From c34d999ca3145d9fe858258cc3342ec493f47d2e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:44 +0000 Subject: rxrpc: rxperf: Fix missing decoding of terminal magic cookie The rxperf RPCs seem to have a magic cookie at the end of the request that was failing to be taken account of by the unmarshalling of the request. Fix the rxperf code to expect this. Fixes: 75bfdbf2fca3 ("rxrpc: Implement an in-kernel rxperf server for testing purposes") Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/20250218192250.296870-2-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- net/rxrpc/rxperf.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index 7ef93407be83..e848a4777b8c 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -478,6 +478,18 @@ static int rxperf_deliver_request(struct rxperf_call *call) call->unmarshal++; fallthrough; case 2: + ret = rxperf_extract_data(call, true); + if (ret < 0) + return ret; + + /* Deal with the terminal magic cookie. */ + call->iov_len = 4; + call->kvec[0].iov_len = call->iov_len; + call->kvec[0].iov_base = call->tmp; + iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len); + call->unmarshal++; + fallthrough; + case 3: ret = rxperf_extract_data(call, false); if (ret < 0) return ret; -- cgit v1.2.3 From 833fefa074444b1e7f7e834cbdce59ce02562ed0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:45 +0000 Subject: rxrpc: peer->mtu_lock is redundant The peer->mtu_lock is only used to lock around writes to peer->max_data - and nothing else; further, all such writes take place in the I/O thread and the lock is only ever write-locked and never read-locked. In a couple of places, the write_seqcount_begin() is wrapped in preempt_disable/enable(), but not in all places. This can cause lockdep to complain: WARNING: CPU: 0 PID: 1549 at include/linux/seqlock.h:221 rxrpc_input_ack_trailer+0x305/0x430 ... RIP: 0010:rxrpc_input_ack_trailer+0x305/0x430 Fix this by just getting rid of the lock. Fixes: eeaedc5449d9 ("rxrpc: Implement path-MTU probing using padded PING ACKs (RFC8899)") Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/20250218192250.296870-3-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- net/rxrpc/ar-internal.h | 1 - net/rxrpc/input.c | 2 -- net/rxrpc/peer_event.c | 9 +-------- net/rxrpc/peer_object.c | 1 - 4 files changed, 1 insertion(+), 12 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5e740c486203..a64a0cab1bf7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -360,7 +360,6 @@ struct rxrpc_peer { u8 pmtud_jumbo; /* Max jumbo packets for the MTU */ bool ackr_adv_pmtud; /* T if the peer advertises path-MTU */ unsigned int ackr_max_data; /* Maximum data advertised by peer */ - seqcount_t mtu_lock; /* Lockless MTU access management */ unsigned int if_mtu; /* Local interface MTU (- hdrsize) for this peer */ unsigned int max_data; /* Maximum packet data capacity for this peer */ unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9047ba13bd31..24aceb183c2c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -810,9 +810,7 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb if (max_mtu < peer->max_data) { trace_rxrpc_pmtud_reduce(peer, sp->hdr.serial, max_mtu, rxrpc_pmtud_reduce_ack); - write_seqcount_begin(&peer->mtu_lock); peer->max_data = max_mtu; - write_seqcount_end(&peer->mtu_lock); } max_data = umin(max_mtu, peer->max_data); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index bc283da9ee40..7f4729234957 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -130,9 +130,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu) peer->pmtud_bad = max_data + 1; trace_rxrpc_pmtud_reduce(peer, 0, max_data, rxrpc_pmtud_reduce_icmp); - write_seqcount_begin(&peer->mtu_lock); peer->max_data = max_data; - write_seqcount_end(&peer->mtu_lock); } } @@ -408,13 +406,8 @@ void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t a } max_data = umin(max_data, peer->ackr_max_data); - if (max_data != peer->max_data) { - preempt_disable(); - write_seqcount_begin(&peer->mtu_lock); + if (max_data != peer->max_data) peer->max_data = max_data; - write_seqcount_end(&peer->mtu_lock); - preempt_enable(); - } jumbo = max_data + sizeof(struct rxrpc_jumbo_header); jumbo /= RXRPC_JUMBO_SUBPKTLEN; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 0fcc87f0409f..2ddc8ed68742 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -235,7 +235,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); - seqcount_init(&peer->mtu_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); peer->recent_srtt_us = UINT_MAX; peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; -- cgit v1.2.3 From 71f5409176f4ffd460689eb5423a20332d00e342 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:46 +0000 Subject: rxrpc: Fix locking issues with the peer record hash rxrpc_new_incoming_peer() can't use spin_lock_bh() whilst its caller has interrupts disabled. WARNING: CPU: 0 PID: 1550 at kernel/softirq.c:369 __local_bh_enable_ip+0x46/0xd0 ... Call Trace: rxrpc_alloc_incoming_call+0x1b0/0x400 rxrpc_new_incoming_call+0x1dd/0x5e0 rxrpc_input_packet+0x84a/0x920 rxrpc_io_thread+0x40d/0xb40 kthread+0x2ec/0x300 ret_from_fork+0x24/0x40 ret_from_fork_asm+0x1a/0x30 irq event stamp: 1811 hardirqs last enabled at (1809): _raw_spin_unlock_irq+0x24/0x50 hardirqs last disabled at (1810): _raw_read_lock_irq+0x17/0x70 softirqs last enabled at (1182): handle_softirqs+0x3ee/0x430 softirqs last disabled at (1811): rxrpc_new_incoming_peer+0x56/0x120 Fix this by using a plain spin_lock() instead. IRQs are held, so softirqs can't happen. Fixes: a2ea9a907260 ("rxrpc: Use irq-disabling spinlocks between app and I/O thread") Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/20250218192250.296870-4-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- net/rxrpc/peer_object.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 2ddc8ed68742..56e09d161a97 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -324,10 +324,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) hash_key = rxrpc_peer_hash_key(local, &peer->srx); rxrpc_init_peer(local, peer, hash_key); - spin_lock_bh(&rxnet->peer_hash_lock); + spin_lock(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - spin_unlock_bh(&rxnet->peer_hash_lock); + spin_unlock(&rxnet->peer_hash_lock); } /* -- cgit v1.2.3 From add117e48df4788a86a21bd0515833c0a6db1ad1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:47 +0000 Subject: afs: Fix the server_list to unuse a displaced server rather than putting it When allocating and building an afs_server_list struct object from a VLDB record, we look up each server address to get the server record for it - but a server may have more than one entry in the record and we discard the duplicate pointers. Currently, however, when we discard, we only put a server record, not unuse it - but the lookup got as an active-user count. The active-user count on an afs_server_list object determines its lifetime whereas the refcount keeps the memory backing it around. Failing to reduce the active-user counter prevents the record from being cleaned up and can lead to multiple copied being seen - and pointing to deleted afs_cell objects and other such things. Fix this by switching the incorrect 'put' to an 'unuse' instead. Without this, occasionally, a dead server record can be seen in /proc/net/afs/servers and list corruption may be observed: list_del corruption. prev->next should be ffff888102423e40, but was 0000000000000000. (prev=ffff88810140cd38) Fixes: 977e5f8ed0ab ("afs: Split the usage count on struct afs_server") Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/20250218192250.296870-5-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- fs/afs/server_list.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 7e7e567a7f8a..d20cd902ef94 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -97,8 +97,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume, break; if (j < slist->nr_servers) { if (slist->servers[j].server == server) { - afs_put_server(volume->cell->net, server, - afs_server_trace_put_slist_isort); + afs_unuse_server(volume->cell->net, server, + afs_server_trace_put_slist_isort); continue; } -- cgit v1.2.3 From 1f0fc3374f3345ff1d150c5c56ac5016e5d3826a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:48 +0000 Subject: afs: Give an afs_server object a ref on the afs_cell object it points to Give an afs_server object a ref on the afs_cell object it points to so that the cell doesn't get deleted before the server record. Whilst this is circular (cell -> vol -> server_list -> server -> cell), the ref only pins the memory, not the lifetime as that's controlled by the activity counter. When the volume's activity counter reaches 0, it detaches from the cell and discards its server list; when a cell's activity counter reaches 0, it discards its root volume. At that point, the circularity is cut. Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation") Signed-off-by: David Howells cc: Marc Dionne cc: Simon Horman cc: linux-afs@lists.infradead.org Link: https://patch.msgid.link/20250218192250.296870-6-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- fs/afs/server.c | 3 +++ include/trace/events/afs.h | 2 ++ 2 files changed, 5 insertions(+) diff --git a/fs/afs/server.c b/fs/afs/server.c index 038f9d0ae3af..4504e16b458c 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -163,6 +163,8 @@ static struct afs_server *afs_install_server(struct afs_cell *cell, rb_insert_color(&server->uuid_rb, &net->fs_servers); hlist_add_head_rcu(&server->proc_link, &net->fs_proc); + afs_get_cell(cell, afs_cell_trace_get_server); + added_dup: write_seqlock(&net->fs_addr_lock); estate = rcu_dereference_protected(server->endpoint_state, @@ -442,6 +444,7 @@ static void afs_server_rcu(struct rcu_head *rcu) atomic_read(&server->active), afs_server_trace_free); afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state), afs_estate_trace_put_server); + afs_put_cell(server->cell, afs_cell_trace_put_server); kfree(server); } diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index b0db89058c91..958a2460330c 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -174,6 +174,7 @@ enum yfs_cm_operation { EM(afs_cell_trace_get_queue_dns, "GET q-dns ") \ EM(afs_cell_trace_get_queue_manage, "GET q-mng ") \ EM(afs_cell_trace_get_queue_new, "GET q-new ") \ + EM(afs_cell_trace_get_server, "GET server") \ EM(afs_cell_trace_get_vol, "GET vol ") \ EM(afs_cell_trace_insert, "INSERT ") \ EM(afs_cell_trace_manage, "MANAGE ") \ @@ -182,6 +183,7 @@ enum yfs_cm_operation { EM(afs_cell_trace_put_destroy, "PUT destry") \ EM(afs_cell_trace_put_queue_work, "PUT q-work") \ EM(afs_cell_trace_put_queue_fail, "PUT q-fail") \ + EM(afs_cell_trace_put_server, "PUT server") \ EM(afs_cell_trace_put_vol, "PUT vol ") \ EM(afs_cell_trace_see_source, "SEE source") \ EM(afs_cell_trace_see_ws, "SEE ws ") \ -- cgit v1.2.3