[PATCH v2 12/23] NFSv4/flexfiles: Implement in-place device re-resolve on CHANGE

[Benjamin Coddington <ben.coddington@hammerspace.com>]

Implement the reresolve_deviceid hook: walk the layout's mirrors and,
for every stripe whose raw deviceid matches the changed one, exchange
the pinned device node out for NULL.  In-flight I/O completes on the old
node through its own reference; the next I/O to the stripe re-resolves
via ff_layout_get_mirror_ds() and picks up the server's new mapping
with a fresh GETDEVICEINFO.  The un-pinned references are handed back
on the walker's list to be put outside the locks.

Matching uses the raw deviceid decoded from the layout (dss[].devid), so
a stripe that was never resolved, or already exchanged, is left alone.
A stripe whose resolution previously failed holds an ERR_PTR sentinel
rather than a node; that is cleared too, so the stripe retries
GETDEVICEINFO on its next I/O.  Nothing dispatches CHANGE to the walker
yet: no behavior change.

Assisted-by: Claude:claude-fable-5
Signed-off-by: Benjamin Coddington <bcodding@hammerspace.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 40 ++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 3572324630df..46ca58e8e96b 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -2508,6 +2508,45 @@ static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg)
 	}
 }
 
+/*
+ * Un-pin every stripe node resolved from @id: in-flight I/O drains on the
+ * old node through its own reference, the next I/O re-resolves.
+ */
+static void ff_layout_reresolve_deviceid(struct pnfs_layout_hdr *lo,
+					 const struct nfs4_deviceid *id,
+					 bool immediate,
+					 struct list_head *head)
+{
+	struct nfs4_flexfile_layout *flo = FF_LAYOUT_FROM_HDR(lo);
+	struct nfs4_ff_layout_mirror *mirror;
+	struct nfs4_ff_layout_ds *old;
+	struct nfs4_deviceid_put *put;
+	u32 dss_id;
+
+	list_for_each_entry(mirror, &flo->mirrors, mirrors) {
+		for (dss_id = 0; dss_id < mirror->dss_count; dss_id++) {
+			if (memcmp(&mirror->dss[dss_id].devid, id,
+				   sizeof(*id)) != 0)
+				continue;
+			/* Allocate before un-pinning: on failure the reference
+			 * stays put rather than being dropped here, where the
+			 * final put may not sleep.
+			 */
+			put = kzalloc_obj(*put, GFP_ATOMIC);
+			if (!put)
+				continue;
+			old = unrcu_pointer(
+				xchg(&mirror->dss[dss_id].mirror_ds, NULL));
+			if (IS_ERR_OR_NULL(old)) {
+				kfree(put);
+				continue;
+			}
+			put->dev = &old->id_node;
+			list_add(&put->node, head);
+		}
+	}
+}
+
 static struct pnfs_ds_commit_info *
 ff_layout_get_ds_info(struct inode *inode)
 {
@@ -3089,6 +3128,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.pg_write_ops		= &ff_layout_pg_write_ops,
 	.get_ds_info		= ff_layout_get_ds_info,
 	.free_deviceid_node	= ff_layout_free_deviceid_node,
+	.reresolve_deviceid	= ff_layout_reresolve_deviceid,
 	.read_pagelist		= ff_layout_read_pagelist,
 	.write_pagelist		= ff_layout_write_pagelist,
 	.alloc_deviceid_node    = ff_layout_alloc_deviceid_node,
-- 
2.53.0