bit(NFS_O_RDWR_STATE, &state->flags); +} + static void nfs_clear_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode) { @@ -1185,8 +1195,12 @@ static void nfs_clear_open_stateid_locked(struct nfs4_state *state, } if (stateid == NULL) return; - if (!nfs_need_update_open_stateid(state, stateid)) + /* Handle races with OPEN */ + if (!nfs4_stateid_match_other(stateid, &state->open_stateid) || + !nfs4_stateid_is_newer(stateid, &state->open_stateid)) { + nfs_resync_open_stateid_locked(state); return; + } if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) nfs4_stateid_copy(&state->stateid, stateid); nfs4_stateid_copy(&state->open_stateid, stateid); -- cgit v1.1 From badc76dd0dc6d55a86c79e952f19d3af24708058 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 18:48:00 -0500 Subject: NFSv4: Convert nfs_alloc_seqid() to return an ERR_PTR() if allocation fails When we relax the sequencing on the NFSv4.1 OPEN/CLOSE code, we will want to use the value NULL to indicate that no sequencing is needed. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 10 +++++----- fs/nfs/nfs4state.c | 10 +++++----- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a6c04a5..c9c3807 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -988,7 +988,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, goto err_free_p; p->o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid, gfp_mask); - if (p->o_arg.seqid == NULL) + if (IS_ERR(p->o_arg.seqid)) goto err_free_label; nfs_sb_active(dentry->d_sb); p->dentry = dget(dentry); @@ -2779,7 +2779,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->arg.fh = NFS_FH(state->inode); /* Serialization for the sequence id */ calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask); - if (calldata->arg.seqid == NULL) + if (IS_ERR(calldata->arg.seqid)) goto out_free_calldata; calldata->arg.fmode = 0; calldata->arg.bitmask = server->cache_consistency_bitmask; @@ -5517,7 +5517,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock * goto out; seqid = nfs_alloc_seqid(&lsp->ls_seqid, GFP_KERNEL); status = -ENOMEM; - if (seqid == NULL) + if (IS_ERR(seqid)) goto out; task = nfs4_do_unlck(request, nfs_file_open_context(request->fl_file), lsp, seqid); status = PTR_ERR(task); @@ -5558,10 +5558,10 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.fh = NFS_FH(inode); p->arg.fl = &p->fl; p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid, gfp_mask); - if (p->arg.open_seqid == NULL) + if (IS_ERR(p->arg.open_seqid)) goto out_free; p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid, gfp_mask); - if (p->arg.lock_seqid == NULL) + 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; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5194933..b922e43 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1003,11 +1003,11 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_m struct nfs_seqid *new; new = kmalloc(sizeof(*new), gfp_mask); - if (new != NULL) { - new->sequence = counter; - INIT_LIST_HEAD(&new->list); - new->task = NULL; - } + if (new == NULL) + return ERR_PTR(-ENOMEM); + new->sequence = counter; + INIT_LIST_HEAD(&new->list); + new->task = NULL; return new; } -- cgit v1.1 From a67964197c946adbb14d91c3d878af22de47091c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 19:04:44 -0500 Subject: NFSv4: Check for NULL argument in nfs_*_seqid() functions Signed-off-by: Trond Myklebust --- fs/nfs/nfs4state.c | 21 ++++++++++++++------- fs/nfs/nfs4xdr.c | 5 ++++- 2 files changed, 18 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index b922e43..590f096 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1015,7 +1015,7 @@ void nfs_release_seqid(struct nfs_seqid *seqid) { struct nfs_seqid_counter *sequence; - if (list_empty(&seqid->list)) + if (seqid == NULL || list_empty(&seqid->list)) return; sequence = seqid->sequence; spin_lock(&sequence->lock); @@ -1071,13 +1071,15 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid) { - struct nfs4_state_owner *sp = container_of(seqid->sequence, - struct nfs4_state_owner, so_seqid); - struct nfs_server *server = sp->so_server; + struct nfs4_state_owner *sp; + + if (seqid == NULL) + return; + sp = container_of(seqid->sequence, struct nfs4_state_owner, so_seqid); if (status == -NFS4ERR_BAD_SEQID) nfs4_drop_state_owner(sp); - if (!nfs4_has_session(server->nfs_client)) + if (!nfs4_has_session(sp->so_server->nfs_client)) nfs_increment_seqid(status, seqid); } @@ -1088,14 +1090,18 @@ void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid) */ void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid) { - nfs_increment_seqid(status, seqid); + if (seqid != NULL) + nfs_increment_seqid(status, seqid); } int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task) { - struct nfs_seqid_counter *sequence = seqid->sequence; + struct nfs_seqid_counter *sequence; int status = 0; + if (seqid == NULL) + goto out; + sequence = seqid->sequence; spin_lock(&sequence->lock); seqid->task = task; if (list_empty(&seqid->list)) @@ -1106,6 +1112,7 @@ int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task) status = -EAGAIN; unlock: spin_unlock(&sequence->lock); +out: return status; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7e7be5a..d05fada 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -946,7 +946,10 @@ static void encode_uint64(struct xdr_stream *xdr, u64 n) static void encode_nfs4_seqid(struct xdr_stream *xdr, const struct nfs_seqid *seqid) { - encode_uint32(xdr, seqid->sequence->counter); + if (seqid != NULL) + encode_uint32(xdr, seqid->sequence->counter); + else + encode_uint32(xdr, 0); } static void encode_compound_hdr(struct xdr_stream *xdr, -- cgit v1.1 From 63f5f796af613898669b23ccfc091ec77de7591c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 19:19:25 -0500 Subject: NFSv4.1: Allow parallel OPEN/OPEN_DOWNGRADE/CLOSE Remove the serialisation of OPEN/OPEN_DOWNGRADE and CLOSE calls for the case of NFSv4.1 and newer. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4_fs.h | 3 +++ fs/nfs/nfs4proc.c | 17 +++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index a081787..e57290a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -44,6 +44,7 @@ enum nfs4_client_state { #define NFS4_RENEW_TIMEOUT 0x01 #define NFS4_RENEW_DELEGATION_CB 0x02 +struct nfs_seqid_counter; struct nfs4_minor_version_ops { u32 minor_version; unsigned init_caps; @@ -56,6 +57,8 @@ struct nfs4_minor_version_ops { struct nfs_fsinfo *); void (*free_lock_state)(struct nfs_server *, struct nfs4_lock_state *); + struct nfs_seqid * + (*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); const struct rpc_call_ops *call_sync_ops; const struct nfs4_state_recovery_ops *reboot_recovery_ops; const struct nfs4_state_recovery_ops *nograce_recovery_ops; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c9c3807..0a279ad 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -977,6 +977,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, struct dentry *parent = dget_parent(dentry); struct inode *dir = parent->d_inode; struct nfs_server *server = NFS_SERVER(dir); + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); struct nfs4_opendata *p; p = kzalloc(sizeof(*p), gfp_mask); @@ -987,7 +988,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, if (IS_ERR(p->f_label)) goto err_free_p; - p->o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid, gfp_mask); + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; + p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask); if (IS_ERR(p->o_arg.seqid)) goto err_free_label; nfs_sb_active(dentry->d_sb); @@ -2751,6 +2753,7 @@ static bool nfs4_roc(struct inode *inode) int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) { struct nfs_server *server = NFS_SERVER(state->inode); + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); struct nfs4_closedata *calldata; struct nfs4_state_owner *sp = state->owner; struct rpc_task *task; @@ -2778,7 +2781,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->state = state; calldata->arg.fh = NFS_FH(state->inode); /* Serialization for the sequence id */ - calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask); + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; + calldata->arg.seqid = alloc_seqid(&state->owner->so_seqid, gfp_mask); if (IS_ERR(calldata->arg.seqid)) goto out_free_calldata; calldata->arg.fmode = 0; @@ -8414,6 +8418,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .match_stateid = nfs4_match_stateid, .find_root_sec = nfs4_find_root_sec, .free_lock_state = nfs4_release_lockowner, + .alloc_seqid = nfs_alloc_seqid, .call_sync_ops = &nfs40_call_sync_ops, .reboot_recovery_ops = &nfs40_reboot_recovery_ops, .nograce_recovery_ops = &nfs40_nograce_recovery_ops, @@ -8422,6 +8427,12 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { }; #if defined(CONFIG_NFS_V4_1) +static struct nfs_seqid * +nfs_alloc_no_seqid(struct nfs_seqid_counter *arg1, gfp_t arg2) +{ + return NULL; +} + static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .minor_version = 1, .init_caps = NFS_CAP_READDIRPLUS @@ -8435,6 +8446,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .match_stateid = nfs41_match_stateid, .find_root_sec = nfs41_find_root_sec, .free_lock_state = nfs41_free_lock_state, + .alloc_seqid = nfs_alloc_no_seqid, .call_sync_ops = &nfs41_call_sync_ops, .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, @@ -8461,6 +8473,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { .find_root_sec = nfs41_find_root_sec, .free_lock_state = nfs41_free_lock_state, .call_sync_ops = &nfs41_call_sync_ops, + .alloc_seqid = nfs_alloc_no_seqid, .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, .state_renewal_ops = &nfs41_state_renewal_ops, -- cgit v1.1 From 39071e6fff7d7e11a5993afd67240ef04a4d05a0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 15:07:56 -0500 Subject: NFSv4: Fix atomicity problems with lock stateid updates When we update the lock stateid, we really do need to ensure that this is done under the state->state_lock, and that we are indeed only updating confirmed locks with a newer version of the same stateid. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 42 +++++++++++++++++++++++++++++------------- 1 file changed, 29 insertions(+), 13 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0a279ad..db9d98e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1297,6 +1297,23 @@ no_delegation: return ret; } +static bool nfs4_update_lock_stateid(struct nfs4_lock_state *lsp, + const nfs4_stateid *stateid) +{ + struct nfs4_state *state = lsp->ls_state; + bool ret = false; + + spin_lock(&state->state_lock); + if (!nfs4_stateid_match_other(stateid, &lsp->ls_stateid)) + goto out_noupdate; + if (!nfs4_stateid_is_newer(stateid, &lsp->ls_stateid)) + goto out_noupdate; + nfs4_stateid_copy(&lsp->ls_stateid, stateid); + ret = true; +out_noupdate: + spin_unlock(&state->state_lock); + return ret; +} static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmode) { @@ -5403,9 +5420,9 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) return; switch (task->tk_status) { case 0: - nfs4_stateid_copy(&calldata->lsp->ls_stateid, - &calldata->res.stateid); renew_lease(calldata->server, calldata->timestamp); + nfs4_update_lock_stateid(calldata->lsp, + &calldata->res.stateid); break; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: @@ -5626,6 +5643,7 @@ out_wait: static void nfs4_lock_done(struct rpc_task *task, void *calldata) { struct nfs4_lockdata *data = calldata; + struct nfs4_lock_state *lsp = data->lsp; dprintk("%s: begin!\n", __func__); @@ -5633,18 +5651,16 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) return; data->rpc_status = task->tk_status; - if (data->arg.new_lock_owner != 0) { - if (data->rpc_status == 0) - nfs_confirm_seqid(&data->lsp->ls_seqid, 0); - else - goto out; - } - if (data->rpc_status == 0) { - nfs4_stateid_copy(&data->lsp->ls_stateid, &data->res.stateid); - set_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags); - renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp); + if (task->tk_status == 0) { + renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), + data->timestamp); + if (data->arg.new_lock_owner != 0) { + nfs_confirm_seqid(&lsp->ls_seqid, 0); + nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); + set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); + } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) + rpc_restart_call_prepare(task); } -out: dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); } -- cgit v1.1 From 6b447539aa9aaac0a0215f3e28a0839553210e7e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 18:38:15 -0500 Subject: NFSv4: Always do open_to_lock_owner if the lock stateid is uninitialised The original text in RFC3530 was terribly confusing since it conflated lockowners and lock stateids. RFC3530bis clarifies that you must use open_to_lock_owner when there is no lock state for that file+lockowner combination. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index db9d98e..f12ded0 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5611,7 +5611,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) goto out_wait; /* Do we need to do an open_to_lock_owner? */ - if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) { + if (!test_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags)) { if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) { goto out_release_lock_seqid; } -- cgit v1.1 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 +++--- 2 files changed, 27 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f12ded0..41e7c2f 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 d05fada..e3018e7 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)); -- cgit v1.1 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 +++++++++++++++---------------------- 1 file changed, 15 insertions(+), 22 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 41e7c2f..9f6baf9 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; -- cgit v1.1 From b4019c0e219bb1301865f8b2efedb4773526ed91 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 14:19:19 -0500 Subject: NFSv4.1: Allow parallel LOCK/LOCKU calls Note, however, that we still serialise on the open stateid if the lock stateid is unconfirmed. Hopefully that will not prove too much of a burden for first time locks; it should leave the ability to parallelise OPENs unchanged, since they no longer call the serialisation primitives. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9f6baf9..66befb0 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5517,6 +5517,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock * struct nfs_seqid *seqid; struct nfs4_lock_state *lsp; struct rpc_task *task; + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); int status = 0; unsigned char fl_flags = request->fl_flags; @@ -5540,7 +5541,8 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock * lsp = request->fl_u.nfs4_fl.owner; if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) == 0) goto out; - seqid = nfs_alloc_seqid(&lsp->ls_seqid, GFP_KERNEL); + alloc_seqid = NFS_SERVER(inode)->nfs_client->cl_mvops->alloc_seqid; + seqid = alloc_seqid(&lsp->ls_seqid, GFP_KERNEL); status = -ENOMEM; if (IS_ERR(seqid)) goto out; @@ -5575,6 +5577,7 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, struct nfs4_lockdata *p; struct inode *inode = lsp->ls_state->inode; struct nfs_server *server = NFS_SERVER(inode); + struct nfs_seqid *(*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); p = kzalloc(sizeof(*p), gfp_mask); if (p == NULL) @@ -5585,7 +5588,8 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid, gfp_mask); if (IS_ERR(p->arg.open_seqid)) goto out_free; - p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid, gfp_mask); + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; + p->arg.lock_seqid = alloc_seqid(&lsp->ls_seqid, gfp_mask); if (IS_ERR(p->arg.lock_seqid)) goto out_free_seqid; p->arg.lock_owner.clientid = server->nfs_client->cl_clientid; -- cgit v1.1 From 40dd4b7aee1a8c3b8dac7b67ba710692d7691b77 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 13:54:37 -0500 Subject: NFSv4.1: Optimise layout return-on-close Optimise the layout return on close code by ensuring that 1) Add a check for whether we hold a layout before taking any spinlocks 2) Only take the spin lock once 3) Use nfs_state->state to speed up open file checks Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 37 +------------------------------------ fs/nfs/pnfs.c | 24 ++++++++++++++++++++---- fs/nfs/pnfs.h | 10 ++++++++++ 3 files changed, 31 insertions(+), 40 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 66befb0..0f75b92 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2714,45 +2714,10 @@ static const struct rpc_call_ops nfs4_close_ops = { .rpc_release = nfs4_free_closedata, }; -static bool nfs4_state_has_opener(struct nfs4_state *state) -{ - /* first check existing openers */ - if (test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0 && - state->n_rdonly != 0) - return true; - - if (test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0 && - state->n_wronly != 0) - return true; - - if (test_bit(NFS_O_RDWR_STATE, &state->flags) != 0 && - state->n_rdwr != 0) - return true; - - return false; -} - static bool nfs4_roc(struct inode *inode) { - struct nfs_inode *nfsi = NFS_I(inode); - struct nfs_open_context *ctx; - struct nfs4_state *state; - - spin_lock(&inode->i_lock); - list_for_each_entry(ctx, &nfsi->open_files, list) { - state = ctx->state; - if (state == NULL) - continue; - if (nfs4_state_has_opener(state)) { - spin_unlock(&inode->i_lock); - return false; - } - } - spin_unlock(&inode->i_lock); - - if (nfs4_check_delegation(inode, FMODE_READ)) + if (!nfs_have_layout(inode)) return false; - return pnfs_roc(inode); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0a5dda4..4d69076 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -34,6 +34,7 @@ #include "pnfs.h" #include "iostat.h" #include "nfs4trace.h" +#include "delegation.h" #define NFSDBG_FACILITY NFSDBG_PNFS #define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ) @@ -954,30 +955,45 @@ pnfs_commit_and_return_layout(struct inode *inode) bool pnfs_roc(struct inode *ino) { + struct nfs_inode *nfsi = NFS_I(ino); + struct nfs_open_context *ctx; + struct nfs4_state *state; struct pnfs_layout_hdr *lo; struct pnfs_layout_segment *lseg, *tmp; LIST_HEAD(tmp_list); bool found = false; spin_lock(&ino->i_lock); - lo = NFS_I(ino)->layout; + lo = nfsi->layout; if (!lo || !test_and_clear_bit(NFS_LAYOUT_ROC, &lo->plh_flags) || test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) - goto out_nolayout; + goto out_noroc; + + /* Don't return layout if we hold a delegation */ + if (nfs4_check_delegation(ino, FMODE_READ)) + goto out_noroc; + + list_for_each_entry(ctx, &nfsi->open_files, list) { + state = ctx->state; + /* Don't return layout if there is open file state */ + if (state != NULL && state->state != 0) + goto out_noroc; + } + list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list) if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { mark_lseg_invalid(lseg, &tmp_list); found = true; } if (!found) - goto out_nolayout; + goto out_noroc; lo->plh_block_lgets++; pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */ spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); return true; -out_nolayout: +out_noroc: spin_unlock(&ino->i_lock); return false; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9ae5b76..a98d8fd 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -275,6 +275,11 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node); bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node); void nfs4_deviceid_purge_client(const struct nfs_client *); +static inline bool nfs_have_layout(struct inode *inode) +{ + return NFS_I(inode)->layout != NULL; +} + static inline struct nfs4_deviceid_node * nfs4_get_deviceid(struct nfs4_deviceid_node *d) { @@ -427,6 +432,11 @@ static inline void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id) #endif /* NFS_DEBUG */ #else /* CONFIG_NFS_V4_1 */ +static inline bool nfs_have_layout(struct inode *inode) +{ + return false; +} + static inline void pnfs_destroy_all_layouts(struct nfs_client *clp) { } -- cgit v1.1 From 89f0ff386cb1ebca0da7940d05bf609bc86f3972 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 3 Jan 2015 14:47:43 -0500 Subject: NFSv4.1: Replace usage of nfs_client->cl_addr in encode_create_session Replace the current code with something that is a little closer to what net/sunrpc/auth_unix.c uses. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4xdr.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index e3018e7..4125339 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1804,9 +1804,8 @@ static void encode_create_session(struct xdr_stream *xdr, struct compound_hdr *hdr) { __be32 *p; - char machine_name[NFS4_MAX_MACHINE_NAME_LEN]; - uint32_t len; struct nfs_client *clp = args->client; + struct rpc_clnt *clnt = clp->cl_rpcclient; struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); u32 max_resp_sz_cached; @@ -1817,11 +1816,8 @@ static void encode_create_session(struct xdr_stream *xdr, max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT; - len = scnprintf(machine_name, sizeof(machine_name), "%s", - clp->cl_ipaddr); - encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr); - p = reserve_space(xdr, 16 + 2*28 + 20 + len + 12); + p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12); p = xdr_encode_hyper(p, clp->cl_clientid); *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ *p++ = cpu_to_be32(args->flags); /*flags */ @@ -1850,7 +1846,7 @@ static void encode_create_session(struct xdr_stream *xdr, /* authsys_parms rfc1831 */ *p++ = cpu_to_be32(nn->boot_time.tv_nsec); /* stamp */ - p = xdr_encode_opaque(p, machine_name, len); + p = xdr_encode_array(p, clnt->cl_nodename, clnt->cl_nodelen); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ *p = cpu_to_be32(0); /* No more gids */ -- cgit v1.1 From cf6726e2ee387b0eff303628eaa0beaf36a1aeb4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 19 Dec 2014 11:22:28 -0500 Subject: NFSv4: Deal with atomic upgrades of an existing delegation Ensure that we deal correctly with the case where the server sends us a newer instance of the same delegation. If the stateids match, but the sequence numbers differ, then treat the new delegation as if it were an atomic upgrade. Signed-off-by: Trond Myklebust --- fs/nfs/delegation.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7f3f606..16b754e 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -301,6 +301,17 @@ nfs_inode_detach_delegation(struct inode *inode) return nfs_detach_delegation(nfsi, delegation, server); } +static void +nfs_update_inplace_delegation(struct nfs_delegation *delegation, + const struct nfs_delegation *update) +{ + if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) { + delegation->stateid.seqid = update->stateid.seqid; + smp_wmb(); + delegation->type = update->type; + } +} + /** * nfs_inode_set_delegation - set up a delegation on an inode * @inode: inode to which delegation applies @@ -334,9 +345,12 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct old_delegation = rcu_dereference_protected(nfsi->delegation, lockdep_is_held(&clp->cl_lock)); if (old_delegation != NULL) { - if (nfs4_stateid_match(&delegation->stateid, - &old_delegation->stateid) && - delegation->type == old_delegation->type) { + /* Is this an update of the existing delegation? */ + if (nfs4_stateid_match_other(&old_delegation->stateid, + &delegation->stateid)) { + nfs_update_inplace_delegation(old_delegation, + delegation); + nfsi->delegation_state = old_delegation->type; goto out; } /* -- cgit v1.1 From 6ffa30d3f734d4f6b478081dfc09592021028f90 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 14 Jan 2015 13:08:57 -0500 Subject: nfs: don't call blocking operations while !TASK_RUNNING Bruce reported seeing this warning pop when mounting using v4.1: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 1121 at kernel/sched/core.c:7300 __might_sleep+0xbd/0xd0() do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait+0x2f/0x90 Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace sunrpc fscache ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hwdep snd_pcm snd_timer ppdev joydev snd virtio_console virtio_balloon pcspkr serio_raw parport_pc parport pvpanic floppy soundcore i2c_piix4 virtio_blk virtio_net qxl drm_kms_helper ttm drm virtio_pci virtio_ring ata_generic virtio pata_acpi CPU: 1 PID: 1121 Comm: nfsv4.1-svc Not tainted 3.19.0-rc4+ #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140709_153950- 04/01/2014 0000000000000000 000000004e5e3f73 ffff8800b998fb48 ffffffff8186ac78 0000000000000000 ffff8800b998fba0 ffff8800b998fb88 ffffffff810ac9da ffff8800b998fb68 ffffffff81c923e7 00000000000004d9 0000000000000000 Call Trace: [] dump_stack+0x4c/0x65 [] warn_slowpath_common+0x8a/0xc0 [] warn_slowpath_fmt+0x55/0x70 [] ? prepare_to_wait+0x2f/0x90 [] ? prepare_to_wait+0x2f/0x90 [] __might_sleep+0xbd/0xd0 [] kmem_cache_alloc_trace+0x243/0x430 [] ? groups_alloc+0x3e/0x130 [] groups_alloc+0x3e/0x130 [] svcauth_unix_accept+0x16e/0x290 [sunrpc] [] svc_authenticate+0xe1/0xf0 [sunrpc] [] svc_process_common+0x244/0x6a0 [sunrpc] [] bc_svc_process+0x1c4/0x260 [sunrpc] [] nfs41_callback_svc+0x128/0x1f0 [nfsv4] [] ? wait_woken+0xc0/0xc0 [] ? nfs4_callback_svc+0x60/0x60 [nfsv4] [] kthread+0x11f/0x140 [] ? local_clock+0x15/0x30 [] ? kthread_create_on_node+0x250/0x250 [] ret_from_fork+0x7c/0xb0 [] ? kthread_create_on_node+0x250/0x250 ---[ end trace 675220a11e30f4f2 ]--- nfs41_callback_svc does most of its work while in TASK_INTERRUPTIBLE, which is just wrong. Fix that by finishing the wait immediately if we've found that the list has something on it. Also, we don't expect this kthread to accept signals, so we should be using a TASK_UNINTERRUPTIBLE sleep instead. That however, opens us up hung task warnings from the watchdog, so have the schedule_timeout wake up every 60s if there's no callback activity. Reported-by: "J. Bruce Fields" Signed-off-by: Jeff Layton Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- fs/nfs/callback.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index b8fb3a4..351be920 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp) if (try_to_freeze()) continue; - prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); + prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE); spin_lock_bh(&serv->sv_cb_lock); if (!list_empty(&serv->sv_cb_list)) { req = list_first_entry(&serv->sv_cb_list, struct rpc_rqst, rq_bc_list); list_del(&req->rq_bc_list); spin_unlock_bh(&serv->sv_cb_lock); + finish_wait(&serv->sv_cb_waitq, &wq); dprintk("Invoking bc_svc_process()\n"); error = bc_svc_process(serv, req, rqstp); dprintk("bc_svc_process() returned w/ error code= %d\n", error); } else { spin_unlock_bh(&serv->sv_cb_lock); - schedule(); + /* schedule_timeout to game the hung task watchdog */ + schedule_timeout(60 * HZ); + finish_wait(&serv->sv_cb_waitq, &wq); } - finish_wait(&serv->sv_cb_waitq, &wq); } return 0; } -- cgit v1.1 From 3a7ed3fff3bb22828f7d7ba6b75c7d22ee54df38 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 8 Jan 2015 01:18:30 -0800 Subject: nfs: prevent truncate on active swapfile Most filesystems prevent truncation of an active swapfile by way of inode_newsize_ok, called from inode_change_ok. NFS doesn't call either from nfs_setattr, presumably because most of these checks are expected to be done server-side. However, the IS_SWAPFILE check can only be done client-side, and truncating a swapfile can't possibly be good. Signed-off-by: Omar Sandoval Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 2211f6b..d2398c1 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -507,10 +507,15 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_valid &= ~ATTR_MODE; if (attr->ia_valid & ATTR_SIZE) { + loff_t i_size; + BUG_ON(!S_ISREG(inode->i_mode)); - if (attr->ia_size == i_size_read(inode)) + i_size = i_size_read(inode); + if (attr->ia_size == i_size) attr->ia_valid &= ~ATTR_SIZE; + else if (attr->ia_size < i_size && IS_SWAPFILE(inode)) + return -ETXTBSY; } /* Optimization: if the end result is no change, don't RPC */ -- cgit v1.1 From c7c545d4a34872f4a3d710e22f21fb61f7258706 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Dec 2014 02:52:26 +0300 Subject: NFS: a couple off by ones These tests are off by one because if len == sizeof(nfs_export_path) then we have truncated the name. Signed-off-by: Dan Carpenter Signed-off-by: Trond Myklebust --- fs/nfs/nfsroot.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index cd3c910..9bc9f04 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -261,11 +261,11 @@ static int __init root_nfs_data(char *cmdline) */ len = snprintf(nfs_export_path, sizeof(nfs_export_path), tmp, utsname()->nodename); - if (len > (int)sizeof(nfs_export_path)) + if (len >= (int)sizeof(nfs_export_path)) goto out_devnametoolong; len = snprintf(nfs_root_device, sizeof(nfs_root_device), "%pI4:%s", &servaddr, nfs_export_path); - if (len > (int)sizeof(nfs_root_device)) + if (len >= (int)sizeof(nfs_root_device)) goto out_devnametoolong; retval = 0; -- cgit v1.1 From f54bcf2ecee982da47c2baf8bd87fd9ad9984651 Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Thu, 11 Dec 2014 15:34:59 -0500 Subject: pnfs: Prepare for flexfiles by pulling out common code The flexfilelayout driver will share some common code with the filelayout driver. This set of changes refactors that common code out to avoid any module depenencies. Signed-off-by: Tom Haynes --- fs/nfs/Makefile | 2 +- fs/nfs/filelayout/filelayout.c | 291 ++------------------------------------ fs/nfs/filelayout/filelayout.h | 11 -- fs/nfs/filelayout/filelayoutdev.c | 2 +- fs/nfs/pnfs.h | 23 +++ fs/nfs/pnfs_nfs.c | 291 ++++++++++++++++++++++++++++++++++++++ 6 files changed, 330 insertions(+), 290 deletions(-) create mode 100644 fs/nfs/pnfs_nfs.c (limited to 'fs/nfs') diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 04cb830..23abffa 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -27,7 +27,7 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o dns_resolve.o nfs4trace.o nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o -nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o pnfs_nfs.o nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/ diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 7afb52f..bc36ed3 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -118,13 +118,6 @@ static void filelayout_reset_read(struct nfs_pgio_header *hdr) } } -static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo) -{ - if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) - return; - pnfs_return_layout(inode); -} - static int filelayout_async_handle_error(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, @@ -339,16 +332,6 @@ static void filelayout_read_count_stats(struct rpc_task *task, void *data) rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics); } -static void filelayout_read_release(void *data) -{ - struct nfs_pgio_header *hdr = data; - struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout; - - filelayout_fenceme(lo->plh_inode, lo); - nfs_put_client(hdr->ds_clp); - hdr->mds_ops->rpc_release(data); -} - static int filelayout_write_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { @@ -371,17 +354,6 @@ static int filelayout_write_done_cb(struct rpc_task *task, return 0; } -/* Fake up some data that will cause nfs_commit_release to retry the writes. */ -static void prepare_to_resend_writes(struct nfs_commit_data *data) -{ - struct nfs_page *first = nfs_list_entry(data->pages.next); - - data->task.tk_status = 0; - memcpy(&data->verf.verifier, &first->wb_verf, - sizeof(data->verf.verifier)); - data->verf.verifier.data[0]++; /* ensure verifier mismatch */ -} - static int filelayout_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *data) { @@ -393,7 +365,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task, switch (err) { case -NFS4ERR_RESET_TO_MDS: - prepare_to_resend_writes(data); + pnfs_generic_prepare_to_resend_writes(data); return -EAGAIN; case -EAGAIN: rpc_restart_call_prepare(task); @@ -451,16 +423,6 @@ static void filelayout_write_count_stats(struct rpc_task *task, void *data) rpc_count_iostats(task, NFS_SERVER(hdr->inode)->client->cl_metrics); } -static void filelayout_write_release(void *data) -{ - struct nfs_pgio_header *hdr = data; - struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout; - - filelayout_fenceme(lo->plh_inode, lo); - nfs_put_client(hdr->ds_clp); - hdr->mds_ops->rpc_release(data); -} - static void filelayout_commit_prepare(struct rpc_task *task, void *data) { struct nfs_commit_data *wdata = data; @@ -471,14 +433,6 @@ static void filelayout_commit_prepare(struct rpc_task *task, void *data) task); } -static void filelayout_write_commit_done(struct rpc_task *task, void *data) -{ - struct nfs_commit_data *wdata = data; - - /* Note this may cause RPC to be resent */ - wdata->mds_ops->rpc_call_done(task, data); -} - static void filelayout_commit_count_stats(struct rpc_task *task, void *data) { struct nfs_commit_data *cdata = data; @@ -486,35 +440,25 @@ static void filelayout_commit_count_stats(struct rpc_task *task, void *data) rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics); } -static void filelayout_commit_release(void *calldata) -{ - struct nfs_commit_data *data = calldata; - - data->completion_ops->completion(data); - pnfs_put_lseg(data->lseg); - nfs_put_client(data->ds_clp); - nfs_commitdata_release(data); -} - static const struct rpc_call_ops filelayout_read_call_ops = { .rpc_call_prepare = filelayout_read_prepare, .rpc_call_done = filelayout_read_call_done, .rpc_count_stats = filelayout_read_count_stats, - .rpc_release = filelayout_read_release, + .rpc_release = pnfs_generic_rw_release, }; static const struct rpc_call_ops filelayout_write_call_ops = { .rpc_call_prepare = filelayout_write_prepare, .rpc_call_done = filelayout_write_call_done, .rpc_count_stats = filelayout_write_count_stats, - .rpc_release = filelayout_write_release, + .rpc_release = pnfs_generic_rw_release, }; static const struct rpc_call_ops filelayout_commit_call_ops = { .rpc_call_prepare = filelayout_commit_prepare, - .rpc_call_done = filelayout_write_commit_done, + .rpc_call_done = pnfs_generic_write_commit_done, .rpc_count_stats = filelayout_commit_count_stats, - .rpc_release = filelayout_commit_release, + .rpc_release = pnfs_generic_commit_release, }; static enum pnfs_try_status @@ -1004,33 +948,6 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) return j; } -/* The generic layer is about to remove the req from the commit list. - * If this will make the bucket empty, it will need to put the lseg reference. - * Note this is must be called holding the inode (/cinfo) lock - */ -static void -filelayout_clear_request_commit(struct nfs_page *req, - struct nfs_commit_info *cinfo) -{ - struct pnfs_layout_segment *freeme = NULL; - - if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) - goto out; - cinfo->ds->nwritten--; - if (list_is_singular(&req->wb_list)) { - struct pnfs_commit_bucket *bucket; - - bucket = list_first_entry(&req->wb_list, - struct pnfs_commit_bucket, - written); - freeme = bucket->wlseg; - bucket->wlseg = NULL; - } -out: - nfs_request_remove_commit_list(req, cinfo); - pnfs_put_lseg_locked(freeme); -} - static void filelayout_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, @@ -1064,7 +981,7 @@ filelayout_mark_request_commit(struct nfs_page *req, * 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 - * filelayout_clear_request_commit + * pnfs_generic_clear_request_commit */ buckets[i].wlseg = pnfs_get_lseg(lseg); } @@ -1142,97 +1059,11 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) &filelayout_commit_call_ops, how, RPC_TASK_SOFTCONN); out_err: - prepare_to_resend_writes(data); - filelayout_commit_release(data); + pnfs_generic_prepare_to_resend_writes(data); + pnfs_generic_commit_release(data); return -EAGAIN; } -static int -transfer_commit_list(struct list_head *src, struct list_head *dst, - struct nfs_commit_info *cinfo, int max) -{ - struct nfs_page *req, *tmp; - int ret = 0; - - list_for_each_entry_safe(req, tmp, src, wb_list) { - if (!nfs_lock_request(req)) - continue; - kref_get(&req->wb_kref); - if (cond_resched_lock(cinfo->lock)) - list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req, cinfo); - clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); - nfs_list_add_request(req, dst); - ret++; - if ((ret == max) && !cinfo->dreq) - break; - } - return ret; -} - -/* Note called with cinfo->lock held. */ -static int -filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, - struct nfs_commit_info *cinfo, - int max) -{ - struct list_head *src = &bucket->written; - struct list_head *dst = &bucket->committing; - int ret; - - ret = transfer_commit_list(src, dst, cinfo, max); - if (ret) { - cinfo->ds->nwritten -= ret; - cinfo->ds->ncommitting += ret; - bucket->clseg = bucket->wlseg; - if (list_empty(src)) - bucket->wlseg = NULL; - else - pnfs_get_lseg(bucket->clseg); - } - return ret; -} - -/* Move reqs from written to committing lists, returning count of number moved. - * Note called with cinfo->lock held. - */ -static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo, - int max) -{ - int i, rv = 0, cnt; - - for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { - cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i], - cinfo, max); - max -= cnt; - rv += cnt; - } - return rv; -} - -/* Pull everything off the committing lists and dump into @dst */ -static void filelayout_recover_commit_reqs(struct list_head *dst, - struct nfs_commit_info *cinfo) -{ - struct pnfs_commit_bucket *b; - struct pnfs_layout_segment *freeme; - int i; - -restart: - spin_lock(cinfo->lock); - for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { - if (transfer_commit_list(&b->written, dst, cinfo, 0)) { - freeme = b->wlseg; - b->wlseg = NULL; - spin_unlock(cinfo->lock); - pnfs_put_lseg(freeme); - goto restart; - } - } - cinfo->ds->nwritten = 0; - spin_unlock(cinfo->lock); -} - /* filelayout_search_commit_reqs - Search lists in @cinfo for the head reqest * for @page * @cinfo - commit info for current inode @@ -1263,108 +1094,14 @@ filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page) return NULL; } -static void filelayout_retry_commit(struct nfs_commit_info *cinfo, int idx) -{ - struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; - struct pnfs_commit_bucket *bucket; - struct pnfs_layout_segment *freeme; - int i; - - for (i = idx; i < fl_cinfo->nbuckets; i++) { - bucket = &fl_cinfo->buckets[i]; - if (list_empty(&bucket->committing)) - continue; - nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); - spin_lock(cinfo->lock); - freeme = bucket->clseg; - bucket->clseg = NULL; - spin_unlock(cinfo->lock); - pnfs_put_lseg(freeme); - } -} - -static unsigned int -alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) -{ - struct pnfs_ds_commit_info *fl_cinfo; - struct pnfs_commit_bucket *bucket; - struct nfs_commit_data *data; - int i; - unsigned int nreq = 0; - - fl_cinfo = cinfo->ds; - bucket = fl_cinfo->buckets; - for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { - if (list_empty(&bucket->committing)) - continue; - data = nfs_commitdata_alloc(); - if (!data) - break; - data->ds_commit_index = i; - spin_lock(cinfo->lock); - data->lseg = bucket->clseg; - bucket->clseg = NULL; - spin_unlock(cinfo->lock); - list_add(&data->pages, list); - nreq++; - } - - /* Clean up on error */ - filelayout_retry_commit(cinfo, i); - /* Caller will clean up entries put on list */ - return nreq; -} - -/* This follows nfs_commit_list pretty closely */ static int filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, int how, struct nfs_commit_info *cinfo) { - struct nfs_commit_data *data, *tmp; - LIST_HEAD(list); - unsigned int nreq = 0; - - if (!list_empty(mds_pages)) { - data = nfs_commitdata_alloc(); - if (data != NULL) { - data->lseg = NULL; - list_add(&data->pages, &list); - nreq++; - } else { - nfs_retry_commit(mds_pages, NULL, cinfo); - filelayout_retry_commit(cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); - return -ENOMEM; - } - } - - nreq += alloc_ds_commits(cinfo, &list); - - if (nreq == 0) { - cinfo->completion_ops->error_cleanup(NFS_I(inode)); - goto out; - } - - atomic_add(nreq, &cinfo->mds->rpcs_out); - - list_for_each_entry_safe(data, tmp, &list, pages) { - list_del_init(&data->pages); - if (!data->lseg) { - nfs_init_commit(data, mds_pages, NULL, cinfo); - nfs_initiate_commit(NFS_CLIENT(inode), data, - data->mds_ops, how, 0); - } else { - struct pnfs_commit_bucket *buckets; - - buckets = cinfo->ds->buckets; - nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo); - filelayout_initiate_commit(data, how); - } - } -out: - cinfo->ds->ncommitting = 0; - return PNFS_ATTEMPTED; + return pnfs_generic_commit_pagelist(inode, mds_pages, how, cinfo, + filelayout_initiate_commit); } + static struct nfs4_deviceid_node * filelayout_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, gfp_t gfp_flags) @@ -1421,9 +1158,9 @@ static struct pnfs_layoutdriver_type filelayout_type = { .pg_write_ops = &filelayout_pg_write_ops, .get_ds_info = &filelayout_get_ds_info, .mark_request_commit = filelayout_mark_request_commit, - .clear_request_commit = filelayout_clear_request_commit, - .scan_commit_lists = filelayout_scan_commit_lists, - .recover_commit_reqs = filelayout_recover_commit_reqs, + .clear_request_commit = pnfs_generic_clear_request_commit, + .scan_commit_lists = pnfs_generic_scan_commit_lists, + .recover_commit_reqs = pnfs_generic_recover_commit_reqs, .search_commit_reqs = filelayout_search_commit_reqs, .commit_pagelist = filelayout_commit_pagelist, .read_pagelist = filelayout_read_pagelist, diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index 7c9f800..a5ce9b4 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -119,17 +119,6 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg) return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node; } -static inline void -filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node) -{ - u32 *p = (u32 *)&node->deviceid; - - printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n", - p[0], p[1], p[2], p[3]); - - set_bit(NFS_DEVICEID_INVALID, &node->flags); -} - static inline bool filelayout_test_devid_invalid(struct nfs4_deviceid_node *node) { diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index bfecac7..d21080a 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -708,7 +708,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", __func__, ds_idx); - filelayout_mark_devid_invalid(devid); + pnfs_generic_mark_devid_invalid(devid); goto out; } smp_rmb(); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9ae5b76..f176634 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -275,6 +275,23 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node); bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node); void nfs4_deviceid_purge_client(const struct nfs_client *); +/* pnfs_nfs.c */ +void pnfs_generic_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo); +void pnfs_generic_commit_release(void *calldata); +void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data); +void pnfs_generic_rw_release(void *data); +void pnfs_generic_recover_commit_reqs(struct list_head *dst, + struct nfs_commit_info *cinfo); +int pnfs_generic_commit_pagelist(struct inode *inode, + struct list_head *mds_pages, + int how, + struct nfs_commit_info *cinfo, + int (*initiate_commit)(struct nfs_commit_data *data, + int how)); +int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max); +void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); + static inline struct nfs4_deviceid_node * nfs4_get_deviceid(struct nfs4_deviceid_node *d) { @@ -317,6 +334,12 @@ pnfs_get_ds_info(struct inode *inode) return ld->get_ds_info(inode); } +static inline void +pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node) +{ + set_bit(NFS_DEVICEID_INVALID, &node->flags); +} + static inline bool pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, struct nfs_commit_info *cinfo) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c new file mode 100644 index 0000000..e5f841cb --- /dev/null +++ b/fs/nfs/pnfs_nfs.c @@ -0,0 +1,291 @@ +/* + * Common NFS I/O operations for the pnfs file based + * layout drivers. + * + * Copyright (c) 2014, Primary Data, Inc. All rights reserved. + * + * Tom Haynes + */ + +#include +#include + +#include "internal.h" +#include "pnfs.h" + +static void pnfs_generic_fenceme(struct inode *inode, + struct pnfs_layout_hdr *lo) +{ + if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + return; + pnfs_return_layout(inode); +} + +void pnfs_generic_rw_release(void *data) +{ + struct nfs_pgio_header *hdr = data; + struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout; + + pnfs_generic_fenceme(lo->plh_inode, lo); + nfs_put_client(hdr->ds_clp); + hdr->mds_ops->rpc_release(data); +} +EXPORT_SYMBOL_GPL(pnfs_generic_rw_release); + +/* Fake up some data that will cause nfs_commit_release to retry the writes. */ +void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data) +{ + struct nfs_page *first = nfs_list_entry(data->pages.next); + + data->task.tk_status = 0; + memcpy(&data->verf.verifier, &first->wb_verf, + sizeof(data->verf.verifier)); + data->verf.verifier.data[0]++; /* ensure verifier mismatch */ +} +EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes); + +void pnfs_generic_write_commit_done(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + /* Note this may cause RPC to be resent */ + wdata->mds_ops->rpc_call_done(task, data); +} +EXPORT_SYMBOL_GPL(pnfs_generic_write_commit_done); + +void pnfs_generic_commit_release(void *calldata) +{ + struct nfs_commit_data *data = calldata; + + data->completion_ops->completion(data); + pnfs_put_lseg(data->lseg); + nfs_put_client(data->ds_clp); + nfs_commitdata_release(data); +} +EXPORT_SYMBOL_GPL(pnfs_generic_commit_release); + +/* The generic layer is about to remove the req from the commit list. + * If this will make the bucket empty, it will need to put the lseg reference. + * Note this is must be called holding the inode (/cinfo) lock + */ +void +pnfs_generic_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo) +{ + struct pnfs_layout_segment *freeme = NULL; + + if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) + goto out; + cinfo->ds->nwritten--; + if (list_is_singular(&req->wb_list)) { + struct pnfs_commit_bucket *bucket; + + bucket = list_first_entry(&req->wb_list, + struct pnfs_commit_bucket, + written); + freeme = bucket->wlseg; + bucket->wlseg = NULL; + } +out: + nfs_request_remove_commit_list(req, cinfo); + pnfs_put_lseg_locked(freeme); +} +EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit); + +static int +pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) +{ + struct nfs_page *req, *tmp; + int ret = 0; + + list_for_each_entry_safe(req, tmp, src, wb_list) { + if (!nfs_lock_request(req)) + continue; + kref_get(&req->wb_kref); + if (cond_resched_lock(cinfo->lock)) + list_safe_reset_next(req, tmp, wb_list); + nfs_request_remove_commit_list(req, cinfo); + clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); + nfs_list_add_request(req, dst); + ret++; + if ((ret == max) && !cinfo->dreq) + break; + } + return ret; +} + +/* Note called with cinfo->lock held. */ +static int +pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, + struct nfs_commit_info *cinfo, + int max) +{ + struct list_head *src = &bucket->written; + struct list_head *dst = &bucket->committing; + int ret; + + ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max); + if (ret) { + cinfo->ds->nwritten -= ret; + cinfo->ds->ncommitting += ret; + bucket->clseg = bucket->wlseg; + if (list_empty(src)) + bucket->wlseg = NULL; + else + pnfs_get_lseg(bucket->clseg); + } + return ret; +} + +/* Move reqs from written to committing lists, returning count of number moved. + * Note called with cinfo->lock held. + */ +int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, + int max) +{ + int i, rv = 0, cnt; + + for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { + cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i], + cinfo, max); + max -= cnt; + rv += cnt; + } + return rv; +} +EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists); + +/* Pull everything off the committing lists and dump into @dst */ +void pnfs_generic_recover_commit_reqs(struct list_head *dst, + struct nfs_commit_info *cinfo) +{ + struct pnfs_commit_bucket *b; + struct pnfs_layout_segment *freeme; + int i; + +restart: + spin_lock(cinfo->lock); + for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { + if (pnfs_generic_transfer_commit_list(&b->written, dst, + cinfo, 0)) { + freeme = b->wlseg; + b->wlseg = NULL; + spin_unlock(cinfo->lock); + pnfs_put_lseg(freeme); + goto restart; + } + } + cinfo->ds->nwritten = 0; + spin_unlock(cinfo->lock); +} +EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs); + +static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx) +{ + struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; + struct pnfs_commit_bucket *bucket; + struct pnfs_layout_segment *freeme; + int i; + + for (i = idx; i < fl_cinfo->nbuckets; i++) { + bucket = &fl_cinfo->buckets[i]; + if (list_empty(&bucket->committing)) + continue; + nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); + spin_lock(cinfo->lock); + freeme = bucket->clseg; + bucket->clseg = NULL; + spin_unlock(cinfo->lock); + pnfs_put_lseg(freeme); + } +} + +static unsigned int +pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo, + struct list_head *list) +{ + struct pnfs_ds_commit_info *fl_cinfo; + struct pnfs_commit_bucket *bucket; + struct nfs_commit_data *data; + int i; + unsigned int nreq = 0; + + fl_cinfo = cinfo->ds; + bucket = fl_cinfo->buckets; + for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { + if (list_empty(&bucket->committing)) + continue; + data = nfs_commitdata_alloc(); + if (!data) + break; + data->ds_commit_index = i; + spin_lock(cinfo->lock); + data->lseg = bucket->clseg; + bucket->clseg = NULL; + spin_unlock(cinfo->lock); + list_add(&data->pages, list); + nreq++; + } + + /* Clean up on error */ + pnfs_generic_retry_commit(cinfo, i); + return nreq; +} + +/* This follows nfs_commit_list pretty closely */ +int +pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, + int how, struct nfs_commit_info *cinfo, + int (*initiate_commit)(struct nfs_commit_data *data, + int how)) +{ + struct nfs_commit_data *data, *tmp; + LIST_HEAD(list); + unsigned int nreq = 0; + + if (!list_empty(mds_pages)) { + data = nfs_commitdata_alloc(); + if (data != NULL) { + data->lseg = NULL; + list_add(&data->pages, &list); + nreq++; + } else { + nfs_retry_commit(mds_pages, NULL, cinfo); + pnfs_generic_retry_commit(cinfo, 0); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); + return -ENOMEM; + } + } + + nreq += pnfs_generic_alloc_ds_commits(cinfo, &list); + + if (nreq == 0) { + cinfo->completion_ops->error_cleanup(NFS_I(inode)); + goto out; + } + + atomic_add(nreq, &cinfo->mds->rpcs_out); + + list_for_each_entry_safe(data, tmp, &list, pages) { + list_del_init(&data->pages); + if (!data->lseg) { + nfs_init_commit(data, mds_pages, NULL, cinfo); + nfs_initiate_commit(NFS_CLIENT(inode), data, + data->mds_ops, how, 0); + } else { + struct pnfs_commit_bucket *buckets; + + buckets = cinfo->ds->buckets; + nfs_init_commit(data, + &buckets[data->ds_commit_index].committing, + data->lseg, + cinfo); + initiate_commit(data, how); + } + } +out: + cinfo->ds->ncommitting = 0; + return PNFS_ATTEMPTED; +} +EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist); -- cgit v1.1 From 085d1e33a6a8495d9afa58ad2b8b7ea74d613515 Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Thu, 11 Dec 2014 13:04:55 -0500 Subject: pnfs: Do not grab the commit_info lock twice when rescheduling writes Acked-by: Jeff Layton Signed-off-by: Tom Haynes --- fs/nfs/direct.c | 19 +++++++++++++++---- fs/nfs/pnfs.h | 15 --------------- fs/nfs/pnfs_nfs.c | 15 ++++++++------- 3 files changed, 23 insertions(+), 26 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 10bf072..e84f764 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -573,6 +573,20 @@ out: return result; } +static void +nfs_direct_write_scan_commit_list(struct inode *inode, + struct list_head *list, + struct nfs_commit_info *cinfo) +{ + spin_lock(cinfo->lock); +#ifdef CONFIG_NFS_V4_1 + if (cinfo->ds != NULL && cinfo->ds->nwritten != 0) + NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo); +#endif + nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0); + spin_unlock(cinfo->lock); +} + static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { struct nfs_pageio_descriptor desc; @@ -582,10 +596,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) LIST_HEAD(failed); nfs_init_cinfo_from_dreq(&cinfo, dreq); - pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo); - spin_lock(cinfo.lock); - nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0); - spin_unlock(cinfo.lock); + nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); dreq->count = 0; get_dreq(dreq); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index f176634..e94f605 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -375,15 +375,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max); } -static inline void -pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list, - struct nfs_commit_info *cinfo) -{ - if (cinfo->ds == NULL || cinfo->ds->nwritten == 0) - return; - NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo); -} - static inline struct nfs_page * pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo, struct page *page) @@ -554,12 +545,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, return 0; } -static inline void -pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list, - struct nfs_commit_info *cinfo) -{ -} - static inline struct nfs_page * pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo, struct page *page) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index e5f841cb..fd2a2f0 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_release); /* The generic layer is about to remove the req from the commit list. * If this will make the bucket empty, it will need to put the lseg reference. - * Note this is must be called holding the inode (/cinfo) lock + * Note this must be called holding the inode (/cinfo) lock */ void pnfs_generic_clear_request_commit(struct nfs_page *req, @@ -115,7 +115,6 @@ pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst, return ret; } -/* Note called with cinfo->lock held. */ static int pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo, @@ -125,6 +124,7 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, struct list_head *dst = &bucket->committing; int ret; + lockdep_assert_held(cinfo->lock); ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max); if (ret) { cinfo->ds->nwritten -= ret; @@ -138,14 +138,15 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, return ret; } -/* Move reqs from written to committing lists, returning count of number moved. - * Note called with cinfo->lock held. +/* Move reqs from written to committing lists, returning count + * of number moved. */ int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max) { int i, rv = 0, cnt; + lockdep_assert_held(cinfo->lock); for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i], cinfo, max); @@ -156,7 +157,7 @@ int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, } EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists); -/* Pull everything off the committing lists and dump into @dst */ +/* Pull everything off the committing lists and dump into @dst. */ void pnfs_generic_recover_commit_reqs(struct list_head *dst, struct nfs_commit_info *cinfo) { @@ -164,8 +165,8 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst, struct pnfs_layout_segment *freeme; int i; + lockdep_assert_held(cinfo->lock); restart: - spin_lock(cinfo->lock); for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { if (pnfs_generic_transfer_commit_list(&b->written, dst, cinfo, 0)) { @@ -173,11 +174,11 @@ restart: b->wlseg = NULL; spin_unlock(cinfo->lock); pnfs_put_lseg(freeme); + spin_lock(cinfo->lock); goto restart; } } cinfo->ds->nwritten = 0; - spin_unlock(cinfo->lock); } EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs); -- cgit v1.1 From 875ae0694be48f3e3bdddd435b79abf52b680299 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 May 2014 21:06:57 +0800 Subject: nfs41: pull data server cache from file layout to generic pnfs Also pull nfs4_pnfs_ds_addr and nfs4_pnfs_ds to generic pnfs. They can all be reused by flexfile layout as well. Reviewed-by: Jeff Layton Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayout.h | 19 --- fs/nfs/filelayout/filelayoutdev.c | 235 +----------------------------------- fs/nfs/pnfs.h | 21 ++++ fs/nfs/pnfs_nfs.c | 242 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 265 insertions(+), 252 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index a5ce9b4..f97eea6 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -56,24 +56,6 @@ enum stripetype4 { STRIPE_DENSE = 2 }; -/* Individual ip address */ -struct nfs4_pnfs_ds_addr { - struct sockaddr_storage da_addr; - size_t da_addrlen; - struct list_head da_node; /* nfs4_pnfs_dev_hlist dev_dslist */ - char *da_remotestr; /* human readable addr+port */ -}; - -struct nfs4_pnfs_ds { - struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ - char *ds_remotestr; /* comma sep list of addrs */ - struct list_head ds_addrs; - struct nfs_client *ds_clp; - atomic_t ds_count; - unsigned long ds_state; -#define NFS4DS_CONNECTING 0 /* ds is establishing connection */ -}; - struct nfs4_file_layout_dsaddr { struct nfs4_deviceid_node id_node; u32 stripe_count; @@ -131,7 +113,6 @@ filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node); extern struct nfs_fh * nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j); -extern void print_ds(struct nfs4_pnfs_ds *ds); u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset); u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j); struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index d21080a..fbfbb70 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -43,114 +43,6 @@ static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; /* - * Data server cache - * - * Data servers can be mapped to different device ids. - * nfs4_pnfs_ds reference counting - * - set to 1 on allocation - * - incremented when a device id maps a data server already in the cache. - * - decremented when deviceid is removed from the cache. - */ -static DEFINE_SPINLOCK(nfs4_ds_cache_lock); -static LIST_HEAD(nfs4_data_server_cache); - -/* Debug routines */ -void -print_ds(struct nfs4_pnfs_ds *ds) -{ - if (ds == NULL) { - printk("%s NULL device\n", __func__); - return; - } - printk(" ds %s\n" - " ref count %d\n" - " client %p\n" - " cl_exchange_flags %x\n", - ds->ds_remotestr, - atomic_read(&ds->ds_count), ds->ds_clp, - ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0); -} - -static bool -same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2) -{ - struct sockaddr_in *a, *b; - struct sockaddr_in6 *a6, *b6; - - if (addr1->sa_family != addr2->sa_family) - return false; - - switch (addr1->sa_family) { - case AF_INET: - a = (struct sockaddr_in *)addr1; - b = (struct sockaddr_in *)addr2; - - if (a->sin_addr.s_addr == b->sin_addr.s_addr && - a->sin_port == b->sin_port) - return true; - break; - - case AF_INET6: - a6 = (struct sockaddr_in6 *)addr1; - b6 = (struct sockaddr_in6 *)addr2; - - /* LINKLOCAL addresses must have matching scope_id */ - if (ipv6_addr_src_scope(&a6->sin6_addr) == - IPV6_ADDR_SCOPE_LINKLOCAL && - a6->sin6_scope_id != b6->sin6_scope_id) - return false; - - if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) && - a6->sin6_port == b6->sin6_port) - return true; - break; - - default: - dprintk("%s: unhandled address family: %u\n", - __func__, addr1->sa_family); - return false; - } - - return false; -} - -static bool -_same_data_server_addrs_locked(const struct list_head *dsaddrs1, - const struct list_head *dsaddrs2) -{ - struct nfs4_pnfs_ds_addr *da1, *da2; - - /* step through both lists, comparing as we go */ - for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node), - da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node); - da1 != NULL && da2 != NULL; - da1 = list_entry(da1->da_node.next, typeof(*da1), da_node), - da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) { - if (!same_sockaddr((struct sockaddr *)&da1->da_addr, - (struct sockaddr *)&da2->da_addr)) - return false; - } - if (da1 == NULL && da2 == NULL) - return true; - - return false; -} - -/* - * Lookup DS by addresses. nfs4_ds_cache_lock is held - */ -static struct nfs4_pnfs_ds * -_data_server_lookup_locked(const struct list_head *dsaddrs) -{ - struct nfs4_pnfs_ds *ds; - - list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) - if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) - return ds; - return NULL; -} - -/* * Create an rpc connection to the nfs4_pnfs_ds data server * Currently only supports IPv4 and IPv6 addresses */ @@ -195,30 +87,6 @@ out_put: goto out; } -static void -destroy_ds(struct nfs4_pnfs_ds *ds) -{ - struct nfs4_pnfs_ds_addr *da; - - dprintk("--> %s\n", __func__); - ifdebug(FACILITY) - print_ds(ds); - - nfs_put_client(ds->ds_clp); - - while (!list_empty(&ds->ds_addrs)) { - da = list_first_entry(&ds->ds_addrs, - struct nfs4_pnfs_ds_addr, - da_node); - list_del_init(&da->da_node); - kfree(da->da_remotestr); - kfree(da); - } - - kfree(ds->ds_remotestr); - kfree(ds); -} - void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) { @@ -229,113 +97,14 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) for (i = 0; i < dsaddr->ds_num; i++) { ds = dsaddr->ds_list[i]; - if (ds != NULL) { - if (atomic_dec_and_lock(&ds->ds_count, - &nfs4_ds_cache_lock)) { - list_del_init(&ds->ds_node); - spin_unlock(&nfs4_ds_cache_lock); - destroy_ds(ds); - } - } + if (ds != NULL) + nfs4_pnfs_ds_put(ds); } kfree(dsaddr->stripe_indices); kfree(dsaddr); } /* - * Create a string with a human readable address and port to avoid - * complicated setup around many dprinks. - */ -static char * -nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags) -{ - struct nfs4_pnfs_ds_addr *da; - char *remotestr; - size_t len; - char *p; - - len = 3; /* '{', '}' and eol */ - list_for_each_entry(da, dsaddrs, da_node) { - len += strlen(da->da_remotestr) + 1; /* string plus comma */ - } - - remotestr = kzalloc(len, gfp_flags); - if (!remotestr) - return NULL; - - p = remotestr; - *(p++) = '{'; - len--; - list_for_each_entry(da, dsaddrs, da_node) { - size_t ll = strlen(da->da_remotestr); - - if (ll > len) - goto out_err; - - memcpy(p, da->da_remotestr, ll); - p += ll; - len -= ll; - - if (len < 1) - goto out_err; - (*p++) = ','; - len--; - } - if (len < 2) - goto out_err; - *(p++) = '}'; - *p = '\0'; - return remotestr; -out_err: - kfree(remotestr); - return NULL; -} - -static struct nfs4_pnfs_ds * -nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) -{ - struct nfs4_pnfs_ds *tmp_ds, *ds = NULL; - char *remotestr; - - if (list_empty(dsaddrs)) { - dprintk("%s: no addresses defined\n", __func__); - goto out; - } - - ds = kzalloc(sizeof(*ds), gfp_flags); - if (!ds) - goto out; - - /* this is only used for debugging, so it's ok if its NULL */ - remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags); - - spin_lock(&nfs4_ds_cache_lock); - tmp_ds = _data_server_lookup_locked(dsaddrs); - if (tmp_ds == NULL) { - INIT_LIST_HEAD(&ds->ds_addrs); - list_splice_init(dsaddrs, &ds->ds_addrs); - ds->ds_remotestr = remotestr; - atomic_set(&ds->ds_count, 1); - INIT_LIST_HEAD(&ds->ds_node); - ds->ds_clp = NULL; - list_add(&ds->ds_node, &nfs4_data_server_cache); - dprintk("%s add new data server %s\n", __func__, - ds->ds_remotestr); - } else { - kfree(remotestr); - kfree(ds); - atomic_inc(&tmp_ds->ds_count); - dprintk("%s data server %s found, inc'ed ds_count to %d\n", - __func__, tmp_ds->ds_remotestr, - atomic_read(&tmp_ds->ds_count)); - ds = tmp_ds; - } - spin_unlock(&nfs4_ds_cache_lock); -out: - return ds; -} - -/* * Currently only supports ipv4, ipv6 and one multi-path address. */ static struct nfs4_pnfs_ds_addr * diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index e94f605..b0168f1 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -40,6 +40,24 @@ enum { NFS_LSEG_LAYOUTCOMMIT, /* layoutcommit bit set for layoutcommit */ }; +/* Individual ip address */ +struct nfs4_pnfs_ds_addr { + struct sockaddr_storage da_addr; + size_t da_addrlen; + struct list_head da_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + char *da_remotestr; /* human readable addr+port */ +}; + +struct nfs4_pnfs_ds { + struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + char *ds_remotestr; /* comma sep list of addrs */ + struct list_head ds_addrs; + struct nfs_client *ds_clp; + atomic_t ds_count; + unsigned long ds_state; +#define NFS4DS_CONNECTING 0 /* ds is establishing connection */ +}; + struct pnfs_layout_segment { struct list_head pls_list; struct list_head pls_lc_list; @@ -291,6 +309,9 @@ int pnfs_generic_commit_pagelist(struct inode *inode, int how)); int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max); void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); +void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); +struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, + gfp_t gfp_flags); static inline struct nfs4_deviceid_node * nfs4_get_deviceid(struct nfs4_deviceid_node *d) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index fd2a2f0..3bb2b74 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -13,6 +13,8 @@ #include "internal.h" #include "pnfs.h" +#define NFSDBG_FACILITY NFSDBG_PNFS + static void pnfs_generic_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo) { @@ -290,3 +292,243 @@ out: return PNFS_ATTEMPTED; } EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist); + +/* + * Data server cache + * + * Data servers can be mapped to different device ids. + * nfs4_pnfs_ds reference counting + * - set to 1 on allocation + * - incremented when a device id maps a data server already in the cache. + * - decremented when deviceid is removed from the cache. + */ +static DEFINE_SPINLOCK(nfs4_ds_cache_lock); +static LIST_HEAD(nfs4_data_server_cache); + +/* Debug routines */ +static void +print_ds(struct nfs4_pnfs_ds *ds) +{ + if (ds == NULL) { + printk(KERN_WARNING "%s NULL device\n", __func__); + return; + } + printk(KERN_WARNING " ds %s\n" + " ref count %d\n" + " client %p\n" + " cl_exchange_flags %x\n", + ds->ds_remotestr, + atomic_read(&ds->ds_count), ds->ds_clp, + ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0); +} + +static bool +same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2) +{ + struct sockaddr_in *a, *b; + struct sockaddr_in6 *a6, *b6; + + if (addr1->sa_family != addr2->sa_family) + return false; + + switch (addr1->sa_family) { + case AF_INET: + a = (struct sockaddr_in *)addr1; + b = (struct sockaddr_in *)addr2; + + if (a->sin_addr.s_addr == b->sin_addr.s_addr && + a->sin_port == b->sin_port) + return true; + break; + + case AF_INET6: + a6 = (struct sockaddr_in6 *)addr1; + b6 = (struct sockaddr_in6 *)addr2; + + /* LINKLOCAL addresses must have matching scope_id */ + if (ipv6_addr_src_scope(&a6->sin6_addr) == + IPV6_ADDR_SCOPE_LINKLOCAL && + a6->sin6_scope_id != b6->sin6_scope_id) + return false; + + if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) && + a6->sin6_port == b6->sin6_port) + return true; + break; + + default: + dprintk("%s: unhandled address family: %u\n", + __func__, addr1->sa_family); + return false; + } + + return false; +} + +static bool +_same_data_server_addrs_locked(const struct list_head *dsaddrs1, + const struct list_head *dsaddrs2) +{ + struct nfs4_pnfs_ds_addr *da1, *da2; + + /* step through both lists, comparing as we go */ + for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node), + da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node); + da1 != NULL && da2 != NULL; + da1 = list_entry(da1->da_node.next, typeof(*da1), da_node), + da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) { + if (!same_sockaddr((struct sockaddr *)&da1->da_addr, + (struct sockaddr *)&da2->da_addr)) + return false; + } + if (da1 == NULL && da2 == NULL) + return true; + + return false; +} + +/* + * Lookup DS by addresses. nfs4_ds_cache_lock is held + */ +static struct nfs4_pnfs_ds * +_data_server_lookup_locked(const struct list_head *dsaddrs) +{ + struct nfs4_pnfs_ds *ds; + + list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) + if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) + return ds; + return NULL; +} + +static void destroy_ds(struct nfs4_pnfs_ds *ds) +{ + struct nfs4_pnfs_ds_addr *da; + + dprintk("--> %s\n", __func__); + ifdebug(FACILITY) + print_ds(ds); + + nfs_put_client(ds->ds_clp); + + while (!list_empty(&ds->ds_addrs)) { + da = list_first_entry(&ds->ds_addrs, + struct nfs4_pnfs_ds_addr, + da_node); + list_del_init(&da->da_node); + kfree(da->da_remotestr); + kfree(da); + } + + kfree(ds->ds_remotestr); + kfree(ds); +} + +void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds) +{ + if (atomic_dec_and_lock(&ds->ds_count, + &nfs4_ds_cache_lock)) { + list_del_init(&ds->ds_node); + spin_unlock(&nfs4_ds_cache_lock); + destroy_ds(ds); + } +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_put); + +/* + * Create a string with a human readable address and port to avoid + * complicated setup around many dprinks. + */ +static char * +nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags) +{ + struct nfs4_pnfs_ds_addr *da; + char *remotestr; + size_t len; + char *p; + + len = 3; /* '{', '}' and eol */ + list_for_each_entry(da, dsaddrs, da_node) { + len += strlen(da->da_remotestr) + 1; /* string plus comma */ + } + + remotestr = kzalloc(len, gfp_flags); + if (!remotestr) + return NULL; + + p = remotestr; + *(p++) = '{'; + len--; + list_for_each_entry(da, dsaddrs, da_node) { + size_t ll = strlen(da->da_remotestr); + + if (ll > len) + goto out_err; + + memcpy(p, da->da_remotestr, ll); + p += ll; + len -= ll; + + if (len < 1) + goto out_err; + (*p++) = ','; + len--; + } + if (len < 2) + goto out_err; + *(p++) = '}'; + *p = '\0'; + return remotestr; +out_err: + kfree(remotestr); + return NULL; +} + +/* + * Given a list of multipath struct nfs4_pnfs_ds_addr, add it to ds cache if + * uncached and return cached struct nfs4_pnfs_ds. + */ +struct nfs4_pnfs_ds * +nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) +{ + struct nfs4_pnfs_ds *tmp_ds, *ds = NULL; + char *remotestr; + + if (list_empty(dsaddrs)) { + dprintk("%s: no addresses defined\n", __func__); + goto out; + } + + ds = kzalloc(sizeof(*ds), gfp_flags); + if (!ds) + goto out; + + /* this is only used for debugging, so it's ok if its NULL */ + remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags); + + spin_lock(&nfs4_ds_cache_lock); + tmp_ds = _data_server_lookup_locked(dsaddrs); + if (tmp_ds == NULL) { + INIT_LIST_HEAD(&ds->ds_addrs); + list_splice_init(dsaddrs, &ds->ds_addrs); + ds->ds_remotestr = remotestr; + atomic_set(&ds->ds_count, 1); + INIT_LIST_HEAD(&ds->ds_node); + ds->ds_clp = NULL; + list_add(&ds->ds_node, &nfs4_data_server_cache); + dprintk("%s add new data server %s\n", __func__, + ds->ds_remotestr); + } else { + kfree(remotestr); + kfree(ds); + atomic_inc(&tmp_ds->ds_count); + dprintk("%s data server %s found, inc'ed ds_count to %d\n", + __func__, tmp_ds->ds_remotestr, + atomic_read(&tmp_ds->ds_count)); + ds = tmp_ds; + } + spin_unlock(&nfs4_ds_cache_lock); +out: + return ds; +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add); -- cgit v1.1 From 6b7f3cf96364eaf597940cb5c68a682894829915 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 May 2014 21:06:59 +0800 Subject: nfs41: pull decode_ds_addr from file layout to generic pnfs It can be reused by flexfile layout. Reviewed-by: Jeff Layton Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayoutdev.c | 152 +------------------------------------- fs/nfs/pnfs.h | 3 + fs/nfs/pnfs_nfs.c | 149 +++++++++++++++++++++++++++++++++++++ 3 files changed, 154 insertions(+), 150 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index fbfbb70..c7f6041 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -31,7 +31,6 @@ #include #include #include -#include #include "../internal.h" #include "../nfs4session.h" @@ -104,153 +103,6 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) kfree(dsaddr); } -/* - * Currently only supports ipv4, ipv6 and one multi-path address. - */ -static struct nfs4_pnfs_ds_addr * -decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags) -{ - struct nfs4_pnfs_ds_addr *da = NULL; - char *buf, *portstr; - __be16 port; - int nlen, rlen; - int tmp[2]; - __be32 *p; - char *netid, *match_netid; - size_t len, match_netid_len; - char *startsep = ""; - char *endsep = ""; - - - /* r_netid */ - p = xdr_inline_decode(streamp, 4); - if (unlikely(!p)) - goto out_err; - nlen = be32_to_cpup(p++); - - p = xdr_inline_decode(streamp, nlen); - if (unlikely(!p)) - goto out_err; - - netid = kmalloc(nlen+1, gfp_flags); - if (unlikely(!netid)) - goto out_err; - - netid[nlen] = '\0'; - memcpy(netid, p, nlen); - - /* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */ - p = xdr_inline_decode(streamp, 4); - if (unlikely(!p)) - goto out_free_netid; - rlen = be32_to_cpup(p); - - p = xdr_inline_decode(streamp, rlen); - if (unlikely(!p)) - goto out_free_netid; - - /* port is ".ABC.DEF", 8 chars max */ - if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) { - dprintk("%s: Invalid address, length %d\n", __func__, - rlen); - goto out_free_netid; - } - buf = kmalloc(rlen + 1, gfp_flags); - if (!buf) { - dprintk("%s: Not enough memory\n", __func__); - goto out_free_netid; - } - buf[rlen] = '\0'; - memcpy(buf, p, rlen); - - /* replace port '.' with '-' */ - portstr = strrchr(buf, '.'); - if (!portstr) { - dprintk("%s: Failed finding expected dot in port\n", - __func__); - goto out_free_buf; - } - *portstr = '-'; - - /* find '.' between address and port */ - portstr = strrchr(buf, '.'); - if (!portstr) { - dprintk("%s: Failed finding expected dot between address and " - "port\n", __func__); - goto out_free_buf; - } - *portstr = '\0'; - - da = kzalloc(sizeof(*da), gfp_flags); - if (unlikely(!da)) - goto out_free_buf; - - INIT_LIST_HEAD(&da->da_node); - - if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr, - sizeof(da->da_addr))) { - dprintk("%s: error parsing address %s\n", __func__, buf); - goto out_free_da; - } - - portstr++; - sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]); - port = htons((tmp[0] << 8) | (tmp[1])); - - switch (da->da_addr.ss_family) { - case AF_INET: - ((struct sockaddr_in *)&da->da_addr)->sin_port = port; - da->da_addrlen = sizeof(struct sockaddr_in); - match_netid = "tcp"; - match_netid_len = 3; - break; - - case AF_INET6: - ((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port; - da->da_addrlen = sizeof(struct sockaddr_in6); - match_netid = "tcp6"; - match_netid_len = 4; - startsep = "["; - endsep = "]"; - break; - - default: - dprintk("%s: unsupported address family: %u\n", - __func__, da->da_addr.ss_family); - goto out_free_da; - } - - if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) { - dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n", - __func__, netid, match_netid); - goto out_free_da; - } - - /* save human readable address */ - len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7; - da->da_remotestr = kzalloc(len, gfp_flags); - - /* NULL is ok, only used for dprintk */ - if (da->da_remotestr) - snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep, - buf, endsep, ntohs(port)); - - dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr); - kfree(buf); - kfree(netid); - return da; - -out_free_da: - kfree(da); -out_free_buf: - dprintk("%s: Error parsing DS addr: %s\n", __func__, buf); - kfree(buf); -out_free_netid: - kfree(netid); -out_err: - return NULL; -} - /* Decode opaque device data and return the result */ struct nfs4_file_layout_dsaddr * nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, @@ -353,8 +205,8 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = decode_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, + &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index b0168f1..403d7bb 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -312,6 +312,9 @@ void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); +struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, + struct xdr_stream *xdr, + gfp_t gfp_flags); static inline struct nfs4_deviceid_node * nfs4_get_deviceid(struct nfs4_deviceid_node *d) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 3bb2b74..81ec449 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -9,6 +9,7 @@ #include #include +#include #include "internal.h" #include "pnfs.h" @@ -532,3 +533,151 @@ out: return ds; } EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add); + +/* + * Currently only supports ipv4, ipv6 and one multi-path address. + */ +struct nfs4_pnfs_ds_addr * +nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags) +{ + struct nfs4_pnfs_ds_addr *da = NULL; + char *buf, *portstr; + __be16 port; + int nlen, rlen; + int tmp[2]; + __be32 *p; + char *netid, *match_netid; + size_t len, match_netid_len; + char *startsep = ""; + char *endsep = ""; + + + /* r_netid */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_err; + nlen = be32_to_cpup(p++); + + p = xdr_inline_decode(xdr, nlen); + if (unlikely(!p)) + goto out_err; + + netid = kmalloc(nlen+1, gfp_flags); + if (unlikely(!netid)) + goto out_err; + + netid[nlen] = '\0'; + memcpy(netid, p, nlen); + + /* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_free_netid; + rlen = be32_to_cpup(p); + + p = xdr_inline_decode(xdr, rlen); + if (unlikely(!p)) + goto out_free_netid; + + /* port is ".ABC.DEF", 8 chars max */ + if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) { + dprintk("%s: Invalid address, length %d\n", __func__, + rlen); + goto out_free_netid; + } + buf = kmalloc(rlen + 1, gfp_flags); + if (!buf) { + dprintk("%s: Not enough memory\n", __func__); + goto out_free_netid; + } + buf[rlen] = '\0'; + memcpy(buf, p, rlen); + + /* replace port '.' with '-' */ + portstr = strrchr(buf, '.'); + if (!portstr) { + dprintk("%s: Failed finding expected dot in port\n", + __func__); + goto out_free_buf; + } + *portstr = '-'; + + /* find '.' between address and port */ + portstr = strrchr(buf, '.'); + if (!portstr) { + dprintk("%s: Failed finding expected dot between address and " + "port\n", __func__); + goto out_free_buf; + } + *portstr = '\0'; + + da = kzalloc(sizeof(*da), gfp_flags); + if (unlikely(!da)) + goto out_free_buf; + + INIT_LIST_HEAD(&da->da_node); + + if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr, + sizeof(da->da_addr))) { + dprintk("%s: error parsing address %s\n", __func__, buf); + goto out_free_da; + } + + portstr++; + sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]); + port = htons((tmp[0] << 8) | (tmp[1])); + + switch (da->da_addr.ss_family) { + case AF_INET: + ((struct sockaddr_in *)&da->da_addr)->sin_port = port; + da->da_addrlen = sizeof(struct sockaddr_in); + match_netid = "tcp"; + match_netid_len = 3; + break; + + case AF_INET6: + ((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port; + da->da_addrlen = sizeof(struct sockaddr_in6); + match_netid = "tcp6"; + match_netid_len = 4; + startsep = "["; + endsep = "]"; + break; + + default: + dprintk("%s: unsupported address family: %u\n", + __func__, da->da_addr.ss_family); + goto out_free_da; + } + + if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) { + dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n", + __func__, netid, match_netid); + goto out_free_da; + } + + /* save human readable address */ + len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7; + da->da_remotestr = kzalloc(len, gfp_flags); + + /* NULL is ok, only used for dprintk */ + if (da->da_remotestr) + snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep, + buf, endsep, ntohs(port)); + + dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr); + kfree(buf); + kfree(netid); + return da; + +out_free_da: + kfree(da); +out_free_buf: + dprintk("%s: Error parsing DS addr: %s\n", __func__, buf); + kfree(buf); +out_free_netid: + kfree(netid); +out_err: + return NULL; +} +EXPORT_SYMBOL_GPL(nfs4_decode_mp_ds_addr); -- cgit v1.1 From 7405f9e195aab95e147cc225f203d11fa74b65a8 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 May 2014 21:06:58 +0800 Subject: nfs41: pull nfs4_ds_connect from file layout to generic pnfs It can be reused by flexfiles layout client. Reviewed-by: Jeff Layton Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayoutdev.c | 78 +++---------------------------------- fs/nfs/pnfs.h | 3 ++ fs/nfs/pnfs_nfs.c | 81 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 89 insertions(+), 73 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index c7f6041..27bdd8c 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -41,51 +41,6 @@ static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; -/* - * Create an rpc connection to the nfs4_pnfs_ds data server - * Currently only supports IPv4 and IPv6 addresses - */ -static int -nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds) -{ - struct nfs_client *clp = ERR_PTR(-EIO); - struct nfs4_pnfs_ds_addr *da; - int status = 0; - - dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr, - mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor); - - list_for_each_entry(da, &ds->ds_addrs, da_node) { - dprintk("%s: DS %s: trying address %s\n", - __func__, ds->ds_remotestr, da->da_remotestr); - - clp = nfs4_set_ds_client(mds_srv->nfs_client, - (struct sockaddr *)&da->da_addr, - da->da_addrlen, IPPROTO_TCP, - dataserver_timeo, dataserver_retrans); - if (!IS_ERR(clp)) - break; - } - - if (IS_ERR(clp)) { - status = PTR_ERR(clp); - goto out; - } - - status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time); - if (status) - goto out_put; - - smp_wmb(); - ds->ds_clp = clp; - dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); -out: - return status; -out_put: - nfs_put_client(clp); - goto out; -} - void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) { @@ -302,22 +257,7 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j) return flseg->fh_array[i]; } -static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) -{ - might_sleep(); - wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING, - nfs_wait_bit_killable, TASK_KILLABLE); -} - -static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) -{ - smp_mb__before_atomic(); - clear_bit(NFS4DS_CONNECTING, &ds->ds_state); - smp_mb__after_atomic(); - wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING); -} - - +/* Upon return, either ds is connected, or ds is NULL */ struct nfs4_pnfs_ds * nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) { @@ -325,6 +265,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx]; struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); struct nfs4_pnfs_ds *ret = ds; + struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", @@ -336,18 +277,9 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) if (ds->ds_clp) goto out_test_devid; - if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { - struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); - int err; - - err = nfs4_ds_connect(s, ds); - if (err) - nfs4_mark_deviceid_unavailable(devid); - nfs4_clear_ds_conn_bit(ds); - } else { - /* Either ds is connected, or ds is NULL */ - nfs4_wait_ds_connect(ds); - } + nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, + dataserver_retrans); + out_test_devid: if (filelayout_test_devid_unavailable(devid)) ret = NULL; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 403d7bb..9a8937c 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -312,6 +312,9 @@ void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); +void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, + struct nfs4_deviceid_node *devid, unsigned int timeo, + unsigned int retrans); struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 81ec449..5a92e76 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -11,6 +11,7 @@ #include #include +#include "nfs4session.h" #include "internal.h" #include "pnfs.h" @@ -534,6 +535,86 @@ out: } EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add); +static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds) +{ + might_sleep(); + wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING, + TASK_KILLABLE); +} + +static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) +{ + smp_mb__before_atomic(); + clear_bit(NFS4DS_CONNECTING, &ds->ds_state); + smp_mb__after_atomic(); + wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING); +} + +static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, + struct nfs4_pnfs_ds *ds, + unsigned int timeo, + unsigned int retrans) +{ + struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs4_pnfs_ds_addr *da; + int status = 0; + + dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr, + mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor); + + list_for_each_entry(da, &ds->ds_addrs, da_node) { + dprintk("%s: DS %s: trying address %s\n", + __func__, ds->ds_remotestr, da->da_remotestr); + + clp = nfs4_set_ds_client(mds_srv->nfs_client, + (struct sockaddr *)&da->da_addr, + da->da_addrlen, IPPROTO_TCP, + timeo, retrans); + if (!IS_ERR(clp)) + break; + } + + if (IS_ERR(clp)) { + status = PTR_ERR(clp); + goto out; + } + + status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time); + if (status) + goto out_put; + + smp_wmb(); + ds->ds_clp = clp; + dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); +out: + return status; +out_put: + nfs_put_client(clp); + goto out; +} + +/* + * Create an rpc connection to the nfs4_pnfs_ds data server. + * Currently only supports IPv4 and IPv6 addresses. + * If connection fails, make devid unavailable. + */ +void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, + struct nfs4_deviceid_node *devid, unsigned int timeo, + unsigned int retrans) +{ + if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { + int err = 0; + + err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, retrans); + if (err) + nfs4_mark_deviceid_unavailable(devid); + nfs4_clear_ds_conn_bit(ds); + } else { + nfs4_wait_ds_connect(ds); + } +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect); + /* * Currently only supports ipv4, ipv6 and one multi-path address. */ -- cgit v1.1 From 064172f3459a914277aa309b2afd3bd5d1c3289a Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 29 May 2014 21:07:00 +0800 Subject: nfs41: allow LD to choose DS connection auth flavor flexfile layout may use different auth flavor as specified by MDS. Reviewed-by: Jeff Layton Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayoutdev.c | 3 ++- fs/nfs/internal.h | 3 ++- fs/nfs/nfs4client.c | 5 +++-- fs/nfs/pnfs.h | 2 +- fs/nfs/pnfs_nfs.c | 10 ++++++---- 5 files changed, 14 insertions(+), 9 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 27bdd8c..5e4b0ce 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -278,7 +278,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) goto out_test_devid; nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, - dataserver_retrans); + dataserver_retrans, + s->nfs_client->cl_rpcclient->cl_auth->au_flavor); out_test_devid: if (filelayout_test_devid_unavailable(devid)) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index efaa31c..7d7c36f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -189,7 +189,8 @@ extern struct nfs_client *nfs4_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); + unsigned int ds_retrans, + rpc_authflavor_t au_flavor); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); #ifdef CONFIG_PROC_FS diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 953daa4..62d93a1 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -849,7 +849,8 @@ error: */ struct nfs_client *nfs4_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) + 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, @@ -874,7 +875,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, */ nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, - mds_clp->cl_rpcclient->cl_auth->au_flavor); + au_flavor); dprintk("<-- %s %p\n", __func__, clp); return clp; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9a8937c..2ea9e9a 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -314,7 +314,7 @@ struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, - unsigned int retrans); + unsigned int retrans, rpc_authflavor_t au_flavor); struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 5a92e76..106ee08 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -553,7 +553,8 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, unsigned int timeo, - unsigned int retrans) + unsigned int retrans, + rpc_authflavor_t au_flavor) { struct nfs_client *clp = ERR_PTR(-EIO); struct nfs4_pnfs_ds_addr *da; @@ -569,7 +570,7 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, clp = nfs4_set_ds_client(mds_srv->nfs_client, (struct sockaddr *)&da->da_addr, da->da_addrlen, IPPROTO_TCP, - timeo, retrans); + timeo, retrans, au_flavor); if (!IS_ERR(clp)) break; } @@ -600,12 +601,13 @@ out_put: */ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, - unsigned int retrans) + unsigned int retrans, rpc_authflavor_t au_flavor) { if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { int err = 0; - err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, retrans); + err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, + retrans, au_flavor); if (err) nfs4_mark_deviceid_unavailable(devid); nfs4_clear_ds_conn_bit(ds); -- cgit v1.1 From 39280a5ae8443dcc1ab3bb5ebc205aab0855b849 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 30 May 2014 18:15:55 +0800 Subject: nfs41: move file layout macros to generic pnfs They can be reused by flexfile layout as well. Also add a code such that if read fails on one DS and there are other DSes available to use, don't resend through MDS but through pNFS so that client can read from other DSes. Reviewed-by: Jeff Layton Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayout.h | 10 ---------- fs/nfs/pnfs.h | 11 +++++++++++ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index f97eea6..2896cb8 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -33,13 +33,6 @@ #include "../pnfs.h" /* - * Default data server connection timeout and retrans vaules. - * Set by module paramters dataserver_timeo and dataserver_retrans. - */ -#define NFS4_DEF_DS_TIMEO 600 /* in tenths of a second */ -#define NFS4_DEF_DS_RETRANS 5 - -/* * Field testing shows we need to support up to 4096 stripe indices. * We store each index as a u8 (u32 on the wire) to keep the memory footprint * reasonable. This in turn means we support a maximum of 256 @@ -48,9 +41,6 @@ #define NFS4_PNFS_MAX_STRIPE_CNT 4096 #define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */ -/* error codes for internal use */ -#define NFS4ERR_RESET_TO_MDS 12001 - enum stripetype4 { STRIPE_SPARSE = 1, STRIPE_DENSE = 2 diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 2ea9e9a..aef89b3 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -77,6 +77,17 @@ enum pnfs_try_status { #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" +/* + * Default data server connection timeout and retrans vaules. + * Set by module parameters dataserver_timeo and dataserver_retrans. + */ +#define NFS4_DEF_DS_TIMEO 600 /* in tenths of a second */ +#define NFS4_DEF_DS_RETRANS 5 + +/* error codes for internal use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + enum { NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ -- cgit v1.1 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 +- 4 files changed, 41 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7d7c36f..7332ba1 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 333ae40..e134d65 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 8c1b437..52e2344 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 6af29c2..5c4394e 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, -- cgit v1.1 From 30626f9c32f0ad5e2c4173f10fb4b1358bbba6ec Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 30 May 2014 18:15:58 +0800 Subject: nfs41: allow LD to choose DS connection version/minor_version flexfile layout may need to set such when making DS connections. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayoutdev.c | 3 ++- fs/nfs/internal.h | 1 + fs/nfs/nfs4client.c | 4 ++-- fs/nfs/pnfs.h | 3 ++- fs/nfs/pnfs_nfs.c | 11 +++++++---- 5 files changed, 14 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 5e4b0ce..4f372e2 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -278,7 +278,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) goto out_test_devid; nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo, - dataserver_retrans, + dataserver_retrans, 4, + s->nfs_client->cl_minorversion, s->nfs_client->cl_rpcclient->cl_auth->au_flavor); out_test_devid: diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7332ba1..5543850 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -190,6 +190,7 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, + u32 minor_version, rpc_authflavor_t au_flavor); extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 62d93a1..102d967 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -850,14 +850,14 @@ error: struct nfs_client *nfs4_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) + u32 minor_version, rpc_authflavor_t au_flavor) { struct nfs_client_initdata cl_init = { .addr = ds_addr, .addrlen = ds_addrlen, .nfs_mod = &nfs_v4, .proto = ds_proto, - .minorversion = mds_clp->cl_minorversion, + .minorversion = minor_version, .net = mds_clp->cl_net, }; struct rpc_timeout ds_timeout; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index aef89b3..70ffec1 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -325,7 +325,8 @@ struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, - unsigned int retrans, rpc_authflavor_t au_flavor); + unsigned int retrans, u32 versoin, u32 minor_version, + rpc_authflavor_t au_flavor); struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 106ee08..ad211a4 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -554,6 +554,7 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, unsigned int timeo, unsigned int retrans, + u32 minor_version, rpc_authflavor_t au_flavor) { struct nfs_client *clp = ERR_PTR(-EIO); @@ -570,7 +571,8 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, clp = nfs4_set_ds_client(mds_srv->nfs_client, (struct sockaddr *)&da->da_addr, da->da_addrlen, IPPROTO_TCP, - timeo, retrans, au_flavor); + timeo, retrans, minor_version, + au_flavor); if (!IS_ERR(clp)) break; } @@ -601,13 +603,14 @@ out_put: */ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, - unsigned int retrans, rpc_authflavor_t au_flavor) + unsigned int retrans, u32 version, + u32 minor_version, rpc_authflavor_t au_flavor) { if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { int err = 0; - err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, - retrans, au_flavor); + err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, retrans, + minor_version, au_flavor); if (err) nfs4_mark_deviceid_unavailable(devid); nfs4_clear_ds_conn_bit(ds); -- cgit v1.1 From 5f01d9539496577b9ee62e213f4122a2a209550c Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 30 May 2014 18:15:59 +0800 Subject: nfs41: create NFSv3 DS connection if specified Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4super.c | 3 ++ fs/nfs/pnfs.h | 7 ++++- fs/nfs/pnfs_nfs.c | 88 +++++++++++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 93 insertions(+), 5 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 6f340f0..48cea3c 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -346,6 +346,9 @@ out: static void __exit exit_nfs_v4(void) { + /* Not called in the _init(), conditionally loaded */ + nfs4_pnfs_v3_ds_connect_unload(); + unregister_nfs_version(&nfs_v4); nfs4_unregister_sysctl(); nfs_idmap_quit(); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 70ffec1..c398821 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -323,9 +323,10 @@ void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags); +void nfs4_pnfs_v3_ds_connect_unload(void); void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_deviceid_node *devid, unsigned int timeo, - unsigned int retrans, u32 versoin, u32 minor_version, + unsigned int retrans, u32 version, u32 minor_version, rpc_authflavor_t au_flavor); struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, @@ -615,6 +616,10 @@ static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) return NULL; } +static inline void nfs4_pnfs_v3_ds_connect_unload(void) +{ +} + #endif /* CONFIG_NFS_V4_1 */ #endif /* FS_NFS_PNFS_H */ diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index ad211a4..23c851d 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "nfs4session.h" #include "internal.h" @@ -550,7 +551,75 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING); } -static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, +static struct nfs_client *(*get_v3_ds_connect)( + 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); + +static bool load_v3_ds_connect(void) +{ + if (!get_v3_ds_connect) { + get_v3_ds_connect = symbol_request(nfs3_set_ds_client); + WARN_ON_ONCE(!get_v3_ds_connect); + } + + return(get_v3_ds_connect != NULL); +} + +void __exit nfs4_pnfs_v3_ds_connect_unload(void) +{ + if (get_v3_ds_connect) { + symbol_put(nfs3_set_ds_client); + get_v3_ds_connect = NULL; + } +} +EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload); + +static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, + struct nfs4_pnfs_ds *ds, + unsigned int timeo, + unsigned int retrans, + rpc_authflavor_t au_flavor) +{ + struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs4_pnfs_ds_addr *da; + int status = 0; + + dprintk("--> %s DS %s au_flavor %d\n", __func__, + ds->ds_remotestr, au_flavor); + + if (!load_v3_ds_connect()) + goto out; + + list_for_each_entry(da, &ds->ds_addrs, da_node) { + dprintk("%s: DS %s: trying address %s\n", + __func__, ds->ds_remotestr, da->da_remotestr); + + clp = get_v3_ds_connect(mds_srv->nfs_client, + (struct sockaddr *)&da->da_addr, + da->da_addrlen, IPPROTO_TCP, + timeo, retrans, au_flavor); + if (!IS_ERR(clp)) + break; + } + + if (IS_ERR(clp)) { + status = PTR_ERR(clp); + goto out; + } + + smp_wmb(); + ds->ds_clp = clp; + dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); +out: + return status; +} + +static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, unsigned int timeo, unsigned int retrans, @@ -562,7 +631,7 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, int status = 0; dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr, - mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor); + au_flavor); list_for_each_entry(da, &ds->ds_addrs, da_node) { dprintk("%s: DS %s: trying address %s\n", @@ -609,8 +678,19 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { int err = 0; - err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, retrans, - minor_version, au_flavor); + if (version == 3) { + err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo, + retrans, au_flavor); + } else if (version == 4) { + err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo, + retrans, minor_version, + au_flavor); + } else { + dprintk("%s: unsupported DS version %d\n", __func__, + version); + err = -EPROTONOSUPPORT; + } + if (err) nfs4_mark_deviceid_unavailable(devid); nfs4_clear_ds_conn_bit(ds); -- cgit v1.1 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 +++--- 5 files changed, 12 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index bc36ed3..25c4896 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 5543850..1d15ffa 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 2b5e769..35a2626 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 c91a479..092ab49 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 af3af68..54d4857 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); } -- cgit v1.1 From c36aae9ad95afa2f9a9e9109d989c21af221fabd Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 9 Jun 2014 07:10:14 +0800 Subject: nfs: allow different protocol in nfs_initiate_commit pnfs flexfile layout client may want to use NFSv3 ops rather than the default MDS v4 ops. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayout.c | 2 +- fs/nfs/internal.h | 1 + fs/nfs/pnfs_nfs.c | 1 + fs/nfs/write.c | 7 ++++--- 4 files changed, 7 insertions(+), 4 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 25c4896..e5a3c5b 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -1055,7 +1055,7 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); if (fh) data->args.fh = fh; - return nfs_initiate_commit(ds_clnt, data, + return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode), &filelayout_commit_call_ops, how, RPC_TASK_SOFTCONN); out_err: diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 1d15ffa..98dee83 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -436,6 +436,7 @@ extern void nfs_write_prepare(struct rpc_task *task, void *calldata); extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); extern int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, + const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags); extern void nfs_init_commit(struct nfs_commit_data *data, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 23c851d..c87f664 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -278,6 +278,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, if (!data->lseg) { nfs_init_commit(data, mds_pages, NULL, cinfo); nfs_initiate_commit(NFS_CLIENT(inode), data, + NFS_PROTO(data->inode), data->mds_ops, how, 0); } else { struct pnfs_commit_bucket *buckets; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 54d4857..8800bd3 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1465,6 +1465,7 @@ void nfs_commitdata_release(struct nfs_commit_data *data) EXPORT_SYMBOL_GPL(nfs_commitdata_release); int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, + const struct nfs_rpc_ops *nfs_ops, const struct rpc_call_ops *call_ops, int how, int flags) { @@ -1486,7 +1487,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, .priority = priority, }; /* Set up the initial task struct. */ - NFS_PROTO(data->inode)->commit_setup(data, &msg); + nfs_ops->commit_setup(data, &msg); dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid); @@ -1589,8 +1590,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, /* Set up the argument struct */ nfs_init_commit(data, head, NULL, cinfo); atomic_inc(&cinfo->mds->rpcs_out); - return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, - how, 0); + return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), + data->mds_ops, how, 0); out_bad: nfs_retry_commit(head, NULL, cinfo); cinfo->completion_ops->error_cleanup(NFS_I(inode)); -- cgit v1.1 From cb04ad2a2bc8978e69f7f582ca2869909c4e0571 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 11 Jun 2014 05:24:15 +0800 Subject: nfs4: pass slot table to nfs40_setup_sequence flexclient needs this as there is no nfs_server to DS connection. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4_fs.h | 4 ++++ fs/nfs/nfs4proc.c | 24 +++++++++++++----------- 2 files changed, 17 insertions(+), 11 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index a081787..90c4ffe 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -443,6 +443,10 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid); extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid); extern void nfs_release_seqid(struct nfs_seqid *seqid); extern void nfs_free_seqid(struct nfs_seqid *seqid); +extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task); extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c347705..e98dda7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -495,12 +495,11 @@ static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args) args->sa_privileged = 1; } -static int nfs40_setup_sequence(const struct nfs_server *server, - struct nfs4_sequence_args *args, - struct nfs4_sequence_res *res, - struct rpc_task *task) +int nfs40_setup_sequence(struct nfs4_slot_table *tbl, + struct nfs4_sequence_args *args, + struct nfs4_sequence_res *res, + struct rpc_task *task) { - struct nfs4_slot_table *tbl = server->nfs_client->cl_slot_tbl; struct nfs4_slot *slot; /* slot already allocated? */ @@ -535,6 +534,7 @@ out_sleep: spin_unlock(&tbl->slot_tbl_lock); return -EAGAIN; } +EXPORT_SYMBOL_GPL(nfs40_setup_sequence); static int nfs40_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) @@ -777,7 +777,8 @@ static int nfs4_setup_sequence(const struct nfs_server *server, int ret = 0; if (!session) - return nfs40_setup_sequence(server, args, res, task); + return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl, + args, res, task); dprintk("--> %s clp %p session %p sr_slot %u\n", __func__, session->clp, session, res->sr_slot ? @@ -818,7 +819,8 @@ static int nfs4_setup_sequence(const struct nfs_server *server, struct nfs4_sequence_res *res, struct rpc_task *task) { - return nfs40_setup_sequence(server, args, res, task); + return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl, + args, res, task); } static int nfs4_sequence_done(struct rpc_task *task, @@ -1679,8 +1681,8 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata) { struct nfs4_opendata *data = calldata; - nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args, - &data->c_res.seq_res, task); + nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl, + &data->c_arg.seq_args, &data->c_res.seq_res, task); } static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) @@ -5974,8 +5976,8 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata { struct nfs_release_lockowner_data *data = calldata; struct nfs_server *server = data->server; - nfs40_setup_sequence(server, &data->args.seq_args, - &data->res.seq_res, task); + nfs40_setup_sequence(server->nfs_client->cl_slot_tbl, + &data->args.seq_args, &data->res.seq_res, task); data->args.lock_owner.clientid = server->nfs_client->cl_clientid; data->timestamp = jiffies; } -- cgit v1.1 From 2c4b131dea469e4df5bd59ccb490063b69e06155 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 11 Jun 2014 05:24:16 +0800 Subject: nfs4: export nfs4_sequence_done Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4_fs.h | 2 ++ fs/nfs/nfs4proc.c | 9 +++++---- 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 90c4ffe..b3c771e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -447,6 +447,8 @@ extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl, struct nfs4_sequence_args *args, struct nfs4_sequence_res *res, struct rpc_task *task); +extern int nfs4_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res); extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e98dda7..f358262 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -694,8 +694,7 @@ out_retry: } EXPORT_SYMBOL_GPL(nfs41_sequence_done); -static int nfs4_sequence_done(struct rpc_task *task, - struct nfs4_sequence_res *res) +int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) { if (res->sr_slot == NULL) return 1; @@ -703,6 +702,7 @@ static int nfs4_sequence_done(struct rpc_task *task, return nfs40_sequence_done(task, res); return nfs41_sequence_done(task, res); } +EXPORT_SYMBOL_GPL(nfs4_sequence_done); int nfs41_setup_sequence(struct nfs4_session *session, struct nfs4_sequence_args *args, @@ -823,11 +823,12 @@ static int nfs4_setup_sequence(const struct nfs_server *server, args, res, task); } -static int nfs4_sequence_done(struct rpc_task *task, - struct nfs4_sequence_res *res) +int nfs4_sequence_done(struct rpc_task *task, + struct nfs4_sequence_res *res) { return nfs40_sequence_done(task, res); } +EXPORT_SYMBOL_GPL(nfs4_sequence_done); #endif /* !CONFIG_NFS_V4_1 */ -- cgit v1.1 From 46a5ab4754cad6aeefd96feae8ba65db8655e1af Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 13 Jun 2014 23:02:25 +0800 Subject: nfs: allow to specify cred in nfs_initiate_pgio so that flexfile layout client can pass in DS credential instead of using user cred, which will be done in the next patch. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/filelayout/filelayout.c | 11 ++++++----- fs/nfs/internal.h | 6 +++--- fs/nfs/pagelist.c | 8 +++++--- 3 files changed, 14 insertions(+), 11 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index e5a3c5b..bfa8547 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -501,8 +501,9 @@ 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_PROTO(hdr->inode), - &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN); + nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, + NFS_PROTO(hdr->inode), &filelayout_read_call_ops, + 0, RPC_TASK_SOFTCONN); return PNFS_ATTEMPTED; } @@ -542,9 +543,9 @@ 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_PROTO(hdr->inode), - &filelayout_write_call_ops, sync, - RPC_TASK_SOFTCONN); + nfs_initiate_pgio(ds_clnt, hdr, hdr->cred, + 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 98dee83..e9305e9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -250,9 +250,9 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); 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); +int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, + struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, + const struct rpc_call_ops *call_ops, int how, int flags); void nfs_free_request(struct nfs_page *req); static inline void nfs_iocounter_init(struct nfs_io_counter *c) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 35a2626..c4d1758 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -597,14 +597,14 @@ 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, + struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags) { struct rpc_task *task; struct rpc_message msg = { .rpc_argp = &hdr->args, .rpc_resp = &hdr->res, - .rpc_cred = hdr->cred, + .rpc_cred = cred, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, @@ -793,7 +793,9 @@ 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, NFS_PROTO(hdr->inode), + hdr, + hdr->cred, + NFS_PROTO(hdr->inode), desc->pg_rpc_callops, desc->pg_ioflags, 0); return ret; -- cgit v1.1 From 16cecdf620eb23d2654a265d9b20e089370d7425 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 22 Jun 2014 12:55:11 -0400 Subject: NFSv4.1/NFSv3: Add pNFS callbacks for nfs3_(read|write|commit)_done() Enable pNFS callbacks to allow flex files to work correctly with a NFSv3-enabled data server. Signed-off-by: Trond Myklebust --- fs/nfs/nfs3proc.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 524f9f8..78e557c 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -800,6 +800,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { struct inode *inode = hdr->inode; + if (hdr->pgio_done_cb != NULL) + return hdr->pgio_done_cb(task, hdr); + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; @@ -825,6 +828,9 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { struct inode *inode = hdr->inode; + if (hdr->pgio_done_cb != NULL) + return hdr->pgio_done_cb(task, hdr); + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; if (task->tk_status >= 0) @@ -845,6 +851,9 @@ static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commi static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data) { + if (data->commit_done_cb != NULL) + return data->commit_done_cb(task, data); + if (nfs3_async_handle_jukebox(task, data->inode)) return -EAGAIN; nfs_refresh_inode(data->inode, data->res.fattr); -- cgit v1.1 From 36d3e3dcc93f1d3f70916ace76d94267b8948a2a Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Tue, 8 Jul 2014 06:21:10 +0800 Subject: nfs: set hostname when creating nfsv3 ds connection lockd assumes hostname exists otherwise kernel oops. It can be reproduced by following steps: 1. mount flexfile MDS 2. write some files 3. mount DS via nfsv3 BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] strlen+0x2/0x20 PGD 0 Oops: 0000 [#1] SMP Modules linked in: nfsd(F) nfs_layout_flexfiles(F) rpcsec_gss_krb5(F) auth_rpcgss(F) nfsv4(F) dns_resolver(F) nfsv3(F) nfs_acl(F) nfs(F) lockd(F) sunrpc(F) fscache(F) ebtable_nat(F) nf_conntrack_netbios_ns(F) nf_conntrack_broadcast(F) ipt_MASQUERADE(F) ip6table_nat(F) nf_nat_ipv6(F) ip6table_mangle(F) ip6t_REJECT(F) nf_conntrack_ipv6(F) nf_defrag_ipv6(F) iptable_nat(F) nf_nat_ipv4(F) nf_nat(F) iptable_mangle(F) nf_conntrack_ipv4(F) nf_defrag_ipv4(F) xt_conntrack(F) nf_conntrack(F) ebtable_filter(F) ebtables(F) ip6table_filter(F) ip6_tables(F) bnep(F) snd_ens1371(F) snd_rawmidi(F) snd_ac97_codec(F) btusb(F) ac97_bus(F) snd_seq(F) snd_seq_device(F) snd_pcm(F) ppdev(F) bluetooth(F) 6lowpan_iphc(F) rfkill(F) vmw_balloon(F) snd_timer(F) snd(F) soundcore(F) gameport(F) i2c_piix4(F) e1000(F) vmw_vmci(F) parport_pc(F) parport(F) shpchp(F) uinput(F) xfs(F) libcrc32c(F) vmwgfx(F) ttm(F) drm(F) mptspi(F) scsi_transport_spi(F) mptscsih(F) mptbase(F) i2c_core(F) CPU: 0 PID: 10397 Comm: mount.nfs Tainted: GF 3.14.7-100.pd_client.001.fc16.x86_64 #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff880008942600 ti: ffff880007990000 task.ti: ffff880007990000 RIP: 0010:[] [] strlen+0x2/0x20 RSP: 0018:ffff880007991aa0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880038d39c20 RCX: 0000000000000004 RDX: 0000000000000006 RSI: 0000000000000010 RDI: 0000000000000000 RBP: ffff880007991b38 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000014600 R11: 0000000000000400 R12: ffffffff81cc8580 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000004 FS: 00007f90cd2ef880(0000) GS:ffff88003f600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000001710000 CR4: 00000000001407f0 Stack: ffffffffa045f52c ffff880001782230 ffff880004141e28 0006880007991ac8 ffffffff816dc14b ffff880000000000 ffff880038d39c20 0000000000000010 0000000481cc0006 0000000000000000 ffffffffa0410be8 000000000000c014 Call Trace: [] ? nlmclnt_lookup_host+0x4c/0x2c0 [lockd] [] ? _raw_spin_unlock_bh+0x1b/0x20 [] ? svc_destroy+0xb8/0x140 [sunrpc] [] nlmclnt_init+0x53/0xc0 [lockd] [] ? nfs_get_client+0x1cc/0x340 [nfs] [] nfs_start_lockd+0xa7/0xd0 [nfs] [] nfs_create_server+0x181/0x5c0 [nfs] [] nfs3_create_server+0x13/0x30 [nfsv3] [] nfs_try_mount+0x21c/0x300 [nfs] [] ? __kmalloc_track_caller+0x1ad/0x240 [] ? nfs_fs_mount+0xc37/0xd80 [nfs] [] nfs_fs_mount+0x2c5/0xd80 [nfs] [] ? nfs_clone_super+0x140/0x140 [nfs] [] ? nfs_clone_sb_security+0x40/0x40 [nfs] [] mount_fs+0x43/0x1b0 [] ? __alloc_percpu+0x10/0x20 [] vfs_kern_mount+0x76/0x120 [] do_mount+0x237/0xa80 Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/nfs3client.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 52e2344..9e9fa34 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -1,5 +1,6 @@ #include #include +#include #include "internal.h" #include "nfs3_fs.h" @@ -89,6 +90,12 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp, }; struct rpc_timeout ds_timeout; struct nfs_client *clp; + char buf[INET6_ADDRSTRLEN + 1]; + + /* fake a hostname because lockd wants it */ + if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + return ERR_PTR(-EINVAL); + cl_init.hostname = buf; /* Use the MDS nfs_client cl_ipaddr. */ nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); -- cgit v1.1 From 72cff4494ea981202c8db6fd18940c8506f14db4 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 7 Aug 2014 10:12:38 +0800 Subject: nfs/flexclient: export pnfs_layoutcommit_inode flexfiles needs to start layoutcommit when necessary Signed-off-by: Peng Tao --- fs/nfs/pnfs.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0a5dda4..2d25670 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1966,6 +1966,7 @@ clear_layoutcommitting: pnfs_clear_layoutcommitting(inode); goto out; } +EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode); struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) { -- cgit v1.1 From abb9a0079c7f06360b83a5dd27ce74b8dc6d01b6 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 22 Aug 2014 17:37:40 +0800 Subject: nfs41: close a small race window when adding new layout to global list Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 2d25670..fa00b56 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1288,7 +1288,6 @@ pnfs_update_layout(struct inode *ino, struct nfs_client *clp = server->nfs_client; struct pnfs_layout_hdr *lo; struct pnfs_layout_segment *lseg = NULL; - bool first; if (!pnfs_enabled_sb(NFS_SERVER(ino))) goto out; @@ -1321,16 +1320,15 @@ pnfs_update_layout(struct inode *ino, if (pnfs_layoutgets_blocked(lo, 0)) goto out_unlock; atomic_inc(&lo->plh_outstanding); - - first = list_empty(&lo->plh_layouts) ? true : false; spin_unlock(&ino->i_lock); - if (first) { + if (list_empty(&lo->plh_layouts)) { /* The lo must be on the clp list if there is any * chance of a CB_LAYOUTRECALL(FILE) coming in. */ spin_lock(&clp->cl_lock); - list_add_tail(&lo->plh_layouts, &server->layouts); + if (list_empty(&lo->plh_layouts)) + list_add_tail(&lo->plh_layouts, &server->layouts); spin_unlock(&clp->cl_lock); } -- cgit v1.1 From 9bf87482ddc6f8db884177a2a16b1a1dc12f8777 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 22 Aug 2014 17:37:41 +0800 Subject: nfs41: serialize first layoutget of a file Per RFC 5661 Errata 3208: | A client MAY always forget its layout state and associated | layout stateid at any time (See also section 12.5.5.1). | In such case, the client MUST use a non-layout stateid for the next | LAYOUTGET operation. This will signal the server that the client has | no more layouts on the file and its respective layout state can be | released before issuing a new layout in response to LAYOUTGET. In order to make such a signal unique to server, client needs to serialize all layoutgets using non-layout stateid. We implement this by serializing layoutgets when client has no layout segments at hand. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 35 +++++++++++++++++++++++++++++++---- fs/nfs/pnfs.h | 1 + 2 files changed, 32 insertions(+), 4 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index fa00b56..7e1bac1 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1288,6 +1288,7 @@ pnfs_update_layout(struct inode *ino, struct nfs_client *clp = server->nfs_client; struct pnfs_layout_hdr *lo; struct pnfs_layout_segment *lseg = NULL; + bool first; if (!pnfs_enabled_sb(NFS_SERVER(ino))) goto out; @@ -1295,6 +1296,8 @@ pnfs_update_layout(struct inode *ino, if (pnfs_within_mdsthreshold(ctx, ino, iomode)) goto out; +lookup_again: + first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { @@ -1312,10 +1315,27 @@ pnfs_update_layout(struct inode *ino, if (pnfs_layout_io_test_failed(lo, iomode)) goto out_unlock; - /* Check to see if the layout for the given range already exists */ - lseg = pnfs_find_lseg(lo, &arg); - if (lseg) - goto out_unlock; + first = list_empty(&lo->plh_segs); + if (first) { + /* The first layoutget for the file. Need to serialize per + * RFC 5661 Errata 3208. + */ + if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET, + &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto lookup_again; + } + } else { + /* Check to see if the layout for the given range + * already exists + */ + lseg = pnfs_find_lseg(lo, &arg); + if (lseg) + goto out_unlock; + } if (pnfs_layoutgets_blocked(lo, 0)) goto out_unlock; @@ -1343,6 +1363,13 @@ pnfs_update_layout(struct inode *ino, lseg = send_layoutget(lo, ctx, &arg, gfp_flags); 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); + } 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 c398821..4cf0d54 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -95,6 +95,7 @@ enum { NFS_LAYOUT_ROC, /* some lseg had roc bit set */ NFS_LAYOUT_RETURN, /* Return this layout ASAP */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ + NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ }; enum layoutdriver_policy_flags { -- cgit v1.1 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 +++ 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 5f61b83..b4e03ed 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 8f4cbe7..2a932fd 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 cb4376b..7d8d7a4 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); -- cgit v1.1 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 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7d8d7a4..3c3ff63 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 7e1bac1..1b544c1 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; -- cgit v1.1 From f40eb5d044e2eea3f866eeeeb45ca30753773cda Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:22 +0800 Subject: nfs41: make a helper function to send layoutreturn It allows to specify different iomode to return. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 53 +++++++++++++++++++++++++++++++++-------------------- 1 file changed, 33 insertions(+), 20 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 1b544c1..1b97209 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -845,6 +845,38 @@ static void pnfs_clear_layoutcommit(struct inode *inode, } } +static int +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, + enum pnfs_iomode iomode) +{ + struct inode *ino = lo->plh_inode; + struct nfs4_layoutreturn *lrp; + int status = 0; + + lrp = kzalloc(sizeof(*lrp), GFP_KERNEL); + if (unlikely(lrp == NULL)) { + status = -ENOMEM; + spin_lock(&ino->i_lock); + lo->plh_block_lgets--; + spin_unlock(&ino->i_lock); + pnfs_put_layout_hdr(lo); + goto out; + } + + 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.layout = lo; + lrp->clp = NFS_SERVER(ino)->nfs_client; + lrp->cred = lo->plh_lc_cred; + + status = nfs4_proc_layoutreturn(lrp); +out: + dprintk("<-- %s status: %d\n", __func__, status); + return status; +} + /* * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr * when the layout segment list is empty. @@ -859,7 +891,6 @@ _pnfs_return_layout(struct inode *ino) struct pnfs_layout_hdr *lo = NULL; struct nfs_inode *nfsi = NFS_I(ino); LIST_HEAD(tmp_list); - struct nfs4_layoutreturn *lrp; nfs4_stateid stateid; int status = 0, empty; @@ -901,25 +932,7 @@ _pnfs_return_layout(struct inode *ino) spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); - lrp = kzalloc(sizeof(*lrp), GFP_KERNEL); - if (unlikely(lrp == NULL)) { - status = -ENOMEM; - spin_lock(&ino->i_lock); - lo->plh_block_lgets--; - spin_unlock(&ino->i_lock); - pnfs_put_layout_hdr(lo); - goto out; - } - - 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; - - status = nfs4_proc_layoutreturn(lrp); + status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY); out: dprintk("<-- %s status: %d\n", __func__, status); return status; -- cgit v1.1 From 016256df3a7e9eeb3f4dea5ccd0e21a0b63841eb Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:23 +0800 Subject: nfs41: add a helper to mark layout for return It marks all matching layout segments as NFS_LSEG_LAYOUTRETURN, which is an indicator for pnfs_put_lseg() to send layoutreturn, and also prevents pnfs_update_layout() from using the returning segments. Once it is set, it never gets cleared. It also sets proper io failure bit so that pnfs path can be retried after PNFS_LAYOUTGET_RETRY_TIMEOUT second. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/pnfs.h | 4 ++++ 2 files changed, 59 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 1b97209..0bd149b 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1479,6 +1479,61 @@ out_forget_reply: goto out; } +static void +pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, + struct list_head *tmp_list, + struct pnfs_layout_range *return_range) +{ + struct pnfs_layout_segment *lseg, *next; + + dprintk("%s:Begin lo %p\n", __func__, lo); + + if (list_empty(&lo->plh_segs)) + return; + + list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) + if (should_free_lseg(&lseg->pls_range, return_range)) { + dprintk("%s: marking lseg %p iomode %d " + "offset %llu length %llu\n", __func__, + lseg, lseg->pls_range.iomode, + lseg->pls_range.offset, + lseg->pls_range.length); + set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); + mark_lseg_invalid(lseg, tmp_list); + } +} + +void pnfs_error_mark_layout_for_return(struct inode *inode, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_hdr *lo = NFS_I(inode)->layout; + int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode); + struct pnfs_layout_range range = { + .iomode = lseg->pls_range.iomode, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + LIST_HEAD(free_me); + + spin_lock(&inode->i_lock); + /* set failure bit so that pnfs path will be retried later */ + pnfs_layout_set_fail_bit(lo, iomode); + set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); + if (lo->plh_return_iomode == 0) + lo->plh_return_iomode = range.iomode; + else if (lo->plh_return_iomode != range.iomode) + lo->plh_return_iomode = IOMODE_ANY; + /* + * mark all matching lsegs so that we are sure to have no live + * segments at hand when sending layoutreturn. See pnfs_put_lseg() + * for how it works. + */ + pnfs_mark_matching_lsegs_return(lo, &free_me, &range); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&free_me); +} +EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return); + void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 4cf0d54..bea2030 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -38,6 +38,7 @@ enum { NFS_LSEG_VALID = 0, /* cleared when lseg is recalled/returned */ NFS_LSEG_ROC, /* roc bit received from server */ NFS_LSEG_LAYOUTCOMMIT, /* layoutcommit bit set for layoutcommit */ + NFS_LSEG_LAYOUTRETURN, /* layoutreturn bit set for layoutreturn */ }; /* Individual ip address */ @@ -184,6 +185,7 @@ struct pnfs_layout_hdr { u32 plh_barrier; /* ignore lower seqids */ unsigned long plh_retry_timestamp; unsigned long plh_flags; + enum pnfs_iomode plh_return_iomode; loff_t plh_lwb; /* last write byte for layoutcommit */ struct rpc_cred *plh_lc_cred; /* layoutcommit cred */ struct inode *plh_inode; @@ -274,6 +276,8 @@ void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp); int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *); int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *); struct nfs4_threshold *pnfs_mdsthreshold_alloc(void); +void pnfs_error_mark_layout_for_return(struct inode *inode, + struct pnfs_layout_segment *lseg); /* nfs4_deviceid_flags */ enum { -- cgit v1.1 From ce6ab4f238cb76d356229e97e1fefb7192388e13 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:24 +0800 Subject: nfs41: don't use a layout if it is marked for returning And if we are to return the same type of layouts, don't bother sending more layoutgets. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4proc.c | 1 + fs/nfs/pnfs.c | 23 ++++++++++++++++++----- fs/nfs/pnfs.h | 1 + 3 files changed, 20 insertions(+), 5 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f358262..1943284 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7540,6 +7540,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) return; if (pnfs_choose_layoutget_stateid(&lgp->args.stateid, NFS_I(lgp->args.inode)->layout, + &lgp->args.range, lgp->args.ctx->state)) { rpc_exit(task, NFS4_OK); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0bd149b..853b544 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -740,25 +740,37 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo, return !pnfs_seqid_is_newer(seqid, lo->plh_barrier); } +static bool +pnfs_layout_returning(const struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range) +{ + return test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) && + (lo->plh_return_iomode == IOMODE_ANY || + lo->plh_return_iomode == range->iomode); +} + /* lget is set to 1 if called from inside send_layoutget call chain */ static bool -pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, int lget) +pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range, int lget) { return lo->plh_block_lgets || test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || (list_empty(&lo->plh_segs) && - (atomic_read(&lo->plh_outstanding) > lget)); + (atomic_read(&lo->plh_outstanding) > lget)) || + pnfs_layout_returning(lo, range); } int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range, struct nfs4_state *open_state) { int status = 0; dprintk("--> %s\n", __func__); spin_lock(&lo->plh_inode->i_lock); - if (pnfs_layoutgets_blocked(lo, 1)) { + if (pnfs_layoutgets_blocked(lo, range, 1)) { status = -EAGAIN; } else if (!nfs4_valid_open_stateid(open_state)) { status = -EBADF; @@ -1192,6 +1204,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, list_for_each_entry(lseg, &lo->plh_segs, pls_list) { if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) && + !test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) && pnfs_lseg_range_match(&lseg->pls_range, range)) { ret = pnfs_get_lseg(lseg); break; @@ -1351,7 +1364,7 @@ lookup_again: goto out_unlock; } - if (pnfs_layoutgets_blocked(lo, 0)) + if (pnfs_layoutgets_blocked(lo, &arg, 0)) goto out_unlock; atomic_inc(&lo->plh_outstanding); spin_unlock(&ino->i_lock); @@ -1432,7 +1445,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp) goto out_forget_reply; } - if (pnfs_layoutgets_blocked(lo, 1)) { + if (pnfs_layoutgets_blocked(lo, &lgp->args.range, 1)) { dprintk("%s forget reply due to state\n", __func__); goto out_forget_reply; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index bea2030..9e6edd1 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -249,6 +249,7 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, bool update_barrier); int pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range, struct nfs4_state *open_state); int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, -- cgit v1.1 From aa1e0e3a8e3f16ff50a72a8c623d7e1c467383bc Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:25 +0800 Subject: nfs41: send layoutreturn in last put_lseg If current lseg is the last lseg marked with NFS_LSEG_LAYOUTRETURN, send layoutreturn. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 853b544..e9acfcf 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -50,6 +50,10 @@ static DEFINE_SPINLOCK(pnfs_spinlock); */ static LIST_HEAD(pnfs_modules_tbl); +static int +pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, + enum pnfs_iomode iomode); + /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * find_pnfs_driver_locked(u32 id) @@ -337,6 +341,29 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } +/* Return true if layoutreturn is needed */ +static bool +pnfs_layout_need_return(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg, + nfs4_stateid *stateid, enum pnfs_iomode *iomode) +{ + struct pnfs_layout_segment *s; + + if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + return false; + + list_for_each_entry(s, &lo->plh_segs, pls_list) + if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + return false; + + *stateid = lo->plh_stateid; + *iomode = lo->plh_return_iomode; + /* decreased in pnfs_send_layoutreturn() */ + lo->plh_block_lgets++; + lo->plh_return_iomode = 0; + return true; +} + void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -352,11 +379,20 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) lo = lseg->pls_layout; inode = lo->plh_inode; if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { + bool need_return; + nfs4_stateid stateid; + enum pnfs_iomode iomode; + pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); + need_return = pnfs_layout_need_return(lo, lseg, + &stateid, &iomode); spin_unlock(&inode->i_lock); pnfs_free_lseg(lseg); - pnfs_put_layout_hdr(lo); + if (need_return) + pnfs_send_layoutreturn(lo, stateid, iomode); + else + pnfs_put_layout_hdr(lo); } } EXPORT_SYMBOL_GPL(pnfs_put_lseg); -- cgit v1.1 From e736a5b98c7aa98fe572990caf5fed9593c72a67 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:26 +0800 Subject: nfs41: clear NFS_LAYOUT_RETURN if layoutreturn is sent or failed to send So that pnfs path is not disabled for ever. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4proc.c | 1 + fs/nfs/pnfs.c | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1943284..e19b5db 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7796,6 +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(NFS_LAYOUT_RETURN, &lo->plh_flags); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_put_layout_hdr(lrp->args.layout); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index e9acfcf..63992c8 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -921,6 +921,11 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, status = nfs4_proc_layoutreturn(lrp); out: + if (status) { + spin_lock(&ino->i_lock); + clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); + spin_unlock(&ino->i_lock); + } dprintk("<-- %s status: %d\n", __func__, status); return status; } -- cgit v1.1 From c220106fb45909719295474e2497ffe03e47dfb3 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:29 +0800 Subject: nfs/filelayout: use pnfs_error_mark_layout_for_return Instead of calling layoutreturn directly, call pnfs_error_mark_layout_for_return to mark layouts for return and let generic code return layout when layout segments are freed. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes Conflicts: fs/nfs/filelayout/filelayout.c --- fs/nfs/filelayout/filelayout.c | 2 +- fs/nfs/pnfs_nfs.c | 10 ---------- 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index bfa8547..5d2eadc 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -200,7 +200,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, dprintk("%s DS connection error %d\n", __func__, task->tk_status); nfs4_mark_deviceid_unavailable(devid); - set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); + pnfs_error_mark_layout_for_return(inode, lseg); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index c87f664..55bff41 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -18,20 +18,10 @@ #define NFSDBG_FACILITY NFSDBG_PNFS -static void pnfs_generic_fenceme(struct inode *inode, - struct pnfs_layout_hdr *lo) -{ - if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) - return; - pnfs_return_layout(inode); -} - void pnfs_generic_rw_release(void *data) { struct nfs_pgio_header *hdr = data; - struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout; - pnfs_generic_fenceme(lo->plh_inode, lo); nfs_put_client(hdr->ds_clp); hdr->mds_ops->rpc_release(data); } -- cgit v1.1 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 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index c4d1758..1c03187 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); } /** -- cgit v1.1 From 180bb5ec06ce3a95dccc751fbf6bf11d3003da98 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 10 Sep 2014 15:48:01 -0400 Subject: pnfs: release lseg in pnfs_generic_pg_cleanup This is needed to support mirrored writes - the first write can't just trash the lseg, we need to keep it around until all mirrors have written. Signed-off-by: Weston Andros Adamson --- fs/nfs/blocklayout/blocklayout.c | 2 ++ fs/nfs/filelayout/filelayout.c | 2 ++ fs/nfs/objlayout/objio_osd.c | 2 ++ fs/nfs/pnfs.c | 32 ++++++++++++++------------------ fs/nfs/pnfs.h | 1 + 5 files changed, 21 insertions(+), 18 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 77fec6a..1cac3c1 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -860,12 +860,14 @@ static const struct nfs_pageio_ops bl_pg_read_ops = { .pg_init = bl_pg_init_read, .pg_test = bl_pg_test_read, .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, }; static const struct nfs_pageio_ops bl_pg_write_ops = { .pg_init = bl_pg_init_write, .pg_test = bl_pg_test_write, .pg_doio = pnfs_generic_pg_writepages, + .pg_cleanup = pnfs_generic_pg_cleanup, }; static struct pnfs_layoutdriver_type blocklayout_type = { diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 5d2eadc..2af32fc 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -933,12 +933,14 @@ static const struct nfs_pageio_ops filelayout_pg_read_ops = { .pg_init = filelayout_pg_init_read, .pg_test = filelayout_pg_test, .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, }; static const struct nfs_pageio_ops filelayout_pg_write_ops = { .pg_init = filelayout_pg_init_write, .pg_test = filelayout_pg_test, .pg_doio = pnfs_generic_pg_writepages, + .pg_cleanup = pnfs_generic_pg_cleanup, }; static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 9e5bc42..d007780 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -607,12 +607,14 @@ static const struct nfs_pageio_ops objio_pg_read_ops = { .pg_init = objio_init_read, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_readpages, + .pg_cleanup = pnfs_generic_pg_cleanup, }; static const struct nfs_pageio_ops objio_pg_write_ops = { .pg_init = objio_init_write, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_writepages, + .pg_cleanup = pnfs_generic_pg_cleanup, }; static struct pnfs_layoutdriver_type objlayout_type = { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 63992c8..2da2e77 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1631,6 +1631,16 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, } EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); +void +pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *desc) +{ + if (desc->pg_lseg) { + pnfs_put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + } +} +EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup); + /* * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number * of bytes (maximum @req->wb_bytes) that can be coalesced. @@ -1756,11 +1766,9 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc, struct pnfs_layout_segment *lseg = desc->pg_lseg; enum pnfs_try_status trypnfs; - desc->pg_lseg = NULL; trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how); if (trypnfs == PNFS_NOT_ATTEMPTED) pnfs_write_through_mds(desc, hdr); - pnfs_put_lseg(lseg); } static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) @@ -1779,17 +1787,13 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { desc->pg_completion_ops->error_cleanup(&desc->pg_list); - pnfs_put_lseg(desc->pg_lseg); - desc->pg_lseg = NULL; return -ENOMEM; } nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); + hdr->lseg = pnfs_get_lseg(desc->pg_lseg); ret = nfs_generic_pgio(desc, hdr); - if (ret != 0) { - pnfs_put_lseg(desc->pg_lseg); - desc->pg_lseg = NULL; - } else + if (!ret) pnfs_do_write(desc, hdr, desc->pg_ioflags); return ret; } @@ -1874,11 +1878,9 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) struct pnfs_layout_segment *lseg = desc->pg_lseg; enum pnfs_try_status trypnfs; - desc->pg_lseg = NULL; trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg); if (trypnfs == PNFS_NOT_ATTEMPTED) pnfs_read_through_mds(desc, hdr); - pnfs_put_lseg(lseg); } static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) @@ -1897,18 +1899,12 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { desc->pg_completion_ops->error_cleanup(&desc->pg_list); - ret = -ENOMEM; - pnfs_put_lseg(desc->pg_lseg); - desc->pg_lseg = NULL; - return ret; + return -ENOMEM; } nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); hdr->lseg = pnfs_get_lseg(desc->pg_lseg); ret = nfs_generic_pgio(desc, hdr); - if (ret != 0) { - pnfs_put_lseg(desc->pg_lseg); - desc->pg_lseg = NULL; - } else + if (!ret) pnfs_do_read(desc, hdr); return ret; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9e6edd1..59c831e 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -230,6 +230,7 @@ void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page * int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc); void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size); +void pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc); size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req); -- cgit v1.1 From 309a1d65b11de24d172f7dbbc21583ebd649c912 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 5 Sep 2014 16:34:29 -0400 Subject: nfs: handle overlapping reqs in lock_and_join This is needed for mirrored DS support, where multuple requests cover the same range. Signed-off-by: Weston Andros Adamson --- fs/nfs/write.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 8800bd3..e997457 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -473,13 +473,18 @@ try_again: do { /* * Subrequests are always contiguous, non overlapping - * and in order. If not, it's a programming error. + * and in order - but may be repeated (mirrored writes). */ - WARN_ON_ONCE(subreq->wb_offset != - (head->wb_offset + total_bytes)); - - /* keep track of how many bytes this group covers */ - total_bytes += subreq->wb_bytes; + if (subreq->wb_offset == (head->wb_offset + total_bytes)) { + /* keep track of how many bytes this group covers */ + total_bytes += subreq->wb_bytes; + } else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset || + ((subreq->wb_offset + subreq->wb_bytes) > + (head->wb_offset + total_bytes)))) { + nfs_page_group_unlock(head); + spin_unlock(&inode->i_lock); + return ERR_PTR(-EIO); + } if (!nfs_lock_request(subreq)) { /* releases page group bit lock and -- cgit v1.1 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 ++-- 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e84f764..d7c2d43 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 2af32fc..520cbc5 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; -- cgit v1.1 From b57ff1303a2d4d1484c7a82bd80a3e014d6cdf5e Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 5 Sep 2014 18:20:21 -0400 Subject: pnfs: pass ds_commit_idx through the commit path Pass ds_commit_idx through the nfs commit path. It's used to select the commit bucket when using pnfs and is ignored when not using pnfs. Several functions had to be changed: nfs_retry_commit, nfs_mark_request_commit, pnfs_mark_request_commit and the pnfs layout driver .mark_request_commit functions. Signed-off-by: Tom Haynes --- fs/nfs/direct.c | 5 +++-- fs/nfs/filelayout/filelayout.c | 3 ++- fs/nfs/internal.h | 6 ++++-- fs/nfs/pnfs.h | 9 +++++---- fs/nfs/pnfs_nfs.c | 4 ++-- fs/nfs/write.c | 14 ++++++++------ 6 files changed, 24 insertions(+), 17 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index d7c2d43..1ee41d7 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -649,7 +649,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_list_remove_request(req); if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) { /* Note the rewrite will go through mds */ - nfs_mark_request_commit(req, NULL, &cinfo); + nfs_mark_request_commit(req, NULL, &cinfo, 0); } else nfs_release_request(req); nfs_unlock_and_release_request(req); @@ -748,7 +748,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (request_commit) { kref_get(&req->wb_kref); - nfs_mark_request_commit(req, hdr->lseg, &cinfo); + nfs_mark_request_commit(req, hdr->lseg, &cinfo, + hdr->ds_commit_idx); } nfs_unlock_and_release_request(req); } diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 520cbc5..3c97694 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -954,7 +954,8 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) static void filelayout_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo) + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e9305e9..05f9a87 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -450,13 +450,15 @@ int nfs_scan_commit(struct inode *inode, struct list_head *dst, struct nfs_commit_info *cinfo); void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo); + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); int nfs_write_need_commit(struct nfs_pgio_header *); int nfs_generic_commit_list(struct inode *inode, struct list_head *head, int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo); + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); void nfs_commitdata_release(struct nfs_commit_data *data); void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, struct nfs_commit_info *cinfo); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 59c831e..a0ab81cc 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -137,7 +137,8 @@ struct pnfs_layoutdriver_type { struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode); void (*mark_request_commit) (struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo); + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); void (*clear_request_commit) (struct nfs_page *req, struct nfs_commit_info *cinfo); int (*scan_commit_lists) (struct nfs_commit_info *cinfo, @@ -389,14 +390,14 @@ pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node) static inline bool pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo) + struct nfs_commit_info *cinfo, u32 ds_commit_idx) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (lseg == NULL || ld->mark_request_commit == NULL) return false; - ld->mark_request_commit(req, lseg, cinfo); + ld->mark_request_commit(req, lseg, cinfo, ds_commit_idx); return true; } @@ -574,7 +575,7 @@ pnfs_get_ds_info(struct inode *inode) static inline bool pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo) + struct nfs_commit_info *cinfo, u32 ds_commit_idx) { return false; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 55bff41..fdc4f65 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -188,7 +188,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx) bucket = &fl_cinfo->buckets[i]; if (list_empty(&bucket->committing)) continue; - nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); + nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo, i); spin_lock(cinfo->lock); freeme = bucket->clseg; bucket->clseg = NULL; @@ -247,7 +247,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, list_add(&data->pages, &list); nreq++; } else { - nfs_retry_commit(mds_pages, NULL, cinfo); + nfs_retry_commit(mds_pages, NULL, cinfo, 0); pnfs_generic_retry_commit(cinfo, 0); cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e997457..2bee165 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -847,9 +847,9 @@ EXPORT_SYMBOL_GPL(nfs_init_cinfo); */ void nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo) + struct nfs_commit_info *cinfo, u32 ds_commit_idx) { - if (pnfs_mark_request_commit(req, lseg, cinfo)) + if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx)) return; nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); } @@ -905,7 +905,8 @@ 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); + nfs_mark_request_commit(req, hdr->lseg, &cinfo, + 0); goto next; } remove_req: @@ -1560,14 +1561,15 @@ EXPORT_SYMBOL_GPL(nfs_init_commit); void nfs_retry_commit(struct list_head *page_list, struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo) + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) { struct nfs_page *req; while (!list_empty(page_list)) { req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); - nfs_mark_request_commit(req, lseg, cinfo); + nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx); if (!cinfo->dreq) { dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, @@ -1598,7 +1600,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), data->mds_ops, how, 0); out_bad: - nfs_retry_commit(head, NULL, cinfo); + nfs_retry_commit(head, NULL, cinfo, 0); cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } -- cgit v1.1 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 +- 7 files changed, 293 insertions(+), 64 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1ee41d7..0178d4f 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 05f9a87..ef1c703 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 d007780..9a5f2ee 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 1c03187..eec12b7 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 2da2e77..5f7c422 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 092ab49..568ecf0 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 2bee165..ceacfee 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); -- cgit v1.1 From 0a00b77b331a0e4aac461d4e920677661256918a Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 19 Sep 2014 12:48:33 -0400 Subject: nfs: mirroring support for direct io The current mirroring code only notices short writes to the first mirror. This patch keeps per-mirror byte counts and only considers a byte to be written once all mirrors report so. Signed-off-by: Weston Andros Adamson --- fs/nfs/direct.c | 71 +++++++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 57 insertions(+), 14 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 0178d4f..651387b 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -66,6 +66,10 @@ static struct kmem_cache *nfs_direct_cachep; /* * This represents a set of asynchronous requests that we're waiting on */ +struct nfs_direct_mirror { + ssize_t count; +}; + struct nfs_direct_req { struct kref kref; /* release manager */ @@ -78,6 +82,10 @@ struct nfs_direct_req { /* completion state */ atomic_t io_count; /* i/os we're waiting for */ spinlock_t lock; /* protect completion state */ + + struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX]; + int mirror_count; + ssize_t count, /* bytes actually processed */ bytes_left, /* bytes left to be sent */ error; /* any reported error */ @@ -108,6 +116,29 @@ static inline int put_dreq(struct nfs_direct_req *dreq) return atomic_dec_and_test(&dreq->io_count); } +static void +nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) +{ + int i; + ssize_t count; + + WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count); + + dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes; + + if (hdr->pgio_mirror_idx == 0) + dreq->count += hdr->good_bytes; + + /* update the dreq->count by finding the minimum agreed count from all + * mirrors */ + count = dreq->mirrors[0].count; + + for (i = 1; i < dreq->mirror_count; i++) + count = min(count, dreq->mirrors[i].count); + + dreq->count = count; +} + /* * nfs_direct_select_verf - select the right verifier * @dreq - direct request possibly spanning multiple servers @@ -241,6 +272,18 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, cinfo->completion_ops = &nfs_direct_commit_completion_ops; } +static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq, + struct nfs_pageio_descriptor *pgio, + struct nfs_page *req) +{ + int mirror_count = 1; + + if (pgio->pg_ops->pg_get_mirror_count) + mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + + dreq->mirror_count = mirror_count; +} + static inline struct nfs_direct_req *nfs_direct_req_alloc(void) { struct nfs_direct_req *dreq; @@ -255,6 +298,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void) INIT_LIST_HEAD(&dreq->mds_cinfo.list); dreq->verf.committed = NFS_INVALID_STABLE_HOW; /* not set yet */ INIT_WORK(&dreq->work, nfs_direct_write_schedule_work); + dreq->mirror_count = 1; spin_lock_init(&dreq->lock); return dreq; @@ -360,14 +404,9 @@ 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 { - /* - * FIXME: right now this only accounts for bytes written - * to the first mirror - */ - if (hdr->pgio_mirror_idx == 0) - dreq->count += hdr->good_bytes; - } + else + nfs_direct_good_bytes(dreq, hdr); + spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { @@ -598,17 +637,23 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) LIST_HEAD(reqs); struct nfs_commit_info cinfo; LIST_HEAD(failed); + int i; nfs_init_cinfo_from_dreq(&cinfo, dreq); nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); dreq->count = 0; + for (i = 0; i < dreq->mirror_count; i++) + dreq->mirrors[i].count = 0; get_dreq(dreq); nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; + req = nfs_list_entry(reqs.next); + nfs_direct_setup_mirroring(dreq, &desc, req); + list_for_each_entry_safe(req, tmp, &reqs, wb_list) { if (!nfs_pageio_add_request(&desc, req)) { nfs_list_remove_request(req); @@ -730,12 +775,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) dreq->error = hdr->error; } if (dreq->error == 0) { - /* - * FIXME: right now this only accounts for bytes written - * to the first mirror - */ - if (hdr->pgio_mirror_idx == 0) - dreq->count += hdr->good_bytes; + nfs_direct_good_bytes(dreq, hdr); if (nfs_write_need_commit(hdr)) { if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) request_commit = true; @@ -841,6 +881,9 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, result = PTR_ERR(req); break; } + + nfs_direct_setup_mirroring(dreq, &desc, req); + nfs_lock_request(req); req->wb_index = pos >> PAGE_SHIFT; req->wb_offset = pos & ~PAGE_MASK; -- cgit v1.1 From 80c76fe314c2859d5aac94b5d66d2b9895aa73d4 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 1 Oct 2014 12:58:25 -0400 Subject: pnfs: fail comparison when bucket verifier not set This skips the WARN_ON_ONCE, but doesnt change behavior (the memcmp would fail). Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes --- fs/nfs/direct.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 651387b..eb81478 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -222,7 +222,11 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, verfp = nfs_direct_select_verf(dreq, data->ds_clp, data->ds_commit_index); - WARN_ON_ONCE(verfp->committed < 0); + + /* verifier not set so always fail */ + if (verfp->committed < 0) + return 1; + return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf)); } -- cgit v1.1 From 566f8737630390b743d79e26e4ac855fe2758129 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 10 Oct 2014 23:25:46 +0800 Subject: nfs41: add a debug warning if we destroy an unempty layout So that we can detect the case if some layout segments are still pinned which is surely a bug that we need to fix. Signed-off-by: Peng Tao --- fs/nfs/pnfs.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5f7c422..e123cfc 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -242,6 +242,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) struct inode *inode = lo->plh_inode; if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { + if (!list_empty(&lo->plh_segs)) + WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); pnfs_detach_layout_hdr(lo); spin_unlock(&inode->i_lock); pnfs_free_layout_hdr(lo); -- cgit v1.1 From 47af81f29556a45493e5c87289c3c16ce911096c Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 10 Nov 2014 08:35:34 +0800 Subject: nfs: only reset desc->pg_mirror_idx when mirroring is supported so that we don't reset desc->pg_mirror_idx for read unnecessarily. Remove WARN_ON_ONCE from __nfs_pageio_add_request to allow LD to set pg_mirror_idx for read where pg_mirror_count is always 1. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/internal.h | 7 +++++++ fs/nfs/pagelist.c | 8 ++++---- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ef1c703..5be06bc 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -6,6 +6,7 @@ #include #include #include +#include #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) @@ -261,6 +262,12 @@ static inline void nfs_iocounter_init(struct nfs_io_counter *c) atomic_set(&c->io_count, 0); } +static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc) +{ + WARN_ON_ONCE(desc->pg_mirror_count < 1); + return desc->pg_mirror_count > 1; +} + /* nfs2xdr.c */ extern struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index eec12b7..f9d8c46 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1021,8 +1021,6 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, 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; @@ -1162,7 +1160,8 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, } else dupreq = req; - desc->pg_mirror_idx = midx; + if (nfs_pgio_has_mirroring(desc)) + desc->pg_mirror_idx = midx; if (!nfs_pageio_add_request_mirror(desc, dupreq)) return 0; } @@ -1181,7 +1180,8 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx]; u32 restore_idx = desc->pg_mirror_idx; - desc->pg_mirror_idx = mirror_idx; + if (nfs_pgio_has_mirroring(desc)) + desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); if (!mirror->pg_recoalesce) -- cgit v1.1 From 48d635f14a544c2b3ca870d2c7349b41160496d2 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 10 Nov 2014 08:35:35 +0800 Subject: nfs: add nfs_pgio_current_mirror helper Let it return current nfs_pgio_mirror in use depending on pg_mirror_count. For read, we always use pg_mirrors[0], so this effectively gives us freedom to use pg_mirror_idx to track the actual mirror to read from through out the IO stack. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/internal.h | 2 ++ fs/nfs/objlayout/objio_osd.c | 2 +- fs/nfs/pagelist.c | 25 +++++++++++++++++-------- fs/nfs/pnfs.c | 9 ++++----- 4 files changed, 24 insertions(+), 14 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 5be06bc..ffe4b7a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -255,6 +255,8 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags); void nfs_free_request(struct nfs_page *req); +struct nfs_pgio_mirror * +nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); static inline void nfs_iocounter_init(struct nfs_io_counter *c) { diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 9a5f2ee..24e1d74 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -537,7 +537,7 @@ 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]; + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio); unsigned int size; size = pnfs_generic_pg_test(pgio, prev, req); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index f9d8c46..960c99f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -42,11 +42,20 @@ static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) return p->pagevec != NULL; } +struct nfs_pgio_mirror * +nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc) +{ + return nfs_pgio_has_mirroring(desc) ? + &desc->pg_mirrors[desc->pg_mirror_idx] : + &desc->pg_mirrors[0]; +} +EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror); + void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); hdr->req = nfs_list_entry(mirror->pg_list.next); @@ -485,7 +494,7 @@ 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) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); if (mirror->pg_count > mirror->pg_bsize) { @@ -782,7 +791,7 @@ 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_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); struct nfs_page *req; struct page **pages, @@ -831,7 +840,7 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) struct nfs_pgio_header *hdr; int ret; - mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + mirror = nfs_pgio_current_mirror(desc); hdr = nfs_pgio_header_alloc(desc->pg_rw_ops); if (!hdr) { @@ -961,7 +970,7 @@ 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_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); struct nfs_page *prev = NULL; @@ -985,7 +994,7 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, */ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); if (!list_empty(&mirror->pg_list)) { @@ -1015,7 +1024,7 @@ 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_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); struct nfs_page *subreq; unsigned int bytes_left = 0; @@ -1078,7 +1087,7 @@ err_ptr: static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) { - struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[desc->pg_mirror_idx]; + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); LIST_HEAD(head); do { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index e123cfc..b822b17 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1731,7 +1731,7 @@ 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]; + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { list_splice_tail_init(&hdr->pages, &mirror->pg_list); @@ -1785,7 +1785,7 @@ 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_mirror *mirror = nfs_pgio_current_mirror(desc); struct nfs_pgio_header *hdr; int ret; @@ -1846,8 +1846,7 @@ 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]; - + struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc); if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { list_splice_tail_init(&hdr->pages, &mirror->pg_list); @@ -1903,7 +1902,7 @@ 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_mirror *mirror = nfs_pgio_current_mirror(desc); struct nfs_pgio_header *hdr; int ret; -- cgit v1.1 From ceb11e13df3e78b450730c615037133c57b90c3b Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 10 Nov 2014 08:35:38 +0800 Subject: pnfs: allow LD to ask to resend read through pnfs If current IO cannot be completed due to some transient errors, LD may want to ask generic layer to resend the request through pnfs again. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 15 ++++++++++++++- fs/nfs/pnfs.h | 2 ++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b822b17..685af4f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1880,15 +1880,28 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr, return trypnfs; } +/* Resend all requests through pnfs. */ +int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr) +{ + struct nfs_pageio_descriptor pgio; + + nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops); + return nfs_pageio_resend(&pgio, hdr); +} +EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs); + static void pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { const struct rpc_call_ops *call_ops = desc->pg_rpc_callops; struct pnfs_layout_segment *lseg = desc->pg_lseg; enum pnfs_try_status trypnfs; + int err = 0; trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg); - if (trypnfs == PNFS_NOT_ATTEMPTED) + if (trypnfs == PNFS_TRY_AGAIN) + err = pnfs_read_resend_pnfs(hdr); + if (trypnfs == PNFS_NOT_ATTEMPTED || err) pnfs_read_through_mds(desc, hdr); } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index a0ab81cc..84c25cd 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -72,6 +72,7 @@ struct pnfs_layout_segment { enum pnfs_try_status { PNFS_ATTEMPTED = 0, PNFS_NOT_ATTEMPTED = 1, + PNFS_TRY_AGAIN = 2, }; #ifdef CONFIG_NFS_V4_1 @@ -268,6 +269,7 @@ int _pnfs_return_layout(struct inode *); int pnfs_commit_and_return_layout(struct inode *); void pnfs_ld_write_done(struct nfs_pgio_header *); void pnfs_ld_read_done(struct nfs_pgio_header *); +int pnfs_read_resend_pnfs(struct nfs_pgio_header *); struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, loff_t pos, -- cgit v1.1 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 +++- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3c3ff63..56d4c91 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 685af4f..9549b89 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; -- cgit v1.1 From 6c16605d6ef0dfb2e154119700d58b85c6b4dc71 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 17 Nov 2014 09:30:40 +0800 Subject: nfs41: allow async version layoutreturn Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4proc.c | 11 +++++++++-- fs/nfs/pnfs.c | 11 ++++++----- fs/nfs/pnfs.h | 2 +- 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e19b5db..2397c0f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7810,7 +7810,7 @@ static const struct rpc_call_ops nfs4_layoutreturn_call_ops = { .rpc_release = nfs4_layoutreturn_release, }; -int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) +int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) { struct rpc_task *task; struct rpc_message msg = { @@ -7824,16 +7824,23 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp) .rpc_message = &msg, .callback_ops = &nfs4_layoutreturn_call_ops, .callback_data = lrp, + .flags = RPC_TASK_ASYNC, }; - int status; + int status = 0; dprintk("--> %s\n", __func__); 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; trace_nfs4_layoutreturn(lrp->args.inode, status); +out: dprintk("<-- %s status=%d\n", __func__, status); rpc_put_task(task); return status; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 9549b89..0a0e209 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -52,7 +52,7 @@ static LIST_HEAD(pnfs_modules_tbl); static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, - enum pnfs_iomode iomode); + enum pnfs_iomode iomode, bool sync); /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * @@ -392,7 +392,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) spin_unlock(&inode->i_lock); pnfs_free_lseg(lseg); if (need_return) - pnfs_send_layoutreturn(lo, stateid, iomode); + pnfs_send_layoutreturn(lo, stateid, iomode, + true); else pnfs_put_layout_hdr(lo); } @@ -897,7 +898,7 @@ static void pnfs_clear_layoutcommit(struct inode *inode, static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, - enum pnfs_iomode iomode) + enum pnfs_iomode iomode, bool sync) { struct inode *ino = lo->plh_inode; struct nfs4_layoutreturn *lrp; @@ -923,7 +924,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, lrp->clp = NFS_SERVER(ino)->nfs_client; lrp->cred = lo->plh_lc_cred; - status = nfs4_proc_layoutreturn(lrp); + status = nfs4_proc_layoutreturn(lrp, sync); out: if (status) { spin_lock(&ino->i_lock); @@ -989,7 +990,7 @@ _pnfs_return_layout(struct inode *ino) spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); - status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY); + status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); out: dprintk("<-- %s status: %d\n", __func__, status); return status; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 84c25cd..b79f494 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -219,7 +219,7 @@ extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev, struct rpc_cred *cred); extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); -extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); +extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync); /* pnfs.c */ void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo); -- cgit v1.1 From 193e3aa2ccfb5a53acf7a690b80a1e415b74dbd7 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 17 Nov 2014 09:30:41 +0800 Subject: nfs41: introduce NFS_LAYOUT_RETURN_BEFORE_CLOSE When it is set, generic pnfs would try to send layoutreturn right before last close/delegation_return regard less NFS_LAYOUT_ROC is set or not. LD can then make sure layoutreturn is always sent rather than being omitted. The difference against NFS_LAYOUT_RETURN is that NFS_LAYOUT_RETURN_BEFORE_CLOSE does not block usage of the layout so LD can set it and expect generic layer to try pnfs path at the same time. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/nfs4proc.c | 2 ++ fs/nfs/pnfs.c | 40 +++++++++++++++++++++++++++++++++------- fs/nfs/pnfs.h | 1 + 3 files changed, 36 insertions(+), 7 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2397c0f..7e1a97a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7797,6 +7797,8 @@ static void nfs4_layoutreturn_release(void *calldata) if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); + clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); + rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); pnfs_put_layout_hdr(lrp->args.layout); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0a0e209..d3c2ca7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -909,6 +909,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, status = -ENOMEM; spin_lock(&ino->i_lock); lo->plh_block_lgets--; + rpc_wake_up(&NFS_SERVER(ino)->roc_rpcwaitq); spin_unlock(&ino->i_lock); pnfs_put_layout_hdr(lo); goto out; @@ -926,11 +927,6 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, status = nfs4_proc_layoutreturn(lrp, sync); out: - if (status) { - spin_lock(&ino->i_lock); - clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); - spin_unlock(&ino->i_lock); - } dprintk("<-- %s status: %d\n", __func__, status); return status; } @@ -1028,8 +1024,9 @@ bool pnfs_roc(struct inode *ino) { struct pnfs_layout_hdr *lo; struct pnfs_layout_segment *lseg, *tmp; + nfs4_stateid stateid; LIST_HEAD(tmp_list); - bool found = false; + bool found = false, layoutreturn = false; spin_lock(&ino->i_lock); lo = NFS_I(ino)->layout; @@ -1050,7 +1047,20 @@ bool pnfs_roc(struct inode *ino) return true; out_nolayout: + if (lo) { + stateid = lo->plh_stateid; + layoutreturn = + test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags); + if (layoutreturn) { + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); + } + } spin_unlock(&ino->i_lock); + if (layoutreturn) + pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, 0, + NFS4_MAX_UINT64, true); return false; } @@ -1085,8 +1095,9 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) struct nfs_inode *nfsi = NFS_I(ino); struct pnfs_layout_hdr *lo; struct pnfs_layout_segment *lseg; + nfs4_stateid stateid; u32 current_seqid; - bool found = false; + bool found = false, layoutreturn = false; spin_lock(&ino->i_lock); list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) @@ -1103,7 +1114,22 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) */ *barrier = current_seqid + atomic_read(&lo->plh_outstanding); out: + if (!found) { + stateid = lo->plh_stateid; + layoutreturn = + test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags); + if (layoutreturn) { + lo->plh_block_lgets++; + pnfs_get_layout_hdr(lo); + } + } spin_unlock(&ino->i_lock); + if (layoutreturn) { + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, 0, + NFS4_MAX_UINT64, false); + } return found; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index b79f494..080bf90 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -96,6 +96,7 @@ enum { NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ NFS_LAYOUT_ROC, /* some lseg had roc bit set */ NFS_LAYOUT_RETURN, /* Return this layout ASAP */ + NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ }; -- cgit v1.1 From 27b6f53987d61822a858b4680c3727bfb19e620a Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 20 Oct 2014 14:44:38 +0800 Subject: nfs/flexfiles: send layoutreturn before freeing lseg Otherwise we'll lose error tracking information when encoding layoutreturn. pnfs_put_lseg may be called from rpc callbacks. So we should not call pnfs_send_layoutreturn directly because it can deadlock in the rpc layer. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- fs/nfs/pnfs.c | 81 +++++++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 56 insertions(+), 25 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d3c2ca7..108a619 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -346,8 +346,7 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, /* Return true if layoutreturn is needed */ static bool pnfs_layout_need_return(struct pnfs_layout_hdr *lo, - struct pnfs_layout_segment *lseg, - nfs4_stateid *stateid, enum pnfs_iomode *iomode) + struct pnfs_layout_segment *lseg) { struct pnfs_layout_segment *s; @@ -355,17 +354,54 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, return false; list_for_each_entry(s, &lo->plh_segs, pls_list) - if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) return false; - *stateid = lo->plh_stateid; - *iomode = lo->plh_return_iomode; - /* decreased in pnfs_send_layoutreturn() */ - lo->plh_block_lgets++; - lo->plh_return_iomode = 0; return true; } +static void pnfs_layoutreturn_free_lseg(struct work_struct *work) +{ + struct pnfs_layout_segment *lseg; + struct pnfs_layout_hdr *lo; + struct inode *inode; + + lseg = container_of(work, struct pnfs_layout_segment, pls_work); + WARN_ON(atomic_read(&lseg->pls_refcount)); + lo = lseg->pls_layout; + inode = lo->plh_inode; + + spin_lock(&inode->i_lock); + if (pnfs_layout_need_return(lo, lseg)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode; + + stateid = lo->plh_stateid; + iomode = lo->plh_return_iomode; + /* decreased in pnfs_send_layoutreturn() */ + lo->plh_block_lgets++; + lo->plh_return_iomode = 0; + spin_unlock(&inode->i_lock); + + pnfs_send_layoutreturn(lo, stateid, iomode, true); + spin_lock(&inode->i_lock); + } else + /* match pnfs_get_layout_hdr #2 in pnfs_put_lseg */ + pnfs_put_layout_hdr(lo); + pnfs_layout_remove_lseg(lo, lseg); + spin_unlock(&inode->i_lock); + pnfs_free_lseg(lseg); + /* match pnfs_get_layout_hdr #1 in pnfs_put_lseg */ + pnfs_put_layout_hdr(lo); +} + +static void +pnfs_layoutreturn_free_lseg_async(struct pnfs_layout_segment *lseg) +{ + INIT_WORK(&lseg->pls_work, pnfs_layoutreturn_free_lseg); + queue_work(nfsiod_workqueue, &lseg->pls_work); +} + void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -381,21 +417,18 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) lo = lseg->pls_layout; inode = lo->plh_inode; if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { - bool need_return; - nfs4_stateid stateid; - enum pnfs_iomode iomode; - pnfs_get_layout_hdr(lo); - pnfs_layout_remove_lseg(lo, lseg); - need_return = pnfs_layout_need_return(lo, lseg, - &stateid, &iomode); - spin_unlock(&inode->i_lock); - pnfs_free_lseg(lseg); - if (need_return) - pnfs_send_layoutreturn(lo, stateid, iomode, - true); - else + if (pnfs_layout_need_return(lo, lseg)) { + spin_unlock(&inode->i_lock); + /* hdr reference dropped in nfs4_layoutreturn_release */ + pnfs_get_layout_hdr(lo); + pnfs_layoutreturn_free_lseg_async(lseg); + } else { + pnfs_layout_remove_lseg(lo, lseg); + spin_unlock(&inode->i_lock); + pnfs_free_lseg(lseg); pnfs_put_layout_hdr(lo); + } } } EXPORT_SYMBOL_GPL(pnfs_put_lseg); @@ -1059,8 +1092,7 @@ out_nolayout: } spin_unlock(&ino->i_lock); if (layoutreturn) - pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, 0, - NFS4_MAX_UINT64, true); + pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); return false; } @@ -1127,8 +1159,7 @@ out: spin_unlock(&ino->i_lock); if (layoutreturn) { rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); - pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, 0, - NFS4_MAX_UINT64, false); + pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false); } return found; } -- cgit v1.1 From c829013dca33110d57c7f625443b716bd7a17671 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 1 Dec 2014 08:22:18 +0800 Subject: nfs41: add NFS_LAYOUT_RETRY_LAYOUTGET to layout header flags Use it to indicate that LD wants to retry layoutget. LD can set it whenever it wants the common pnfs code to return and retry pnfs path through a new layout. The bit gets cleared when client does a new layoutget, when client closes the file (ROC case), or when kernel needs to evict the inode (non-ROC case). Signed-off-by: Peng Tao --- fs/nfs/pnfs.c | 3 +++ fs/nfs/pnfs.h | 18 ++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 108a619..893f6b5 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -615,6 +615,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) pnfs_get_layout_hdr(lo); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); + pnfs_clear_retry_layoutget(lo); spin_unlock(&nfsi->vfs_inode.i_lock); pnfs_free_lseg_list(&tmp_list); pnfs_put_layout_hdr(lo); @@ -1066,6 +1067,7 @@ bool pnfs_roc(struct inode *ino) if (!lo || !test_and_clear_bit(NFS_LAYOUT_ROC, &lo->plh_flags) || test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) goto out_nolayout; + pnfs_clear_retry_layoutget(lo); list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list) if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { mark_lseg_invalid(lseg, &tmp_list); @@ -1491,6 +1493,7 @@ lookup_again: arg.length = PAGE_CACHE_ALIGN(arg.length); lseg = send_layoutget(lo, ctx, &arg, gfp_flags); + pnfs_clear_retry_layoutget(lo); atomic_dec(&lo->plh_outstanding); out_put_layout_hdr: if (first) { diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 080bf90..fed6ae0 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -99,6 +99,7 @@ enum { NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ + NFS_LAYOUT_RETRY_LAYOUTGET, /* Retry layoutget */ }; enum layoutdriver_policy_flags { @@ -350,6 +351,23 @@ nfs4_get_deviceid(struct nfs4_deviceid_node *d) return d; } +static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + if (!test_and_set_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) + atomic_inc(&lo->plh_refcount); +} + +static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) + atomic_dec(&lo->plh_refcount); +} + +static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags); +} + static inline struct pnfs_layout_segment * pnfs_get_lseg(struct pnfs_layout_segment *lseg) { -- cgit v1.1 From 012fa16dca0da6c487dd066829ff0b0954925fe6 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 1 Dec 2014 08:22:21 +0800 Subject: nfs: add a helper to set NFS_ODIRECT_RESCHED_WRITES to direct writes To allow pnfs LD to ask direct writes to be resend. Signed-off-by: Peng Tao --- fs/nfs/direct.c | 6 ++++++ fs/nfs/internal.h | 1 + 2 files changed, 7 insertions(+) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index eb81478..4fad6b7 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -116,6 +116,12 @@ static inline int put_dreq(struct nfs_direct_req *dreq) return atomic_dec_and_test(&dreq->io_count); } +void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq) +{ + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; +} +EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes); + static void nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ffe4b7a..44e8496 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -502,6 +502,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode) inode_dio_wait(inode); } extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); +extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq); /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_pgio_header *); -- cgit v1.1 From aa8a45ee974dfe3ffe290daaf5db457afae56fde Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 1 Dec 2014 08:22:23 +0800 Subject: nfs41: wait for LAYOUTRETURN before retrying LAYOUTGET Also take care to stop waiting if someone clears retry bit. Signed-off-by: Peng Tao --- fs/nfs/nfs4proc.c | 4 +++- fs/nfs/pnfs.c | 39 ++++++++++++++++++++++++++++++++++++++- fs/nfs/pnfs.h | 5 ++++- 3 files changed, 45 insertions(+), 3 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7e1a97a..44c600a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7796,7 +7796,9 @@ 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(NFS_LAYOUT_RETURN, &lo->plh_flags); + clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); + smp_mb__after_atomic(); + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); 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 893f6b5..c4c9fe6 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1398,6 +1398,26 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, return ret; } +/* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */ +static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key) +{ + if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags)) + return 1; + return nfs_wait_bit_killable(key); +} + +static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) +{ + /* + * send layoutcommit as it can hold up layoutreturn due to lseg + * reference + */ + pnfs_layoutcommit_inode(lo->plh_inode, false); + return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, + pnfs_layoutget_retry_bit_wait, + TASK_UNINTERRUPTIBLE); +} + /* * Layout segment is retreived from the server if not cached. * The appropriate layout segment is referenced and returned to the caller. @@ -1444,7 +1464,8 @@ lookup_again: } /* if LAYOUTGET already failed once we don't try again */ - if (pnfs_layout_io_test_failed(lo, iomode)) + if (pnfs_layout_io_test_failed(lo, iomode) && + !pnfs_should_retry_layoutget(lo)) goto out_unlock; first = list_empty(&lo->plh_segs); @@ -1469,6 +1490,22 @@ lookup_again: goto out_unlock; } + /* + * Because we free lsegs before sending LAYOUTRETURN, we need to wait + * for LAYOUTRETURN even if first is true. + */ + if (!lseg && pnfs_should_retry_layoutget(lo) && + test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + dprintk("%s wait for layoutreturn\n", __func__); + if (pnfs_prepare_to_retry_layoutget(lo)) { + pnfs_put_layout_hdr(lo); + dprintk("%s retrying\n", __func__); + goto lookup_again; + } + goto out_put_layout_hdr; + } + if (pnfs_layoutgets_blocked(lo, &arg, 0)) goto out_unlock; atomic_inc(&lo->plh_outstanding); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index fed6ae0..49a4667 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -359,8 +359,11 @@ static inline void pnfs_set_retry_layoutget(struct pnfs_layout_hdr *lo) static inline void pnfs_clear_retry_layoutget(struct pnfs_layout_hdr *lo) { - if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) + if (test_and_clear_bit(NFS_LAYOUT_RETRY_LAYOUTGET, &lo->plh_flags)) { atomic_dec(&lo->plh_refcount); + /* wake up waiters for LAYOUTRETURN as that is not needed */ + wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); + } } static inline bool pnfs_should_retry_layoutget(struct pnfs_layout_hdr *lo) -- cgit v1.1 From 5fadeb47dcc5c30d4b6cf481b4a78689eab59443 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 19 Jan 2015 12:41:16 +0800 Subject: nfs: count DIO good bytes correctly with mirroring When resending to MDS, we might resend multiple mirroring requests to MDS. As a result, nfs_direct_good_bytes() ends up counting bytes multiple times, causing application to get wrong return results in read/write syscalls. Fix it by tracking start of a dreq and checking the range of pgio header. Cc: Weston Andros Adamson Signed-off-by: Peng Tao --- fs/nfs/direct.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4fad6b7..3715b49 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -88,6 +88,7 @@ struct nfs_direct_req { ssize_t count, /* bytes actually processed */ bytes_left, /* bytes left to be sent */ + io_start, /* start of IO */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ @@ -130,10 +131,11 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) WARN_ON_ONCE(hdr->pgio_mirror_idx >= dreq->mirror_count); - dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes; - - if (hdr->pgio_mirror_idx == 0) - dreq->count += hdr->good_bytes; + count = dreq->mirrors[hdr->pgio_mirror_idx].count; + if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) { + count = hdr->io_start + hdr->good_bytes - dreq->io_start; + dreq->mirrors[hdr->pgio_mirror_idx].count = count; + } /* update the dreq->count by finding the minimum agreed count from all * mirrors */ @@ -594,6 +596,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, dreq->inode = inode; dreq->bytes_left = count; + dreq->io_start = pos; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { @@ -1002,6 +1005,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, dreq->inode = inode; dreq->bytes_left = count; + dreq->io_start = pos; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { -- cgit v1.1 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 + 10 files changed, 2320 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 'fs/nfs') diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 3dece03..c7abc10 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 23abffa..1e987ac 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-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/ diff --git a/fs/nfs/flexfilelayout/Makefile b/fs/nfs/flexfilelayout/Makefile new file mode 100644 index 0000000..1d2c9f6 --- /dev/null +++ b/fs/nfs/flexfilelayout/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the pNFS Flexfile Layout Driver kernel module +# +obj-$(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 0000000..f29fb7d --- /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 0000000..070f204 --- /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 0000000..3bbb16b --- /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 2f5db84..857e2a9 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 44c600a..ca6dda0 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 c4c9fe6..0fb0f19 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 49a4667..7642021 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 *); -- cgit v1.1 From cb5d04bc39e914124e811ea55f3034d2379a5f6c Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 24 Jan 2015 22:14:52 +0800 Subject: nfs41: .init_read and .init_write can be called with valid pg_lseg With pgio refactoring in v3.15, .init_read and .init_write can be called with valid pgio->pg_lseg. file layout was fixed at that time by commit c6194271f (pnfs: filelayout: support non page aligned layouts). But the generic helper still needs to be fixed. Cc: stable@vger.kernel.org # 3.15+ Signed-off-by: Peng Tao --- fs/nfs/pnfs.c | 41 ++++++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 21 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0fb0f19..c7be9b9 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1711,19 +1711,19 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r { u64 rd_size = req->wb_bytes; - WARN_ON_ONCE(pgio->pg_lseg != NULL); - - if (pgio->pg_dreq == NULL) - rd_size = i_size_read(pgio->pg_inode) - req_offset(req); - else - rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); - - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, - req_offset(req), - rd_size, - IOMODE_READ, - GFP_KERNEL); + if (pgio->pg_lseg == NULL) { + if (pgio->pg_dreq == NULL) + rd_size = i_size_read(pgio->pg_inode) - req_offset(req); + else + rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); + + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + req_offset(req), + rd_size, + IOMODE_READ, + GFP_KERNEL); + } /* If no lseg, fall back to read through mds */ if (pgio->pg_lseg == NULL) nfs_pageio_reset_read_mds(pgio); @@ -1735,14 +1735,13 @@ void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size) { - WARN_ON_ONCE(pgio->pg_lseg != NULL); - - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - req->wb_context, - req_offset(req), - wb_size, - IOMODE_RW, - GFP_NOFS); + if (pgio->pg_lseg == NULL) + pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, + req->wb_context, + req_offset(req), + wb_size, + IOMODE_RW, + GFP_NOFS); /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) nfs_pageio_reset_write_mds(pgio); -- cgit v1.1 From 7c13789e3e6c66dbcaade1760087429240eb3d27 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 30 Jan 2015 11:01:02 -0500 Subject: pnfs: lookup new lseg at lseg boundary Before mirroring support was added, the pageio descriptor's pg_lseg was set to null when an RPC was sent. Because of this, pg_init was called at lseg boundaries with pg_lseg = NULL, and it could be set to the new lseg. Signed-off-by: Weston Andros Adamson --- fs/nfs/pnfs.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c7be9b9..9304984 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1788,10 +1788,16 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, seg_end = end_offset(pgio->pg_lseg->pls_range.offset, pgio->pg_lseg->pls_range.length); req_start = req_offset(req); - WARN_ON_ONCE(req_start > seg_end); + WARN_ON_ONCE(req_start >= seg_end); /* start of request is past the last byte of this segment */ - if (req_start >= seg_end) + if (req_start >= seg_end) { + /* reference the new lseg */ + if (pgio->pg_ops->pg_cleanup) + pgio->pg_ops->pg_cleanup(pgio); + if (pgio->pg_ops->pg_init) + pgio->pg_ops->pg_init(pgio, req); return 0; + } /* adjust 'size' iff there are fewer bytes left in the * segment than what nfs_generic_pg_test returned */ -- cgit v1.1 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 +++++++++++++++++++++++++++++++++++++------------------ 2 files changed, 83 insertions(+), 26 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6e1c9b2..cd4295d 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 a2329d6..e23a0a6 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; -- cgit v1.1 From ea7c38fef0b774a5dc16fb0ca5935f0ae8568176 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 15:13:24 -0500 Subject: NFSv4: Ensure we reference the inode for return-on-close in delegreturn If we have to do a return-on-close in the delegreturn code, then we must ensure that the inode and super block remain referenced. Cc: Peng Tao Cc: stable@vger.kernel.org # 3.17.x Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- fs/nfs/internal.h | 22 +++++++++++++++++++++- fs/nfs/nfs4proc.c | 14 +++++++++----- fs/nfs/super.c | 9 ++++++--- 3 files changed, 36 insertions(+), 9 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index a98cf20..21469e6 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -391,7 +391,7 @@ extern struct rpc_stat nfs_rpcstat; extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); -extern void nfs_sb_active(struct super_block *sb); +extern bool nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); /* namespace.c */ @@ -514,6 +514,26 @@ extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, struct rpc_cred *cred); +static inline struct inode *nfs_igrab_and_active(struct inode *inode) +{ + inode = igrab(inode); + if (inode != NULL && !nfs_sb_active(inode->i_sb)) { + iput(inode); + inode = NULL; + } + return inode; +} + +static inline void nfs_iput_and_deactive(struct inode *inode) +{ + if (inode != NULL) { + struct super_block *sb = inode->i_sb; + + iput(inode); + nfs_sb_deactive(sb); + } +} + /* * Determine the device name as a string */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cd4295d..dd892a4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5175,9 +5175,13 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) static void nfs4_delegreturn_release(void *calldata) { struct nfs4_delegreturndata *data = calldata; + struct inode *inode = data->inode; - if (data->roc) - pnfs_roc_release(data->inode); + if (inode) { + if (data->roc) + pnfs_roc_release(inode); + nfs_iput_and_deactive(inode); + } kfree(calldata); } @@ -5234,9 +5238,9 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co nfs_fattr_init(data->res.fattr); data->timestamp = jiffies; data->rpc_status = 0; - data->inode = inode; - data->roc = list_empty(&NFS_I(inode)->open_files) ? - pnfs_roc(inode) : false; + data->inode = nfs_igrab_and_active(inode); + if (data->inode) + data->roc = nfs4_roc(inode); task_setup_data.callback_data = data; msg.rpc_argp = &data->args; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 31a11b0..368d939 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -405,12 +405,15 @@ void __exit unregister_nfs_fs(void) unregister_filesystem(&nfs_fs_type); } -void nfs_sb_active(struct super_block *sb) +bool nfs_sb_active(struct super_block *sb) { struct nfs_server *server = NFS_SB(sb); - if (atomic_inc_return(&server->active) == 1) - atomic_inc(&sb->s_active); + if (!atomic_inc_not_zero(&sb->s_active)) + return false; + if (atomic_inc_return(&server->active) != 1) + atomic_dec(&sb->s_active); + return true; } EXPORT_SYMBOL_GPL(nfs_sb_active); -- cgit v1.1 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 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index dd892a4..e092b85 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; -- cgit v1.1 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 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e092b85..2e7c9f7 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; -- cgit v1.1 From e4af440aaf390ac1d39b26ef6cf4a28bcb6a5979 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 17:05:08 -0500 Subject: NFSv4.1: pnfs_send_layoutreturn should use GFP_NOFS In we want to be able to call pnfs_send_layoutreturn() from within the writeback path, we really want it to use GFP_NOFS in order to prevent recursion. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 703501d..a1d8620 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -948,7 +948,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid, struct nfs4_layoutreturn *lrp; int status = 0; - lrp = kzalloc(sizeof(*lrp), GFP_KERNEL); + lrp = kzalloc(sizeof(*lrp), GFP_NOFS); if (unlikely(lrp == NULL)) { status = -ENOMEM; spin_lock(&ino->i_lock); -- cgit v1.1 From 4ef2e4f84c523ebbc930ce05fa27b9b1350f4a4b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 17:27:39 -0500 Subject: NFSv4.1: Fix pnfs_put_lseg races pnfs_layoutreturn_free_lseg_async() can also race with inode put in the general case. We can now fix this, and also simplify the code. Cc: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 53 +++++++++++++++++++---------------------------------- 1 file changed, 19 insertions(+), 34 deletions(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a1d8620..107b321 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -361,14 +361,9 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, return true; } -static void pnfs_layoutreturn_free_lseg(struct work_struct *work) +static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, + struct pnfs_layout_hdr *lo, struct inode *inode) { - struct pnfs_layout_segment *lseg; - struct pnfs_layout_hdr *lo; - struct inode *inode; - - lseg = container_of(work, struct pnfs_layout_segment, pls_work); - WARN_ON(atomic_read(&lseg->pls_refcount)); lo = lseg->pls_layout; inode = lo->plh_inode; @@ -383,24 +378,12 @@ static void pnfs_layoutreturn_free_lseg(struct work_struct *work) lo->plh_block_lgets++; lo->plh_return_iomode = 0; spin_unlock(&inode->i_lock); + pnfs_get_layout_hdr(lo); - pnfs_send_layoutreturn(lo, stateid, iomode, true); - spin_lock(&inode->i_lock); + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, stateid, iomode, false); } else - /* match pnfs_get_layout_hdr #2 in pnfs_put_lseg */ - pnfs_put_layout_hdr(lo); - pnfs_layout_remove_lseg(lo, lseg); - spin_unlock(&inode->i_lock); - pnfs_free_lseg(lseg); - /* match pnfs_get_layout_hdr #1 in pnfs_put_lseg */ - pnfs_put_layout_hdr(lo); -} - -static void -pnfs_layoutreturn_free_lseg_async(struct pnfs_layout_segment *lseg) -{ - INIT_WORK(&lseg->pls_work, pnfs_layoutreturn_free_lseg); - queue_work(nfsiod_workqueue, &lseg->pls_work); + spin_unlock(&inode->i_lock); } void @@ -415,21 +398,23 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg, atomic_read(&lseg->pls_refcount), test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); + + /* Handle the case where refcount != 1 */ + if (atomic_add_unless(&lseg->pls_refcount, -1, 1)) + return; + lo = lseg->pls_layout; inode = lo->plh_inode; + /* Do we need a layoutreturn? */ + if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); + if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { pnfs_get_layout_hdr(lo); - if (pnfs_layout_need_return(lo, lseg)) { - spin_unlock(&inode->i_lock); - /* hdr reference dropped in nfs4_layoutreturn_release */ - pnfs_get_layout_hdr(lo); - pnfs_layoutreturn_free_lseg_async(lseg); - } else { - pnfs_layout_remove_lseg(lo, lseg); - spin_unlock(&inode->i_lock); - pnfs_free_lseg(lseg); - pnfs_put_layout_hdr(lo); - } + pnfs_layout_remove_lseg(lo, lseg); + spin_unlock(&inode->i_lock); + pnfs_free_lseg(lseg); + pnfs_put_layout_hdr(lo); } } EXPORT_SYMBOL_GPL(pnfs_put_lseg); -- cgit v1.1 From 480486b4733d5bc7d9fe765b34bc6c2b72d5c12e Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Mon, 9 Feb 2015 17:48:32 -0800 Subject: pnfs/flexfiles: Do not dprintk after the free Found by 0-DAY kernel test infrastructure: fs/nfs/flexfilelayout/flexfilelayoutdev.c:520:13-16: ERROR: reference preceded by free on line 518 fs/nfs/flexfilelayout/flexfilelayoutdev.c:520:26-29: ERROR: reference preceded by free on line 518 fs/nfs/flexfilelayout/flexfilelayoutdev.c:520:39-42: ERROR: reference preceded by free on line 518 fs/nfs/flexfilelayout/flexfilelayoutdev.c:521:3-6: ERROR: reference preceded by free on line 518 Reported-by: Julia Lawall Signed-off-by: Tom Haynes Signed-off-by: Trond Myklebust --- fs/nfs/flexfilelayout/flexfilelayoutdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 3bbb16b..e2c01f2 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -515,10 +515,10 @@ int ff_layout_encode_ds_ioerr(struct nfs4_flexfile_layout *flo, *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); + kfree(err); } return 0; -- cgit v1.1 From 4c21462acc530bb81c6ae30e5bbd0b06f8c50626 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 10 Feb 2015 11:03:22 +0300 Subject: pnfs: delete an unintended goto There was an extra goto here where it shouldn't be, because of a merge error. Fixes: e2c63e091e29 ('Merge branch 'flexfiles'') Signed-off-by: Dan Carpenter Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/nfs') diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 107b321..4f802b0 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1078,7 +1078,6 @@ bool pnfs_roc(struct inode *ino) goto out_noroc; } - goto out_noroc; pnfs_clear_retry_layoutget(lo); list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list) if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { -- cgit v1.1