From bd30e8d7bfa6e528f9e746c940e6f7246c7899d6 Mon Sep 17 00:00:00 2001 From: Hsin-chen Chuang Date: Fri, 14 Feb 2025 19:17:09 +0800 Subject: [PATCH 01/53] Bluetooth: Always allow SCO packets for user channel The SCO packets from Bluetooth raw socket are now rejected because hci_conn_num is left 0. This patch allows such the usecase to enable the userspace SCO support. Fixes: b16b327edb4d ("Bluetooth: btusb: add sysfs attribute to control USB alt setting") Signed-off-by: Hsin-chen Chuang Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btusb.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 90966dfbd278..8149e53fd0a7 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2102,7 +2102,8 @@ static int btusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return submit_or_queue_tx_urb(hdev, urb); case HCI_SCODATA_PKT: - if (hci_conn_num(hdev, SCO_LINK) < 1) + if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + hci_conn_num(hdev, SCO_LINK) < 1) return -ENODEV; urb = alloc_isoc_urb(hdev, skb); @@ -2576,7 +2577,8 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb) return submit_or_queue_tx_urb(hdev, urb); case HCI_SCODATA_PKT: - if (hci_conn_num(hdev, SCO_LINK) < 1) + if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + hci_conn_num(hdev, SCO_LINK) < 1) return -ENODEV; urb = alloc_isoc_urb(hdev, skb); From b25120e1d5f2ebb3db00af557709041f47f7f3d0 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 14 Feb 2025 10:30:25 -0500 Subject: [PATCH 02/53] Bluetooth: L2CAP: Fix L2CAP_ECRED_CONN_RSP response L2CAP_ECRED_CONN_RSP needs to respond DCID in the same order received as SCID but the order is reversed due to use of list_add which actually prepend channels to the list so the response is reversed: > ACL Data RX: Handle 16 flags 0x02 dlen 26 LE L2CAP: Enhanced Credit Connection Request (0x17) ident 2 len 18 PSM: 39 (0x0027) MTU: 256 MPS: 251 Credits: 65535 Source CID: 116 Source CID: 117 Source CID: 118 Source CID: 119 Source CID: 120 < ACL Data TX: Handle 16 flags 0x00 dlen 26 LE L2CAP: Enhanced Credit Connection Response (0x18) ident 2 len 18 MTU: 517 MPS: 247 Credits: 3 Result: Connection successful (0x0000) Destination CID: 68 Destination CID: 67 Destination CID: 66 Destination CID: 65 Destination CID: 64 Also make sure the response don't include channels that are not on BT_CONNECT2 since the chan->ident can be set to the same value as in the following trace: < ACL Data TX: Handle 16 flags 0x00 dlen 12 LE L2CAP: LE Flow Control Credit (0x16) ident 6 len 4 Source CID: 64 Credits: 1 ... > ACL Data RX: Handle 16 flags 0x02 dlen 18 LE L2CAP: Enhanced Credit Connection Request (0x17) ident 6 len 10 PSM: 39 (0x0027) MTU: 517 MPS: 251 Credits: 255 Source CID: 70 < ACL Data TX: Handle 16 flags 0x00 dlen 20 LE L2CAP: Enhanced Credit Connection Response (0x18) ident 6 len 12 MTU: 517 MPS: 247 Credits: 3 Result: Connection successful (0x0000) Destination CID: 64 Destination CID: 68 Closes: https://github.com/bluez/bluez/issues/1094 Fixes: 9aa9d9473f15 ("Bluetooth: L2CAP: Fix responding with wrong PDU type") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/l2cap_core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index fec11e576f31..b22078b67972 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -632,7 +632,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) test_bit(FLAG_HOLD_HCI_CONN, &chan->flags)) hci_conn_hold(conn->hcon); - list_add(&chan->list, &conn->chan_l); + /* Append to the list since the order matters for ECRED */ + list_add_tail(&chan->list, &conn->chan_l); } void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) @@ -3771,7 +3772,11 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_conn_rsp *rsp_flex = container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); - if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) + /* Check if channel for outgoing connection or if it wasn't deferred + * since in those cases it must be skipped. + */ + if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags) || + !test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags)) return; /* Reset ident so only one response is sent */ From 992ee3ed6e9fdd0be83a7daa5ff738e3cf86047f Mon Sep 17 00:00:00 2001 From: George Moussalem Date: Wed, 19 Feb 2025 14:09:21 +0100 Subject: [PATCH 03/53] net: phy: qcom: qca807x fix condition for DAC_DSP_BIAS_CURRENT While setting the DAC value, the wrong boolean value is evaluated to set the DSP bias current. So let's correct the conditional statement and use the right boolean value read from the DTS set in the priv. Cc: stable@vger.kernel.org Fixes: d1cb613efbd3 ("net: phy: qcom: add support for QCA807x PHY Family") Signed-off-by: George Moussalem Signed-off-by: Christian Marangi Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20250219130923.7216-1-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/qcom/qca807x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 3279de857b47..2ad8c2586d64 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -774,7 +774,7 @@ static int qca807x_config_init(struct phy_device *phydev) control_dac &= ~QCA807X_CONTROL_DAC_MASK; if (!priv->dac_full_amplitude) control_dac |= QCA807X_CONTROL_DAC_DSP_AMPLITUDE; - if (!priv->dac_full_amplitude) + if (!priv->dac_full_bias_current) control_dac |= QCA807X_CONTROL_DAC_DSP_BIAS_CURRENT; if (!priv->dac_disable_bias_current_tweak) control_dac |= QCA807X_CONTROL_DAC_BIAS_CURRENT_TWEAK; From f06e4bfd010faefa637689d2df2c727dbf6e1d27 Mon Sep 17 00:00:00 2001 From: Qunqin Zhao Date: Wed, 19 Feb 2025 10:07:01 +0800 Subject: [PATCH 04/53] net: stmmac: dwmac-loongson: Add fix_soc_reset() callback Loongson's DWMAC device may take nearly two seconds to complete DMA reset, however, the default waiting time for reset is 200 milliseconds. Therefore, the following error message may appear: [14.427169] dwmac-loongson-pci 0000:00:03.2: Failed to reset the dma Fixes: 803fc61df261 ("net: stmmac: dwmac-loongson: Add Loongson Multi-channels GMAC support") Cc: stable@vger.kernel.org Signed-off-by: Qunqin Zhao Reviewed-by: Huacai Chen Reviewed-by: Jacob Keller Acked-by: Yanteng Si Link: https://patch.msgid.link/20250219020701.15139-1-zhaoqunqin@loongson.cn Signed-off-by: Jakub Kicinski --- .../net/ethernet/stmicro/stmmac/dwmac-loongson.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index bfe6e2d631bd..f5acfb7d4ff6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -516,6 +516,19 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev, return 0; } +/* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */ +static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr) +{ + u32 value = readl(ioaddr + DMA_BUS_MODE); + + value |= DMA_BUS_MODE_SFT_RESET; + writel(value, ioaddr + DMA_BUS_MODE); + + return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value, + !(value & DMA_BUS_MODE_SFT_RESET), + 10000, 2000000); +} + static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct plat_stmmacenet_data *plat; @@ -566,6 +579,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id plat->bsp_priv = ld; plat->setup = loongson_dwmac_setup; + plat->fix_soc_reset = loongson_dwmac_fix_reset; ld->dev = &pdev->dev; ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; From c34d999ca3145d9fe858258cc3342ec493f47d2e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:44 +0000 Subject: [PATCH 05/53] 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; From 833fefa074444b1e7f7e834cbdce59ce02562ed0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:45 +0000 Subject: [PATCH 06/53] 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; From 71f5409176f4ffd460689eb5423a20332d00e342 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:46 +0000 Subject: [PATCH 07/53] 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); } /* From add117e48df4788a86a21bd0515833c0a6db1ad1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:47 +0000 Subject: [PATCH 08/53] 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; } From 1f0fc3374f3345ff1d150c5c56ac5016e5d3826a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 18 Feb 2025 19:22:48 +0000 Subject: [PATCH 09/53] 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 ") \ From 5c70eb5c593d64d93b178905da215a9fd288a4b5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Feb 2025 13:18:54 +0000 Subject: [PATCH 10/53] net: better track kernel sockets lifetime While kernel sockets are dismantled during pernet_operations->exit(), their freeing can be delayed by any tx packets still held in qdisc or device queues, due to skb_set_owner_w() prior calls. This then trigger the following warning from ref_tracker_dir_exit() [1] To fix this, make sure that kernel sockets own a reference on net->passive. Add sk_net_refcnt_upgrade() helper, used whenever a kernel socket is converted to a refcounted one. [1] [ 136.263918][ T35] ref_tracker: net notrefcnt@ffff8880638f01e0 has 1/2 users at [ 136.263918][ T35] sk_alloc+0x2b3/0x370 [ 136.263918][ T35] inet6_create+0x6ce/0x10f0 [ 136.263918][ T35] __sock_create+0x4c0/0xa30 [ 136.263918][ T35] inet_ctl_sock_create+0xc2/0x250 [ 136.263918][ T35] igmp6_net_init+0x39/0x390 [ 136.263918][ T35] ops_init+0x31e/0x590 [ 136.263918][ T35] setup_net+0x287/0x9e0 [ 136.263918][ T35] copy_net_ns+0x33f/0x570 [ 136.263918][ T35] create_new_namespaces+0x425/0x7b0 [ 136.263918][ T35] unshare_nsproxy_namespaces+0x124/0x180 [ 136.263918][ T35] ksys_unshare+0x57d/0xa70 [ 136.263918][ T35] __x64_sys_unshare+0x38/0x40 [ 136.263918][ T35] do_syscall_64+0xf3/0x230 [ 136.263918][ T35] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 136.263918][ T35] [ 136.343488][ T35] ref_tracker: net notrefcnt@ffff8880638f01e0 has 1/2 users at [ 136.343488][ T35] sk_alloc+0x2b3/0x370 [ 136.343488][ T35] inet6_create+0x6ce/0x10f0 [ 136.343488][ T35] __sock_create+0x4c0/0xa30 [ 136.343488][ T35] inet_ctl_sock_create+0xc2/0x250 [ 136.343488][ T35] ndisc_net_init+0xa7/0x2b0 [ 136.343488][ T35] ops_init+0x31e/0x590 [ 136.343488][ T35] setup_net+0x287/0x9e0 [ 136.343488][ T35] copy_net_ns+0x33f/0x570 [ 136.343488][ T35] create_new_namespaces+0x425/0x7b0 [ 136.343488][ T35] unshare_nsproxy_namespaces+0x124/0x180 [ 136.343488][ T35] ksys_unshare+0x57d/0xa70 [ 136.343488][ T35] __x64_sys_unshare+0x38/0x40 [ 136.343488][ T35] do_syscall_64+0xf3/0x230 [ 136.343488][ T35] entry_SYSCALL_64_after_hwframe+0x77/0x7f Fixes: 0cafd77dcd03 ("net: add a refcount tracker for kernel sockets") Reported-by: syzbot+30a19e01a97420719891@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/67b72aeb.050a0220.14d86d.0283.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250220131854.4048077-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 1 + net/core/sock.c | 27 ++++++++++++++++++++++----- net/mptcp/subflow.c | 5 +---- net/netlink/af_netlink.c | 10 ---------- net/rds/tcp.c | 8 ++------ net/smc/af_smc.c | 5 +---- net/sunrpc/svcsock.c | 5 +---- net/sunrpc/xprtsock.c | 8 ++------ 8 files changed, 30 insertions(+), 39 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 8036b3b79cd8..7ef728324e4e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1751,6 +1751,7 @@ static inline bool sock_allow_reclassification(const struct sock *csk) struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); +void sk_net_refcnt_upgrade(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); void sk_free_unlock_clone(struct sock *sk); diff --git a/net/core/sock.c b/net/core/sock.c index eae2ae70a2e0..6c0e87f97fa4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2246,6 +2246,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } else { + net_passive_inc(net); __netns_tracker_alloc(net, &sk->ns_tracker, false, priority); } @@ -2270,6 +2271,7 @@ EXPORT_SYMBOL(sk_alloc); static void __sk_destruct(struct rcu_head *head) { struct sock *sk = container_of(head, struct sock, sk_rcu); + struct net *net = sock_net(sk); struct sk_filter *filter; if (sk->sk_destruct) @@ -2301,14 +2303,28 @@ static void __sk_destruct(struct rcu_head *head) put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); - if (likely(sk->sk_net_refcnt)) - put_net_track(sock_net(sk), &sk->ns_tracker); - else - __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); - + if (likely(sk->sk_net_refcnt)) { + put_net_track(net, &sk->ns_tracker); + } else { + __netns_tracker_free(net, &sk->ns_tracker, false); + net_passive_dec(net); + } sk_prot_free(sk->sk_prot_creator, sk); } +void sk_net_refcnt_upgrade(struct sock *sk) +{ + struct net *net = sock_net(sk); + + WARN_ON_ONCE(sk->sk_net_refcnt); + __netns_tracker_free(net, &sk->ns_tracker, false); + net_passive_dec(net); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); +} +EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade); + void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); @@ -2405,6 +2421,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * is not properly dismantling its kernel sockets at netns * destroy time. */ + net_passive_inc(sock_net(newsk)); __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fd021cf8286e..dfcbef9c4624 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1772,10 +1772,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, * needs it. * Update ns_tracker to current stack trace and refcounted tracker. */ - __netns_tracker_free(net, &sf->sk->ns_tracker, false); - sf->sk->sk_net_refcnt = 1; - get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sf->sk); err = tcp_set_ulp(sf->sk, "mptcp"); if (err) goto err_free; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 85311226183a..a53ea60d0a78 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -795,16 +795,6 @@ static int netlink_release(struct socket *sock) sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); - /* Because struct net might disappear soon, do not keep a pointer. */ - if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { - __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); - /* Because of deferred_put_nlk_sk and use of work queue, - * it is possible netns will be freed before this socket. - */ - sock_net_set(sk, &init_net); - __netns_tracker_alloc(&init_net, &sk->ns_tracker, - false, GFP_KERNEL); - } call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 0581c53e6517..3cc2f303bf78 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -504,12 +504,8 @@ bool rds_tcp_tune(struct socket *sock) release_sock(sk); return false; } - /* Update ns_tracker to current stack trace and refcounted tracker */ - __netns_tracker_free(net, &sk->ns_tracker, false); - - sk->sk_net_refcnt = 1; - netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sk); + put_net(net); } rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index ca6984541edb..3e6cb35baf25 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3337,10 +3337,7 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family) * which need net ref. */ sk = smc->clcsock->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sk); return 0; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index cb3bd12f5818..72e5a01df3d3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1541,10 +1541,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, newlen = error; if (protocol == IPPROTO_TCP) { - __netns_tracker_free(net, &sock->sk->ns_tracker, false); - sock->sk->sk_net_refcnt = 1; - get_net_track(net, &sock->sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + sk_net_refcnt_upgrade(sock->sk); if ((error = kernel_listen(sock, 64)) < 0) goto bummer; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c60936d8cef7..940fe65b2a35 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1941,12 +1941,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, goto out; } - if (protocol == IPPROTO_TCP) { - __netns_tracker_free(xprt->xprt_net, &sock->sk->ns_tracker, false); - sock->sk->sk_net_refcnt = 1; - get_net_track(xprt->xprt_net, &sock->sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(xprt->xprt_net, 1); - } + if (protocol == IPPROTO_TCP) + sk_net_refcnt_upgrade(sock->sk); filp = sock_alloc_file(sock, O_NONBLOCK, NULL); if (IS_ERR(filp)) From 0e4427f8f587c4b603475468bb3aee9418574893 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 20 Feb 2025 09:25:59 +0200 Subject: [PATCH 11/53] net: loopback: Avoid sending IP packets without an Ethernet header After commit 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev") IPv4 neighbors can be constructed on the blackhole net device, but they are constructed with an output function (neigh_direct_output()) that simply calls dev_queue_xmit(). The latter will transmit packets via 'skb->dev' which might not be the blackhole net device if dst_dev_put() switched 'dst->dev' to the blackhole net device while another CPU was using the dst entry in ip_output(), but after it already initialized 'skb->dev' from 'dst->dev'. Specifically, the following can happen: CPU1 CPU2 udp_sendmsg(sk1) udp_sendmsg(sk2) udp_send_skb() [...] ip_output() skb->dev = skb_dst(skb)->dev dst_dev_put() dst->dev = blackhole_netdev ip_finish_output2() resolves neigh on dst->dev neigh_output() neigh_direct_output() dev_queue_xmit() This will result in IPv4 packets being sent without an Ethernet header via a valid net device: tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on enp9s0, link-type EN10MB (Ethernet), snapshot length 262144 bytes 22:07:02.329668 20:00:40:11:18:fb > 45:00:00:44:f4:94, ethertype Unknown (0x58c6), length 68: 0x0000: 8dda 74ca f1ae ca6c ca6c 0098 969c 0400 ..t....l.l...... 0x0010: 0000 4730 3f18 6800 0000 0000 0000 9971 ..G0?.h........q 0x0020: c4c9 9055 a157 0a70 9ead bf83 38ca ab38 ...U.W.p....8..8 0x0030: 8add ab96 e052 .....R Fix by making sure that neighbors are constructed on top of the blackhole net device with an output function that simply consumes the packets, in a similar fashion to dst_discard_out() and blackhole_netdev_xmit(). Fixes: 8d7017fd621d ("blackhole_netdev: use blackhole_netdev to invalidate dst entries") Fixes: 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev") Reported-by: Florian Meister Closes: https://lore.kernel.org/netdev/20250210084931.23a5c2e4@hermes.local/ Signed-off-by: Ido Schimmel Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250220072559.782296-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/loopback.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index c8840c3b9a1b..f1d68153987e 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -244,8 +244,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } +static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb) +{ + kfree_skb(skb); + return 0; +} + +static int blackhole_neigh_construct(struct net_device *dev, + struct neighbour *n) +{ + n->output = blackhole_neigh_output; + return 0; +} + static const struct net_device_ops blackhole_netdev_ops = { .ndo_start_xmit = blackhole_netdev_xmit, + .ndo_neigh_construct = blackhole_neigh_construct, }; /* This is a dst-dummy device used specifically for invalidated From c180188ec02281126045414e90d08422a80f75b4 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Feb 2025 12:07:52 +0100 Subject: [PATCH 12/53] net: set the minimum for net_hotdata.netdev_budget_usecs Commit 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning") added a possibility to set net_hotdata.netdev_budget_usecs, but added no lower bound checking. Commit a4837980fd9f ("net: revert default NAPI poll timeout to 2 jiffies") made the *initial* value HZ-dependent, so the initial value is at least 2 jiffies even for lower HZ values (2 ms for 1000 Hz, 8ms for 250 Hz, 20 ms for 100 Hz). But a user still can set improper values by a sysctl. Set .extra1 (the lower bound) for net_hotdata.netdev_budget_usecs to the same value as in the latter commit. That is to 2 jiffies. Fixes: a4837980fd9f ("net: revert default NAPI poll timeout to 2 jiffies") Fixes: 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning") Signed-off-by: Jiri Slaby (SUSE) Cc: Dmitry Yakunin Cc: Konstantin Khlebnikov Link: https://patch.msgid.link/20250220110752.137639-1-jirislaby@kernel.org Signed-off-by: Jakub Kicinski --- net/core/sysctl_net_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index ad2741f1346a..c7769ee0d9c5 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -34,6 +34,7 @@ static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; +static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -587,7 +588,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .extra1 = &netdev_budget_usecs_min, }, { .procname = "fb_tunnels_only_for_init_net", From 27843ce6ba3d3122b65066550fe33fb8839f8aef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Feb 2025 15:53:36 +0000 Subject: [PATCH 13/53] ipvlan: ensure network headers are in skb linear part syzbot found that ipvlan_process_v6_outbound() was assuming the IPv6 network header isis present in skb->head [1] Add the needed pskb_network_may_pull() calls for both IPv4 and IPv6 handlers. [1] BUG: KMSAN: uninit-value in __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47 __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47 ipv6_addr_type include/net/ipv6.h:555 [inline] ip6_route_output_flags_noref net/ipv6/route.c:2616 [inline] ip6_route_output_flags+0x51/0x720 net/ipv6/route.c:2651 ip6_route_output include/net/ip6_route.h:93 [inline] ipvlan_route_v6_outbound+0x24e/0x520 drivers/net/ipvlan/ipvlan_core.c:476 ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:491 [inline] ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:541 [inline] ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:605 [inline] ipvlan_queue_xmit+0xd72/0x1780 drivers/net/ipvlan/ipvlan_core.c:671 ipvlan_start_xmit+0x5b/0x210 drivers/net/ipvlan/ipvlan_main.c:223 __netdev_start_xmit include/linux/netdevice.h:5150 [inline] netdev_start_xmit include/linux/netdevice.h:5159 [inline] xmit_one net/core/dev.c:3735 [inline] dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3751 sch_direct_xmit+0x399/0xd40 net/sched/sch_generic.c:343 qdisc_restart net/sched/sch_generic.c:408 [inline] __qdisc_run+0x14da/0x35d0 net/sched/sch_generic.c:416 qdisc_run+0x141/0x4d0 include/net/pkt_sched.h:127 net_tx_action+0x78b/0x940 net/core/dev.c:5484 handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:561 __do_softirq+0x14/0x1a kernel/softirq.c:595 do_softirq+0x9a/0x100 kernel/softirq.c:462 __local_bh_enable_ip+0x9f/0xb0 kernel/softirq.c:389 local_bh_enable include/linux/bottom_half.h:33 [inline] rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline] __dev_queue_xmit+0x2758/0x57d0 net/core/dev.c:4611 dev_queue_xmit include/linux/netdevice.h:3311 [inline] packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276 packet_snd net/packet/af_packet.c:3132 [inline] packet_sendmsg+0x93e0/0xa7e0 net/packet/af_packet.c:3164 sock_sendmsg_nosec net/socket.c:718 [inline] Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Reported-by: syzbot+93ab4a777bafb9d9f960@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/67b74f01.050a0220.14d86d.02d8.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Mahesh Bandewar Link: https://patch.msgid.link/20250220155336.61884-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ipvlan/ipvlan_core.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index fd591ddb3884..ca62188a317a 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -416,20 +416,25 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) { - const struct iphdr *ip4h = ip_hdr(skb); struct net_device *dev = skb->dev; struct net *net = dev_net(dev); - struct rtable *rt; int err, ret = NET_XMIT_DROP; + const struct iphdr *ip4h; + struct rtable *rt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)), .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, - .daddr = ip4h->daddr, - .saddr = ip4h->saddr, }; + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + goto err; + + ip4h = ip_hdr(skb); + fl4.daddr = ip4h->daddr; + fl4.saddr = ip4h->saddr; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)); + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; @@ -488,6 +493,12 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) struct net_device *dev = skb->dev; int err, ret = NET_XMIT_DROP; + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) { + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return ret; + } + err = ipvlan_route_v6_outbound(dev, skb); if (unlikely(err)) { DEV_STATS_INC(dev, tx_errors); From fa52f15c745ce55261b92873676f64f7348cfe82 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 20 Feb 2025 11:29:50 -0500 Subject: [PATCH 14/53] net: cadence: macb: Synchronize stats calculations Stats calculations involve a RMW to add the stat update to the existing value. This is currently not protected by any synchronization mechanism, so data races are possible. Add a spinlock to protect the update. The reader side could be protected using u64_stats, but we would still need a spinlock for the update side anyway. And we always do an update immediately before reading the stats anyway. Fixes: 89e5785fc8a6 ("[PATCH] Atmel MACB ethernet driver") Signed-off-by: Sean Anderson Link: https://patch.msgid.link/20250220162950.95941-1-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb.h | 2 ++ drivers/net/ethernet/cadence/macb_main.c | 12 ++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 5740c98d8c9f..2847278d9cd4 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -1279,6 +1279,8 @@ struct macb { struct clk *rx_clk; struct clk *tsu_clk; struct net_device *dev; + /* Protects hw_stats and ethtool_stats */ + spinlock_t stats_lock; union { struct macb_stats macb; struct gem_stats gem; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 48496209fb16..c1f57d96e63f 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1978,10 +1978,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(ISR_ROVR)) { /* We missed at least one packet */ + spin_lock(&bp->stats_lock); if (macb_is_gem(bp)) bp->hw_stats.gem.rx_overruns++; else bp->hw_stats.macb.rx_overruns++; + spin_unlock(&bp->stats_lock); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(ISR_ROVR)); @@ -3102,6 +3104,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) if (!netif_running(bp->dev)) return nstat; + spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + @@ -3131,6 +3134,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) nstat->tx_aborted_errors = hwstat->tx_excessive_collisions; nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors; nstat->tx_fifo_errors = hwstat->tx_underrun; + spin_unlock_irq(&bp->stats_lock); return nstat; } @@ -3138,12 +3142,13 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) static void gem_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { - struct macb *bp; + struct macb *bp = netdev_priv(dev); - bp = netdev_priv(dev); + spin_lock_irq(&bp->stats_lock); gem_update_stats(bp); memcpy(data, &bp->ethtool_stats, sizeof(u64) * (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES)); + spin_unlock_irq(&bp->stats_lock); } static int gem_get_sset_count(struct net_device *dev, int sset) @@ -3193,6 +3198,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev) return gem_get_stats(bp); /* read stats from hardware */ + spin_lock_irq(&bp->stats_lock); macb_update_stats(bp); /* Convert HW stats into netdevice stats */ @@ -3226,6 +3232,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev) nstat->tx_carrier_errors = hwstat->tx_carrier_errors; nstat->tx_fifo_errors = hwstat->tx_underruns; /* Don't know about heartbeat or window errors... */ + spin_unlock_irq(&bp->stats_lock); return nstat; } @@ -5097,6 +5104,7 @@ static int macb_probe(struct platform_device *pdev) } } spin_lock_init(&bp->lock); + spin_lock_init(&bp->stats_lock); /* setup capabilities */ macb_configure_caps(bp, macb_config); From 28b04731a38c80092f47437af6c2770765e0b99f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 20 Feb 2025 16:50:12 -0800 Subject: [PATCH 15/53] MAINTAINERS: fix DWMAC S32 entry Using L: with more than a bare email address causes getmaintainer.pl to be unable to parse the entry. Fix this by doing as other entries that use this email address and convert it to an R: entry. Link: https://patch.msgid.link/20250221005012.1051897-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 3864d473f52f..ac15093537c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2877,7 +2877,7 @@ F: drivers/pinctrl/nxp/ ARM/NXP S32G/S32R DWMAC ETHERNET DRIVER M: Jan Petrous -L: NXP S32 Linux Team +R: s32@nxp.com S: Maintained F: Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml F: drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c From f15176b8b6e72ac30e14fd273282d2b72562d26b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 20 Feb 2025 19:48:15 +0100 Subject: [PATCH 16/53] net: dsa: rtl8366rb: Fix compilation problem When the kernel is compiled without LED framework support the rtl8366rb fails to build like this: rtl8366rb.o: in function `rtl8366rb_setup_led': rtl8366rb.c:953:(.text.unlikely.rtl8366rb_setup_led+0xe8): undefined reference to `led_init_default_state_get' rtl8366rb.c:980:(.text.unlikely.rtl8366rb_setup_led+0x240): undefined reference to `devm_led_classdev_register_ext' As this is constantly coming up in different randconfig builds, bite the bullet and create a separate file for the offending code, split out a header with all stuff needed both in the core driver and the leds code. Add a new bool Kconfig option for the LED compile target, such that it depends on LEDS_CLASS=y || LEDS_CLASS=RTL8366RB which make LED support always available when LEDS_CLASS is compiled into the kernel and enforce that if the LEDS_CLASS is a module, then the RTL8366RB driver needs to be a module as well so that modprobe can resolve the dependencies. Fixes: 32d617005475 ("net: dsa: realtek: add LED drivers for rtl8366rb") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202502070525.xMUImayb-lkp@intel.com/ Signed-off-by: Linus Walleij Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/realtek/Kconfig | 6 + drivers/net/dsa/realtek/Makefile | 3 + drivers/net/dsa/realtek/rtl8366rb-leds.c | 177 ++++++++++++++++ drivers/net/dsa/realtek/rtl8366rb.c | 258 +---------------------- drivers/net/dsa/realtek/rtl8366rb.h | 107 ++++++++++ 5 files changed, 299 insertions(+), 252 deletions(-) create mode 100644 drivers/net/dsa/realtek/rtl8366rb-leds.c create mode 100644 drivers/net/dsa/realtek/rtl8366rb.h diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig index 6989972eebc3..10687722d14c 100644 --- a/drivers/net/dsa/realtek/Kconfig +++ b/drivers/net/dsa/realtek/Kconfig @@ -43,4 +43,10 @@ config NET_DSA_REALTEK_RTL8366RB help Select to enable support for Realtek RTL8366RB. +config NET_DSA_REALTEK_RTL8366RB_LEDS + bool "Support RTL8366RB LED control" + depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB) + depends on NET_DSA_REALTEK_RTL8366RB + default NET_DSA_REALTEK_RTL8366RB + endif diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile index 35491dc20d6d..17367bcba496 100644 --- a/drivers/net/dsa/realtek/Makefile +++ b/drivers/net/dsa/realtek/Makefile @@ -12,4 +12,7 @@ endif obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o rtl8366-objs := rtl8366-core.o rtl8366rb.o +ifdef CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS +rtl8366-objs += rtl8366rb-leds.o +endif obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c new file mode 100644 index 000000000000..99c890681ae6 --- /dev/null +++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include "rtl83xx.h" +#include "rtl8366rb.h" + +static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port) +{ + switch (led_group) { + case 0: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + case 1: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + case 2: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + case 3: + return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + default: + return 0; + } +} + +static int rb8366rb_get_port_led(struct rtl8366rb_led *led) +{ + struct realtek_priv *priv = led->priv; + u8 led_group = led->led_group; + u8 port_num = led->port_num; + int ret; + u32 val; + + ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group), + &val); + if (ret) { + dev_err(priv->dev, "error reading LED on port %d group %d\n", + led_group, port_num); + return ret; + } + + return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num)); +} + +static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable) +{ + struct realtek_priv *priv = led->priv; + u8 led_group = led->led_group; + u8 port_num = led->port_num; + int ret; + + ret = regmap_update_bits(priv->map, + RTL8366RB_LED_X_X_CTRL_REG(led_group), + rtl8366rb_led_group_port_mask(led_group, + port_num), + enable ? 0xffff : 0); + if (ret) { + dev_err(priv->dev, "error updating LED on port %d group %d\n", + led_group, port_num); + return ret; + } + + /* Change the LED group to manual controlled LEDs if required */ + ret = rb8366rb_set_ledgroup_mode(priv, led_group, + RTL8366RB_LEDGROUP_FORCE); + + if (ret) { + dev_err(priv->dev, "error updating LED GROUP group %d\n", + led_group); + return ret; + } + + return 0; +} + +static int +rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev, + enum led_brightness brightness) +{ + struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led, + cdev); + + return rb8366rb_set_port_led(led, brightness == LED_ON); +} + +static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp, + struct fwnode_handle *led_fwnode) +{ + struct rtl8366rb *rb = priv->chip_data; + struct led_init_data init_data = { }; + enum led_default_state state; + struct rtl8366rb_led *led; + u32 led_group; + int ret; + + ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group); + if (ret) + return ret; + + if (led_group >= RTL8366RB_NUM_LEDGROUPS) { + dev_warn(priv->dev, "Invalid LED reg %d defined for port %d", + led_group, dp->index); + return -EINVAL; + } + + led = &rb->leds[dp->index][led_group]; + led->port_num = dp->index; + led->led_group = led_group; + led->priv = priv; + + state = led_init_default_state_get(led_fwnode); + switch (state) { + case LEDS_DEFSTATE_ON: + led->cdev.brightness = 1; + rb8366rb_set_port_led(led, 1); + break; + case LEDS_DEFSTATE_KEEP: + led->cdev.brightness = + rb8366rb_get_port_led(led); + break; + case LEDS_DEFSTATE_OFF: + default: + led->cdev.brightness = 0; + rb8366rb_set_port_led(led, 0); + } + + led->cdev.max_brightness = 1; + led->cdev.brightness_set_blocking = + rtl8366rb_cled_brightness_set_blocking; + init_data.fwnode = led_fwnode; + init_data.devname_mandatory = true; + + init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d", + dp->ds->index, dp->index, led_group); + if (!init_data.devicename) + return -ENOMEM; + + ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data); + if (ret) { + dev_warn(priv->dev, "Failed to init LED %d for port %d", + led_group, dp->index); + return ret; + } + + return 0; +} + +int rtl8366rb_setup_leds(struct realtek_priv *priv) +{ + struct dsa_switch *ds = &priv->ds; + struct device_node *leds_np; + struct dsa_port *dp; + int ret = 0; + + dsa_switch_for_each_port(dp, ds) { + if (!dp->dn) + continue; + + leds_np = of_get_child_by_name(dp->dn, "leds"); + if (!leds_np) { + dev_dbg(priv->dev, "No leds defined for port %d", + dp->index); + continue; + } + + for_each_child_of_node_scoped(leds_np, led_np) { + ret = rtl8366rb_setup_led(priv, dp, + of_fwnode_handle(led_np)); + if (ret) + break; + } + + of_node_put(leds_np); + if (ret) + return ret; + } + return 0; +} diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index 4c4a95d4380c..f54771cab56d 100644 --- a/drivers/net/dsa/realtek/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -27,11 +27,7 @@ #include "realtek-smi.h" #include "realtek-mdio.h" #include "rtl83xx.h" - -#define RTL8366RB_PORT_NUM_CPU 5 -#define RTL8366RB_NUM_PORTS 6 -#define RTL8366RB_PHY_NO_MAX 4 -#define RTL8366RB_PHY_ADDR_MAX 31 +#include "rtl8366rb.h" /* Switch Global Configuration register */ #define RTL8366RB_SGCR 0x0000 @@ -176,39 +172,6 @@ */ #define RTL8366RB_VLAN_INGRESS_CTRL2_REG 0x037f -/* LED control registers */ -/* The LED blink rate is global; it is used by all triggers in all groups. */ -#define RTL8366RB_LED_BLINKRATE_REG 0x0430 -#define RTL8366RB_LED_BLINKRATE_MASK 0x0007 -#define RTL8366RB_LED_BLINKRATE_28MS 0x0000 -#define RTL8366RB_LED_BLINKRATE_56MS 0x0001 -#define RTL8366RB_LED_BLINKRATE_84MS 0x0002 -#define RTL8366RB_LED_BLINKRATE_111MS 0x0003 -#define RTL8366RB_LED_BLINKRATE_222MS 0x0004 -#define RTL8366RB_LED_BLINKRATE_446MS 0x0005 - -/* LED trigger event for each group */ -#define RTL8366RB_LED_CTRL_REG 0x0431 -#define RTL8366RB_LED_CTRL_OFFSET(led_group) \ - (4 * (led_group)) -#define RTL8366RB_LED_CTRL_MASK(led_group) \ - (0xf << RTL8366RB_LED_CTRL_OFFSET(led_group)) - -/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only - * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is - * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored. - */ -#define RTL8366RB_LED_0_1_CTRL_REG 0x0432 -#define RTL8366RB_LED_2_3_CTRL_REG 0x0433 -#define RTL8366RB_LED_X_X_CTRL_REG(led_group) \ - ((led_group) <= 1 ? \ - RTL8366RB_LED_0_1_CTRL_REG : \ - RTL8366RB_LED_2_3_CTRL_REG) -#define RTL8366RB_LED_0_X_CTRL_MASK GENMASK(5, 0) -#define RTL8366RB_LED_X_1_CTRL_MASK GENMASK(11, 6) -#define RTL8366RB_LED_2_X_CTRL_MASK GENMASK(5, 0) -#define RTL8366RB_LED_X_3_CTRL_MASK GENMASK(11, 6) - #define RTL8366RB_MIB_COUNT 33 #define RTL8366RB_GLOBAL_MIB_COUNT 1 #define RTL8366RB_MIB_COUNTER_PORT_OFFSET 0x0050 @@ -244,7 +207,6 @@ #define RTL8366RB_PORT_STATUS_AN_MASK 0x0080 #define RTL8366RB_NUM_VLANS 16 -#define RTL8366RB_NUM_LEDGROUPS 4 #define RTL8366RB_NUM_VIDS 4096 #define RTL8366RB_PRIORITYMAX 7 #define RTL8366RB_NUM_FIDS 8 @@ -351,46 +313,6 @@ #define RTL8366RB_GREEN_FEATURE_TX BIT(0) #define RTL8366RB_GREEN_FEATURE_RX BIT(2) -enum rtl8366_ledgroup_mode { - RTL8366RB_LEDGROUP_OFF = 0x0, - RTL8366RB_LEDGROUP_DUP_COL = 0x1, - RTL8366RB_LEDGROUP_LINK_ACT = 0x2, - RTL8366RB_LEDGROUP_SPD1000 = 0x3, - RTL8366RB_LEDGROUP_SPD100 = 0x4, - RTL8366RB_LEDGROUP_SPD10 = 0x5, - RTL8366RB_LEDGROUP_SPD1000_ACT = 0x6, - RTL8366RB_LEDGROUP_SPD100_ACT = 0x7, - RTL8366RB_LEDGROUP_SPD10_ACT = 0x8, - RTL8366RB_LEDGROUP_SPD100_10_ACT = 0x9, - RTL8366RB_LEDGROUP_FIBER = 0xa, - RTL8366RB_LEDGROUP_AN_FAULT = 0xb, - RTL8366RB_LEDGROUP_LINK_RX = 0xc, - RTL8366RB_LEDGROUP_LINK_TX = 0xd, - RTL8366RB_LEDGROUP_MASTER = 0xe, - RTL8366RB_LEDGROUP_FORCE = 0xf, - - __RTL8366RB_LEDGROUP_MODE_MAX -}; - -struct rtl8366rb_led { - u8 port_num; - u8 led_group; - struct realtek_priv *priv; - struct led_classdev cdev; -}; - -/** - * struct rtl8366rb - RTL8366RB-specific data - * @max_mtu: per-port max MTU setting - * @pvid_enabled: if PVID is set for respective port - * @leds: per-port and per-ledgroup led info - */ -struct rtl8366rb { - unsigned int max_mtu[RTL8366RB_NUM_PORTS]; - bool pvid_enabled[RTL8366RB_NUM_PORTS]; - struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS]; -}; - static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = { { 0, 0, 4, "IfInOctets" }, { 0, 4, 4, "EtherStatsOctets" }, @@ -831,9 +753,10 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, return 0; } -static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, - u8 led_group, - enum rtl8366_ledgroup_mode mode) +/* This code is used also with LEDs disabled */ +int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, + u8 led_group, + enum rtl8366_ledgroup_mode mode) { int ret; u32 val; @@ -850,144 +773,7 @@ static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, return 0; } -static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port) -{ - switch (led_group) { - case 0: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - case 1: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - case 2: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - case 3: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); - default: - return 0; - } -} - -static int rb8366rb_get_port_led(struct rtl8366rb_led *led) -{ - struct realtek_priv *priv = led->priv; - u8 led_group = led->led_group; - u8 port_num = led->port_num; - int ret; - u32 val; - - ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group), - &val); - if (ret) { - dev_err(priv->dev, "error reading LED on port %d group %d\n", - led_group, port_num); - return ret; - } - - return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num)); -} - -static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable) -{ - struct realtek_priv *priv = led->priv; - u8 led_group = led->led_group; - u8 port_num = led->port_num; - int ret; - - ret = regmap_update_bits(priv->map, - RTL8366RB_LED_X_X_CTRL_REG(led_group), - rtl8366rb_led_group_port_mask(led_group, - port_num), - enable ? 0xffff : 0); - if (ret) { - dev_err(priv->dev, "error updating LED on port %d group %d\n", - led_group, port_num); - return ret; - } - - /* Change the LED group to manual controlled LEDs if required */ - ret = rb8366rb_set_ledgroup_mode(priv, led_group, - RTL8366RB_LEDGROUP_FORCE); - - if (ret) { - dev_err(priv->dev, "error updating LED GROUP group %d\n", - led_group); - return ret; - } - - return 0; -} - -static int -rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev, - enum led_brightness brightness) -{ - struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led, - cdev); - - return rb8366rb_set_port_led(led, brightness == LED_ON); -} - -static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp, - struct fwnode_handle *led_fwnode) -{ - struct rtl8366rb *rb = priv->chip_data; - struct led_init_data init_data = { }; - enum led_default_state state; - struct rtl8366rb_led *led; - u32 led_group; - int ret; - - ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group); - if (ret) - return ret; - - if (led_group >= RTL8366RB_NUM_LEDGROUPS) { - dev_warn(priv->dev, "Invalid LED reg %d defined for port %d", - led_group, dp->index); - return -EINVAL; - } - - led = &rb->leds[dp->index][led_group]; - led->port_num = dp->index; - led->led_group = led_group; - led->priv = priv; - - state = led_init_default_state_get(led_fwnode); - switch (state) { - case LEDS_DEFSTATE_ON: - led->cdev.brightness = 1; - rb8366rb_set_port_led(led, 1); - break; - case LEDS_DEFSTATE_KEEP: - led->cdev.brightness = - rb8366rb_get_port_led(led); - break; - case LEDS_DEFSTATE_OFF: - default: - led->cdev.brightness = 0; - rb8366rb_set_port_led(led, 0); - } - - led->cdev.max_brightness = 1; - led->cdev.brightness_set_blocking = - rtl8366rb_cled_brightness_set_blocking; - init_data.fwnode = led_fwnode; - init_data.devname_mandatory = true; - - init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d", - dp->ds->index, dp->index, led_group); - if (!init_data.devicename) - return -ENOMEM; - - ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data); - if (ret) { - dev_warn(priv->dev, "Failed to init LED %d for port %d", - led_group, dp->index); - return ret; - } - - return 0; -} - +/* This code is used also with LEDs disabled */ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv) { int ret = 0; @@ -1008,38 +794,6 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv) return ret; } -static int rtl8366rb_setup_leds(struct realtek_priv *priv) -{ - struct dsa_switch *ds = &priv->ds; - struct device_node *leds_np; - struct dsa_port *dp; - int ret = 0; - - dsa_switch_for_each_port(dp, ds) { - if (!dp->dn) - continue; - - leds_np = of_get_child_by_name(dp->dn, "leds"); - if (!leds_np) { - dev_dbg(priv->dev, "No leds defined for port %d", - dp->index); - continue; - } - - for_each_child_of_node_scoped(leds_np, led_np) { - ret = rtl8366rb_setup_led(priv, dp, - of_fwnode_handle(led_np)); - if (ret) - break; - } - - of_node_put(leds_np); - if (ret) - return ret; - } - return 0; -} - static int rtl8366rb_setup(struct dsa_switch *ds) { struct realtek_priv *priv = ds->priv; diff --git a/drivers/net/dsa/realtek/rtl8366rb.h b/drivers/net/dsa/realtek/rtl8366rb.h new file mode 100644 index 000000000000..685ff3275faa --- /dev/null +++ b/drivers/net/dsa/realtek/rtl8366rb.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RTL8366RB_H +#define _RTL8366RB_H + +#include "realtek.h" + +#define RTL8366RB_PORT_NUM_CPU 5 +#define RTL8366RB_NUM_PORTS 6 +#define RTL8366RB_PHY_NO_MAX 4 +#define RTL8366RB_NUM_LEDGROUPS 4 +#define RTL8366RB_PHY_ADDR_MAX 31 + +/* LED control registers */ +/* The LED blink rate is global; it is used by all triggers in all groups. */ +#define RTL8366RB_LED_BLINKRATE_REG 0x0430 +#define RTL8366RB_LED_BLINKRATE_MASK 0x0007 +#define RTL8366RB_LED_BLINKRATE_28MS 0x0000 +#define RTL8366RB_LED_BLINKRATE_56MS 0x0001 +#define RTL8366RB_LED_BLINKRATE_84MS 0x0002 +#define RTL8366RB_LED_BLINKRATE_111MS 0x0003 +#define RTL8366RB_LED_BLINKRATE_222MS 0x0004 +#define RTL8366RB_LED_BLINKRATE_446MS 0x0005 + +/* LED trigger event for each group */ +#define RTL8366RB_LED_CTRL_REG 0x0431 +#define RTL8366RB_LED_CTRL_OFFSET(led_group) \ + (4 * (led_group)) +#define RTL8366RB_LED_CTRL_MASK(led_group) \ + (0xf << RTL8366RB_LED_CTRL_OFFSET(led_group)) + +/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only + * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is + * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored. + */ +#define RTL8366RB_LED_0_1_CTRL_REG 0x0432 +#define RTL8366RB_LED_2_3_CTRL_REG 0x0433 +#define RTL8366RB_LED_X_X_CTRL_REG(led_group) \ + ((led_group) <= 1 ? \ + RTL8366RB_LED_0_1_CTRL_REG : \ + RTL8366RB_LED_2_3_CTRL_REG) +#define RTL8366RB_LED_0_X_CTRL_MASK GENMASK(5, 0) +#define RTL8366RB_LED_X_1_CTRL_MASK GENMASK(11, 6) +#define RTL8366RB_LED_2_X_CTRL_MASK GENMASK(5, 0) +#define RTL8366RB_LED_X_3_CTRL_MASK GENMASK(11, 6) + +enum rtl8366_ledgroup_mode { + RTL8366RB_LEDGROUP_OFF = 0x0, + RTL8366RB_LEDGROUP_DUP_COL = 0x1, + RTL8366RB_LEDGROUP_LINK_ACT = 0x2, + RTL8366RB_LEDGROUP_SPD1000 = 0x3, + RTL8366RB_LEDGROUP_SPD100 = 0x4, + RTL8366RB_LEDGROUP_SPD10 = 0x5, + RTL8366RB_LEDGROUP_SPD1000_ACT = 0x6, + RTL8366RB_LEDGROUP_SPD100_ACT = 0x7, + RTL8366RB_LEDGROUP_SPD10_ACT = 0x8, + RTL8366RB_LEDGROUP_SPD100_10_ACT = 0x9, + RTL8366RB_LEDGROUP_FIBER = 0xa, + RTL8366RB_LEDGROUP_AN_FAULT = 0xb, + RTL8366RB_LEDGROUP_LINK_RX = 0xc, + RTL8366RB_LEDGROUP_LINK_TX = 0xd, + RTL8366RB_LEDGROUP_MASTER = 0xe, + RTL8366RB_LEDGROUP_FORCE = 0xf, + + __RTL8366RB_LEDGROUP_MODE_MAX +}; + +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS) + +struct rtl8366rb_led { + u8 port_num; + u8 led_group; + struct realtek_priv *priv; + struct led_classdev cdev; +}; + +int rtl8366rb_setup_leds(struct realtek_priv *priv); + +#else + +static inline int rtl8366rb_setup_leds(struct realtek_priv *priv) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS) */ + +/** + * struct rtl8366rb - RTL8366RB-specific data + * @max_mtu: per-port max MTU setting + * @pvid_enabled: if PVID is set for respective port + * @leds: per-port and per-ledgroup led info + */ +struct rtl8366rb { + unsigned int max_mtu[RTL8366RB_NUM_PORTS]; + bool pvid_enabled[RTL8366RB_NUM_PORTS]; +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS) + struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS]; +#endif +}; + +/* This code is used also with LEDs disabled */ +int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv, + u8 led_group, + enum rtl8366_ledgroup_mode mode); + +#endif /* _RTL8366RB_H */ From db10fde5c4f96231e1d2bbfd01feb5f2f59b96d1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 20 Feb 2025 18:51:40 -0800 Subject: [PATCH 17/53] net: ethtool: fix ioctl confusing drivers about desired HDS user config The legacy ioctl path does not have support for extended attributes. So we issue a GET to fetch the current settings from the driver, in an attempt to keep them unchanged. HDS is a bit "special" as the GET only returns on/off while the SET takes a "ternary" argument (on/off/default). If the driver was in the "default" setting - executing the ioctl path binds it to on or off, even tho the user did not intend to change HDS config. Factor the relevant logic out of the netlink code and reuse it. Fixes: 87c8f8496a05 ("bnxt_en: add support for tcp-data-split ethtool command") Acked-by: Stanislav Fomichev Tested-by: Daniel Xu Tested-by: Taehee Yoo Link: https://patch.msgid.link/20250221025141.1132944-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- net/ethtool/common.c | 16 ++++++++++++++++ net/ethtool/common.h | 6 ++++++ net/ethtool/ioctl.c | 4 ++-- net/ethtool/rings.c | 9 ++++----- 4 files changed, 28 insertions(+), 7 deletions(-) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index d88e9080643b..b97374b508f6 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "netlink.h" #include "common.h" @@ -771,6 +772,21 @@ int ethtool_check_ops(const struct ethtool_ops *ops) return 0; } +void ethtool_ringparam_get_cfg(struct net_device *dev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kparam, + struct netlink_ext_ack *extack) +{ + memset(param, 0, sizeof(*param)); + memset(kparam, 0, sizeof(*kparam)); + + param->cmd = ETHTOOL_GRINGPARAM; + dev->ethtool_ops->get_ringparam(dev, param, kparam, extack); + + /* Driver gives us current state, we want to return current config */ + kparam->tcp_data_split = dev->cfg->hds_config; +} + static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info) { memset(info, 0, sizeof(*info)); diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 58e9e7db06f9..a1088c2441d0 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -51,6 +51,12 @@ int ethtool_check_max_channel(struct net_device *dev, struct ethtool_channels channels, struct genl_info *info); int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context); + +void ethtool_ringparam_get_cfg(struct net_device *dev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kparam, + struct netlink_ext_ack *extack); + int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); int ethtool_get_ts_info_by_phc(struct net_device *dev, struct kernel_ethtool_ts_info *info, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7609ce2b2c5e..1c3ba2247776 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2059,8 +2059,8 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM }; struct kernel_ethtool_ringparam kernel_ringparam; + struct ethtool_ringparam ringparam, max; int ret; if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam) @@ -2069,7 +2069,7 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) if (copy_from_user(&ringparam, useraddr, sizeof(ringparam))) return -EFAULT; - dev->ethtool_ops->get_ringparam(dev, &max, &kernel_ringparam, NULL); + ethtool_ringparam_get_cfg(dev, &max, &kernel_ringparam, NULL); /* ensure new ring parameters are within the maximums */ if (ringparam.rx_pending > max.rx_max_pending || diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 7839bfd1ac6a..aeedd5ec6b8c 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -215,17 +215,16 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info, static int ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) { - struct kernel_ethtool_ringparam kernel_ringparam = {}; - struct ethtool_ringparam ringparam = {}; + struct kernel_ethtool_ringparam kernel_ringparam; struct net_device *dev = req_info->dev; + struct ethtool_ringparam ringparam; struct nlattr **tb = info->attrs; const struct nlattr *err_attr; bool mod = false; int ret; - dev->ethtool_ops->get_ringparam(dev, &ringparam, - &kernel_ringparam, info->extack); - kernel_ringparam.tcp_data_split = dev->cfg->hds_config; + ethtool_ringparam_get_cfg(dev, &ringparam, &kernel_ringparam, + info->extack); ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod); ethnl_update_u32(&ringparam.rx_mini_pending, From 29b036be1b0bfcfc958380d5931325997fddf08a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 20 Feb 2025 18:51:41 -0800 Subject: [PATCH 18/53] selftests: drv-net: test XDP, HDS auto and the ioctl path Test XDP and HDS interaction. While at it add a test for using the IOCTL, as that turned out to be the real culprit. Testing bnxt: # NETIF=eth0 ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..12 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by the device ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.enabled_set_xdp ok 10 hds.ioctl ok 11 hds.ioctl_set_xdp ok 12 hds.ioctl_enabled_set_xdp # Totals: pass:11 fail:0 xfail:0 xpass:0 skip:1 error:0 and netdevsim: # ./ksft-net-drv/drivers/net/hds.py KTAP version 1 1..12 ok 1 hds.get_hds ok 2 hds.get_hds_thresh ok 3 hds.set_hds_disable ok 4 hds.set_hds_enable ok 5 hds.set_hds_thresh_zero ok 6 hds.set_hds_thresh_max ok 7 hds.set_hds_thresh_gt ok 8 hds.set_xdp ok 9 hds.enabled_set_xdp ok 10 hds.ioctl ok 11 hds.ioctl_set_xdp ok 12 hds.ioctl_enabled_set_xdp # Totals: pass:12 fail:0 xfail:0 xpass:0 skip:0 error:0 Netdevsim needs a sane default for tx/rx ring size. ethtool 6.11 is needed for the --disable-netlink option. Acked-by: Stanislav Fomichev Tested-by: Taehee Yoo Link: https://patch.msgid.link/20250221025141.1132944-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/netdevsim/ethtool.c | 2 + tools/testing/selftests/drivers/net/hds.py | 145 +++++++++++++++++- tools/testing/selftests/net/lib/Makefile | 3 + .../testing/selftests/net/lib/xdp_dummy.bpf.c | 13 ++ 4 files changed, 160 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/net/lib/xdp_dummy.bpf.c diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 5c80fbee7913..7ab358616e03 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -184,9 +184,11 @@ static const struct ethtool_ops nsim_ethtool_ops = { static void nsim_ethtool_ring_init(struct netdevsim *ns) { + ns->ethtool.ring.rx_pending = 512; ns->ethtool.ring.rx_max_pending = 4096; ns->ethtool.ring.rx_jumbo_max_pending = 4096; ns->ethtool.ring.rx_mini_max_pending = 4096; + ns->ethtool.ring.tx_pending = 512; ns->ethtool.ring.tx_max_pending = 4096; } diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 394971b25c0b..873f5219e41d 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -2,17 +2,54 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import os from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx -from lib.py import EthtoolFamily, NlError +from lib.py import CmdExitFailure, EthtoolFamily, NlError from lib.py import NetDrvEnv +from lib.py import defer, ethtool, ip -def get_hds(cfg, netnl) -> None: + +def _get_hds_mode(cfg, netnl) -> str: try: rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) except NlError as e: raise KsftSkipEx('ring-get not supported by device') if 'tcp-data-split' not in rings: raise KsftSkipEx('tcp-data-split not supported by device') + return rings['tcp-data-split'] + + +def _xdp_onoff(cfg): + test_dir = os.path.dirname(os.path.realpath(__file__)) + prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + ip("link set dev %s xdp obj %s sec xdp" % + (cfg.ifname, prog)) + ip("link set dev %s xdp off" % cfg.ifname) + + +def _ioctl_ringparam_modify(cfg, netnl) -> None: + """ + Helper for performing a hopefully unimportant IOCTL SET. + IOCTL does not support HDS, so it should not affect the HDS config. + """ + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + + if 'tx' not in rings: + raise KsftSkipEx('setting Tx ring size not supported') + + try: + ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] // 2}") + except CmdExitFailure as e: + ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] * 2}") + defer(ethtool, f"-G {cfg.ifname} tx {rings['tx']}") + + +def get_hds(cfg, netnl) -> None: + _get_hds_mode(cfg, netnl) + def get_hds_thresh(cfg, netnl) -> None: try: @@ -104,6 +141,103 @@ def set_hds_thresh_gt(cfg, netnl) -> None: netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt}) ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _xdp_onoff(cfg) + + +def enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _xdp_onoff(cfg) + + +def enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) # Trigger skip if not supported + + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + +def ioctl(cfg, netnl) -> None: + mode1 = _get_hds_mode(cfg, netnl) + _ioctl_ringparam_modify(cfg, netnl) + mode2 = _get_hds_mode(cfg, netnl) + + ksft_eq(mode1, mode2) + + +def ioctl_set_xdp(cfg, netnl) -> None: + """ + Like set_xdp(), but we perturb the settings via the legacy ioctl. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _ioctl_ringparam_modify(cfg, netnl) + + _xdp_onoff(cfg) + + +def ioctl_enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) # Trigger skip if not supported + + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + def main() -> None: with NetDrvEnv(__file__, queue_count=3) as cfg: ksft_run([get_hds, @@ -112,7 +246,12 @@ def main() -> None: set_hds_enable, set_hds_thresh_zero, set_hds_thresh_max, - set_hds_thresh_gt], + set_hds_thresh_gt, + set_xdp, + enabled_set_xdp, + ioctl, + ioctl_set_xdp, + ioctl_enabled_set_xdp], args=(cfg, EthtoolFamily())) ksft_exit() diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index bc6b6762baf3..c22623b9a2a5 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -9,7 +9,10 @@ TEST_FILES := ../../../../../Documentation/netlink/specs TEST_FILES += ../../../../net/ynl TEST_GEN_FILES += csum +TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) TEST_INCLUDES := $(wildcard py/*.py sh/*.sh) include ../../lib.mk + +include ../bpf.mk diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include +#include + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; From de2c211868b9424f9aa9b3432c4430825bafb41b Mon Sep 17 00:00:00 2001 From: Philo Lu Date: Sat, 22 Feb 2025 11:35:18 +0800 Subject: [PATCH 19/53] ipvs: Always clear ipvs_property flag in skb_scrub_packet() We found an issue when using bpf_redirect with ipvs NAT mode after commit ff70202b2d1a ("dev_forward_skb: do not scrub skb mark within the same name space"). Particularly, we use bpf_redirect to return the skb directly back to the netif it comes from, i.e., xnet is false in skb_scrub_packet(), and then ipvs_property is preserved and SNAT is skipped in the rx path. ipvs_property has been already cleared when netns is changed in commit 2b5ec1a5f973 ("netfilter/ipvs: clear ipvs_property flag when SKB net namespace changed"). This patch just clears it in spite of netns. Fixes: 2b5ec1a5f973 ("netfilter/ipvs: clear ipvs_property flag when SKB net namespace changed") Signed-off-by: Philo Lu Acked-by: Julian Anastasov Link: https://patch.msgid.link/20250222033518.126087-1-lulie@linux.alibaba.com Signed-off-by: Paolo Abeni --- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7b03b64fdcb2..b1c81687e9d8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6033,11 +6033,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->offload_fwd_mark = 0; skb->offload_l3_fwd_mark = 0; #endif + ipvs_reset(skb); if (!xnet) return; - ipvs_reset(skb); skb->mark = 0; skb_clear_tstamp(skb); } From bc50682128bde778a1ddc457a02d92a637c20c6f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Sat, 22 Feb 2025 12:28:04 -0500 Subject: [PATCH 20/53] MAINTAINERS: socket timestamping: add Jason Xing as reviewer Jason has been helping as reviewer for this area already, and has contributed various features directly, notably BPF timestamping. Also extend coverage to all timestamping tests, including those new with BPF timestamping. Link: https://lore.kernel.org/netdev/20250220072940.99994-1-kerneljasonxing@gmail.com/ Signed-off-by: Willem de Bruijn Reviewed-by: Jason Xing Link: https://patch.msgid.link/20250222172839.642079-1-willemdebruijn.kernel@gmail.com Signed-off-by: Paolo Abeni --- MAINTAINERS | 3 +++ 1 file changed, 3 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ac15093537c6..c92bcd02049e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21923,10 +21923,13 @@ F: sound/soc/uniphier/ SOCKET TIMESTAMPING M: Willem de Bruijn +R: Jason Xing S: Maintained F: Documentation/networking/timestamping.rst F: include/linux/net_tstamp.h F: include/uapi/linux/net_tstamp.h +F: tools/testing/selftests/bpf/*/net_timestamping* +F: tools/testing/selftests/net/*timestamp* F: tools/testing/selftests/net/so_txtime.c SOEKRIS NET48XX LED SUPPORT From bab3a6e9ffd600f9db0ebaf8f45e1c6111cf314c Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Mon, 24 Feb 2025 06:17:16 +0100 Subject: [PATCH 21/53] net: ethernet: ti: am65-cpsw: select PAGE_POOL am65-cpsw uses page_pool_dev_alloc_pages(), thus needs PAGE_POOL selected to avoid linker errors. This is missing since the driver started to use page_pool helpers in 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support") Fixes: 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support") Signed-off-by: Sascha Hauer Reviewed-by: Michal Swiatkowski Link: https://patch.msgid.link/20250224-net-am654-nuss-kconfig-v2-1-c124f4915c92@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 0d5a862cd78a..3a13d60a947a 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -99,6 +99,7 @@ config TI_K3_AM65_CPSW_NUSS select NET_DEVLINK select TI_DAVINCI_MDIO select PHYLINK + select PAGE_POOL select TI_K3_CPPI_DESC_POOL imply PHY_TI_GMII_SEL depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS From 18912c520674ec4d920fe3826e7e4fefeecdf5ae Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 24 Feb 2025 09:44:01 -0800 Subject: [PATCH 22/53] tcp: devmem: don't write truncated dmabuf CMSGs to userspace Currently, we report -ETOOSMALL (err) only on the first iteration (!sent). When we get put_cmsg error after a bunch of successful put_cmsg calls, we don't signal the error at all. This might be confusing on the userspace side which will see truncated CMSGs but no MSG_CTRUNC signal. Consider the following case: - sizeof(struct cmsghdr) = 16 - sizeof(struct dmabuf_cmsg) = 24 - total cmsg size (CMSG_LEN) = 40 (16+24) When calling recvmsg with msg_controllen=60, the userspace will receive two(!) dmabuf_cmsg(s), the first one will be a valid one and the second one will be silently truncated. There is no easy way to discover the truncation besides doing something like "cm->cmsg_len != CMSG_LEN(sizeof(dmabuf_cmsg))". Introduce new put_devmem_cmsg wrapper that reports an error instead of doing the truncation. Mina suggests that it's the intended way this API should work. Note that we might now report MSG_CTRUNC when the users (incorrectly) call us with msg_control == NULL. Fixes: 8f0b3cc9a4c1 ("tcp: RX path for devmem TCP") Reviewed-by: Mina Almasry Signed-off-by: Stanislav Fomichev Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250224174401.3582695-1-sdf@fomichev.me Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 2 ++ net/core/scm.c | 10 ++++++++++ net/ipv4/tcp.c | 26 ++++++++++---------------- 3 files changed, 22 insertions(+), 16 deletions(-) diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..c3322eb3d686 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,8 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data); struct timespec64; struct __kernel_timespec; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..733c0cbd393d 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -282,6 +282,16 @@ efault: } EXPORT_SYMBOL(put_cmsg); +int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data) +{ + /* Don't produce truncated CMSGs */ + if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len)) + return -ETOOSMALL; + + return put_cmsg(msg, level, type, len, data); +} + void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d704bda6c41..d74281eca14f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2438,14 +2438,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; - err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, - sizeof(dmabuf_cmsg), &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } sent += copy; @@ -2499,16 +2497,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, offset += copy; remaining_len -= copy; - err = put_cmsg(msg, SOL_SOCKET, - SO_DEVMEM_DMABUF, - sizeof(dmabuf_cmsg), - &dmabuf_cmsg); - if (err || msg->msg_flags & MSG_CTRUNC) { - msg->msg_flags &= ~MSG_CTRUNC; - if (!err) - err = -ETOOSMALL; + err = put_cmsg_notrunc(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err) goto out; - } atomic_long_inc(&niov->pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); From f865c24bc55158313d5779fc81116023a6940ca3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 24 Feb 2025 19:11:50 +0100 Subject: [PATCH 23/53] mptcp: always handle address removal under msk socket lock Syzkaller reported a lockdep splat in the PM control path: WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 sock_owned_by_me include/net/sock.h:1711 [inline] WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 msk_owned_by_me net/mptcp/protocol.h:363 [inline] WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788 Modules linked in: CPU: 0 UID: 0 PID: 6693 Comm: syz.0.205 Not tainted 6.14.0-rc2-syzkaller-00303-gad1b832bf1cf #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 12/27/2024 RIP: 0010:sock_owned_by_me include/net/sock.h:1711 [inline] RIP: 0010:msk_owned_by_me net/mptcp/protocol.h:363 [inline] RIP: 0010:mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788 Code: 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc e8 ca 7b d3 f5 eb b9 e8 c3 7b d3 f5 90 0f 0b 90 e9 dd fb ff ff e8 b5 7b d3 f5 90 <0f> 0b 90 e9 3e fb ff ff 44 89 f1 80 e1 07 38 c1 0f 8c eb fb ff ff RSP: 0000:ffffc900034f6f60 EFLAGS: 00010283 RAX: ffffffff8bee3c2b RBX: 0000000000000001 RCX: 0000000000080000 RDX: ffffc90004d42000 RSI: 000000000000a407 RDI: 000000000000a408 RBP: ffffc900034f7030 R08: ffffffff8bee37f6 R09: 0100000000000000 R10: dffffc0000000000 R11: ffffed100bcc62e4 R12: ffff88805e6316e0 R13: ffff88805e630c00 R14: dffffc0000000000 R15: ffff88805e630c00 FS: 00007f7e9a7e96c0(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2fd18ff8 CR3: 0000000032c24000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mptcp_pm_remove_addr+0x103/0x1d0 net/mptcp/pm.c:59 mptcp_pm_remove_anno_addr+0x1f4/0x2f0 net/mptcp/pm_netlink.c:1486 mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_netlink.c:1518 [inline] mptcp_pm_nl_del_addr_doit+0x118d/0x1af0 net/mptcp/pm_netlink.c:1629 genl_family_rcv_msg_doit net/netlink/genetlink.c:1115 [inline] genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline] genl_rcv_msg+0xb1f/0xec0 net/netlink/genetlink.c:1210 netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2543 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219 netlink_unicast_kernel net/netlink/af_netlink.c:1322 [inline] netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1348 netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:718 [inline] __sock_sendmsg+0x221/0x270 net/socket.c:733 ____sys_sendmsg+0x53a/0x860 net/socket.c:2573 ___sys_sendmsg net/socket.c:2627 [inline] __sys_sendmsg+0x269/0x350 net/socket.c:2659 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f7e9998cde9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f7e9a7e9038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f7e99ba5fa0 RCX: 00007f7e9998cde9 RDX: 000000002000c094 RSI: 0000400000000000 RDI: 0000000000000007 RBP: 00007f7e99a0e2a0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f7e99ba5fa0 R15: 00007fff49231088 Indeed the PM can try to send a RM_ADDR over a msk without acquiring first the msk socket lock. The bugged code-path comes from an early optimization: when there are no subflows, the PM should (usually) not send RM_ADDR notifications. The above statement is incorrect, as without locks another process could concurrent create a new subflow and cause the RM_ADDR generation. Additionally the supposed optimization is not very effective even performance-wise, as most mptcp sockets should have at least one subflow: the MPC one. Address the issue removing the buggy code path, the existing "slow-path" will handle correctly even the edge case. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reported-by: syzbot+cd3ce3d03a3393ae9700@syzkaller.appspotmail.com Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/546 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-1-f550f636b435@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 572d160edca3..c0e47f4f7b1a 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1514,11 +1514,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, if (mptcp_pm_is_userspace(msk)) goto next; - if (list_empty(&msk->conn_list)) { - mptcp_pm_remove_anno_addr(msk, addr, false); - goto next; - } - lock_sock(sk); remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && From 8668860b0ad32a13fcd6c94a0995b7aa7638c9ef Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 24 Feb 2025 19:11:51 +0100 Subject: [PATCH 24/53] mptcp: reset when MPTCP opts are dropped after join Before this patch, if the checksum was not used, the subflow was only reset if map_data_len was != 0. If there were no MPTCP options or an invalid mapping, map_data_len was not set to the data len, and then the subflow was not reset as it should have been, leaving the MPTCP connection in a wrong fallback mode. This map_data_len condition has been introduced to handle the reception of the infinite mapping. Instead, a new dedicated mapping error could have been returned and treated as a special case. However, the commit 31bf11de146c ("mptcp: introduce MAPPING_BAD_CSUM") has been introduced by Paolo Abeni soon after, and backported later on to stable. It better handle the csum case, and it means the exception for valid_csum_seen in subflow_can_fallback(), plus this one for the infinite mapping in subflow_check_data_avail(), are no longer needed. In other words, the code can be simplified there: a fallback should only be done if msk->allow_infinite_fallback is set. This boolean is set to false once MPTCP-specific operations acting on the whole MPTCP connection vs the initial path have been done, e.g. a second path has been created, or an MPTCP re-injection -- yes, possible even with a single subflow. The subflow_can_fallback() helper can then be dropped, and replaced by this single condition. This also makes the code clearer: a fallback should only be done if it is possible to do so. While at it, no need to set map_data_len to 0 in get_mapping_status() for the infinite mapping case: it will be set to skb->len just after, at the end of subflow_check_data_avail(), and not read in between. Fixes: f8d4bcacff3b ("mptcp: infinite mapping receiving") Cc: stable@vger.kernel.org Reported-by: Chester A. Unal Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/544 Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Tested-by: Chester A. Unal Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-2-f550f636b435@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index dfcbef9c4624..9f18217dddc8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1142,7 +1142,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (data_len == 0) { pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); - subflow->map_data_len = 0; return MAPPING_INVALID; } @@ -1286,18 +1285,6 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss mptcp_schedule_work(sk); } -static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) -{ - struct mptcp_sock *msk = mptcp_sk(subflow->conn); - - if (subflow->mp_join) - return false; - else if (READ_ONCE(msk->csum_enabled)) - return !subflow->valid_csum_seen; - else - return READ_ONCE(msk->allow_infinite_fallback); -} - static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1393,7 +1380,7 @@ fallback: return true; } - if (!subflow_can_fallback(subflow) && subflow->map_data_len) { + if (!READ_ONCE(msk->allow_infinite_fallback)) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ From db75a16813aabae3b78c06b1b99f5e314c1f55d3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 24 Feb 2025 19:11:52 +0100 Subject: [PATCH 25/53] mptcp: safety check before fallback Recently, some fallback have been initiated, while the connection was not supposed to fallback. Add a safety check with a warning to detect when an wrong attempt to fallback is being done. This should help detecting any future issues quicker. Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-3-f550f636b435@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index f6a207958459..ad21925af061 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1199,6 +1199,8 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } + if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback))) + return; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } From 79990cf5e7aded76d0c092c9f5ed31eb1c75e02c Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Mon, 24 Feb 2025 11:06:41 -0800 Subject: [PATCH 26/53] ice: Fix deinitializing VF in error path If ice_ena_vfs() fails after calling ice_create_vf_entries(), it frees all VFs without removing them from snapshot PF-VF mailbox list, leading to list corruption. Reproducer: devlink dev eswitch set $PF1_PCI mode switchdev ip l s $PF1 up ip l s $PF1 promisc on sleep 1 echo 1 > /sys/class/net/$PF1/device/sriov_numvfs sleep 1 echo 1 > /sys/class/net/$PF1/device/sriov_numvfs Trace (minimized): list_add corruption. next->prev should be prev (ffff8882e241c6f0), but was 0000000000000000. (next=ffff888455da1330). kernel BUG at lib/list_debug.c:29! RIP: 0010:__list_add_valid_or_report+0xa6/0x100 ice_mbx_init_vf_info+0xa7/0x180 [ice] ice_initialize_vf_entry+0x1fa/0x250 [ice] ice_sriov_configure+0x8d7/0x1520 [ice] ? __percpu_ref_switch_mode+0x1b1/0x5d0 ? __pfx_ice_sriov_configure+0x10/0x10 [ice] Sometimes a KASAN report can be seen instead with a similar stack trace: BUG: KASAN: use-after-free in __list_add_valid_or_report+0xf1/0x100 VFs are added to this list in ice_mbx_init_vf_info(), but only removed in ice_free_vfs(). Move the removing to ice_free_vf_entries(), which is also being called in other places where VFs are being removed (including ice_free_vfs() itself). Fixes: 8cd8a6b17d27 ("ice: move VF overflow message count into struct ice_mbx_vf_info") Reported-by: Sujai Buvaneswaran Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com Reviewed-by: Martyna Szapar-Mudlaw Signed-off-by: Marcin Szycik Reviewed-by: Simon Horman Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-2-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_sriov.c | 5 +---- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 8 ++++++++ drivers/net/ethernet/intel/ice/ice_vf_lib_private.h | 1 + 3 files changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index b83f99c01d91..8aabf7749aa5 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf) hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) { hash_del_rcu(&vf->entry); + ice_deinitialize_vf_entry(vf); ice_put_vf(vf); } } @@ -193,10 +194,6 @@ void ice_free_vfs(struct ice_pf *pf) wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } - /* clear malicious info since the VF is getting released */ - if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) - list_del(&vf->mbx_info.list_entry); - mutex_unlock(&vf->cfg_lock); } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index c7c0c2f50c26..815ad0bfe832 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -1036,6 +1036,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf) mutex_init(&vf->cfg_lock); } +void ice_deinitialize_vf_entry(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) + list_del(&vf->mbx_info.list_entry); +} + /** * ice_dis_vf_qs - Disable the VF queues * @vf: pointer to the VF structure diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 0c7e77c0a09f..5392b0404986 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -24,6 +24,7 @@ #endif void ice_initialize_vf_entry(struct ice_vf *vf); +void ice_deinitialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); From 5c07be96d8b3f8447e980f29b967bf2e1d7ac732 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Mon, 24 Feb 2025 11:06:42 -0800 Subject: [PATCH 27/53] ice: Avoid setting default Rx VSI twice in switchdev setup As part of switchdev environment setup, uplink VSI is configured as default for both Tx and Rx. Default Rx VSI is also used by promiscuous mode. If promisc mode is enabled and an attempt to enter switchdev mode is made, the setup will fail because Rx VSI is already configured as default (rule exists). Reproducer: devlink dev eswitch set $PF1_PCI mode switchdev ip l s $PF1 up ip l s $PF1 promisc on echo 1 > /sys/class/net/$PF1/device/sriov_numvfs In switchdev setup, use ice_set_dflt_vsi() instead of plain ice_cfg_dflt_vsi(), which avoids repeating setting default VSI for Rx if it's already configured. Fixes: 50d62022f455 ("ice: default Tx rule instead of to queue") Reported-by: Sujai Buvaneswaran Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com Reviewed-by: Martyna Szapar-Mudlaw Signed-off-by: Marcin Szycik Reviewed-by: Simon Horman Tested-by: Sujai Buvaneswaran Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-3-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_eswitch.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index fb527434b58b..d649c197cf67 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -38,8 +38,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) if (ice_vsi_add_vlan_zero(uplink_vsi)) goto err_vlan_zero; - if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, - ICE_FLTR_RX)) + if (ice_set_dflt_vsi(uplink_vsi)) goto err_def_rx; if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true, From c6124f6fd3ca37d53ec5cbf62f9d9130ef439eca Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 24 Feb 2025 11:06:44 -0800 Subject: [PATCH 28/53] iavf: fix circular lock dependency with netdev_lock We have recently seen reports of lockdep circular lock dependency warnings when loading the iAVF driver: [ 1504.790308] ====================================================== [ 1504.790309] WARNING: possible circular locking dependency detected [ 1504.790310] 6.13.0 #net_next_rt.c2933b2befe2.el9 Not tainted [ 1504.790311] ------------------------------------------------------ [ 1504.790312] kworker/u128:0/13566 is trying to acquire lock: [ 1504.790313] ffff97d0e4738f18 (&dev->lock){+.+.}-{4:4}, at: register_netdevice+0x52c/0x710 [ 1504.790320] [ 1504.790320] but task is already holding lock: [ 1504.790321] ffff97d0e47392e8 (&adapter->crit_lock){+.+.}-{4:4}, at: iavf_finish_config+0x37/0x240 [iavf] [ 1504.790330] [ 1504.790330] which lock already depends on the new lock. [ 1504.790330] [ 1504.790330] [ 1504.790330] the existing dependency chain (in reverse order) is: [ 1504.790331] [ 1504.790331] -> #1 (&adapter->crit_lock){+.+.}-{4:4}: [ 1504.790333] __lock_acquire+0x52d/0xbb0 [ 1504.790337] lock_acquire+0xd9/0x330 [ 1504.790338] mutex_lock_nested+0x4b/0xb0 [ 1504.790341] iavf_finish_config+0x37/0x240 [iavf] [ 1504.790347] process_one_work+0x248/0x6d0 [ 1504.790350] worker_thread+0x18d/0x330 [ 1504.790352] kthread+0x10e/0x250 [ 1504.790354] ret_from_fork+0x30/0x50 [ 1504.790357] ret_from_fork_asm+0x1a/0x30 [ 1504.790361] [ 1504.790361] -> #0 (&dev->lock){+.+.}-{4:4}: [ 1504.790364] check_prev_add+0xf1/0xce0 [ 1504.790366] validate_chain+0x46a/0x570 [ 1504.790368] __lock_acquire+0x52d/0xbb0 [ 1504.790370] lock_acquire+0xd9/0x330 [ 1504.790371] mutex_lock_nested+0x4b/0xb0 [ 1504.790372] register_netdevice+0x52c/0x710 [ 1504.790374] iavf_finish_config+0xfa/0x240 [iavf] [ 1504.790379] process_one_work+0x248/0x6d0 [ 1504.790381] worker_thread+0x18d/0x330 [ 1504.790383] kthread+0x10e/0x250 [ 1504.790385] ret_from_fork+0x30/0x50 [ 1504.790387] ret_from_fork_asm+0x1a/0x30 [ 1504.790389] [ 1504.790389] other info that might help us debug this: [ 1504.790389] [ 1504.790389] Possible unsafe locking scenario: [ 1504.790389] [ 1504.790390] CPU0 CPU1 [ 1504.790391] ---- ---- [ 1504.790391] lock(&adapter->crit_lock); [ 1504.790393] lock(&dev->lock); [ 1504.790394] lock(&adapter->crit_lock); [ 1504.790395] lock(&dev->lock); [ 1504.790397] [ 1504.790397] *** DEADLOCK *** This appears to be caused by the change in commit 5fda3f35349b ("net: make netdev_lock() protect netdev->reg_state"), which added a netdev_lock() in register_netdevice. The iAVF driver calls register_netdevice() from iavf_finish_config(), as a final stage of its state machine post-probe. It currently takes the RTNL lock, then the netdev lock, and then the device critical lock. This pattern is used throughout the driver. Thus there is a strong dependency that the crit_lock should not be acquired before the net device lock. The change to register_netdevice creates an ABBA lock order violation because the iAVF driver is holding the crit_lock while calling register_netdevice, which then takes the netdev_lock. It seems likely that future refactors could result in netdev APIs which hold the netdev_lock while calling into the driver. This means that we should not re-order the locks so that netdev_lock is acquired after the device private crit_lock. Instead, notice that we already release the netdev_lock prior to calling the register_netdevice. This flow only happens during the early driver initialization as we transition through the __IAVF_STARTUP, __IAVF_INIT_VERSION_CHECK, __IAVF_INIT_GET_RESOURCES, etc. Analyzing the places where we take crit_lock in the driver there are two sources: a) several of the work queue tasks including adminq_task, watchdog_task, reset_task, and the finish_config task. b) various callbacks which ultimately stem back to .ndo operations or ethtool operations. The latter cannot be triggered until after the netdevice registration is completed successfully. The iAVF driver uses alloc_ordered_workqueue, which is an unbound workqueue that has a max limit of 1, and thus guarantees that only a single work item on the queue is executing at any given time, so none of the other work threads could be executing due to the ordered workqueue guarantees. The iavf_finish_config() function also does not do anything else after register_netdevice, unless it fails. It seems unlikely that the driver private crit_lock is protecting anything that register_netdevice() itself touches. Thus, to fix this ABBA lock violation, lets simply release the adapter->crit_lock as well as netdev_lock prior to calling register_netdevice(). We do still keep holding the RTNL lock as required by the function. If we do fail to register the netdevice, then we re-acquire the adapter critical lock to finish the transition back to __IAVF_INIT_CONFIG_ADAPTER. This ensures every call where both netdev_lock and the adapter->crit_lock are acquired under the same ordering. Fixes: afc664987ab3 ("eth: iavf: extend the netdev_lock usage") Signed-off-by: Jacob Keller Tested-by: Przemek Kitszel Reviewed-by: Przemek Kitszel Reviewed-by: Jakub Kicinski Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-5-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/iavf/iavf_main.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 852e5b62f0a5..6faa62bced3a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1983,7 +1983,7 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; - bool netdev_released = false; + bool locks_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); @@ -2012,19 +2012,22 @@ static void iavf_finish_config(struct work_struct *work) netif_set_real_num_tx_queues(adapter->netdev, pairs); if (adapter->netdev->reg_state != NETREG_REGISTERED) { + mutex_unlock(&adapter->crit_lock); netdev_unlock(adapter->netdev); - netdev_released = true; + locks_released = true; err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", err); /* go back and try again.*/ + mutex_lock(&adapter->crit_lock); iavf_free_rss(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); + mutex_unlock(&adapter->crit_lock); goto out; } } @@ -2040,9 +2043,10 @@ static void iavf_finish_config(struct work_struct *work) } out: - mutex_unlock(&adapter->crit_lock); - if (!netdev_released) + if (!locks_released) { + mutex_unlock(&adapter->crit_lock); netdev_unlock(adapter->netdev); + } rtnl_unlock(); } From b1e44b4aecb551727a368df5b85c535f2ce932ea Mon Sep 17 00:00:00 2001 From: Piotr Kwapulinski Date: Mon, 24 Feb 2025 11:06:45 -0800 Subject: [PATCH 29/53] ixgbe: fix media cage present detection for E610 device The commit 23c0e5a16bcc ("ixgbe: Add link management support for E610 device") introduced incorrect checking of media cage presence for E610 device. Fix it. Fixes: 23c0e5a16bcc ("ixgbe: Add link management support for E610 device") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/e7d73b32-f12a-49d1-8b60-1ef83359ec13@stanley.mountain/ Reviewed-by: Michal Swiatkowski Reviewed-by: Przemek Kitszel Signed-off-by: Piotr Kwapulinski Reviewed-by: Simon Horman Tested-by: Bharath R Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250224190647.3601930-6-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c index 683c668672d6..cb07ecd8937d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c @@ -1122,7 +1122,7 @@ static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw) * returns error (ENOENT), then no cage present. If no cage present then * connection type is backplane or BASE-T. */ - return ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); + return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL); } /** From 39ab773e4c120f7f98d759415ccc2aca706bbc10 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:44 +0800 Subject: [PATCH 30/53] net: enetc: fix the off-by-one issue in enetc_map_tx_buffs() When a DMA mapping error occurs while processing skb frags, it will free one more tx_swbd than expected, so fix this off-by-one issue. Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Cc: stable@vger.kernel.org Suggested-by: Vladimir Oltean Suggested-by: Michal Swiatkowski Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20250224111251.1061098-2-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 26 ++++++++++++++------ 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 6a6fc819dfde..55ad31a5073e 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -167,6 +167,24 @@ static bool enetc_skb_is_tcp(struct sk_buff *skb) return skb->csum_offset == offsetof(struct tcphdr, check); } +/** + * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame + * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located + * @count: Number of Tx buffer descriptors which need to be unmapped + * @i: Index of the last successfully mapped Tx buffer descriptor + */ +static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i) +{ + while (count--) { + struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i]; + + enetc_free_tx_frame(tx_ring, tx_swbd); + if (i == 0) + i = tx_ring->bd_count; + i--; + } +} + static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) { bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false; @@ -372,13 +390,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) dma_err: dev_err(tx_ring->dev, "DMA map error"); - do { - tx_swbd = &tx_ring->tx_swbd[i]; - enetc_free_tx_frame(tx_ring, tx_swbd); - if (i == 0) - i = tx_ring->bd_count; - i--; - } while (count--); + enetc_unwind_tx_frame(tx_ring, count, i); return 0; } From da291996b16ebd10626d4b20288327b743aff110 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:45 +0800 Subject: [PATCH 31/53] net: enetc: keep track of correct Tx BD count in enetc_map_tx_tso_buffs() When creating a TSO header, if the skb is VLAN tagged, the extended BD will be used and the 'count' should be increased by 2 instead of 1. Otherwise, when an error occurs, less tx_swbd will be freed than the actual number. Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO") Cc: stable@vger.kernel.org Suggested-by: Vladimir Oltean Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20250224111251.1061098-3-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 55ad31a5073e..174db9e2ce81 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -395,14 +395,15 @@ dma_err: return 0; } -static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, - struct enetc_tx_swbd *tx_swbd, - union enetc_tx_bd *txbd, int *i, int hdr_len, - int data_len) +static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, int *i, int hdr_len, + int data_len) { union enetc_tx_bd txbd_tmp; u8 flags = 0, e_flags = 0; dma_addr_t addr; + int count = 1; enetc_clear_tx_bd(&txbd_tmp); addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; @@ -445,7 +446,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, /* Write the BD */ txbd_tmp.ext.e_flags = e_flags; *txbd = txbd_tmp; + count++; } + + return count; } static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, @@ -802,9 +806,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb /* compute the csum over the L4 header */ csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos); - enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len); + count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, + &i, hdr_len, data_len); bd_data_num = 0; - count++; while (data_len > 0) { int size; From 432a2cb3ee97a7c6ea578888fe81baad035b9307 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:46 +0800 Subject: [PATCH 32/53] net: enetc: correct the xdp_tx statistics The 'xdp_tx' is used to count the number of XDP_TX frames sent, not the number of Tx BDs. Fixes: 7ed2bc80074e ("net: enetc: add support for XDP_TX") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Ioana Ciornei Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-4-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 174db9e2ce81..3cb9ebb13b19 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1917,7 +1917,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_xdp_drop(rx_ring, orig_i, i); tx_ring->stats.xdp_tx_drops++; } else { - tx_ring->stats.xdp_tx += xdp_tx_bd_cnt; + tx_ring->stats.xdp_tx++; rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt; xdp_tx_frm_cnt++; /* The XDP_TX enqueue was successful, so we From a562d0c4a893eae3ea51d512c4d90ab858a6b7ec Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:47 +0800 Subject: [PATCH 33/53] net: enetc: VFs do not support HWTSTAMP_TX_ONESTEP_SYNC Actually ENETC VFs do not support HWTSTAMP_TX_ONESTEP_SYNC because only ENETC PF can access PMa_SINGLE_STEP registers. And there will be a crash if VFs are used to test one-step timestamp, the crash log as follows. [ 129.110909] Unable to handle kernel paging request at virtual address 00000000000080c0 [ 129.287769] Call trace: [ 129.290219] enetc_port_mac_wr+0x30/0xec (P) [ 129.294504] enetc_start_xmit+0xda4/0xe74 [ 129.298525] enetc_xmit+0x70/0xec [ 129.301848] dev_hard_start_xmit+0x98/0x118 Fixes: 41514737ecaa ("enetc: add get_ts_info interface for ethtool") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-5-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 3 +++ drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 7 +++++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3cb9ebb13b19..e946d8652790 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3244,6 +3244,9 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr) new_offloads |= ENETC_F_TX_TSTAMP; break; case HWTSTAMP_TX_ONESTEP_SYNC: + if (!enetc_si_is_pf(priv->si)) + return -EOPNOTSUPP; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP; break; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index bf34b5bb1e35..ece3ae28ba82 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -832,6 +832,7 @@ static int enetc_set_coalesce(struct net_device *ndev, static int enetc_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *info) { + struct enetc_ndev_priv *priv = netdev_priv(ndev); int *phc_idx; phc_idx = symbol_get(enetc_phc_index); @@ -852,8 +853,10 @@ static int enetc_get_ts_info(struct net_device *ndev, SOF_TIMESTAMPING_TX_SOFTWARE; info->tx_types = (1 << HWTSTAMP_TX_OFF) | - (1 << HWTSTAMP_TX_ON) | - (1 << HWTSTAMP_TX_ONESTEP_SYNC); + (1 << HWTSTAMP_TX_ON); + + if (enetc_si_is_pf(priv->si)) + info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC); info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | (1 << HWTSTAMP_FILTER_ALL); From bbcbc906ab7b5834c1219cd17a38d78dba904aa0 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:48 +0800 Subject: [PATCH 34/53] net: enetc: update UDP checksum when updating originTimestamp field There is an issue with one-step timestamp based on UDP/IP. The peer will discard the sync packet because of the wrong UDP checksum. For ENETC v1, the software needs to update the UDP checksum when updating the originTimestamp field, so that the hardware can correctly update the UDP checksum when updating the correction field. Otherwise, the UDP checksum in the sync packet will be wrong. Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-6-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 41 ++++++++++++++++---- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index e946d8652790..9801c51b6a59 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -297,9 +297,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) } if (do_onestep_tstamp) { - u32 lo, hi, val; - u64 sec, nsec; + __be32 new_sec_l, new_nsec; + u32 lo, hi, nsec, val; + __be16 new_sec_h; u8 *data; + u64 sec; lo = enetc_rd_hot(hw, ENETC_SICTR0); hi = enetc_rd_hot(hw, ENETC_SICTR1); @@ -313,13 +315,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) /* Update originTimestamp field of Sync packet * - 48 bits seconds field * - 32 bits nanseconds field + * + * In addition, the UDP checksum needs to be updated + * by software after updating originTimestamp field, + * otherwise the hardware will calculate the wrong + * checksum when updating the correction field and + * update it to the packet. */ data = skb_mac_header(skb); - *(__be16 *)(data + offset2) = - htons((sec >> 32) & 0xffff); - *(__be32 *)(data + offset2 + 2) = - htonl(sec & 0xffffffff); - *(__be32 *)(data + offset2 + 6) = htonl(nsec); + new_sec_h = htons((sec >> 32) & 0xffff); + new_sec_l = htonl(sec & 0xffffffff); + new_nsec = htonl(nsec); + if (udp) { + struct udphdr *uh = udp_hdr(skb); + __be32 old_sec_l, old_nsec; + __be16 old_sec_h; + + old_sec_h = *(__be16 *)(data + offset2); + inet_proto_csum_replace2(&uh->check, skb, old_sec_h, + new_sec_h, false); + + old_sec_l = *(__be32 *)(data + offset2 + 2); + inet_proto_csum_replace4(&uh->check, skb, old_sec_l, + new_sec_l, false); + + old_nsec = *(__be32 *)(data + offset2 + 6); + inet_proto_csum_replace4(&uh->check, skb, old_nsec, + new_nsec, false); + } + + *(__be16 *)(data + offset2) = new_sec_h; + *(__be32 *)(data + offset2 + 2) = new_sec_l; + *(__be32 *)(data + offset2 + 6) = new_nsec; /* Configure single-step register */ val = ENETC_PM0_SINGLE_STEP_EN; From 8e43decdfbb477dd7800e3902d2d2f105d22ef5f Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:49 +0800 Subject: [PATCH 35/53] net: enetc: add missing enetc4_link_deinit() The enetc4_link_init() is called when the PF driver probes to create phylink and MDIO bus, but we forgot to call enetc4_link_deinit() to free the phylink and MDIO bus when the driver was unbound. so add missing enetc4_link_deinit() to enetc4_pf_netdev_destroy(). Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-7-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index fc41078c4f5d..48861c8b499a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -684,6 +684,7 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si) struct net_device *ndev = si->ndev; unregister_netdev(ndev); + enetc4_link_deinit(priv); enetc_free_msix(priv); free_netdev(ndev); } From 119049b66b883c7e7e575a0b69dc6e3d211662cc Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:50 +0800 Subject: [PATCH 36/53] net: enetc: remove the mm_lock from the ENETC v4 driver Currently, the ENETC v4 driver has not added the MAC merge layer support in the upstream, so the mm_lock is not initialized and used, so remove the mm_lock from the driver. Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF") Cc: stable@vger.kernel.org Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Link: https://patch.msgid.link/20250224111251.1061098-8-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 48861c8b499a..73ac8c6afb3a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -672,7 +672,6 @@ err_link_init: err_alloc_msix: err_config_si: err_clk_get: - mutex_destroy(&priv->mm_lock); free_netdev(ndev); return err; From 249df695c3ffe8c8d36d46c2580ce72410976f96 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Mon, 24 Feb 2025 19:12:51 +0800 Subject: [PATCH 37/53] net: enetc: fix the off-by-one issue in enetc_map_tx_tso_buffs() There is an off-by-one issue for the err_chained_bd path, it will free one more tx_swbd than expected. But there is no such issue for the err_map_data path. To fix this off-by-one issue and make the two error handling consistent, the increment of 'i' and 'count' remain in sync and enetc_unwind_tx_frame() is called for error handling. Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO") Cc: stable@vger.kernel.org Suggested-by: Vladimir Oltean Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20250224111251.1061098-9-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 9801c51b6a59..2106861463e4 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -859,8 +859,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd, tso.data, size, size == data_len); - if (err) + if (err) { + if (i == 0) + i = tx_ring->bd_count; + i--; + goto err_map_data; + } data_len -= size; count++; @@ -889,13 +894,7 @@ err_map_data: dev_err(tx_ring->dev, "DMA map error"); err_chained_bd: - do { - tx_swbd = &tx_ring->tx_swbd[i]; - enetc_free_tx_frame(tx_ring, tx_swbd); - if (i == 0) - i = tx_ring->bd_count; - i--; - } while (count--); + enetc_unwind_tx_frame(tx_ring, count, i); return 0; } From 8d52da23b6c68a0f6bad83959ebb61a2cf623c4e Mon Sep 17 00:00:00 2001 From: Wang Hai Date: Mon, 24 Feb 2025 17:00:47 +0800 Subject: [PATCH 38/53] tcp: Defer ts_recent changes until req is owned Recently a bug was discovered where the server had entered TCP_ESTABLISHED state, but the upper layers were not notified. The same 5-tuple packet may be processed by different CPUSs, so two CPUs may receive different ack packets at the same time when the state is TCP_NEW_SYN_RECV. In that case, req->ts_recent in tcp_check_req may be changed concurrently, which will probably cause the newsk's ts_recent to be incorrectly large. So that tcp_validate_incoming will fail. At this point, newsk will not be able to enter the TCP_ESTABLISHED. cpu1 cpu2 tcp_check_req tcp_check_req req->ts_recent = rcv_tsval = t1 req->ts_recent = rcv_tsval = t2 syn_recv_sock tcp_sk(child)->rx_opt.ts_recent = req->ts_recent = t2 // t1 < t2 tcp_child_process tcp_rcv_state_process tcp_validate_incoming tcp_paws_check if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) // t2 - t1 > paws_win, failed tcp_v4_do_rcv tcp_rcv_state_process // TCP_ESTABLISHED The cpu2's skb or a newly received skb will call tcp_v4_do_rcv to get the newsk into the TCP_ESTABLISHED state, but at this point it is no longer possible to notify the upper layer application. A notification mechanism could be added here, but the fix is more complex, so the current fix is used. In tcp_check_req, req->ts_recent is used to assign a value to tcp_sk(child)->rx_opt.ts_recent, so removing the change in req->ts_recent and changing tcp_sk(child)->rx_opt.ts_recent directly after owning the req fixes this bug. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Wang Hai Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_minisocks.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b089b08e9617..dfdb7a4608a8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -815,12 +815,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ - /* TODO: We probably should defer ts_recent change once - * we take ownership of @req. - */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); - if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting at tcp_rsk(req)->rcv_isn + 1. */ @@ -869,6 +863,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; + if (own_req && tmp_opt.saw_tstamp && + !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) + tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval; + if (own_req && rsk_drop_req(req)) { reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); From 01c9c123db76357d4373b2e97b760a856d6fe822 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 25 Feb 2025 13:10:23 -0800 Subject: [PATCH 39/53] net: Use rtnl_net_dev_lock() in register_netdevice_notifier_dev_net(). Breno Leitao reported the splat below. [0] Commit 65161fb544aa ("net: Fix dev_net(dev) race in unregister_netdevice_notifier_dev_net().") added the DEBUG_NET_WARN_ON_ONCE(), assuming that the netdev is not registered before register_netdevice_notifier_dev_net(). But the assumption was simply wrong. Let's use rtnl_net_dev_lock() in register_netdevice_notifier_dev_net(). [0]: WARNING: CPU: 25 PID: 849 at net/core/dev.c:2150 register_netdevice_notifier_dev_net (net/core/dev.c:2150) ? __warn (kernel/panic.c:242 kernel/panic.c:748) ? register_netdevice_notifier_dev_net (net/core/dev.c:2150) ? register_netdevice_notifier_dev_net (net/core/dev.c:2150) ? report_bug (lib/bug.c:? lib/bug.c:219) ? handle_bug (arch/x86/kernel/traps.c:285) ? exc_invalid_op (arch/x86/kernel/traps.c:309) ? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621) ? register_netdevice_notifier_dev_net (net/core/dev.c:2150) ? register_netdevice_notifier_dev_net (./include/net/net_namespace.h:406 ./include/linux/netdevice.h:2663 net/core/dev.c:2144) mlx5e_mdev_notifier_event+0x9f/0xf0 mlx5_ib notifier_call_chain.llvm.12241336988804114627 (kernel/notifier.c:85) blocking_notifier_call_chain (kernel/notifier.c:380) mlx5_core_uplink_netdev_event_replay (drivers/net/ethernet/mellanox/mlx5/core/main.c:352) mlx5_ib_roce_init.llvm.12447516292400117075+0x1c6/0x550 mlx5_ib mlx5r_probe+0x375/0x6a0 mlx5_ib ? kernfs_put (./include/linux/instrumented.h:96 ./include/linux/atomic/atomic-arch-fallback.h:2278 ./include/linux/atomic/atomic-instrumented.h:1384 fs/kernfs/dir.c:557) ? auxiliary_match_id (drivers/base/auxiliary.c:174) ? mlx5r_mp_remove+0x160/0x160 mlx5_ib really_probe (drivers/base/dd.c:? drivers/base/dd.c:658) driver_probe_device (drivers/base/dd.c:830) __driver_attach (drivers/base/dd.c:1217) bus_for_each_dev (drivers/base/bus.c:369) ? driver_attach (drivers/base/dd.c:1157) bus_add_driver (drivers/base/bus.c:679) driver_register (drivers/base/driver.c:249) Fixes: 7fb1073300a2 ("net: Hold rtnl_net_lock() in (un)?register_netdevice_notifier_dev_net().") Reported-by: Breno Leitao Closes: https://lore.kernel.org/netdev/20250224-noisy-cordial-roadrunner-fad40c@leitao/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Tested-by: Breno Leitao Link: https://patch.msgid.link/20250225211023.96448-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index 1b252e9459fd..70c01bd1799e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2141,21 +2141,15 @@ int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - /* rtnl_net_lock() assumes dev is not yet published by - * register_netdevice(). - */ - DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list)); - - rtnl_net_lock(net); - err = __register_netdevice_notifier_net(net, nb, false); + rtnl_net_dev_lock(dev); + err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); return err; } From de70981f295e7eab86325db3bf349fa676f16c42 Mon Sep 17 00:00:00 2001 From: Harshitha Ramamurthy Date: Wed, 26 Feb 2025 00:35:26 +0000 Subject: [PATCH 40/53] gve: unlink old napi when stopping a queue using queue API When a queue is stopped using the ndo queue API, before destroying its page pool, the associated NAPI instance needs to be unlinked to avoid warnings. Handle this by calling page_pool_disable_direct_recycling() when stopping a queue. Cc: stable@vger.kernel.org Fixes: ebdfae0d377b ("gve: adopt page pool for DQ RDA mode") Reviewed-by: Praveen Kaligineedi Signed-off-by: Harshitha Ramamurthy Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20250226003526.1546854-1-hramamurthy@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8ac0047f1ada..f0674a443567 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -109,10 +109,12 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx) void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + struct gve_rx_ring *rx = &priv->rx[idx]; if (!gve_rx_was_added_to_block(priv, idx)) return; + page_pool_disable_direct_recycling(rx->dqo.page_pool); gve_remove_napi(priv, ntfy_idx); gve_rx_remove_from_block(priv, idx); gve_rx_reset_ring_dqo(priv, idx); From 49806fe6e61b045b5be8610e08b5a3083c109aa0 Mon Sep 17 00:00:00 2001 From: Mohammad Heib Date: Tue, 25 Feb 2025 13:28:52 +0200 Subject: [PATCH 41/53] net: Clear old fragment checksum value in napi_reuse_skb In certain cases, napi_get_frags() returns an skb that points to an old received fragment, This skb may have its skb->ip_summed, csum, and other fields set from previous fragment handling. Some network drivers set skb->ip_summed to either CHECKSUM_COMPLETE or CHECKSUM_UNNECESSARY when getting skb from napi_get_frags(), while others only set skb->ip_summed when RX checksum offload is enabled on the device, and do not set any value for skb->ip_summed when hardware checksum offload is disabled, assuming that the skb->ip_summed initiated to zero by napi_reuse_skb, ionic driver for example will ignore/unset any value for the ip_summed filed if HW checksum offload is disabled, and if we have a situation where the user disables the checksum offload during a traffic that could lead to the following errors shown in the kernel logs: dump_stack_lvl+0x34/0x48 __skb_gro_checksum_complete+0x7e/0x90 tcp6_gro_receive+0xc6/0x190 ipv6_gro_receive+0x1ec/0x430 dev_gro_receive+0x188/0x360 ? ionic_rx_clean+0x25a/0x460 [ionic] napi_gro_frags+0x13c/0x300 ? __pfx_ionic_rx_service+0x10/0x10 [ionic] ionic_rx_service+0x67/0x80 [ionic] ionic_cq_service+0x58/0x90 [ionic] ionic_txrx_napi+0x64/0x1b0 [ionic] __napi_poll+0x27/0x170 net_rx_action+0x29c/0x370 handle_softirqs+0xce/0x270 __irq_exit_rcu+0xa3/0xc0 common_interrupt+0x80/0xa0 This inconsistency sometimes leads to checksum validation issues in the upper layers of the network stack. To resolve this, this patch clears the skb->ip_summed value for each reused skb in by napi_reuse_skb(), ensuring that the caller is responsible for setting the correct checksum status. This eliminates potential checksum validation issues caused by improper handling of skb->ip_summed. Fixes: 76620aafd66f ("gro: New frags interface to avoid copying shinfo") Signed-off-by: Mohammad Heib Reviewed-by: Shannon Nelson Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250225112852.2507709-1-mheib@redhat.com Signed-off-by: Jakub Kicinski --- net/core/gro.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/gro.c b/net/core/gro.c index 78b320b63174..0ad549b07e03 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -653,6 +653,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; + skb->ip_summed = CHECKSUM_NONE; skb_shinfo(skb)->gso_type = 0; skb_shinfo(skb)->gso_size = 0; if (unlikely(skb->slow_gro)) { From 77e45145e3039a0fb212556ab3f8c87f54771757 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 23 Feb 2025 23:17:08 +0100 Subject: [PATCH 42/53] net: Handle napi_schedule() calls from non-interrupt napi_schedule() is expected to be called either: * From an interrupt, where raised softirqs are handled on IRQ exit * From a softirq disabled section, where raised softirqs are handled on the next call to local_bh_enable(). * From a softirq handler, where raised softirqs are handled on the next round in do_softirq(), or further deferred to a dedicated kthread. Other bare tasks context may end up ignoring the raised NET_RX vector until the next random softirq handling opportunity, which may not happen before a while if the CPU goes idle afterwards with the tick stopped. Such "misuses" have been detected on several places thanks to messages of the kind: "NOHZ tick-stop error: local softirq work is pending, handler #08!!!" For example: __raise_softirq_irqoff __napi_schedule rtl8152_runtime_resume.isra.0 rtl8152_resume usb_resume_interface.isra.0 usb_resume_both __rpm_callback rpm_callback rpm_resume __pm_runtime_resume usb_autoresume_device usb_remote_wakeup hub_event process_one_work worker_thread kthread ret_from_fork ret_from_fork_asm And also: * drivers/net/usb/r8152.c::rtl_work_func_t * drivers/net/netdevsim/netdev.c::nsim_start_xmit There is a long history of issues of this kind: 019edd01d174 ("ath10k: sdio: Add missing BH locking around napi_schdule()") 330068589389 ("idpf: disable local BH when scheduling napi for marker packets") e3d5d70cb483 ("net: lan78xx: fix "softirq work is pending" error") e55c27ed9ccf ("mt76: mt7615: add missing bh-disable around rx napi schedule") c0182aa98570 ("mt76: mt7915: add missing bh-disable around tx napi enable/schedule") 970be1dff26d ("mt76: disable BH around napi_schedule() calls") 019edd01d174 ("ath10k: sdio: Add missing BH locking around napi_schdule()") 30bfec4fec59 ("can: rx-offload: can_rx_offload_threaded_irq_finish(): add new function to be called from threaded interrupt") e63052a5dd3c ("mlx5e: add add missing BH locking around napi_schdule()") 83a0c6e58901 ("i40e: Invoke softirqs after napi_reschedule") bd4ce941c8d5 ("mlx4: Invoke softirqs after napi_reschedule") 8cf699ec849f ("mlx4: do not call napi_schedule() without care") ec13ee80145c ("virtio_net: invoke softirqs after __napi_schedule") This shows that relying on the caller to arrange a proper context for the softirqs to be handled while calling napi_schedule() is very fragile and error prone. Also fixing them can also prove challenging if the caller may be called from different kinds of contexts. Therefore fix this from napi_schedule() itself with waking up ksoftirqd when softirqs are raised from task contexts. Reported-by: Paul Menzel Reported-by: Jakub Kicinski Reported-by: Francois Romieu Closes: https://lore.kernel.org/lkml/354a2690-9bbf-4ccb-8769-fa94707a9340@molgen.mpg.de/ Cc: Breno Leitao Signed-off-by: Frederic Weisbecker Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250223221708.27130-1-frederic@kernel.org Signed-off-by: Jakub Kicinski --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 70c01bd1799e..30da277c5a6f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4757,7 +4757,7 @@ use_local_napi: * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) - __raise_softirq_irqoff(NET_RX_SOFTIRQ); + raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS From bc23d4e30866011700787bab8563de45d5bf8431 Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Tue, 25 Feb 2025 10:14:57 +0800 Subject: [PATCH 43/53] af_unix: Fix memory leak in unix_dgram_sendmsg() After running the 'sendmsg02' program of Linux Test Project (LTP), kmemleak reports the following memory leak: # cat /sys/kernel/debug/kmemleak unreferenced object 0xffff888243866800 (size 2048): comm "sendmsg02", pid 67, jiffies 4294903166 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 5e 00 00 00 00 00 00 00 ........^....... 01 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace (crc 7e96a3f2): kmemleak_alloc+0x56/0x90 kmem_cache_alloc_noprof+0x209/0x450 sk_prot_alloc.constprop.0+0x60/0x160 sk_alloc+0x32/0xc0 unix_create1+0x67/0x2b0 unix_create+0x47/0xa0 __sock_create+0x12e/0x200 __sys_socket+0x6d/0x100 __x64_sys_socket+0x1b/0x30 x64_sys_call+0x7e1/0x2140 do_syscall_64+0x54/0x110 entry_SYSCALL_64_after_hwframe+0x76/0x7e Commit 689c398885cc ("af_unix: Defer sock_put() to clean up path in unix_dgram_sendmsg().") defers sock_put() in the error handling path. However, it fails to account for the condition 'msg->msg_namelen != 0', resulting in a memory leak when the code jumps to the 'lookup' label. Fix issue by calling sock_put() if 'msg->msg_namelen != 0' is met. Fixes: 689c398885cc ("af_unix: Defer sock_put() to clean up path in unix_dgram_sendmsg().") Signed-off-by: Adrian Huang Acked-by: Joe Damato Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250225021457.1824-1-ahuang12@lenovo.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 34945de1fb1f..f0e613d97664 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2102,6 +2102,7 @@ restart_locked: goto out_sock_put; } + sock_put(other); goto lookup; } From 2d253726ff7106b39a44483b6864398bba8a2f74 Mon Sep 17 00:00:00 2001 From: Harshal Chaudhari Date: Mon, 24 Feb 2025 20:20:58 -0800 Subject: [PATCH 44/53] net: mvpp2: cls: Fixed Non IP flow, with vlan tag flow defination. Non IP flow, with vlan tag not working as expected while running below command for vlan-priority. fixed that. ethtool -N eth1 flow-type ether vlan 0x8000 vlan-mask 0x1fff action 0 loc 0 Fixes: 1274daede3ef ("net: mvpp2: cls: Add steering based on vlan Id and priority.") Signed-off-by: Harshal Chaudhari Reviewed-by: Maxime Chevallier Link: https://patch.msgid.link/20250225042058.2643838-1-hchaudhari@marvell.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 1641791a2d5b..8ed83fb98862 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = { MVPP2_PRS_RI_VLAN_MASK), /* Non IP flow, with vlan tag */ MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG, - MVPP22_CLS_HEK_OPT_VLAN, + MVPP22_CLS_HEK_TAGGED, 0, 0), }; From 7f3528f7d2f98b70e19a6bb7b130fc82c079ac54 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Tue, 25 Feb 2025 09:26:06 +0200 Subject: [PATCH 45/53] net/mlx5: Fix vport QoS cleanup on error When enabling vport QoS fails, the scheduling node was never freed, causing a leak. Add the missing free and reset the vport scheduling node pointer to NULL. Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions") Signed-off-by: Carolina Jubran Reviewed-by: Cosmin Ratiu Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20250225072608.526866-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 8b7c843446e1..07a28073a49e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -591,8 +591,11 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t sched_node->vport = vport; vport->qos.sched_node = sched_node; err = esw_qos_vport_enable(vport, parent, extack); - if (err) + if (err) { + __esw_qos_free_node(sched_node); esw_qos_put(esw); + vport->qos.sched_node = NULL; + } return err; } From 47bcd9bf3d231bfd4698d7d3013597490fd5e2d6 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Tue, 25 Feb 2025 09:26:07 +0200 Subject: [PATCH 46/53] net/mlx5: Restore missing trace event when enabling vport QoS Restore the `trace_mlx5_esw_vport_qos_create` event when creating the vport scheduling element. This trace event was lost during refactoring. Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions") Signed-off-by: Carolina Jubran Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20250225072608.526866-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 07a28073a49e..823c1ba456cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -564,6 +564,9 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_ return err; esw_qos_normalize_min_rate(parent->esw, parent, extack); + trace_mlx5_esw_vport_qos_create(vport->dev, vport, + vport->qos.sched_node->max_rate, + vport->qos.sched_node->bw_share); return 0; } From 2f5a6014eb168a97b24153adccfa663d3b282767 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 25 Feb 2025 09:26:08 +0200 Subject: [PATCH 47/53] net/mlx5: IRQ, Fix null string in debug print irq_pool_alloc() debug print can print a null string. Fix it by providing a default string to print. Fixes: 71e084e26414 ("net/mlx5: Allocating a pool of MSI-X vectors for SFs") Signed-off-by: Shay Drory Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202501141055.SwfIphN0-lkp@intel.com/ Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Reviewed-by: Kalesh AP Link: https://patch.msgid.link/20250225072608.526866-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 7db9cab9bedf..d9362eabc6a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -572,7 +572,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ; pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ; mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d", - name, size, start); + name ? name : "mlx5_pcif_pool", size, start); return pool; } From 1cf9631d836b289bd5490776551961c883ae8a4f Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Mon, 24 Feb 2025 20:29:17 +0300 Subject: [PATCH 48/53] usbnet: gl620a: fix endpoint checking in genelink_bind() Syzbot reports [1] a warning in usb_submit_urb() triggered by inconsistencies between expected and actually present endpoints in gl620a driver. Since genelink_bind() does not properly verify whether specified eps are in fact provided by the device, in this case, an artificially manufactured one, one may get a mismatch. Fix the issue by resorting to a usbnet utility function usbnet_get_endpoints(), usually reserved for this very problem. Check for endpoints and return early before proceeding further if any are missing. [1] Syzbot report: usb 5-1: Manufacturer: syz usb 5-1: SerialNumber: syz usb 5-1: config 0 descriptor?? gl620a 5-1:0.23 usb0: register 'gl620a' at usb-dummy_hcd.0-1, ... ------------[ cut here ]------------ usb 5-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 2 PID: 1841 at drivers/usb/core/urb.c:503 usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503 Modules linked in: CPU: 2 UID: 0 PID: 1841 Comm: kworker/2:2 Not tainted 6.12.0-syzkaller-07834-g06afb0f36106 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Workqueue: mld mld_ifc_work RIP: 0010:usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503 ... Call Trace: usbnet_start_xmit+0x6be/0x2780 drivers/net/usb/usbnet.c:1467 __netdev_start_xmit include/linux/netdevice.h:5002 [inline] netdev_start_xmit include/linux/netdevice.h:5011 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x9a/0x7b0 net/core/dev.c:3606 sch_direct_xmit+0x1ae/0xc30 net/sched/sch_generic.c:343 __dev_xmit_skb net/core/dev.c:3827 [inline] __dev_queue_xmit+0x13d4/0x43e0 net/core/dev.c:4400 dev_queue_xmit include/linux/netdevice.h:3168 [inline] neigh_resolve_output net/core/neighbour.c:1514 [inline] neigh_resolve_output+0x5bc/0x950 net/core/neighbour.c:1494 neigh_output include/net/neighbour.h:539 [inline] ip6_finish_output2+0xb1b/0x2070 net/ipv6/ip6_output.c:141 __ip6_finish_output net/ipv6/ip6_output.c:215 [inline] ip6_finish_output+0x3f9/0x1360 net/ipv6/ip6_output.c:226 NF_HOOK_COND include/linux/netfilter.h:303 [inline] ip6_output+0x1f8/0x540 net/ipv6/ip6_output.c:247 dst_output include/net/dst.h:450 [inline] NF_HOOK include/linux/netfilter.h:314 [inline] NF_HOOK include/linux/netfilter.h:308 [inline] mld_sendpack+0x9f0/0x11d0 net/ipv6/mcast.c:1819 mld_send_cr net/ipv6/mcast.c:2120 [inline] mld_ifc_work+0x740/0xca0 net/ipv6/mcast.c:2651 process_one_work+0x9c5/0x1ba0 kernel/workqueue.c:3229 process_scheduled_works kernel/workqueue.c:3310 [inline] worker_thread+0x6c8/0xf00 kernel/workqueue.c:3391 kthread+0x2c1/0x3a0 kernel/kthread.c:389 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 Reported-by: syzbot+d693c07c6f647e0388d3@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d693c07c6f647e0388d3 Fixes: 47ee3051c856 ("[PATCH] USB: usbnet (5/9) module for genesys gl620a cables") Cc: stable@vger.kernel.org Signed-off-by: Nikita Zhandarovich Link: https://patch.msgid.link/20250224172919.1220522-1-n.zhandarovich@fintech.ru Signed-off-by: Paolo Abeni --- drivers/net/usb/gl620a.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c index 46af78caf457..0bfa37c14059 100644 --- a/drivers/net/usb/gl620a.c +++ b/drivers/net/usb/gl620a.c @@ -179,9 +179,7 @@ static int genelink_bind(struct usbnet *dev, struct usb_interface *intf) { dev->hard_mtu = GL_RCV_BUF_SIZE; dev->net->hard_header_len += 4; - dev->in = usb_rcvbulkpipe(dev->udev, dev->driver_info->in); - dev->out = usb_sndbulkpipe(dev->udev, dev->driver_info->out); - return 0; + return usbnet_get_endpoints(dev, intf); } static const struct driver_info genelink_info = { From c64a0727f9b1cbc63a5538c8c0014e9a175ad864 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Tue, 25 Feb 2025 18:51:38 +0100 Subject: [PATCH 49/53] net: ipv6: fix dst ref loop on input in seg6 lwt Prevent a dst ref loop on input in seg6_iptunnel. Fixes: af4a2209b134 ("ipv6: sr: use dst_cache in seg6_input") Cc: David Lebrun Cc: Ido Schimmel Reviewed-by: Ido Schimmel Signed-off-by: Justin Iurman Signed-off-by: Paolo Abeni --- net/ipv6/seg6_iptunnel.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 33833b2064c0..51583461ae29 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -472,10 +472,18 @@ static int seg6_input_core(struct net *net, struct sock *sk, { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; + struct lwtunnel_state *lwtst; struct seg6_lwt *slwt; int err; - slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); + /* We cannot dereference "orig_dst" once ip6_route_input() or + * skb_dst_drop() is called. However, in order to detect a dst loop, we + * need the address of its lwtstate. So, save the address of lwtstate + * now and use it later as a comparison. + */ + lwtst = orig_dst->lwtstate; + + slwt = seg6_lwt_lwtunnel(lwtst); local_bh_disable(); dst = dst_cache_get(&slwt->cache); @@ -490,7 +498,9 @@ static int seg6_input_core(struct net *net, struct sock *sk, if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); - if (!dst->error) { + + /* cache only if we don't create a dst reference loop */ + if (!dst->error && lwtst != dst->lwtstate) { local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); From 13e55fbaec176119cff68a7e1693b251c8883c5f Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Tue, 25 Feb 2025 18:51:39 +0100 Subject: [PATCH 50/53] net: ipv6: fix dst ref loop on input in rpl lwt Prevent a dst ref loop on input in rpl_iptunnel. Fixes: a7a29f9c361f ("net: ipv6: add rpl sr tunnel") Cc: Alexander Aring Cc: Ido Schimmel Reviewed-by: Ido Schimmel Signed-off-by: Justin Iurman Signed-off-by: Paolo Abeni --- net/ipv6/rpl_iptunnel.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 0ac4283acdf2..7c05ac846646 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -262,10 +262,18 @@ static int rpl_input(struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; + struct lwtunnel_state *lwtst; struct rpl_lwt *rlwt; int err; - rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); + /* We cannot dereference "orig_dst" once ip6_route_input() or + * skb_dst_drop() is called. However, in order to detect a dst loop, we + * need the address of its lwtstate. So, save the address of lwtstate + * now and use it later as a comparison. + */ + lwtst = orig_dst->lwtstate; + + rlwt = rpl_lwt_lwtunnel(lwtst); local_bh_disable(); dst = dst_cache_get(&rlwt->cache); @@ -280,7 +288,9 @@ static int rpl_input(struct sk_buff *skb) if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); - if (!dst->error) { + + /* cache only if we don't create a dst reference loop */ + if (!dst->error && lwtst != dst->lwtstate) { local_bh_disable(); dst_cache_set_ip6(&rlwt->cache, dst, &ipv6_hdr(skb)->saddr); From 1cbddbddee68d17feb6467fc556c144777af91ef Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Wed, 26 Feb 2025 18:19:57 +0000 Subject: [PATCH 51/53] selftests: drv-net: Check if combined-count exists Some drivers, like tg3, do not set combined-count: $ ethtool -l enp4s0f1 Channel parameters for enp4s0f1: Pre-set maximums: RX: 4 TX: 4 Other: n/a Combined: n/a Current hardware settings: RX: 4 TX: 1 Other: n/a Combined: n/a In the case where combined-count is not set, the ethtool netlink code in the kernel elides the value and the code in the test: netnl.channels_get(...) With a tg3 device, the returned dictionary looks like: {'header': {'dev-index': 3, 'dev-name': 'enp4s0f1'}, 'rx-max': 4, 'rx-count': 4, 'tx-max': 4, 'tx-count': 1} Note that the key 'combined-count' is missing. As a result of this missing key the test raises an exception: # Exception| if channels['combined-count'] == 0: # Exception| ~~~~~~~~^^^^^^^^^^^^^^^^^^ # Exception| KeyError: 'combined-count' Change the test to check if 'combined-count' is a key in the dictionary first and if not assume that this means the driver has separate RX and TX queues. With this change, the test now passes successfully on tg3 and mlx5 (which does have a 'combined-count'). Fixes: 1cf270424218 ("net: selftest: add test for netdev netlink queue-get API") Signed-off-by: Joe Damato Reviewed-by: David Wei Link: https://patch.msgid.link/20250226181957.212189-1-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/drivers/net/queues.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 38303da957ee..8a518905a9f9 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -45,10 +45,9 @@ def addremove_queues(cfg, nl) -> None: netnl = EthtoolFamily() channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}}) - if channels['combined-count'] == 0: - rx_type = 'rx' - else: - rx_type = 'combined' + rx_type = 'rx' + if channels.get('combined-count', 0) > 0: + rx_type = 'combined' expected = curr_queues - 1 cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10) From 674fcb4f4a7e3e277417a01788cc6daae47c3804 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Feb 2025 22:12:52 +0000 Subject: [PATCH 52/53] idpf: fix checksums set in idpf_rx_rsc() idpf_rx_rsc() uses skb_transport_offset(skb) while the transport header is not set yet. This triggers the following warning for CONFIG_DEBUG_NET=y builds. DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)) [ 69.261620] WARNING: CPU: 7 PID: 0 at ./include/linux/skbuff.h:3020 idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261629] Modules linked in: vfat fat dummy bridge intel_uncore_frequency_tpmi intel_uncore_frequency_common intel_vsec_tpmi idpf intel_vsec cdc_ncm cdc_eem cdc_ether usbnet mii xhci_pci xhci_hcd ehci_pci ehci_hcd libeth [ 69.261644] CPU: 7 UID: 0 PID: 0 Comm: swapper/7 Tainted: G S W 6.14.0-smp-DEV #1697 [ 69.261648] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN [ 69.261650] RIP: 0010:idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261677] ? __warn (kernel/panic.c:242 kernel/panic.c:748) [ 69.261682] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261687] ? report_bug (lib/bug.c:?) [ 69.261690] ? handle_bug (arch/x86/kernel/traps.c:285) [ 69.261694] ? exc_invalid_op (arch/x86/kernel/traps.c:309) [ 69.261697] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:621) [ 69.261700] ? __pfx_idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:4011) idpf [ 69.261704] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf [ 69.261708] ? idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:3072) idpf [ 69.261712] __napi_poll (net/core/dev.c:7194) [ 69.261716] net_rx_action (net/core/dev.c:7265) [ 69.261718] ? __qdisc_run (net/sched/sch_generic.c:293) [ 69.261721] ? sched_clock (arch/x86/include/asm/preempt.h:84 arch/x86/kernel/tsc.c:288) [ 69.261726] handle_softirqs (kernel/softirq.c:561) Fixes: 3a8845af66edb ("idpf: add RX splitq napi poll support") Signed-off-by: Eric Dumazet Cc: Alan Brady Cc: Joshua Hay Cc: Willem de Bruijn Acked-by: Przemek Kitszel Link: https://patch.msgid.link/20250226221253.1927782-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 9be6a6b59c4e..977741c41498 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3013,7 +3013,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_size = rsc_seg_len; skb_reset_network_header(skb); - len = skb->len - skb_transport_offset(skb); if (ipv4) { struct iphdr *ipv4h = ip_hdr(skb); @@ -3022,6 +3021,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, /* Reset and set transport header offset in skb */ skb_set_transport_header(skb, sizeof(struct iphdr)); + len = skb->len - skb_transport_offset(skb); /* Compute the TCP pseudo header checksum*/ tcp_hdr(skb)->check = @@ -3031,6 +3031,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + len = skb->len - skb_transport_offset(skb); tcp_hdr(skb)->check = ~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0); } From 54e1b4becf5e220be03db4e1be773c1310e8cbbd Mon Sep 17 00:00:00 2001 From: Meghana Malladi Date: Thu, 27 Feb 2025 14:54:41 +0530 Subject: [PATCH 53/53] net: ti: icss-iep: Reject perout generation request IEP driver supports both perout and pps signal generation but perout feature is faulty with half-cooked support due to some missing configuration. Remove perout support from the driver and reject perout requests with "not supported" error code. Fixes: c1e0230eeaab2 ("net: ti: icss-iep: Add IEP driver") Signed-off-by: Meghana Malladi Reviewed-by: Vadim Fedorenko Link: https://patch.msgid.link/20250227092441.1848419-1-m-malladi@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icss_iep.c | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 768578c0d958..d59c1744840a 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -474,26 +474,7 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep, static int icss_iep_perout_enable(struct icss_iep *iep, struct ptp_perout_request *req, int on) { - int ret = 0; - - mutex_lock(&iep->ptp_clk_mutex); - - if (iep->pps_enabled) { - ret = -EBUSY; - goto exit; - } - - if (iep->perout_enabled == !!on) - goto exit; - - ret = icss_iep_perout_enable_hw(iep, req, on); - if (!ret) - iep->perout_enabled = !!on; - -exit: - mutex_unlock(&iep->ptp_clk_mutex); - - return ret; + return -EOPNOTSUPP; } static void icss_iep_cap_cmp_work(struct work_struct *work)