afs: Allow dumping of server cursor on operation failure

Provide an option to allow the file or volume location server cursor to be
dumped if the rotation routine falls off the end without managing to
contact a server.

Signed-off-by: David Howells <dhowells@redhat.com>

5 files changed, 127 insertions, 0 deletions

diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig
index ebba3b18e5da..701aaa9b1899 100644
--- a/fs/afs/Kconfig
+++ b/fs/afs/Kconfig
@@ -27,3 +27,15 @@ config AFS_FSCACHE
 	help
 	  Say Y here if you want AFS data to be cached locally on disk through
 	  the generic filesystem cache manager
+
+config AFS_DEBUG_CURSOR
+	bool "AFS server cursor debugging"
+	depends on AFS_FS
+	help
+	  Say Y here to cause the contents of a server cursor to be dumped to
+	  the dmesg log if the server rotation algorithm fails to successfully
+	  contact a server.
+
+	  See <file:Documentation/filesystems/afs.txt> for more information.
+
+	  If unsure, say N.
diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c
index 3f60b4012587..bc5ce31a4ae4 100644
--- a/fs/afs/addr_list.c
+++ b/fs/afs/addr_list.c
@@ -358,6 +358,8 @@ bool afs_iterate_addresses(struct afs_addr_cursor *ac)
 	if (!ac->alist)
 		return false;
 
+	ac->nr_iterations++;
+
 	if (ac->begun) {
 		ac->index++;
 		if (ac->index == ac->alist->nr_addrs)
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index ce79bd514331..ac9da1e4050e 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -660,6 +660,7 @@ struct afs_addr_cursor {
 	short			error;
 	bool			begun;		/* T if we've begun iteration */
 	bool			responded;	/* T if the current address responded */
+	unsigned short		nr_iterations;	/* Number of address iterations */
 };
 
 /*
@@ -677,6 +678,7 @@ struct afs_vl_cursor {
 #define AFS_VL_CURSOR_STOP	0x0001		/* Set to cease iteration */
 #define AFS_VL_CURSOR_RETRY	0x0002		/* Set to do a retry */
 #define AFS_VL_CURSOR_RETRIED	0x0004		/* Set if started a retry */
+	unsigned short		nr_iterations;	/* Number of server iterations */
 };
 
 /*
@@ -700,6 +702,7 @@ struct afs_fs_cursor {
 #define AFS_FS_CURSOR_VNOVOL	0x0008		/* Set if seen VNOVOL */
 #define AFS_FS_CURSOR_CUR_ONLY	0x0010		/* Set if current server only (file lock held) */
 #define AFS_FS_CURSOR_NO_VSLEEP	0x0020		/* Set to prevent sleep on VBUSY, VOFFLINE, ... */
+	unsigned short		nr_iterations;	/* Number of server iterations */
 };
 
 /*
diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c
index 41405dde0113..7c4487781637 100644
--- a/fs/afs/rotate.c
+++ b/fs/afs/rotate.c
@@ -156,6 +156,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc)
 		return false;
 	}
 
+	fc->nr_iterations++;
+
 	/* Evaluate the result of the previous operation, if there was one. */
 	switch (error) {
 	case SHRT_MAX:
@@ -520,12 +522,67 @@ iterate_address:
 }
 
 /*
+ * Dump cursor state in the case of the error being EDESTADDRREQ.
+ */
+static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc)
+{
+	static int count;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3)
+		return;
+	count++;
+
+	rcu_read_lock();
+
+	pr_notice("EDESTADDR occurred\n");
+	pr_notice("FC: cbb=%x cbb2=%x fl=%hx err=%hd\n",
+		  fc->cb_break, fc->cb_break_2, fc->flags, fc->error);
+	pr_notice("FC: st=%u ix=%u ni=%u\n",
+		  fc->start, fc->index, fc->nr_iterations);
+
+	if (fc->server_list) {
+		const struct afs_server_list *sl = fc->server_list;
+		pr_notice("FC: SL nr=%u ix=%u vnov=%hx\n",
+			  sl->nr_servers, sl->index, sl->vnovol_mask);
+		for (i = 0; i < sl->nr_servers; i++) {
+			const struct afs_server *s = sl->servers[i].server;
+			pr_notice("FC: server fl=%lx av=%u %pU\n",
+				  s->flags, s->addr_version, &s->uuid);
+			if (s->addresses) {
+				const struct afs_addr_list *a =
+					rcu_dereference(s->addresses);
+				pr_notice("FC:  - av=%u nr=%u/%u/%u ax=%u\n",
+					  a->version,
+					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
+					  a->index);
+				pr_notice("FC:  - pr=%lx yf=%lx\n",
+					  a->probed, a->yfs);
+				if (a == fc->ac.alist)
+					pr_notice("FC:  - current\n");
+			}
+		}
+	}
+
+	pr_notice("AC: as=%u ax=%u ac=%d er=%d b=%u r=%u ni=%u\n",
+		  fc->ac.start, fc->ac.index, fc->ac.abort_code, fc->ac.error,
+		  fc->ac.begun, fc->ac.responded, fc->ac.nr_iterations);
+
+	rcu_read_unlock();
+}
+
+/*
  * Tidy up a filesystem cursor and unlock the vnode.
  */
 int afs_end_vnode_operation(struct afs_fs_cursor *fc)
 {
 	struct afs_net *net = afs_v2net(fc->vnode);
 
+	if (fc->error == -EDESTADDRREQ ||
+	    fc->error == -ENETUNREACH ||
+	    fc->error == -EHOSTUNREACH)
+		afs_dump_edestaddrreq(fc);
+
 	mutex_unlock(&fc->vnode->io_lock);
 
 	afs_end_cursor(&fc->ac);
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index 44a936ad9c7a..5b99ea7be194 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -83,6 +83,8 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc)
 		return false;
 	}
 
+	vc->nr_iterations++;
+
 	/* Evaluate the result of the previous operation, if there was one. */
 	switch (error) {
 	case SHRT_MAX:
@@ -235,12 +237,63 @@ failed:
 }
 
 /*
+ * Dump cursor state in the case of the error being EDESTADDRREQ.
+ */
+static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc)
+{
+	static int count;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3)
+		return;
+	count++;
+
+	rcu_read_lock();
+	pr_notice("EDESTADDR occurred\n");
+	pr_notice("VC: st=%u ix=%u ni=%hu fl=%hx err=%hd\n",
+		  vc->start, vc->index, vc->nr_iterations, vc->flags, vc->error);
+
+	if (vc->server_list) {
+		const struct afs_vlserver_list *sl = vc->server_list;
+		pr_notice("VC: SL nr=%u ix=%u\n",
+			  sl->nr_servers, sl->index);
+		for (i = 0; i < sl->nr_servers; i++) {
+			const struct afs_vlserver *s = sl->servers[i].server;
+			pr_notice("VC: server fl=%lx %s+%hu\n",
+				  s->flags, s->name, s->port);
+			if (s->addresses) {
+				const struct afs_addr_list *a =
+					rcu_dereference(s->addresses);
+				pr_notice("VC:  - av=%u nr=%u/%u/%u ax=%u\n",
+					  a->version,
+					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
+					  a->index);
+				pr_notice("VC:  - pr=%lx yf=%lx\n",
+					  a->probed, a->yfs);
+				if (a == vc->ac.alist)
+					pr_notice("VC:  - current\n");
+			}
+		}
+	}
+
+	pr_notice("AC: as=%u ax=%u ac=%d er=%d b=%u r=%u ni=%hu\n",
+		  vc->ac.start, vc->ac.index, vc->ac.abort_code, vc->ac.error,
+		  vc->ac.begun, vc->ac.responded, vc->ac.nr_iterations);
+	rcu_read_unlock();
+}
+
+/*
  * Tidy up a volume location server cursor and unlock the vnode.
  */
 int afs_end_vlserver_operation(struct afs_vl_cursor *vc)
 {
 	struct afs_net *net = vc->cell->net;
 
+	if (vc->error == -EDESTADDRREQ ||
+	    vc->error == -ENETUNREACH ||
+	    vc->error == -EHOSTUNREACH)
+		afs_vl_dump_edestaddrreq(vc);
+
 	afs_end_cursor(&vc->ac);
 	afs_put_vlserverlist(net, vc->server_list);