rxrpc, afs: Allow afs to pin rxrpc_peer objects

Change rxrpc's API such that:

 (1) A new function, rxrpc_kernel_lookup_peer(), is provided to look up an
     rxrpc_peer record for a remote address and a corresponding function,
     rxrpc_kernel_put_peer(), is provided to dispose of it again.

 (2) When setting up a call, the rxrpc_peer object used during a call is
     now passed in rather than being set up by rxrpc_connect_call().  For
     afs, this meenat passing it to rxrpc_kernel_begin_call() rather than
     the full address (the service ID then has to be passed in as a
     separate parameter).

 (3) A new function, rxrpc_kernel_remote_addr(), is added so that afs can
     get a pointer to the transport address for display purposed, and
     another, rxrpc_kernel_remote_srx(), to gain a pointer to the full
     rxrpc address.

 (4) The function to retrieve the RTT from a call, rxrpc_kernel_get_srtt(),
     is then altered to take a peer.  This now returns the RTT or -1 if
     there are insufficient samples.

 (5) Rename rxrpc_kernel_get_peer() to rxrpc_kernel_call_get_peer().

 (6) Provide a new function, rxrpc_kernel_get_peer(), to get a ref on a
     peer the caller already has.

This allows the afs filesystem to pin the rxrpc_peer records that it is
using, allowing faster lookups and pointer comparisons rather than
comparing sockaddr_rxrpc contents.  It also makes it easier to get hold of
the RTT.  The following changes are made to afs:

 (1) The addr_list struct's addrs[] elements now hold a peer struct pointer
     and a service ID rather than a sockaddr_rxrpc.

 (2) When displaying the transport address, rxrpc_kernel_remote_addr() is
     used.

 (3) The port arg is removed from afs_alloc_addrlist() since it's always
     overridden.

 (4) afs_merge_fs_addr4() and afs_merge_fs_addr6() do peer lookup and may
     now return an error that must be handled.

 (5) afs_find_server() now takes a peer pointer to specify the address.

 (6) afs_find_server(), afs_compare_fs_alists() and afs_merge_fs_addr[46]{}
     now do peer pointer comparison rather than address comparison.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org

fs/afs/addr_list.c

@@ -13,26 +13,33 @@
 #include "internal.h"
 #include "afs_fs.h"
 
+static void afs_free_addrlist(struct rcu_head *rcu)
+{
+	struct afs_addr_list *alist = container_of(rcu, struct afs_addr_list, rcu);
+	unsigned int i;
+
+	for (i = 0; i < alist->nr_addrs; i++)
+		rxrpc_kernel_put_peer(alist->addrs[i].peer);
+}
+
 /*
  * Release an address list.
  */
 void afs_put_addrlist(struct afs_addr_list *alist)
 {
 	if (alist && refcount_dec_and_test(&alist->usage))
-		kfree_rcu(alist, rcu);
+		call_rcu(&alist->rcu, afs_free_addrlist);
 }
 
 /*
  * Allocate an address list.
  */
-struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
-					 unsigned short service,
-					 unsigned short port)
+struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id)
 {
 	struct afs_addr_list *alist;
 	unsigned int i;
 
-	_enter("%u,%u,%u", nr, service, port);
+	_enter("%u,%u", nr, service_id);
 
 	if (nr > AFS_MAX_ADDRESSES)
 		nr = AFS_MAX_ADDRESSES;
@@ -44,16 +51,8 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr,
 	refcount_set(&alist->usage, 1);
 	alist->max_addrs = nr;
 
-	for (i = 0; i < nr; i++) {
-		struct sockaddr_rxrpc *srx = &alist->addrs[i].srx;
-		srx->srx_family			= AF_RXRPC;
-		srx->srx_service		= service;
-		srx->transport_type		= SOCK_DGRAM;
-		srx->transport_len		= sizeof(srx->transport.sin6);
-		srx->transport.sin6.sin6_family	= AF_INET6;
-		srx->transport.sin6.sin6_port	= htons(port);
-	}
-
+	for (i = 0; i < nr; i++)
+		alist->addrs[i].service_id = service_id;
 	return alist;
 }
 
@@ -126,7 +125,7 @@ struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
 	if (!vllist->servers[0].server)
 		goto error_vl;
 
-	alist = afs_alloc_addrlist(nr, service, AFS_VL_PORT);
+	alist = afs_alloc_addrlist(nr, service);
 	if (!alist)
 		goto error;
 
@@ -197,9 +196,11 @@ struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net,
 		}
 
 		if (family == AF_INET)
-			afs_merge_fs_addr4(alist, x[0], xport);
+			ret = afs_merge_fs_addr4(net, alist, x[0], xport);
 		else
-			afs_merge_fs_addr6(alist, x, xport);
+			ret = afs_merge_fs_addr6(net, alist, x, xport);
+		if (ret < 0)
+			goto error;
 
 	} while (p < end);
 
@@ -271,25 +272,33 @@ struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry
 /*
  * Merge an IPv4 entry into a fileserver address list.
  */
-void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
+int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist,
+		       __be32 xdr, u16 port)
 {
-	struct sockaddr_rxrpc *srx;
-	u32 addr = ntohl(xdr);
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_peer *peer;
 	int i;
 
 	if (alist->nr_addrs >= alist->max_addrs)
-		return;
+		return 0;
 
-	for (i = 0; i < alist->nr_ipv4; i++) {
-		struct sockaddr_in *a = &alist->addrs[i].srx.transport.sin;
-		u32 a_addr = ntohl(a->sin_addr.s_addr);
-		u16 a_port = ntohs(a->sin_port);
+	srx.srx_family = AF_RXRPC;
+	srx.transport_type = SOCK_DGRAM;
+	srx.transport_len = sizeof(srx.transport.sin);
+	srx.transport.sin.sin_family = AF_INET;
+	srx.transport.sin.sin_port = htons(port);
+	srx.transport.sin.sin_addr.s_addr = xdr;
 
-		if (addr == a_addr && port == a_port)
-			return;
-		if (addr == a_addr && port < a_port)
-			break;
-		if (addr < a_addr)
+	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	for (i = 0; i < alist->nr_ipv4; i++) {
+		if (peer == alist->addrs[i].peer) {
+			rxrpc_kernel_put_peer(peer);
+			return 0;
+		}
+		if (peer <= alist->addrs[i].peer)
 			break;
 	}
 
@@ -298,54 +307,52 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port)
 			alist->addrs + i,
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
 
-	srx = &alist->addrs[i].srx;
-	srx->srx_family = AF_RXRPC;
-	srx->transport_type = SOCK_DGRAM;
-	srx->transport_len = sizeof(srx->transport.sin);
-	srx->transport.sin.sin_family = AF_INET;
-	srx->transport.sin.sin_port = htons(port);
-	srx->transport.sin.sin_addr.s_addr = xdr;
+	alist->addrs[i].peer = peer;
 	alist->nr_ipv4++;
 	alist->nr_addrs++;
+	return 0;
 }
 
 /*
  * Merge an IPv6 entry into a fileserver address list.
  */
-void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port)
+int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist,
+		       __be32 *xdr, u16 port)
 {
-	struct sockaddr_rxrpc *srx;
-	int i, diff;
+	struct sockaddr_rxrpc srx;
+	struct rxrpc_peer *peer;
+	int i;
 
 	if (alist->nr_addrs >= alist->max_addrs)
-		return;
+		return 0;
 
-	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
-		struct sockaddr_in6 *a = &alist->addrs[i].srx.transport.sin6;
-		u16 a_port = ntohs(a->sin6_port);
+	srx.srx_family = AF_RXRPC;
+	srx.transport_type = SOCK_DGRAM;
+	srx.transport_len = sizeof(srx.transport.sin6);
+	srx.transport.sin6.sin6_family = AF_INET6;
+	srx.transport.sin6.sin6_port = htons(port);
+	memcpy(&srx.transport.sin6.sin6_addr, xdr, 16);
 
-		diff = memcmp(xdr, &a->sin6_addr, 16);
-		if (diff == 0 && port == a_port)
-			return;
-		if (diff == 0 && port < a_port)
-			break;
-		if (diff < 0)
+	peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL);
+	if (!peer)
+		return -ENOMEM;
+
+	for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) {
+		if (peer == alist->addrs[i].peer) {
+			rxrpc_kernel_put_peer(peer);
+			return 0;
+		}
+		if (peer <= alist->addrs[i].peer)
 			break;
 	}
 
 	if (i < alist->nr_addrs)
 		memmove(alist->addrs + i + 1,
 			alist->addrs + i,
 			sizeof(alist->addrs[0]) * (alist->nr_addrs - i));
-
-	srx = &alist->addrs[i].srx;
-	srx->srx_family = AF_RXRPC;
-	srx->transport_type = SOCK_DGRAM;
-	srx->transport_len = sizeof(srx->transport.sin6);
-	srx->transport.sin6.sin6_family = AF_INET6;
-	srx->transport.sin6.sin6_port = htons(port);
-	memcpy(&srx->transport.sin6.sin6_addr, xdr, 16);
+	alist->addrs[i].peer = peer;
 	alist->nr_addrs++;
+	return 0;
 }
 
 /*

fs/afs/cmservice.c

@@ -146,10 +146,11 @@ static int afs_find_cm_server_by_peer(struct afs_call *call)
 {
 	struct sockaddr_rxrpc srx;
 	struct afs_server *server;
+	struct rxrpc_peer *peer;
 
-	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);
+	peer = rxrpc_kernel_get_call_peer(call->net->socket, call->rxcall);
 
-	server = afs_find_server(call->net, &srx);
+	server = afs_find_server(call->net, peer);
 	if (!server) {
 		trace_afs_cm_no_server(call, &srx);
 		return 0;

fs/afs/fs_probe.c

@@ -101,6 +101,7 @@ static void afs_fs_probe_not_done(struct afs_net *net,
 void afs_fileserver_probe_result(struct afs_call *call)
 {
 	struct afs_addr_list *alist = call->alist;
+	struct afs_address *addr = &alist->addrs[call->addr_ix];
 	struct afs_server *server = call->server;
 	unsigned int index = call->addr_ix;
 	unsigned int rtt_us = 0, cap0;
@@ -153,12 +154,12 @@ void afs_fileserver_probe_result(struct afs_call *call)
 	if (call->service_id == YFS_FS_SERVICE) {
 		server->probe.is_yfs = true;
 		set_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
-		alist->addrs[index].srx.srx_service = call->service_id;
+		addr->service_id = call->service_id;
 	} else {
 		server->probe.not_yfs = true;
 		if (!server->probe.is_yfs) {
 			clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
-			alist->addrs[index].srx.srx_service = call->service_id;
+			addr->service_id = call->service_id;
 		}
 		cap0 = ntohl(call->tmp);
 		if (cap0 & AFS3_VICED_CAPABILITY_64BITFILES)
@@ -167,7 +168,7 @@ void afs_fileserver_probe_result(struct afs_call *call)
 			clear_bit(AFS_SERVER_FL_HAS_FS64, &server->flags);
 	}
 
-	rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us);
+	rtt_us = rxrpc_kernel_get_srtt(addr->peer);
 	if (rtt_us < server->probe.rtt) {
 		server->probe.rtt = rtt_us;
 		server->rtt = rtt_us;
@@ -181,8 +182,8 @@ void afs_fileserver_probe_result(struct afs_call *call)
 out:
 	spin_unlock(&server->probe_lock);
 
-	_debug("probe %pU [%u] %pISpc rtt=%u ret=%d",
-	       &server->uuid, index, &alist->addrs[index].srx.transport,
+	_debug("probe %pU [%u] %pISpc rtt=%d ret=%d",
+	       &server->uuid, index, rxrpc_kernel_remote_addr(alist->addrs[index].peer),
 	       rtt_us, ret);
 
 	return afs_done_one_fs_probe(call->net, server);

fs/afs/internal.h

@@ -72,6 +72,11 @@ enum afs_call_state {
 	AFS_CALL_COMPLETE,		/* Completed or failed */
 };
 
+struct afs_address {
+	struct rxrpc_peer	*peer;
+	u16			service_id;
+};
+
 /*
  * List of server addresses.
  */
@@ -87,9 +92,7 @@ struct afs_addr_list {
 	enum dns_lookup_status	status:8;
 	unsigned long		failed;		/* Mask of addrs that failed locally/ICMP */
 	unsigned long		responded;	/* Mask of addrs that responded */
-	struct {
-		struct sockaddr_rxrpc	srx;
-	} addrs[] __counted_by(max_addrs);
+	struct afs_address	addrs[] __counted_by(max_addrs);
 #define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8))
 };
 
@@ -420,7 +423,7 @@ struct afs_vlserver {
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT in uS */
+		unsigned int	rtt;		/* Best RTT in uS (or UINT_MAX) */
 		u32		abort_code;
 		short		error;
 		unsigned short	flags;
@@ -537,7 +540,7 @@ struct afs_server {
 	atomic_t		probe_outstanding;
 	spinlock_t		probe_lock;
 	struct {
-		unsigned int	rtt;		/* RTT in uS */
+		unsigned int	rtt;		/* Best RTT in uS (or UINT_MAX) */
 		u32		abort_code;
 		short		error;
 		bool		responded:1;
@@ -964,9 +967,7 @@ static inline struct afs_addr_list *afs_get_addrlist(struct afs_addr_list *alist
 		refcount_inc(&alist->usage);
 	return alist;
 }
-extern struct afs_addr_list *afs_alloc_addrlist(unsigned int,
-						unsigned short,
-						unsigned short);
+extern struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, u16 service_id);
 extern void afs_put_addrlist(struct afs_addr_list *);
 extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *,
 						      const char *, size_t, char,
@@ -977,8 +978,10 @@ extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *);
 extern bool afs_iterate_addresses(struct afs_addr_cursor *);
 extern int afs_end_cursor(struct afs_addr_cursor *);
 
-extern void afs_merge_fs_addr4(struct afs_addr_list *, __be32, u16);
-extern void afs_merge_fs_addr6(struct afs_addr_list *, __be32 *, u16);
+extern int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *addr,
+			      __be32 xdr, u16 port);
+extern int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *addr,
+			      __be32 *xdr, u16 port);
 
 /*
  * callback.c
@@ -1405,8 +1408,7 @@ extern void __exit afs_clean_up_permit_cache(void);
  */
 extern spinlock_t afs_server_peer_lock;
 
-extern struct afs_server *afs_find_server(struct afs_net *,
-					  const struct sockaddr_rxrpc *);
+extern struct afs_server *afs_find_server(struct afs_net *, const struct rxrpc_peer *);
 extern struct afs_server *afs_find_server_by_uuid(struct afs_net *, const uuid_t *);
 extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *, u32);
 extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace);

fs/afs/proc.c

@@ -307,7 +307,7 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v)
 		for (i = 0; i < alist->nr_addrs; i++)
 			seq_printf(m, " %c %pISpc\n",
 				   alist->preferred == i ? '>' : '-',
-				   &alist->addrs[i].srx.transport);
+				   rxrpc_kernel_remote_addr(alist->addrs[i].peer));
 	}
 	seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt);
 	seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n",
@@ -398,9 +398,10 @@ static int afs_proc_servers_show(struct seq_file *m, void *v)
 	seq_printf(m, "  - ALIST v=%u rsp=%lx f=%lx\n",
 		   alist->version, alist->responded, alist->failed);
 	for (i = 0; i < alist->nr_addrs; i++)
-		seq_printf(m, "    [%x] %pISpc%s\n",
-			   i, &alist->addrs[i].srx.transport,
-			   alist->preferred == i ? "*" : "");
+		seq_printf(m, "    [%x] %pISpc%s rtt=%d\n",
+			   i, rxrpc_kernel_remote_addr(alist->addrs[i].peer),
+			   alist->preferred == i ? "*" : "",
+			   rxrpc_kernel_get_srtt(alist->addrs[i].peer));
 	return 0;
 }
 

fs/afs/rotate.c

@@ -113,7 +113,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	struct afs_server *server;
 	struct afs_vnode *vnode = op->file[0].vnode;
 	struct afs_error e;
-	u32 rtt;
+	unsigned int rtt;
 	int error = op->ac.error, i;
 
 	_enter("%lx[%d],%lx[%d],%d,%d",
@@ -420,7 +420,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 	}
 
 	op->index = -1;
-	rtt = U32_MAX;
+	rtt = UINT_MAX;
 	for (i = 0; i < op->server_list->nr_servers; i++) {
 		struct afs_server *s = op->server_list->servers[i].server;
 
@@ -488,7 +488,7 @@ bool afs_select_fileserver(struct afs_operation *op)
 
 	_debug("address [%u] %u/%u %pISp",
 	       op->index, op->ac.index, op->ac.alist->nr_addrs,
-	       &op->ac.alist->addrs[op->ac.index].srx.transport);
+	       rxrpc_kernel_remote_addr(op->ac.alist->addrs[op->ac.index].peer));
 
 	_leave(" = t");
 	return true;