[PATCH v2 39/40] afs: Fix offline and busy message emission

From: David Howells
Date: Wed Dec 13 2023 - 08:53:12 EST


The current code assumes that offline and busy volume states apply to all
instances of a volume, not just the one on the server that returned
VOFFLINE or VBUSY and will emit a notice to dmesg suggesting that the
entire volume is unavailable.

Fix that by moving the flags recording this to the afs_server_entry struct
that is used to represent a particular instance of a volume on a specific
server. The notice is altered to include the server UUID also.

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Marc Dionne <marc.dionne@xxxxxxxxxxxx>
cc: linux-afs@xxxxxxxxxxxxxxxxxxx
---
fs/afs/internal.h | 8 ++++----
fs/afs/rotate.c | 31 +++++++++++++++++++++----------
2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index e3e373c1fecf..a6a4fc417dba 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -612,6 +612,8 @@ struct afs_server_entry {
time64_t cb_expires_at; /* Time at which volume-level callback expires */
unsigned long flags;
#define AFS_SE_EXCLUDED 0 /* Set if server is to be excluded in rotation */
+#define AFS_SE_VOLUME_OFFLINE 1 /* Set if volume offline notice given */
+#define AFS_SE_VOLUME_BUSY 2 /* Set if volume busy notice given */
};

struct afs_server_list {
@@ -645,10 +647,8 @@ struct afs_volume {
#define AFS_VOLUME_UPDATING 1 /* - T if an update is in progress */
#define AFS_VOLUME_WAIT 2 /* - T if users must wait for update */
#define AFS_VOLUME_DELETED 3 /* - T if volume appears deleted */
-#define AFS_VOLUME_OFFLINE 4 /* - T if volume offline notice given */
-#define AFS_VOLUME_BUSY 5 /* - T if volume busy notice given */
-#define AFS_VOLUME_MAYBE_NO_IBULK 6 /* - T if some servers don't have InlineBulkStatus */
-#define AFS_VOLUME_RM_TREE 7 /* - Set if volume removed from cell->volumes */
+#define AFS_VOLUME_MAYBE_NO_IBULK 4 /* - T if some servers don't have InlineBulkStatus */
+#define AFS_VOLUME_RM_TREE 5 /* - Set if volume removed from cell->volumes */
#ifdef CONFIG_AFS_FSCACHE
struct fscache_volume *cache; /* Caching cookie */
#endif
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index ef7fe70777be..700a27bc8c25 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -111,7 +111,7 @@ static bool afs_start_fs_iteration(struct afs_operation *op,
/*
* Post volume busy note.
*/
-static void afs_busy(struct afs_volume *volume, u32 abort_code)
+static void afs_busy(struct afs_operation *op, u32 abort_code)
{
const char *m;

@@ -122,7 +122,8 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code)
default: m = "busy"; break;
}

- pr_notice("kAFS: Volume %llu '%s' is %s\n", volume->vid, volume->name, m);
+ pr_notice("kAFS: Volume %llu '%s' on server %pU is %s\n",
+ op->volume->vid, op->volume->name, &op->server->uuid, m);
}

/*
@@ -181,6 +182,10 @@ bool afs_select_fileserver(struct afs_operation *op)
/* Evaluate the result of the previous operation, if there was one. */
switch (op->call_error) {
case 0:
+ clear_bit(AFS_SE_VOLUME_OFFLINE,
+ &op->server_list->servers[op->server_index].flags);
+ clear_bit(AFS_SE_VOLUME_BUSY,
+ &op->server_list->servers[op->server_index].flags);
op->cumul_error.responded = true;

/* We succeeded, but we may need to redo the op from another
@@ -314,9 +319,11 @@ bool afs_select_fileserver(struct afs_operation *op)
* expected to come back but it might take a long time (could be
* days).
*/
- if (!test_and_set_bit(AFS_VOLUME_OFFLINE, &op->volume->flags)) {
- afs_busy(op->volume, abort_code);
- clear_bit(AFS_VOLUME_BUSY, &op->volume->flags);
+ if (!test_and_set_bit(AFS_SE_VOLUME_OFFLINE,
+ &op->server_list->servers[op->server_index].flags)) {
+ afs_busy(op, abort_code);
+ clear_bit(AFS_SE_VOLUME_BUSY,
+ &op->server_list->servers[op->server_index].flags);
}
if (op->flags & AFS_OPERATION_NO_VSLEEP) {
afs_op_set_error(op, -EADV);
@@ -343,9 +350,11 @@ bool afs_select_fileserver(struct afs_operation *op)
afs_op_set_error(op, -EBUSY);
goto failed;
}
- if (!test_and_set_bit(AFS_VOLUME_BUSY, &op->volume->flags)) {
- afs_busy(op->volume, abort_code);
- clear_bit(AFS_VOLUME_OFFLINE, &op->volume->flags);
+ if (!test_and_set_bit(AFS_SE_VOLUME_BUSY,
+ &op->server_list->servers[op->server_index].flags)) {
+ afs_busy(op, abort_code);
+ clear_bit(AFS_SE_VOLUME_OFFLINE,
+ &op->server_list->servers[op->server_index].flags);
}
busy:
if (op->flags & AFS_OPERATION_CUR_ONLY) {
@@ -426,8 +435,10 @@ bool afs_select_fileserver(struct afs_operation *op)
default:
afs_op_accumulate_error(op, error, abort_code);
failed_but_online:
- clear_bit(AFS_VOLUME_OFFLINE, &op->volume->flags);
- clear_bit(AFS_VOLUME_BUSY, &op->volume->flags);
+ clear_bit(AFS_SE_VOLUME_OFFLINE,
+ &op->server_list->servers[op->server_index].flags);
+ clear_bit(AFS_SE_VOLUME_BUSY,
+ &op->server_list->servers[op->server_index].flags);
goto failed;
}