From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/nfs/pnfs.c | 530 +++++++++++++++++++++++++++++++++++++++++++---------------
1 files changed, 393 insertions(+), 137 deletions(-)
diff --git a/kernel/fs/nfs/pnfs.c b/kernel/fs/nfs/pnfs.c
index c900cb2..2143672 100644
--- a/kernel/fs/nfs/pnfs.c
+++ b/kernel/fs/nfs/pnfs.c
@@ -92,6 +92,17 @@
return local;
}
+const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id)
+{
+ return find_pnfs_driver(id);
+}
+
+void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld)
+{
+ if (ld)
+ module_put(ld->owner);
+}
+
void
unset_pnfs_layoutdriver(struct nfs_server *nfss)
{
@@ -268,14 +279,14 @@
struct nfs_server *server = NFS_SERVER(lo->plh_inode);
struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
- if (!list_empty(&lo->plh_layouts)) {
+ if (test_and_clear_bit(NFS_LAYOUT_HASHED, &lo->plh_flags)) {
struct nfs_client *clp = server->nfs_client;
spin_lock(&clp->cl_lock);
- list_del_init(&lo->plh_layouts);
+ list_del_rcu(&lo->plh_layouts);
spin_unlock(&clp->cl_lock);
}
- put_rpccred(lo->plh_lc_cred);
+ put_cred(lo->plh_lc_cred);
return ld->free_layout_hdr(lo);
}
@@ -314,6 +325,31 @@
}
}
+static struct inode *
+pnfs_grab_inode_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+ struct inode *inode = igrab(lo->plh_inode);
+ if (inode)
+ return inode;
+ set_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags);
+ return NULL;
+}
+
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+ return (s32)(s1 - s2) > 0;
+}
+
+static void pnfs_barrier_update(struct pnfs_layout_hdr *lo, u32 newseq)
+{
+ if (pnfs_seqid_is_newer(newseq, lo->plh_barrier) || !lo->plh_barrier)
+ lo->plh_barrier = newseq;
+}
+
static void
pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
u32 seq)
@@ -322,10 +358,15 @@
iomode = IOMODE_ANY;
lo->plh_return_iomode = iomode;
set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
- if (seq != 0) {
- WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq);
+ /*
+ * We must set lo->plh_return_seq to avoid livelocks with
+ * pnfs_layout_need_return()
+ */
+ if (seq == 0)
+ seq = be32_to_cpu(lo->plh_stateid.seqid);
+ if (!lo->plh_return_seq || pnfs_seqid_is_newer(seq, lo->plh_return_seq))
lo->plh_return_seq = seq;
- }
+ pnfs_barrier_update(lo, seq);
}
static void
@@ -364,9 +405,10 @@
}
/*
- * Update the seqid of a layout stateid
+ * Update the seqid of a layout stateid after receiving
+ * NFS4ERR_OLD_STATEID
*/
-bool nfs4_layoutreturn_refresh_stateid(nfs4_stateid *dst,
+bool nfs4_layout_refresh_old_stateid(nfs4_stateid *dst,
struct pnfs_layout_range *dst_range,
struct inode *inode)
{
@@ -382,7 +424,15 @@
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match_other(dst, &lo->plh_stateid)) {
+ if (lo && pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(dst, &lo->plh_stateid)) {
+ /* Is our call using the most recent seqid? If so, bump it */
+ if (!nfs4_stateid_is_newer(&lo->plh_stateid, dst)) {
+ nfs4_stateid_seqid_inc(dst);
+ ret = true;
+ goto out;
+ }
+ /* Try to update the seqid to the most recent */
err = pnfs_mark_matching_lsegs_return(lo, &head, &range, 0);
if (err != -EBUSY) {
dst->seqid = lo->plh_stateid.seqid;
@@ -390,6 +440,7 @@
ret = true;
}
}
+out:
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
return ret;
@@ -418,6 +469,7 @@
pnfs_clear_lseg_state(lseg, lseg_list);
pnfs_clear_layoutreturn_info(lo);
pnfs_free_returned_lsegs(lo, lseg_list, &range, 0);
+ set_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags);
if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
!test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags))
pnfs_clear_layoutreturn_waitbit(lo);
@@ -491,6 +543,7 @@
{
INIT_LIST_HEAD(&lseg->pls_list);
INIT_LIST_HEAD(&lseg->pls_lc_list);
+ INIT_LIST_HEAD(&lseg->pls_commits);
refcount_set(&lseg->pls_refcount, 1);
set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
lseg->pls_layout = lo;
@@ -616,15 +669,6 @@
rv = 1;
}
return rv;
-}
-
-/*
- * Compare 2 layout stateid sequence ids, to see which is newer,
- * taking into account wraparound issues.
- */
-static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
-{
- return (s32)(s1 - s2) > 0;
}
static bool
@@ -801,9 +845,10 @@
/* If the sb is being destroyed, just bail */
if (!nfs_sb_active(server->super))
break;
- inode = igrab(lo->plh_inode);
+ inode = pnfs_grab_inode_layout_hdr(lo);
if (inode != NULL) {
- list_del_init(&lo->plh_layouts);
+ if (test_and_clear_bit(NFS_LAYOUT_HASHED, &lo->plh_flags))
+ list_del_rcu(&lo->plh_layouts);
if (pnfs_layout_add_bulk_destroy_list(inode,
layout_list))
continue;
@@ -813,7 +858,6 @@
} else {
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
- set_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags);
}
nfs_sb_deactive(server->super);
spin_lock(&clp->cl_lock);
@@ -910,7 +954,7 @@
}
/*
- * Called by the state manger to remove all layouts established under an
+ * Called by the state manager to remove all layouts established under an
* expired lease.
*/
void
@@ -922,37 +966,48 @@
pnfs_destroy_layouts_byclid(clp, false);
}
+static void
+pnfs_set_layout_cred(struct pnfs_layout_hdr *lo, const struct cred *cred)
+{
+ const struct cred *old;
+
+ if (cred && cred_fscmp(lo->plh_lc_cred, cred) != 0) {
+ old = xchg(&lo->plh_lc_cred, get_cred(cred));
+ put_cred(old);
+ }
+}
+
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
- bool update_barrier)
+ const struct cred *cred, bool update_barrier)
{
- u32 oldseq, newseq, new_barrier = 0;
-
- oldseq = be32_to_cpu(lo->plh_stateid.seqid);
- newseq = be32_to_cpu(new->seqid);
+ u32 oldseq = be32_to_cpu(lo->plh_stateid.seqid);
+ u32 newseq = be32_to_cpu(new->seqid);
if (!pnfs_layout_is_valid(lo)) {
+ pnfs_set_layout_cred(lo, cred);
nfs4_stateid_copy(&lo->plh_stateid, new);
lo->plh_barrier = newseq;
pnfs_clear_layoutreturn_info(lo);
clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
return;
}
- if (pnfs_seqid_is_newer(newseq, oldseq)) {
+
+ if (pnfs_seqid_is_newer(newseq, oldseq))
nfs4_stateid_copy(&lo->plh_stateid, new);
- /*
- * Because of wraparound, we want to keep the barrier
- * "close" to the current seqids.
- */
- new_barrier = newseq - atomic_read(&lo->plh_outstanding);
- }
- if (update_barrier)
- new_barrier = be32_to_cpu(new->seqid);
- else if (new_barrier == 0)
+
+ if (update_barrier) {
+ pnfs_barrier_update(lo, newseq);
return;
- if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
- lo->plh_barrier = new_barrier;
+ }
+ /*
+ * Because of wraparound, we want to keep the barrier
+ * "close" to the current seqids. We really only want to
+ * get here from a layoutget call.
+ */
+ if (atomic_read(&lo->plh_outstanding) == 1)
+ pnfs_barrier_update(lo, be32_to_cpu(lo->plh_stateid.seqid));
}
static bool
@@ -961,7 +1016,7 @@
{
u32 seqid = be32_to_cpu(stateid->seqid);
- return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
+ return lo->plh_barrier && pnfs_seqid_is_newer(lo->plh_barrier, seqid);
}
/* lget is set to 1 if called from inside send_layoutget call chain */
@@ -1007,7 +1062,7 @@
struct page **pages;
int i;
- pages = kcalloc(size, sizeof(struct page *), gfp_flags);
+ pages = kmalloc_array(size, sizeof(struct page *), gfp_flags);
if (!pages) {
dprintk("%s: can't alloc array of %zu pages\n", __func__, size);
return NULL;
@@ -1017,7 +1072,7 @@
pages[i] = alloc_page(gfp_flags);
if (!pages[i]) {
dprintk("%s: failed to allocate page\n", __func__);
- nfs4_free_pages(pages, size);
+ nfs4_free_pages(pages, i);
return NULL;
}
}
@@ -1033,6 +1088,7 @@
gfp_t gfp_flags)
{
struct nfs_server *server = pnfs_find_server(ino, ctx);
+ size_t max_reply_sz = server->pnfs_curr_ld->max_layoutget_response;
size_t max_pages = max_response_pages(server);
struct nfs4_layoutget *lgp;
@@ -1041,6 +1097,12 @@
lgp = kzalloc(sizeof(*lgp), gfp_flags);
if (lgp == NULL)
return NULL;
+
+ if (max_reply_sz) {
+ size_t npages = (max_reply_sz + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (npages < max_pages)
+ max_pages = npages;
+ }
lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
if (!lgp->args.layout.pages) {
@@ -1073,7 +1135,7 @@
lgp->args.ctx = get_nfs_open_context(ctx);
nfs4_stateid_copy(&lgp->args.stateid, stateid);
lgp->gfp_flags = gfp_flags;
- lgp->cred = get_rpccred(ctx->cred);
+ lgp->cred = ctx->cred;
return lgp;
}
@@ -1084,7 +1146,6 @@
nfs4_free_pages(lgp->args.layout.pages, max_pages);
if (lgp->args.inode)
pnfs_put_layout_hdr(NFS_I(lgp->args.inode)->layout);
- put_rpccred(lgp->cred);
put_nfs_open_context(lgp->args.ctx);
kfree(lgp);
}
@@ -1121,7 +1182,7 @@
pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
pnfs_free_returned_lsegs(lo, &freeme, range, seq);
- pnfs_set_layout_stateid(lo, stateid, true);
+ pnfs_set_layout_stateid(lo, stateid, NULL, true);
} else
pnfs_mark_layout_stateid_invalid(lo, &freeme);
out_unlock:
@@ -1134,6 +1195,7 @@
static bool
pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
nfs4_stateid *stateid,
+ const struct cred **cred,
enum pnfs_iomode *iomode)
{
/* Serialise LAYOUTGET/LAYOUTRETURN */
@@ -1143,21 +1205,17 @@
return false;
set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
pnfs_get_layout_hdr(lo);
+ nfs4_stateid_copy(stateid, &lo->plh_stateid);
+ *cred = get_cred(lo->plh_lc_cred);
if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) {
- if (stateid != NULL) {
- nfs4_stateid_copy(stateid, &lo->plh_stateid);
- if (lo->plh_return_seq != 0)
- stateid->seqid = cpu_to_be32(lo->plh_return_seq);
- }
+ if (lo->plh_return_seq != 0)
+ stateid->seqid = cpu_to_be32(lo->plh_return_seq);
if (iomode != NULL)
*iomode = lo->plh_return_iomode;
pnfs_clear_layoutreturn_info(lo);
- return true;
- }
- if (stateid != NULL)
- nfs4_stateid_copy(stateid, &lo->plh_stateid);
- if (iomode != NULL)
+ } else if (iomode != NULL)
*iomode = IOMODE_ANY;
+ pnfs_barrier_update(lo, be32_to_cpu(stateid->seqid));
return true;
}
@@ -1179,20 +1237,26 @@
}
static int
-pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
- enum pnfs_iomode iomode, bool sync)
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo,
+ const nfs4_stateid *stateid,
+ const struct cred **pcred,
+ enum pnfs_iomode iomode,
+ bool sync)
{
struct inode *ino = lo->plh_inode;
struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
struct nfs4_layoutreturn *lrp;
+ const struct cred *cred = *pcred;
int status = 0;
+ *pcred = NULL;
lrp = kzalloc(sizeof(*lrp), GFP_NOFS);
if (unlikely(lrp == NULL)) {
status = -ENOMEM;
spin_lock(&ino->i_lock);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&ino->i_lock);
+ put_cred(cred);
pnfs_put_layout_hdr(lo);
goto out;
}
@@ -1200,7 +1264,7 @@
pnfs_init_layoutreturn_args(&lrp->args, lo, stateid, iomode);
lrp->args.ld_private = &lrp->ld_private;
lrp->clp = NFS_SERVER(ino)->nfs_client;
- lrp->cred = lo->plh_lc_cred;
+ lrp->cred = cred;
if (ld->prepare_layoutreturn)
ld->prepare_layoutreturn(&lrp->args);
@@ -1241,15 +1305,16 @@
return;
spin_lock(&inode->i_lock);
if (pnfs_layout_need_return(lo)) {
+ const struct cred *cred;
nfs4_stateid stateid;
enum pnfs_iomode iomode;
bool send;
- send = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
+ send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode);
spin_unlock(&inode->i_lock);
if (send) {
/* Send an async layoutreturn so we dont deadlock */
- pnfs_send_layoutreturn(lo, &stateid, iomode, false);
+ pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false);
}
} else
spin_unlock(&inode->i_lock);
@@ -1274,6 +1339,7 @@
.length = NFS4_MAX_UINT64,
};
LIST_HEAD(tmp_list);
+ const struct cred *cred;
nfs4_stateid stateid;
int status = 0;
bool send, valid_layout;
@@ -1309,13 +1375,15 @@
!valid_layout) {
spin_unlock(&ino->i_lock);
dprintk("NFS: %s no layout segments to return\n", __func__);
- goto out_put_layout_hdr;
+ goto out_wait_layoutreturn;
}
- send = pnfs_prepare_layoutreturn(lo, &stateid, NULL);
+ send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL);
spin_unlock(&ino->i_lock);
if (send)
- status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
+ status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY, true);
+out_wait_layoutreturn:
+ wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE);
out_put_layout_hdr:
pnfs_free_lseg_list(&tmp_list);
pnfs_put_layout_hdr(lo);
@@ -1354,13 +1422,14 @@
bool pnfs_roc(struct inode *ino,
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
- const struct rpc_cred *cred)
+ const struct cred *cred)
{
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, *next;
+ const struct cred *lc_cred;
nfs4_stateid stateid;
enum pnfs_iomode iomode = 0;
bool layoutreturn = false, roc = false;
@@ -1369,6 +1438,7 @@
if (!nfs_have_layout(ino))
return false;
retry:
+ rcu_read_lock();
spin_lock(&ino->i_lock);
lo = nfsi->layout;
if (!lo || !pnfs_layout_is_valid(lo) ||
@@ -1379,6 +1449,7 @@
pnfs_get_layout_hdr(lo);
if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) {
spin_unlock(&ino->i_lock);
+ rcu_read_unlock();
wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN,
TASK_UNINTERRUPTIBLE);
pnfs_put_layout_hdr(lo);
@@ -1392,7 +1463,7 @@
skip_read = true;
}
- list_for_each_entry(ctx, &nfsi->open_files, list) {
+ list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
state = ctx->state;
if (state == NULL)
continue;
@@ -1428,18 +1499,20 @@
* 2. we don't send layoutreturn
*/
/* lo ref dropped in pnfs_roc_release() */
- layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
+ layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &lc_cred, &iomode);
/* If the creds don't match, we can't compound the layoutreturn */
- if (!layoutreturn || cred != lo->plh_lc_cred)
+ if (!layoutreturn || cred_fscmp(cred, lc_cred) != 0)
goto out_noroc;
roc = layoutreturn;
pnfs_init_layoutreturn_args(args, lo, &stateid, iomode);
res->lrs_present = 0;
layoutreturn = false;
+ put_cred(lc_cred);
out_noroc:
spin_unlock(&ino->i_lock);
+ rcu_read_unlock();
pnfs_layoutcommit_inode(ino, true);
if (roc) {
struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
@@ -1449,9 +1522,53 @@
return true;
}
if (layoutreturn)
- pnfs_send_layoutreturn(lo, &stateid, iomode, true);
+ pnfs_send_layoutreturn(lo, &stateid, &lc_cred, iomode, true);
pnfs_put_layout_hdr(lo);
return false;
+}
+
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret)
+{
+ struct nfs4_layoutreturn_args *arg = *argpp;
+ int retval = -EAGAIN;
+
+ if (!arg)
+ return 0;
+ /* Handle Layoutreturn errors */
+ switch (*ret) {
+ case 0:
+ retval = 0;
+ break;
+ case -NFS4ERR_NOMATCHING_LAYOUT:
+ /* Was there an RPC level error? If not, retry */
+ if (task->tk_rpc_status == 0)
+ break;
+ /* If the call was not sent, let caller handle it */
+ if (!RPC_WAS_SENT(task))
+ return 0;
+ /*
+ * Otherwise, assume the call succeeded and
+ * that we need to release the layout
+ */
+ *ret = 0;
+ (*respp)->lrs_present = 0;
+ retval = 0;
+ break;
+ case -NFS4ERR_DELAY:
+ /* Let the caller handle the retry */
+ *ret = -NFS4ERR_NOMATCHING_LAYOUT;
+ return 0;
+ case -NFS4ERR_OLD_STATEID:
+ if (!nfs4_layout_refresh_old_stateid(&arg->stateid,
+ &arg->range, arg->inode))
+ break;
+ *ret = -NFS4ERR_NOMATCHING_LAYOUT;
+ return -EAGAIN;
+ }
+ *argpp = NULL;
+ *respp = NULL;
+ return retval;
}
void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
@@ -1475,16 +1592,16 @@
case 0:
if (res->lrs_present)
res_stateid = &res->stateid;
- /* Fallthrough */
+ fallthrough;
default:
arg_stateid = &args->stateid;
}
+ trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret);
pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
res_stateid);
if (ld_private && ld_private->ops && ld_private->ops->free)
ld_private->ops->free(ld_private);
pnfs_put_layout_hdr(lo);
- trace_nfs4_layoutreturn_on_close(args->inode, 0);
}
bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
@@ -1621,7 +1738,7 @@
INIT_LIST_HEAD(&lo->plh_return_segs);
INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
- lo->plh_lc_cred = get_rpccred(ctx->cred);
+ lo->plh_lc_cred = get_cred(ctx->cred);
lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID;
return lo;
}
@@ -1807,8 +1924,14 @@
static void nfs_layoutget_end(struct pnfs_layout_hdr *lo)
{
- if (atomic_dec_and_test(&lo->plh_outstanding))
- wake_up_var(&lo->plh_outstanding);
+ if (atomic_dec_and_test(&lo->plh_outstanding) &&
+ test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags))
+ wake_up_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN);
+}
+
+static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+ return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags);
}
static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
@@ -1823,15 +1946,14 @@
static void _add_to_server_list(struct pnfs_layout_hdr *lo,
struct nfs_server *server)
{
- if (list_empty(&lo->plh_layouts)) {
+ if (!test_and_set_bit(NFS_LAYOUT_HASHED, &lo->plh_flags)) {
struct nfs_client *clp = server->nfs_client;
/* 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);
- if (list_empty(&lo->plh_layouts))
- list_add_tail(&lo->plh_layouts, &server->layouts);
+ list_add_tail_rcu(&lo->plh_layouts, &server->layouts);
spin_unlock(&clp->cl_lock);
}
}
@@ -1886,6 +2008,7 @@
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) {
spin_unlock(&ino->i_lock);
+ lseg = ERR_PTR(-ENOMEM);
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_NOMEM);
goto out;
@@ -1910,15 +2033,36 @@
* If the layout segment list is empty, but there are outstanding
* layoutget calls, then they might be subject to a layoutrecall.
*/
- if (list_empty(&lo->plh_segs) &&
+ if (test_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags) &&
atomic_read(&lo->plh_outstanding) != 0) {
spin_unlock(&ino->i_lock);
- lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding,
- !atomic_read(&lo->plh_outstanding)));
+ lseg = ERR_PTR(wait_on_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN,
+ TASK_KILLABLE));
if (IS_ERR(lseg))
goto out_put_layout_hdr;
pnfs_put_layout_hdr(lo);
goto lookup_again;
+ }
+
+ /*
+ * Because we free lsegs when sending LAYOUTRETURN, we need to wait
+ * for LAYOUTRETURN.
+ */
+ if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+ spin_unlock(&ino->i_lock);
+ dprintk("%s wait for layoutreturn\n", __func__);
+ lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
+ if (!IS_ERR(lseg)) {
+ pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg,
+ PNFS_UPDATE_LAYOUT_RETRY);
+ goto lookup_again;
+ }
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_RETURN);
+ goto out_put_layout_hdr;
}
lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
@@ -1928,18 +2072,13 @@
goto out_unlock;
}
- if (!nfs4_valid_open_stateid(ctx->state)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_INVALID_OPEN);
- goto out_unlock;
- }
-
/*
* Choose a stateid for the LAYOUTGET. If we don't have a layout
* stateid, or it has been invalidated, then we must use the open
* stateid.
*/
if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+ int status;
/*
* The first layoutget for the file. Need to serialize per
@@ -1958,39 +2097,24 @@
goto lookup_again;
}
+ spin_unlock(&ino->i_lock);
first = true;
- if (nfs4_select_rw_stateid(ctx->state,
+ status = nfs4_select_rw_stateid(ctx->state,
iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ,
- NULL, &stateid, NULL) != 0) {
+ NULL, &stateid, NULL);
+ if (status != 0) {
+ lseg = ERR_PTR(status);
trace_pnfs_update_layout(ino, pos, count,
iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_INVALID_OPEN);
- goto out_unlock;
- }
- } else {
- nfs4_stateid_copy(&stateid, &lo->plh_stateid);
- }
-
- /*
- * Because we free lsegs before sending LAYOUTRETURN, we need to wait
- * for LAYOUTRETURN even if first is true.
- */
- if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
- spin_unlock(&ino->i_lock);
- dprintk("%s wait for layoutreturn\n", __func__);
- lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
- if (!IS_ERR(lseg)) {
- if (first)
- pnfs_clear_first_layoutget(lo);
+ nfs4_schedule_stateid_recovery(server, ctx->state);
+ pnfs_clear_first_layoutget(lo);
pnfs_put_layout_hdr(lo);
- dprintk("%s retrying\n", __func__);
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
- lseg, PNFS_UPDATE_LAYOUT_RETRY);
goto lookup_again;
}
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_RETURN);
- goto out_put_layout_hdr;
+ spin_lock(&ino->i_lock);
+ } else {
+ nfs4_stateid_copy(&stateid, &lo->plh_stateid);
}
if (pnfs_layoutgets_blocked(lo)) {
@@ -2013,6 +2137,7 @@
lgp = pnfs_alloc_init_layoutget_args(ino, ctx, &stateid, &arg, gfp_flags);
if (!lgp) {
+ lseg = ERR_PTR(-ENOMEM);
trace_pnfs_update_layout(ino, pos, count, iomode, lo, NULL,
PNFS_UPDATE_LAYOUT_NOMEM);
nfs_layoutget_end(lo);
@@ -2032,6 +2157,12 @@
case -ERECALLCONFLICT:
case -EAGAIN:
break;
+ case -ENODATA:
+ /* The server returned NFS4ERR_LAYOUTUNAVAILABLE */
+ pnfs_layout_set_fail_bit(
+ lo, pnfs_iomode_to_fail_bit(iomode));
+ lseg = NULL;
+ goto out_put_layout_hdr;
default:
if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
@@ -2054,6 +2185,8 @@
out_put_layout_hdr:
if (first)
pnfs_clear_first_layoutget(lo);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_EXIT);
pnfs_put_layout_hdr(lo);
out:
dprintk("%s: inode %s/%llu pNFS layout segment %s for "
@@ -2118,8 +2251,6 @@
pnfs_put_layout_hdr(lo);
return NULL;
}
-
-extern const nfs4_stateid current_stateid;
static void _lgopen_prepare_attached(struct nfs4_opendata *data,
struct nfs_open_context *ctx)
@@ -2285,17 +2416,20 @@
goto out_forget;
}
- if (!pnfs_layout_is_valid(lo)) {
- /* We have a completely new layout */
- pnfs_set_layout_stateid(lo, &res->stateid, true);
- } else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
+ if (test_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags) &&
+ !pnfs_is_first_layoutget(lo))
+ goto out_forget;
+
+ if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+ if (!pnfs_layout_is_valid(lo))
+ lo->plh_barrier = 0;
dprintk("%s forget reply due to sequence\n", __func__);
goto out_forget;
}
- pnfs_set_layout_stateid(lo, &res->stateid, false);
- } else {
+ pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false);
+ } else if (pnfs_layout_is_valid(lo)) {
/*
* We got an entirely new state ID. Mark all segments for the
* inode invalid, and retry the layoutget
@@ -2308,6 +2442,9 @@
pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
&range, 0);
goto out_forget;
+ } else {
+ /* We have a completely new layout */
+ pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
}
pnfs_get_lseg(lseg);
@@ -2389,42 +2526,158 @@
return -ENOENT;
}
-void pnfs_error_mark_layout_for_return(struct inode *inode,
- struct pnfs_layout_segment *lseg)
+static void
+pnfs_mark_layout_for_return(struct inode *inode,
+ const struct pnfs_layout_range *range)
{
- struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
- struct pnfs_layout_range range = {
- .iomode = lseg->pls_range.iomode,
- .offset = 0,
- .length = NFS4_MAX_UINT64,
- };
+ struct pnfs_layout_hdr *lo;
bool return_now = false;
spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
if (!pnfs_layout_is_valid(lo)) {
spin_unlock(&inode->i_lock);
return;
}
- pnfs_set_plh_return_info(lo, range.iomode, 0);
+ pnfs_set_plh_return_info(lo, range->iomode, 0);
/*
* 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.
*/
- if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, &range, 0) != -EBUSY) {
+ if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, range, 0) != -EBUSY) {
+ const struct cred *cred;
nfs4_stateid stateid;
enum pnfs_iomode iomode;
- return_now = pnfs_prepare_layoutreturn(lo, &stateid, &iomode);
+ return_now = pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode);
spin_unlock(&inode->i_lock);
if (return_now)
- pnfs_send_layoutreturn(lo, &stateid, iomode, false);
+ pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false);
} else {
spin_unlock(&inode->i_lock);
nfs_commit_inode(inode, 0);
}
}
+
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+ struct pnfs_layout_segment *lseg)
+{
+ struct pnfs_layout_range range = {
+ .iomode = lseg->pls_range.iomode,
+ .offset = 0,
+ .length = NFS4_MAX_UINT64,
+ };
+
+ pnfs_mark_layout_for_return(inode, &range);
+}
EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
+
+static bool
+pnfs_layout_can_be_returned(struct pnfs_layout_hdr *lo)
+{
+ return pnfs_layout_is_valid(lo) &&
+ !test_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags) &&
+ !test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+}
+
+static struct pnfs_layout_segment *
+pnfs_find_first_lseg(struct pnfs_layout_hdr *lo,
+ const struct pnfs_layout_range *range,
+ enum pnfs_iomode iomode)
+{
+ struct pnfs_layout_segment *lseg;
+
+ list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
+ if (!test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+ continue;
+ if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+ continue;
+ if (lseg->pls_range.iomode != iomode && iomode != IOMODE_ANY)
+ continue;
+ if (pnfs_lseg_range_intersecting(&lseg->pls_range, range))
+ return lseg;
+ }
+ return NULL;
+}
+
+/* Find open file states whose mode matches that of the range */
+static bool
+pnfs_should_return_unused_layout(struct pnfs_layout_hdr *lo,
+ const struct pnfs_layout_range *range)
+{
+ struct list_head *head;
+ struct nfs_open_context *ctx;
+ fmode_t mode = 0;
+
+ if (!pnfs_layout_can_be_returned(lo) ||
+ !pnfs_find_first_lseg(lo, range, range->iomode))
+ return false;
+
+ head = &NFS_I(lo->plh_inode)->open_files;
+ list_for_each_entry_rcu(ctx, head, list) {
+ if (ctx->state)
+ mode |= ctx->state->state & (FMODE_READ|FMODE_WRITE);
+ }
+
+ switch (range->iomode) {
+ default:
+ break;
+ case IOMODE_READ:
+ mode &= ~FMODE_WRITE;
+ break;
+ case IOMODE_RW:
+ if (pnfs_find_first_lseg(lo, range, IOMODE_READ))
+ mode &= ~FMODE_READ;
+ }
+ return mode == 0;
+}
+
+static int
+pnfs_layout_return_unused_byserver(struct nfs_server *server, void *data)
+{
+ const struct pnfs_layout_range *range = data;
+ struct pnfs_layout_hdr *lo;
+ struct inode *inode;
+restart:
+ rcu_read_lock();
+ list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) {
+ if (!pnfs_layout_can_be_returned(lo) ||
+ test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+ continue;
+ inode = lo->plh_inode;
+ spin_lock(&inode->i_lock);
+ if (!pnfs_should_return_unused_layout(lo, range)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ spin_unlock(&inode->i_lock);
+ inode = pnfs_grab_inode_layout_hdr(lo);
+ if (!inode)
+ continue;
+ rcu_read_unlock();
+ pnfs_mark_layout_for_return(inode, range);
+ iput(inode);
+ cond_resched();
+ goto restart;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+void
+pnfs_layout_return_unused_byclid(struct nfs_client *clp,
+ enum pnfs_iomode iomode)
+{
+ struct pnfs_layout_range range = {
+ .iomode = iomode,
+ .offset = 0,
+ .length = NFS4_MAX_UINT64,
+ };
+
+ nfs_client_for_each_server(clp, pnfs_layout_return_unused_byserver,
+ &range);
+}
void
pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio)
@@ -2441,7 +2694,7 @@
* Check for any intersection between the request and the pgio->pg_lseg,
* and if none, put this pgio->pg_lseg away.
*/
-static void
+void
pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
if (pgio->pg_lseg && !pnfs_lseg_request_intersecting(pgio->pg_lseg, req)) {
@@ -2449,6 +2702,7 @@
pgio->pg_lseg = NULL;
}
}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_range);
void
pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
@@ -2464,7 +2718,7 @@
rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
req_offset(req),
rd_size,
IOMODE_READ,
@@ -2491,12 +2745,12 @@
pnfs_generic_pg_check_range(pgio, req);
if (pgio->pg_lseg == NULL) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
+ nfs_req_openctx(req),
req_offset(req),
wb_size,
IOMODE_RW,
false,
- GFP_NOFS);
+ GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
@@ -2768,7 +3022,8 @@
}
/* Resend all requests through pnfs. */
-void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr,
+ unsigned int mirror_idx)
{
struct nfs_pageio_descriptor pgio;
@@ -2779,6 +3034,7 @@
nfs_pageio_init_read(&pgio, hdr->inode, false,
hdr->completion_ops);
+ pgio.pg_mirror_idx = mirror_idx;
hdr->task.tk_status = nfs_pageio_resend(&pgio, hdr);
}
}
@@ -2966,10 +3222,10 @@
end_pos = nfsi->layout->plh_lwb;
nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid);
+ data->cred = get_cred(nfsi->layout->plh_lc_cred);
spin_unlock(&inode->i_lock);
data->args.inode = inode;
- data->cred = get_rpccred(nfsi->layout->plh_lc_cred);
nfs_fattr_init(&data->fattr);
data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
data->res.fattr = &data->fattr;
@@ -2982,7 +3238,7 @@
if (ld->prepare_layoutcommit) {
status = ld->prepare_layoutcommit(&data->args);
if (status) {
- put_rpccred(data->cred);
+ put_cred(data->cred);
spin_lock(&inode->i_lock);
set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
if (end_pos > nfsi->layout->plh_lwb)
--
Gitblit v1.6.2