From e38910c0072b541a91954682c8b074a93e57c09b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 7 Jun 2023 09:27:08 +0200 Subject: can: isotp: isotp_sendmsg(): fix return error fix on TX path With commit d674a8f123b4 ("can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX path") the missing correct return value in the case of a protocol error was introduced. But the way the error value has been read and sent to the user space does not follow the common scheme to clear the error after reading which is provided by the sock_error() function. This leads to an error report at the following write() attempt although everything should be working. Fixes: d674a8f123b4 ("can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX path") Reported-by: Carsten Schmidt Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230607072708.38809-1-socketcan@hartkopp.net Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/isotp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index 84f9aba02901..ca9d728d6d72 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1112,8 +1112,9 @@ wait_free_buffer: if (err) goto err_event_drop; - if (sk->sk_err) - return -sk->sk_err; + err = sock_error(sk); + if (err) + return err; } return size; -- cgit v1.2.3-58-ga151 From 9c50e2b150c8ee0eee5f8154e2ad168cdd748877 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 7 Jun 2023 14:32:29 -0700 Subject: igc: Fix race condition in PTP tx code Currently, the igc driver supports timestamping only one tx packet at a time. During the transmission flow, the skb that requires hardware timestamping is saved in adapter->ptp_tx_skb. Once hardware has the timestamp, an interrupt is delivered, and adapter->ptp_tx_work is scheduled. In igc_ptp_tx_work(), we read the timestamp register, update adapter->ptp_tx_skb, and notify the network stack. While the thread executing the transmission flow (the user process running in kernel mode) and the thread executing ptp_tx_work don't access adapter->ptp_tx_skb concurrently, there are two other places where adapter->ptp_tx_skb is accessed: igc_ptp_tx_hang() and igc_ptp_suspend(). igc_ptp_tx_hang() is executed by the adapter->watchdog_task worker thread which runs periodically so it is possible we have two threads accessing ptp_tx_skb at the same time. Consider the following scenario: right after __IGC_PTP_TX_IN_PROGRESS is set in igc_xmit_frame_ring(), igc_ptp_tx_hang() is executed. Since adapter->ptp_tx_start hasn't been written yet, this is considered a timeout and adapter->ptp_tx_skb is cleaned up. This patch fixes the issue described above by adding the ptp_tx_lock to protect access to ptp_tx_skb and ptp_tx_start fields from igc_adapter. Since igc_xmit_frame_ring() called in atomic context by the networking stack, ptp_tx_lock is defined as a spinlock, and the irq safe variants of lock/unlock are used. With the introduction of the ptp_tx_lock, the __IGC_PTP_TX_IN_PROGRESS flag doesn't provide much of a use anymore so this patch gets rid of it. Fixes: 2c344ae24501 ("igc: Add support for TX timestamping") Signed-off-by: Andre Guedes Signed-off-by: Vinicius Costa Gomes Reviewed-by: Kurt Kanzenbach Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc.h | 5 ++- drivers/net/ethernet/intel/igc/igc_main.c | 9 +++-- drivers/net/ethernet/intel/igc/igc_ptp.c | 57 +++++++++++++++++-------------- 3 files changed, 41 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 34aebf00a512..7da0657ea48f 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -229,6 +229,10 @@ struct igc_adapter { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_caps; struct work_struct ptp_tx_work; + /* Access to ptp_tx_skb and ptp_tx_start are protected by the + * ptp_tx_lock. + */ + spinlock_t ptp_tx_lock; struct sk_buff *ptp_tx_skb; struct hwtstamp_config tstamp_config; unsigned long ptp_tx_start; @@ -401,7 +405,6 @@ enum igc_state_t { __IGC_TESTING, __IGC_RESETTING, __IGC_DOWN, - __IGC_PTP_TX_IN_PROGRESS, }; enum igc_tx_flags { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index fa764190f270..9fcb263bd3a7 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1590,9 +1590,10 @@ done: * the other timer registers before skipping the * timestamping request. */ - if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && - !test_and_set_bit_lock(__IGC_PTP_TX_IN_PROGRESS, - &adapter->state)) { + unsigned long flags; + + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); + if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && !adapter->ptp_tx_skb) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGC_TX_FLAGS_TSTAMP; @@ -1601,6 +1602,8 @@ done: } else { adapter->tx_hwtstamp_skipped++; } + + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } if (skb_vlan_tag_present(skb)) { diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 4e10ced736db..56128e55f5c0 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -603,6 +603,7 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, return 0; } +/* Requires adapter->ptp_tx_lock held by caller. */ static void igc_ptp_tx_timeout(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -610,7 +611,6 @@ static void igc_ptp_tx_timeout(struct igc_adapter *adapter) dev_kfree_skb_any(adapter->ptp_tx_skb); adapter->ptp_tx_skb = NULL; adapter->tx_hwtstamp_timeouts++; - clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); /* Clear the tx valid bit in TSYNCTXCTL register to enable interrupt. */ rd32(IGC_TXSTMPH); netdev_warn(adapter->netdev, "Tx timestamp timeout\n"); @@ -618,20 +618,20 @@ static void igc_ptp_tx_timeout(struct igc_adapter *adapter) void igc_ptp_tx_hang(struct igc_adapter *adapter) { - bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + - IGC_PTP_TX_TIMEOUT); + unsigned long flags; - if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state)) - return; + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - /* If we haven't received a timestamp within the timeout, it is - * reasonable to assume that it will never occur, so we can unlock the - * timestamp bit when this occurs. - */ - if (timeout) { - cancel_work_sync(&adapter->ptp_tx_work); - igc_ptp_tx_timeout(adapter); - } + if (!adapter->ptp_tx_skb) + goto unlock; + + if (time_is_after_jiffies(adapter->ptp_tx_start + IGC_PTP_TX_TIMEOUT)) + goto unlock; + + igc_ptp_tx_timeout(adapter); + +unlock: + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } /** @@ -641,6 +641,8 @@ void igc_ptp_tx_hang(struct igc_adapter *adapter) * If we were asked to do hardware stamping and such a time stamp is * available, then it must have been for this skb here because we only * allow only one such packet into the queue. + * + * Context: Expects adapter->ptp_tx_lock to be held by caller. */ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) { @@ -676,13 +678,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) shhwtstamps.hwtstamp = ktime_add_ns(shhwtstamps.hwtstamp, adjust); - /* Clear the lock early before calling skb_tstamp_tx so that - * applications are not woken up before the lock bit is clear. We use - * a copy of the skb pointer to ensure other threads can't change it - * while we're notifying the stack. - */ adapter->ptp_tx_skb = NULL; - clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); /* Notify the stack and free the skb after we've unlocked */ skb_tstamp_tx(skb, &shhwtstamps); @@ -693,24 +689,33 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) * igc_ptp_tx_work * @work: pointer to work struct * - * This work function polls the TSYNCTXCTL valid bit to determine when a - * timestamp has been taken for the current stored skb. + * This work function checks the TSYNCTXCTL valid bit to determine when + * a timestamp has been taken for the current stored skb. */ static void igc_ptp_tx_work(struct work_struct *work) { struct igc_adapter *adapter = container_of(work, struct igc_adapter, ptp_tx_work); struct igc_hw *hw = &adapter->hw; + unsigned long flags; u32 tsynctxctl; - if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state)) - return; + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); + + if (!adapter->ptp_tx_skb) + goto unlock; tsynctxctl = rd32(IGC_TSYNCTXCTL); - if (WARN_ON_ONCE(!(tsynctxctl & IGC_TSYNCTXCTL_TXTT_0))) - return; + tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0; + if (!tsynctxctl) { + WARN_ONCE(1, "Received a TSTAMP interrupt but no TSTAMP is ready.\n"); + goto unlock; + } igc_ptp_tx_hwtstamp(adapter); + +unlock: + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); } /** @@ -959,6 +964,7 @@ void igc_ptp_init(struct igc_adapter *adapter) return; } + spin_lock_init(&adapter->ptp_tx_lock); spin_lock_init(&adapter->tmreg_lock); INIT_WORK(&adapter->ptp_tx_work, igc_ptp_tx_work); @@ -1023,7 +1029,6 @@ void igc_ptp_suspend(struct igc_adapter *adapter) cancel_work_sync(&adapter->ptp_tx_work); dev_kfree_skb_any(adapter->ptp_tx_skb); adapter->ptp_tx_skb = NULL; - clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); -- cgit v1.2.3-58-ga151 From ce58c7cc8b9910f2bc1d038d7ba60c3f011b2cb2 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 7 Jun 2023 14:32:30 -0700 Subject: igc: Check if hardware TX timestamping is enabled earlier Before requesting a packet transmission to be hardware timestamped, check if the user has TX timestamping enabled. Fixes an issue that if a packet was internally forwarded to the NIC, and it had the SKBTX_HW_TSTAMP flag set, the driver would mark that timestamp as skipped. In reality, that timestamp was "not for us", as TX timestamp could never be enabled in the NIC. Checking if the TX timestamping is enabled earlier has a secondary effect that when TX timestamping is disabled, there's no need to check for timestamp timeouts. We should only take care to free any pending timestamp when TX timestamping is disabled, as that skb would never be released otherwise. Fixes: 2c344ae24501 ("igc: Add support for TX timestamping") Suggested-by: Vladimir Oltean Signed-off-by: Vinicius Costa Gomes Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc.h | 1 + drivers/net/ethernet/intel/igc/igc_main.c | 5 ++-- drivers/net/ethernet/intel/igc/igc_ptp.c | 42 ++++++++++++++++++++++++++++--- 3 files changed, 43 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 7da0657ea48f..66fb67c17e4f 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -581,6 +581,7 @@ enum igc_ring_flags_t { IGC_RING_FLAG_TX_CTX_IDX, IGC_RING_FLAG_TX_DETECT_HANG, IGC_RING_FLAG_AF_XDP_ZC, + IGC_RING_FLAG_TX_HWTSTAMP, }; #define ring_uses_large_buffer(ring) \ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9fcb263bd3a7..eb50bfd5b867 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1585,7 +1585,8 @@ done: } } - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) && + skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { /* FIXME: add support for retrieving timestamps from * the other timer registers before skipping the * timestamping request. @@ -1593,7 +1594,7 @@ done: unsigned long flags; spin_lock_irqsave(&adapter->ptp_tx_lock, flags); - if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && !adapter->ptp_tx_skb) { + if (!adapter->ptp_tx_skb) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGC_TX_FLAGS_TSTAMP; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 56128e55f5c0..42f622ceb64b 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -536,9 +536,36 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter) wr32(IGC_TSYNCRXCTL, val); } +static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) +{ + unsigned long flags; + + cancel_work_sync(&adapter->ptp_tx_work); + + spin_lock_irqsave(&adapter->ptp_tx_lock, flags); + + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + + spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); +} + static void igc_ptp_disable_tx_timestamp(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + int i; + + /* Clear the flags first to avoid new packets to be enqueued + * for TX timestamping. + */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *tx_ring = adapter->tx_ring[i]; + + clear_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags); + } + + /* Now we can clean the pending TX timestamp requests. */ + igc_ptp_clear_tx_tstamp(adapter); wr32(IGC_TSYNCTXCTL, 0); } @@ -546,12 +573,23 @@ static void igc_ptp_disable_tx_timestamp(struct igc_adapter *adapter) static void igc_ptp_enable_tx_timestamp(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + int i; wr32(IGC_TSYNCTXCTL, IGC_TSYNCTXCTL_ENABLED | IGC_TSYNCTXCTL_TXSYNSIG); /* Read TXSTMP registers to discard any timestamp previously stored. */ rd32(IGC_TXSTMPL); rd32(IGC_TXSTMPH); + + /* The hardware is ready to accept TX timestamp requests, + * notify the transmit path. + */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *tx_ring = adapter->tx_ring[i]; + + set_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags); + } + } /** @@ -1026,9 +1064,7 @@ void igc_ptp_suspend(struct igc_adapter *adapter) if (!(adapter->ptp_flags & IGC_PTP_ENABLED)) return; - cancel_work_sync(&adapter->ptp_tx_work); - dev_kfree_skb_any(adapter->ptp_tx_skb); - adapter->ptp_tx_skb = NULL; + igc_ptp_clear_tx_tstamp(adapter); if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); -- cgit v1.2.3-58-ga151 From afa141583d82725f682b2fa762cb36a07f58b3f3 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 7 Jun 2023 14:32:31 -0700 Subject: igc: Retrieve TX timestamp during interrupt handling When the interrupt is handled, the TXTT_0 bit in the TSYNCTXCTL register should already be set and the timestamp value already loaded in the appropriate register. This simplifies the handling, and reduces the latency for retrieving the TX timestamp, which increase the amount of TX timestamps that can be handled in a given time period. As the "work" function doesn't run in a workqueue anymore, rename it to something more sensible, a event handler. Using ntpperf[1] we can see the following performance improvements: Before: $ sudo ./ntpperf -i enp3s0 -m 10:22:22:22:22:21 -d 192.168.1.3 -s 172.18.0.0/16 -I -H -o -37 | responses | TX timestamp offset (ns) rate clients | lost invalid basic xleave | min mean max stddev 1000 100 0.00% 0.00% 0.00% 100.00% -56 +9 +52 19 1500 150 0.00% 0.00% 0.00% 100.00% -40 +30 +75 22 2250 225 0.00% 0.00% 0.00% 100.00% -11 +29 +72 15 3375 337 0.00% 0.00% 0.00% 100.00% -18 +40 +88 22 5062 506 0.00% 0.00% 0.00% 100.00% -19 +23 +77 15 7593 759 0.00% 0.00% 0.00% 100.00% +7 +47 +5168 43 11389 1138 0.00% 0.00% 0.00% 100.00% -11 +41 +5240 39 17083 1708 0.00% 0.00% 0.00% 100.00% +19 +60 +5288 50 25624 2562 0.00% 0.00% 0.00% 100.00% +1 +56 +5368 58 38436 3843 0.00% 0.00% 0.00% 100.00% -84 +12 +8847 66 57654 5765 0.00% 0.00% 100.00% 0.00% 86481 8648 0.00% 0.00% 100.00% 0.00% 129721 12972 0.00% 0.00% 100.00% 0.00% 194581 16384 0.00% 0.00% 100.00% 0.00% 291871 16384 27.35% 0.00% 72.65% 0.00% 437806 16384 50.05% 0.00% 49.95% 0.00% After: $ sudo ./ntpperf -i enp3s0 -m 10:22:22:22:22:21 -d 192.168.1.3 -s 172.18.0.0/16 -I -H -o -37 | responses | TX timestamp offset (ns) rate clients | lost invalid basic xleave | min mean max stddev 1000 100 0.00% 0.00% 0.00% 100.00% -44 +0 +61 19 1500 150 0.00% 0.00% 0.00% 100.00% -6 +39 +81 16 2250 225 0.00% 0.00% 0.00% 100.00% -22 +25 +69 15 3375 337 0.00% 0.00% 0.00% 100.00% -28 +15 +56 14 5062 506 0.00% 0.00% 0.00% 100.00% +7 +78 +143 27 7593 759 0.00% 0.00% 0.00% 100.00% -54 +24 +144 47 11389 1138 0.00% 0.00% 0.00% 100.00% -90 -33 +28 21 17083 1708 0.00% 0.00% 0.00% 100.00% -50 -2 +35 14 25624 2562 0.00% 0.00% 0.00% 100.00% -62 +7 +66 23 38436 3843 0.00% 0.00% 0.00% 100.00% -33 +30 +5395 36 57654 5765 0.00% 0.00% 100.00% 0.00% 86481 8648 0.00% 0.00% 100.00% 0.00% 129721 12972 0.00% 0.00% 100.00% 0.00% 194581 16384 19.50% 0.00% 80.50% 0.00% 291871 16384 35.81% 0.00% 64.19% 0.00% 437806 16384 55.40% 0.00% 44.60% 0.00% [1] https://github.com/mlichvar/ntpperf Signed-off-by: Vinicius Costa Gomes Reviewed-by: Kurt Kanzenbach Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc.h | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_ptp.c | 15 +++++---------- 3 files changed, 7 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 66fb67c17e4f..a00738bf6b19 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -228,7 +228,6 @@ struct igc_adapter { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_caps; - struct work_struct ptp_tx_work; /* Access to ptp_tx_skb and ptp_tx_start are protected by the * ptp_tx_lock. */ @@ -638,6 +637,7 @@ int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igc_ptp_tx_hang(struct igc_adapter *adapter); void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts); +void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter); #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring)) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index eb50bfd5b867..eb4f0e562f60 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5223,7 +5223,7 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) if (tsicr & IGC_TSICR_TXTS) { /* retrieve hardware timestamp */ - schedule_work(&adapter->ptp_tx_work); + igc_ptp_tx_tstamp_event(adapter); ack |= IGC_TSICR_TXTS; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 42f622ceb64b..cf963a12a92f 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -540,8 +540,6 @@ static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) { unsigned long flags; - cancel_work_sync(&adapter->ptp_tx_work); - spin_lock_irqsave(&adapter->ptp_tx_lock, flags); dev_kfree_skb_any(adapter->ptp_tx_skb); @@ -724,16 +722,14 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) } /** - * igc_ptp_tx_work - * @work: pointer to work struct + * igc_ptp_tx_tstamp_event + * @adapter: board private structure * - * This work function checks the TSYNCTXCTL valid bit to determine when - * a timestamp has been taken for the current stored skb. + * Called when a TX timestamp interrupt happens to retrieve the + * timestamp and send it up to the socket. */ -static void igc_ptp_tx_work(struct work_struct *work) +void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter) { - struct igc_adapter *adapter = container_of(work, struct igc_adapter, - ptp_tx_work); struct igc_hw *hw = &adapter->hw; unsigned long flags; u32 tsynctxctl; @@ -1004,7 +1000,6 @@ void igc_ptp_init(struct igc_adapter *adapter) spin_lock_init(&adapter->ptp_tx_lock); spin_lock_init(&adapter->tmreg_lock); - INIT_WORK(&adapter->ptp_tx_work, igc_ptp_tx_work); adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; -- cgit v1.2.3-58-ga151 From c789ad7cbebcac5d5f417296c140a1252c689524 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 7 Jun 2023 14:32:32 -0700 Subject: igc: Work around HW bug causing missing timestamps There's an hardware issue that can cause missing timestamps. The bug is that the interrupt is only cleared if the IGC_TXSTMPH_0 register is read. The bug can cause a race condition if a timestamp is captured at the wrong time, and we will miss that timestamp. To reduce the time window that the problem is able to happen, in case no timestamp was ready, we read the "previous" value of the timestamp registers, and we compare with the "current" one, if it didn't change we can be reasonably sure that no timestamp was captured. If they are different, we use the new value as the captured timestamp. The HW bug is not easy to reproduce, got to reproduce it when smashing the NIC with timestamping requests from multiple applications (e.g. multiple ntpperf instances + ptp4l), after 10s of minutes. This workaround has more impact when multiple timestamp registers are used, and the IGC_TXSTMPH_0 register always need to be read, so the interrupt is cleared. Fixes: 2c344ae24501 ("igc: Add support for TX timestamping") Signed-off-by: Vinicius Costa Gomes Tested-by: Naama Meir Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/igc/igc_ptp.c | 48 ++++++++++++++++++++++++-------- 1 file changed, 37 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index cf963a12a92f..32ef112f8291 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -685,14 +685,49 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) struct sk_buff *skb = adapter->ptp_tx_skb; struct skb_shared_hwtstamps shhwtstamps; struct igc_hw *hw = &adapter->hw; + u32 tsynctxctl; int adjust = 0; u64 regval; if (WARN_ON_ONCE(!skb)) return; - regval = rd32(IGC_TXSTMPL); - regval |= (u64)rd32(IGC_TXSTMPH) << 32; + tsynctxctl = rd32(IGC_TSYNCTXCTL); + tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0; + if (tsynctxctl) { + regval = rd32(IGC_TXSTMPL); + regval |= (u64)rd32(IGC_TXSTMPH) << 32; + } else { + /* There's a bug in the hardware that could cause + * missing interrupts for TX timestamping. The issue + * is that for new interrupts to be triggered, the + * IGC_TXSTMPH_0 register must be read. + * + * To avoid discarding a valid timestamp that just + * happened at the "wrong" time, we need to confirm + * that there was no timestamp captured, we do that by + * assuming that no two timestamps in sequence have + * the same nanosecond value. + * + * So, we read the "low" register, read the "high" + * register (to latch a new timestamp) and read the + * "low" register again, if "old" and "new" versions + * of the "low" register are different, a valid + * timestamp was captured, we can read the "high" + * register again. + */ + u32 txstmpl_old, txstmpl_new; + + txstmpl_old = rd32(IGC_TXSTMPL); + rd32(IGC_TXSTMPH); + txstmpl_new = rd32(IGC_TXSTMPL); + + if (txstmpl_old == txstmpl_new) + return; + + regval = txstmpl_new; + regval |= (u64)rd32(IGC_TXSTMPH) << 32; + } if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) return; @@ -730,22 +765,13 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) */ void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; unsigned long flags; - u32 tsynctxctl; spin_lock_irqsave(&adapter->ptp_tx_lock, flags); if (!adapter->ptp_tx_skb) goto unlock; - tsynctxctl = rd32(IGC_TSYNCTXCTL); - tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0; - if (!tsynctxctl) { - WARN_ONCE(1, "Received a TSTAMP interrupt but no TSTAMP is ready.\n"); - goto unlock; - } - igc_ptp_tx_hwtstamp(adapter); unlock: -- cgit v1.2.3-58-ga151 From 533bbc7ce562e476ac381e8ddcb27c46279a44f9 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 21 Jun 2023 08:09:49 +0200 Subject: Bluetooth: MAINTAINERS: add Devicetree bindings to Bluetooth drivers The Devicetree bindings should be picked up by subsystem maintainers, but respective pattern for Bluetooth drivers was missing. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Simon Horman Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 35e19594640d..4b53a958e3a7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3613,6 +3613,7 @@ S: Supported W: http://www.bluez.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git +F: Documentation/devicetree/bindings/net/bluetooth/ F: drivers/bluetooth/ BLUETOOTH SUBSYSTEM -- cgit v1.2.3-58-ga151 From b9ec61be2d91cc09b5e7302e65442e6d71f0ed93 Mon Sep 17 00:00:00 2001 From: Sathesh Edara Date: Wed, 21 Jun 2023 03:16:49 -0700 Subject: MAINTAINERS: update email addresses of octeon_ep driver maintainers Update email addresses of Marvell octeon_ep driver maintainers. Also remove a former maintainer. As a maintainer below are the responsibilities: - Pushing the bug fixes and new features to upstream. - Responsible for reviewing the external changes submitted for the octeon_ep driver. - Reply to maintainers questions in a timely manner. Signed-off-by: Sathesh Edara Signed-off-by: Jakub Kicinski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4b53a958e3a7..1ddfde285a06 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12552,7 +12552,7 @@ F: drivers/mtd/nand/raw/marvell_nand.c MARVELL OCTEON ENDPOINT DRIVER M: Veerasenareddy Burru -M: Abhijit Ayarekar +M: Sathesh Edara L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/marvell/octeon_ep -- cgit v1.2.3-58-ga151 From c4fc88ad2a765224a648db8ab35f125e120fe41b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Jun 2023 15:55:37 +0200 Subject: net: stmmac: fix double serdes powerdown Commit 49725ffc15fc ("net: stmmac: power up/down serdes in stmmac_open/release") correctly added a call to the serdes_powerdown() callback to stmmac_release() but did not remove the one from stmmac_remove() which leads to a doubled call to serdes_powerdown(). This can lead to all kinds of problems: in the case of the qcom ethqos driver, it caused an unbalanced regulator disable splat. Fixes: 49725ffc15fc ("net: stmmac: power up/down serdes in stmmac_open/release") Signed-off-by: Bartosz Golaszewski Reviewed-by: Jiri Pirko Acked-by: Junxiao Chang Reviewed-by: Andrew Halaney Tested-by: Andrew Halaney Link: https://lore.kernel.org/r/20230621135537.376649-1-brgl@bgdev.pl Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 87510951f4e8..b74946bbee3c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7457,12 +7457,6 @@ void stmmac_dvr_remove(struct device *dev) netif_carrier_off(ndev); unregister_netdev(ndev); - /* Serdes power down needs to happen after VLAN filter - * is deleted that is triggered by unregister_netdev(). - */ - if (priv->plat->serdes_powerdown) - priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv); - #ifdef CONFIG_DEBUG_FS stmmac_exit_fs(ndev); #endif -- cgit v1.2.3-58-ga151 From 8d61f926d42045961e6b65191c09e3678d86a9cf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Jun 2023 15:43:37 +0000 Subject: netlink: fix potential deadlock in netlink_set_err() syzbot reported a possible deadlock in netlink_set_err() [1] A similar issue was fixed in commit 1d482e666b8e ("netlink: disable IRQs for netlink_lock_table()") in netlink_lock_table() This patch adds IRQ safety to netlink_set_err() and __netlink_diag_dump() which were not covered by cited commit. [1] WARNING: possible irq lock inversion dependency detected 6.4.0-rc6-syzkaller-00240-g4e9f0ec38852 #0 Not tainted syz-executor.2/23011 just changed the state of lock: ffffffff8e1a7a58 (nl_table_lock){.+.?}-{2:2}, at: netlink_set_err+0x2e/0x3a0 net/netlink/af_netlink.c:1612 but this lock was taken by another, SOFTIRQ-safe lock in the past: (&local->queue_stop_reason_lock){..-.}-{2:2} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(nl_table_lock); local_irq_disable(); lock(&local->queue_stop_reason_lock); lock(nl_table_lock); lock(&local->queue_stop_reason_lock); *** DEADLOCK *** Fixes: 1d482e666b8e ("netlink: disable IRQs for netlink_lock_table()") Reported-by: syzbot+a7d200a347f912723e5c@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=a7d200a347f912723e5c Link: https://lore.kernel.org/netdev/000000000000e38d1605fea5747e@google.com/T/#u Signed-off-by: Eric Dumazet Cc: Johannes Berg Link: https://lore.kernel.org/r/20230621154337.1668594-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/netlink/af_netlink.c | 5 +++-- net/netlink/diag.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3a1e0fd5bf14..5968b6450d82 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1600,6 +1600,7 @@ out: int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; + unsigned long flags; struct sock *sk; int ret = 0; @@ -1609,12 +1610,12 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) /* sk->sk_err wants a positive error value */ info.code = -code; - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index c6255eac305c..4143b2ea4195 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -94,6 +94,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; struct netlink_sock *nlsk; + unsigned long flags; struct sock *sk; int num = 2; int ret = 0; @@ -152,7 +153,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num++; mc_list: - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &tbl->mc_list) { if (sk_hashed(sk)) continue; @@ -173,7 +174,7 @@ mc_list: } num++; } - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); done: cb->args[0] = num; -- cgit v1.2.3-58-ga151 From aa5406950726e336c5c9585b09799a734b6e77bf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Jun 2023 17:47:20 +0000 Subject: netlink: do not hard code device address lenth in fdb dumps syzbot reports that some netdev devices do not have a six bytes address [1] Replace ETH_ALEN by dev->addr_len. [1] (Case of a device where dev->addr_len = 4) BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline] BUG: KMSAN: kernel-infoleak in copyout+0xb8/0x100 lib/iov_iter.c:169 instrument_copy_to_user include/linux/instrumented.h:114 [inline] copyout+0xb8/0x100 lib/iov_iter.c:169 _copy_to_iter+0x6d8/0x1d00 lib/iov_iter.c:536 copy_to_iter include/linux/uio.h:206 [inline] simple_copy_to_iter+0x68/0xa0 net/core/datagram.c:513 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:419 skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:527 skb_copy_datagram_msg include/linux/skbuff.h:3960 [inline] netlink_recvmsg+0x4ae/0x15a0 net/netlink/af_netlink.c:1970 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg net/socket.c:1040 [inline] ____sys_recvmsg+0x283/0x7f0 net/socket.c:2722 ___sys_recvmsg+0x223/0x840 net/socket.c:2764 do_recvmmsg+0x4f9/0xfd0 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x397/0x490 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was stored to memory at: __nla_put lib/nlattr.c:1009 [inline] nla_put+0x1c6/0x230 lib/nlattr.c:1067 nlmsg_populate_fdb_fill+0x2b8/0x600 net/core/rtnetlink.c:4071 nlmsg_populate_fdb net/core/rtnetlink.c:4418 [inline] ndo_dflt_fdb_dump+0x616/0x840 net/core/rtnetlink.c:4456 rtnl_fdb_dump+0x14ff/0x1fc0 net/core/rtnetlink.c:4629 netlink_dump+0x9d1/0x1310 net/netlink/af_netlink.c:2268 netlink_recvmsg+0xc5c/0x15a0 net/netlink/af_netlink.c:1995 sock_recvmsg_nosec+0x7a/0x120 net/socket.c:1019 ____sys_recvmsg+0x664/0x7f0 net/socket.c:2720 ___sys_recvmsg+0x223/0x840 net/socket.c:2764 do_recvmmsg+0x4f9/0xfd0 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x397/0x490 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12d/0xb60 mm/slab.h:716 slab_alloc_node mm/slub.c:3451 [inline] __kmem_cache_alloc_node+0x4ff/0x8b0 mm/slub.c:3490 kmalloc_trace+0x51/0x200 mm/slab_common.c:1057 kmalloc include/linux/slab.h:559 [inline] __hw_addr_create net/core/dev_addr_lists.c:60 [inline] __hw_addr_add_ex+0x2e5/0x9e0 net/core/dev_addr_lists.c:118 __dev_mc_add net/core/dev_addr_lists.c:867 [inline] dev_mc_add+0x9a/0x130 net/core/dev_addr_lists.c:885 igmp6_group_added+0x267/0xbc0 net/ipv6/mcast.c:680 ipv6_mc_up+0x296/0x3b0 net/ipv6/mcast.c:2754 ipv6_mc_remap+0x1e/0x30 net/ipv6/mcast.c:2708 addrconf_type_change net/ipv6/addrconf.c:3731 [inline] addrconf_notify+0x4d3/0x1d90 net/ipv6/addrconf.c:3699 notifier_call_chain kernel/notifier.c:93 [inline] raw_notifier_call_chain+0xe4/0x430 kernel/notifier.c:461 call_netdevice_notifiers_info net/core/dev.c:1935 [inline] call_netdevice_notifiers_extack net/core/dev.c:1973 [inline] call_netdevice_notifiers+0x1ee/0x2d0 net/core/dev.c:1987 bond_enslave+0xccd/0x53f0 drivers/net/bonding/bond_main.c:1906 do_set_master net/core/rtnetlink.c:2626 [inline] rtnl_newlink_create net/core/rtnetlink.c:3460 [inline] __rtnl_newlink net/core/rtnetlink.c:3660 [inline] rtnl_newlink+0x378c/0x40e0 net/core/rtnetlink.c:3673 rtnetlink_rcv_msg+0x16a6/0x1840 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x371/0x650 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0xf28/0x1230 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x122f/0x13d0 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x999/0xd50 net/socket.c:2503 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2557 __sys_sendmsg net/socket.c:2586 [inline] __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x304/0x490 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Bytes 2856-2857 of 3500 are uninitialized Memory access of size 3500 starts at ffff888018d99104 Data copied to user address 0000000020000480 Fixes: d83b06036048 ("net: add fdb generic dump routine") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/20230621174720.1845040-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/core/rtnetlink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 41de3a2f29e1..7776611a14ae 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4090,7 +4090,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, ndm->ndm_ifindex = dev->ifindex; ndm->ndm_state = ndm_state; - if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr)) goto nla_put_failure; if (vid) if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid)) @@ -4104,10 +4104,10 @@ nla_put_failure: return -EMSGSIZE; } -static inline size_t rtnl_fdb_nlmsg_size(void) +static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + - nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(dev->addr_len) + /* NDA_LLADDR */ nla_total_size(sizeof(u16)) + /* NDA_VLAN */ 0; } @@ -4119,7 +4119,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC); if (!skb) goto errout; -- cgit v1.2.3-58-ga151 From fc0649395dca81f2b3b02d9b248acb38cbcee55c Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Wed, 21 Jun 2023 06:38:48 +0200 Subject: net: phy: dp83td510: fix kernel stall during netboot in DP83TD510E PHY driver Fix an issue where the kernel would stall during netboot, showing the "sched: RT throttling activated" message. This stall was triggered by the behavior of the mii_interrupt bit (Bit 7 - DP83TD510E_STS_MII_INT) in the DP83TD510E's PHY_STS Register (Address = 0x10). The DP83TD510E datasheet (2020) states that the bit clears on write, however, in practice, the bit clears on read. This discrepancy had significant implications on the driver's interrupt handling. The PHY_STS Register was used by handle_interrupt() to check for pending interrupts and by read_status() to get the current link status. The call to read_status() was unintentionally clearing the mii_interrupt status bit without deasserting the IRQ pin, causing handle_interrupt() to miss other pending interrupts. This issue was most apparent during netboot. The fix refrains from using the PHY_STS Register for interrupt handling. Instead, we now solely rely on the INTERRUPT_REG_1 Register (Address = 0x12) and INTERRUPT_REG_2 Register (Address = 0x13) for this purpose. These registers directly influence the IRQ pin state and are latched high until read. Note: The INTERRUPT_REG_2 Register (Address = 0x13) exists and can also be used for interrupt handling, specifically for "Aneg page received interrupt" and "Polarity change interrupt". However, these features are currently not supported by this driver. Fixes: 165cd04fe253 ("net: phy: dp83td510: Add support for the DP83TD510 Ethernet PHY") Cc: Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230621043848.3806124-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83td510.c | 23 +++++------------------ 1 file changed, 5 insertions(+), 18 deletions(-) diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index 3cd9a77f9532..d7616b13c594 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -12,6 +12,11 @@ /* MDIO_MMD_VEND2 registers */ #define DP83TD510E_PHY_STS 0x10 +/* Bit 7 - mii_interrupt, active high. Clears on read. + * Note: Clearing does not necessarily deactivate IRQ pin if interrupts pending. + * This differs from the DP83TD510E datasheet (2020) which states this bit + * clears on write 0. + */ #define DP83TD510E_STS_MII_INT BIT(7) #define DP83TD510E_LINK_STATUS BIT(0) @@ -53,12 +58,6 @@ static int dp83td510_config_intr(struct phy_device *phydev) int ret; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { - /* Clear any pending interrupts */ - ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PHY_STS, - 0x0); - if (ret) - return ret; - ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_INTERRUPT_REG_1, DP83TD510E_INT1_LINK_EN); @@ -81,10 +80,6 @@ static int dp83td510_config_intr(struct phy_device *phydev) DP83TD510E_GENCFG_INT_EN); if (ret) return ret; - - /* Clear any pending interrupts */ - ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PHY_STS, - 0x0); } return ret; @@ -94,14 +89,6 @@ static irqreturn_t dp83td510_handle_interrupt(struct phy_device *phydev) { int ret; - ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PHY_STS); - if (ret < 0) { - phy_error(phydev); - return IRQ_NONE; - } else if (!(ret & DP83TD510E_STS_MII_INT)) { - return IRQ_NONE; - } - /* Read the current enabled interrupts */ ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_INTERRUPT_REG_1); if (ret < 0) { -- cgit v1.2.3-58-ga151 From 1b5ea7ffb7a3bdfffb4b7f40ce0d20a3372ee405 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 22 Jun 2023 03:31:07 -0700 Subject: net: bcmgenet: Ensure MDIO unregistration has clocks enabled With support for Ethernet PHY LEDs having been added, while unregistering a MDIO bus and its child device liks PHYs there may be "late" accesses to the MDIO bus. One typical use case is setting the PHY LEDs brightness to OFF for instance. We need to ensure that the MDIO bus controller remains entirely functional since it runs off the main GENET adapter clock. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/20230617155500.4005881-1-andrew@lunn.ch/ Fixes: 9a4e79697009 ("net: bcmgenet: utilize generic Broadcom UniMAC MDIO controller driver") Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230622103107.1760280-1-florian.fainelli@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index c15ed0acdb77..0092e46c46f8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -673,5 +673,7 @@ void bcmgenet_mii_exit(struct net_device *dev) if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); + clk_prepare_enable(priv->clk); platform_device_unregister(priv->mii_pdev); + clk_disable_unprepare(priv->clk); } -- cgit v1.2.3-58-ga151 From 6a940abdef3162e5723f1495b8a49859d1708f79 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Jun 2023 15:23:04 +0000 Subject: bonding: do not assume skb mac_header is set Drivers must not assume in their ndo_start_xmit() that skbs have their mac_header set. skb->data is all what is needed. bonding seems to be one of the last offender as caught by syzbot: WARNING: CPU: 1 PID: 12155 at include/linux/skbuff.h:2907 skb_mac_offset include/linux/skbuff.h:2913 [inline] WARNING: CPU: 1 PID: 12155 at include/linux/skbuff.h:2907 bond_xmit_hash drivers/net/bonding/bond_main.c:4170 [inline] WARNING: CPU: 1 PID: 12155 at include/linux/skbuff.h:2907 bond_xmit_3ad_xor_slave_get drivers/net/bonding/bond_main.c:5149 [inline] WARNING: CPU: 1 PID: 12155 at include/linux/skbuff.h:2907 bond_3ad_xor_xmit drivers/net/bonding/bond_main.c:5186 [inline] WARNING: CPU: 1 PID: 12155 at include/linux/skbuff.h:2907 __bond_start_xmit drivers/net/bonding/bond_main.c:5442 [inline] WARNING: CPU: 1 PID: 12155 at include/linux/skbuff.h:2907 bond_start_xmit+0x14ab/0x19d0 drivers/net/bonding/bond_main.c:5470 Modules linked in: CPU: 1 PID: 12155 Comm: syz-executor.3 Not tainted 6.1.30-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/25/2023 RIP: 0010:skb_mac_header include/linux/skbuff.h:2907 [inline] RIP: 0010:skb_mac_offset include/linux/skbuff.h:2913 [inline] RIP: 0010:bond_xmit_hash drivers/net/bonding/bond_main.c:4170 [inline] RIP: 0010:bond_xmit_3ad_xor_slave_get drivers/net/bonding/bond_main.c:5149 [inline] RIP: 0010:bond_3ad_xor_xmit drivers/net/bonding/bond_main.c:5186 [inline] RIP: 0010:__bond_start_xmit drivers/net/bonding/bond_main.c:5442 [inline] RIP: 0010:bond_start_xmit+0x14ab/0x19d0 drivers/net/bonding/bond_main.c:5470 Code: 8b 7c 24 30 e8 76 dd 1a 01 48 85 c0 74 0d 48 89 c3 e8 29 67 2e fe e9 15 ef ff ff e8 1f 67 2e fe e9 10 ef ff ff e8 15 67 2e fe <0f> 0b e9 45 f8 ff ff e8 09 67 2e fe e9 dc fa ff ff e8 ff 66 2e fe RSP: 0018:ffffc90002fff6e0 EFLAGS: 00010283 RAX: ffffffff835874db RBX: 000000000000ffff RCX: 0000000000040000 RDX: ffffc90004dcf000 RSI: 00000000000000b5 RDI: 00000000000000b6 RBP: ffffc90002fff8b8 R08: ffffffff83586d16 R09: ffffffff83586584 R10: 0000000000000007 R11: ffff8881599fc780 R12: ffff88811b6a7b7e R13: 1ffff110236d4f6f R14: ffff88811b6a7ac0 R15: 1ffff110236d4f76 FS: 00007f2e9eb47700(0000) GS:ffff8881f6b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2e421000 CR3: 000000010e6d4000 CR4: 00000000003526e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [] netdev_start_xmit include/linux/netdevice.h:4925 [inline] [] __dev_direct_xmit+0x4ef/0x850 net/core/dev.c:4380 [] dev_direct_xmit include/linux/netdevice.h:3043 [inline] [] packet_direct_xmit+0x18b/0x300 net/packet/af_packet.c:284 [] packet_snd net/packet/af_packet.c:3112 [inline] [] packet_sendmsg+0x4a22/0x64d0 net/packet/af_packet.c:3143 [] sock_sendmsg_nosec net/socket.c:716 [inline] [] sock_sendmsg net/socket.c:736 [inline] [] __sys_sendto+0x472/0x5f0 net/socket.c:2139 [] __do_sys_sendto net/socket.c:2151 [inline] [] __se_sys_sendto net/socket.c:2147 [inline] [] __x64_sys_sendto+0xe5/0x100 net/socket.c:2147 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x2f/0x50 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 7b8fc0103bb5 ("bonding: add a vlan+srcmac tx hashing option") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Jarod Wilson Cc: Moshe Tal Cc: Jussi Maki Cc: Jay Vosburgh Cc: Andy Gospodarek Cc: Vladimir Oltean Link: https://lore.kernel.org/r/20230622152304.2137482-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index edbaa1444f8e..091e035c76a6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4197,7 +4197,7 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) return skb->hash; return __bond_xmit_hash(bond, skb, skb->data, skb->protocol, - skb_mac_offset(skb), skb_network_offset(skb), + 0, skb_network_offset(skb), skb_headlen(skb)); } -- cgit v1.2.3-58-ga151 From 11b73313c12403f617b47752db0ab3deef201af7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Jun 2023 18:15:03 +0000 Subject: sch_netem: fix issues in netem_change() vs get_dist_table() In blamed commit, I missed that get_dist_table() was allocating memory using GFP_KERNEL, and acquiring qdisc lock to perform the swap of newly allocated table with current one. In this patch, get_dist_table() is allocating memory and copy user data before we acquire the qdisc lock. Then we perform swap operations while being protected by the lock. Note that after this patch netem_change() no longer can do partial changes. If an error is returned, qdisc conf is left unchanged. Fixes: 2174a08db80d ("sch_netem: acquire qdisc lock in netem_change()") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Acked-by: Jamal Hadi Salim Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230622181503.2327695-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/sched/sch_netem.c | 59 ++++++++++++++++++++++----------------------------- 1 file changed, 25 insertions(+), 34 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e79be1b3e74d..b93ec2a3454e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -773,12 +773,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -793,13 +791,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -956,6 +948,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -966,6 +960,18 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; @@ -975,26 +981,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; + q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1044,17 +1041,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, unlock: sch_tree_unlock(sch); - return ret; -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; - - goto unlock; +table_free: + dist_free(delay_dist); + dist_free(slot_dist); + return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, -- cgit v1.2.3-58-ga151 From 5f789f103671fec3733ebe756e56adf15c90c21d Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 22 Jun 2023 23:03:34 +0200 Subject: selftests: rtnetlink: remove netdevsim device after ipsec offload test On systems where netdevsim is built-in or loaded before the test starts, kci_test_ipsec_offload doesn't remove the netdevsim device it created during the test. Fixes: e05b2d141fef ("netdevsim: move netdev creation/destruction to dev probe") Signed-off-by: Sabrina Dubroca Reviewed-by: Simon Horman Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/e1cb94f4f82f4eca4a444feec4488a1323396357.1687466906.git.sd@queasysnail.net Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/rtnetlink.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 383ac6fc037d..ba286d680fd9 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -860,6 +860,7 @@ EOF fi # clean up any leftovers + echo 0 > /sys/bus/netdevsim/del_device $probed && rmmod netdevsim if [ $ret -ne 0 ]; then -- cgit v1.2.3-58-ga151 From ce3aee7114c575fab32a5e9e939d4bbb3dcca79f Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 22 Jun 2023 14:32:31 -0700 Subject: gtp: Fix use-after-free in __gtp_encap_destroy(). syzkaller reported use-after-free in __gtp_encap_destroy(). [0] It shows the same process freed sk and touched it illegally. Commit e198987e7dd7 ("gtp: fix suspicious RCU usage") added lock_sock() and release_sock() in __gtp_encap_destroy() to protect sk->sk_user_data, but release_sock() is called after sock_put() releases the last refcnt. [0]: BUG: KASAN: slab-use-after-free in instrument_atomic_read_write include/linux/instrumented.h:96 [inline] BUG: KASAN: slab-use-after-free in atomic_try_cmpxchg_acquire include/linux/atomic/atomic-instrumented.h:541 [inline] BUG: KASAN: slab-use-after-free in queued_spin_lock include/asm-generic/qspinlock.h:111 [inline] BUG: KASAN: slab-use-after-free in do_raw_spin_lock include/linux/spinlock.h:186 [inline] BUG: KASAN: slab-use-after-free in __raw_spin_lock_bh include/linux/spinlock_api_smp.h:127 [inline] BUG: KASAN: slab-use-after-free in _raw_spin_lock_bh+0x75/0xe0 kernel/locking/spinlock.c:178 Write of size 4 at addr ffff88800dbef398 by task syz-executor.2/2401 CPU: 1 PID: 2401 Comm: syz-executor.2 Not tainted 6.4.0-rc5-01219-gfa0e21fa4443 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:351 [inline] print_report+0xcc/0x620 mm/kasan/report.c:462 kasan_report+0xb2/0xe0 mm/kasan/report.c:572 check_region_inline mm/kasan/generic.c:181 [inline] kasan_check_range+0x39/0x1c0 mm/kasan/generic.c:187 instrument_atomic_read_write include/linux/instrumented.h:96 [inline] atomic_try_cmpxchg_acquire include/linux/atomic/atomic-instrumented.h:541 [inline] queued_spin_lock include/asm-generic/qspinlock.h:111 [inline] do_raw_spin_lock include/linux/spinlock.h:186 [inline] __raw_spin_lock_bh include/linux/spinlock_api_smp.h:127 [inline] _raw_spin_lock_bh+0x75/0xe0 kernel/locking/spinlock.c:178 spin_lock_bh include/linux/spinlock.h:355 [inline] release_sock+0x1f/0x1a0 net/core/sock.c:3526 gtp_encap_disable_sock drivers/net/gtp.c:651 [inline] gtp_encap_disable+0xb9/0x220 drivers/net/gtp.c:664 gtp_dev_uninit+0x19/0x50 drivers/net/gtp.c:728 unregister_netdevice_many_notify+0x97e/0x1520 net/core/dev.c:10841 rtnl_delete_link net/core/rtnetlink.c:3216 [inline] rtnl_dellink+0x3c0/0xb30 net/core/rtnetlink.c:3268 rtnetlink_rcv_msg+0x450/0xb10 net/core/rtnetlink.c:6423 netlink_rcv_skb+0x15d/0x450 net/netlink/af_netlink.c:2548 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x700/0x930 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x91c/0xe30 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b7/0x200 net/socket.c:747 ____sys_sendmsg+0x75a/0x990 net/socket.c:2493 ___sys_sendmsg+0x11d/0x1c0 net/socket.c:2547 __sys_sendmsg+0xfe/0x1d0 net/socket.c:2576 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f1168b1fe5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 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 8b 0d 73 9f 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007f1167edccc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004bbf80 RCX: 00007f1168b1fe5d RDX: 0000000000000000 RSI: 00000000200002c0 RDI: 0000000000000003 RBP: 00000000004bbf80 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007f1168b80530 R15: 0000000000000000 Allocated by task 1483: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 __kasan_slab_alloc+0x59/0x70 mm/kasan/common.c:328 kasan_slab_alloc include/linux/kasan.h:186 [inline] slab_post_alloc_hook mm/slab.h:711 [inline] slab_alloc_node mm/slub.c:3451 [inline] slab_alloc mm/slub.c:3459 [inline] __kmem_cache_alloc_lru mm/slub.c:3466 [inline] kmem_cache_alloc+0x16d/0x340 mm/slub.c:3475 sk_prot_alloc+0x5f/0x280 net/core/sock.c:2073 sk_alloc+0x34/0x6c0 net/core/sock.c:2132 inet6_create net/ipv6/af_inet6.c:192 [inline] inet6_create+0x2c7/0xf20 net/ipv6/af_inet6.c:119 __sock_create+0x2a1/0x530 net/socket.c:1535 sock_create net/socket.c:1586 [inline] __sys_socket_create net/socket.c:1623 [inline] __sys_socket_create net/socket.c:1608 [inline] __sys_socket+0x137/0x250 net/socket.c:1651 __do_sys_socket net/socket.c:1664 [inline] __se_sys_socket net/socket.c:1662 [inline] __x64_sys_socket+0x72/0xb0 net/socket.c:1662 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 2401: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:521 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10c/0x1b0 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:162 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3786 [inline] kmem_cache_free+0xb4/0x490 mm/slub.c:3808 sk_prot_free net/core/sock.c:2113 [inline] __sk_destruct+0x500/0x720 net/core/sock.c:2207 sk_destruct+0xc1/0xe0 net/core/sock.c:2222 __sk_free+0xed/0x3d0 net/core/sock.c:2233 sk_free+0x7c/0xa0 net/core/sock.c:2244 sock_put include/net/sock.h:1981 [inline] __gtp_encap_destroy+0x165/0x1b0 drivers/net/gtp.c:634 gtp_encap_disable_sock drivers/net/gtp.c:651 [inline] gtp_encap_disable+0xb9/0x220 drivers/net/gtp.c:664 gtp_dev_uninit+0x19/0x50 drivers/net/gtp.c:728 unregister_netdevice_many_notify+0x97e/0x1520 net/core/dev.c:10841 rtnl_delete_link net/core/rtnetlink.c:3216 [inline] rtnl_dellink+0x3c0/0xb30 net/core/rtnetlink.c:3268 rtnetlink_rcv_msg+0x450/0xb10 net/core/rtnetlink.c:6423 netlink_rcv_skb+0x15d/0x450 net/netlink/af_netlink.c:2548 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x700/0x930 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x91c/0xe30 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b7/0x200 net/socket.c:747 ____sys_sendmsg+0x75a/0x990 net/socket.c:2493 ___sys_sendmsg+0x11d/0x1c0 net/socket.c:2547 __sys_sendmsg+0xfe/0x1d0 net/socket.c:2576 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff88800dbef300 which belongs to the cache UDPv6 of size 1344 The buggy address is located 152 bytes inside of freed 1344-byte region [ffff88800dbef300, ffff88800dbef840) The buggy address belongs to the physical page: page:00000000d31bfed5 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88800dbeed40 pfn:0xdbe8 head:00000000d31bfed5 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 memcg:ffff888008ee0801 flags: 0x100000000010200(slab|head|node=0|zone=1) page_type: 0xffffffff() raw: 0100000000010200 ffff88800c7a3000 dead000000000122 0000000000000000 raw: ffff88800dbeed40 0000000080160015 00000001ffffffff ffff888008ee0801 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88800dbef280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88800dbef300: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88800dbef380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88800dbef400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88800dbef480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: e198987e7dd7 ("gtp: fix suspicious RCU usage") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Reviewed-by: Pablo Neira Ayuso Link: https://lore.kernel.org/r/20230622213231.24651-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- drivers/net/gtp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 15c7dc82107f..acb20ad4e37e 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -631,7 +631,9 @@ static void __gtp_encap_destroy(struct sock *sk) gtp->sk1u = NULL; udp_sk(sk)->encap_type = 0; rcu_assign_sk_user_data(sk, NULL); + release_sock(sk); sock_put(sk); + return; } release_sock(sk); } -- cgit v1.2.3-58-ga151 From f1bc9fc4a06de0108e0dca2a9a7e99ba1fc632f9 Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Thu, 22 Jun 2023 22:22:45 +0300 Subject: net: axienet: Move reset before 64-bit DMA detection 64-bit DMA detection will fail if axienet was started before (by boot loader, boot ROM, etc). In this state axienet will not start properly. XAXIDMA_TX_CDESC_OFFSET + 4 register (MM2S_CURDESC_MSB) is used to detect 64-bit DMA capability here. But datasheet says: When DMACR.RS is 1 (axienet is in enabled state), CURDESC_PTR becomes Read Only (RO) and is used to fetch the first descriptor. So iowrite32()/ioread32() trick to this register to detect 64-bit DMA will not work. So move axienet reset before 64-bit DMA detection. Fixes: f735c40ed93c ("net: axienet: Autodetect 64-bit DMA capability") Signed-off-by: Maxim Kochetkov Reviewed-by: Robert Hancock Reviewed-by: Radhey Shyam Pandey Link: https://lore.kernel.org/r/20230622192245.116864-1-fido_max@inbox.ru Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 3e310b55bce2..734822321e0a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2042,6 +2042,11 @@ static int axienet_probe(struct platform_device *pdev) goto cleanup_clk; } + /* Reset core now that clocks are enabled, prior to accessing MDIO */ + ret = __axienet_device_reset(lp); + if (ret) + goto cleanup_clk; + /* Autodetect the need for 64-bit DMA pointers. * When the IP is configured for a bus width bigger than 32 bits, * writing the MSB registers is mandatory, even if they are all 0. @@ -2096,11 +2101,6 @@ static int axienet_probe(struct platform_device *pdev) lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD; lp->coalesce_usec_tx = XAXIDMA_DFT_TX_USEC; - /* Reset core now that clocks are enabled, prior to accessing MDIO */ - ret = __axienet_device_reset(lp); - if (ret) - goto cleanup_clk; - ret = axienet_mdio_setup(lp); if (ret) dev_warn(&pdev->dev, -- cgit v1.2.3-58-ga151 From d1b355438b8325a486f087e506d412c4e852f37b Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Fri, 23 Jun 2023 15:34:48 +0100 Subject: sfc: fix crash when reading stats while NIC is resetting efx_net_stats() (.ndo_get_stats64) can be called during an ethtool selftest, during which time nic_data->mc_stats is NULL as the NIC has been fini'd. In this case do not attempt to fetch the latest stats from the hardware, else we will crash on a NULL dereference: BUG: kernel NULL pointer dereference, address: 0000000000000038 RIP efx_nic_update_stats abridged calltrace: efx_ef10_update_stats_pf efx_net_stats dev_get_stats dev_seq_printf_stats Skipping the read is safe, we will simply give out stale stats. To ensure that the free in efx_ef10_fini_nic() does not race against efx_ef10_update_stats_pf(), which could cause a TOCTTOU bug, take the efx->stats_lock in fini_nic (it is already held across update_stats). Fixes: d3142c193dca ("sfc: refactor EF10 stats handling") Reviewed-by: Pieter Jansen van Vuuren Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef10.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index b63e47af6365..8c019f382a7f 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1297,8 +1297,10 @@ static void efx_ef10_fini_nic(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; + spin_lock_bh(&efx->stats_lock); kfree(nic_data->mc_stats); nic_data->mc_stats = NULL; + spin_unlock_bh(&efx->stats_lock); } static int efx_ef10_init_nic(struct efx_nic *efx) @@ -1852,9 +1854,14 @@ static size_t efx_ef10_update_stats_pf(struct efx_nic *efx, u64 *full_stats, efx_ef10_get_stat_mask(efx, mask); - efx_nic_copy_stats(efx, nic_data->mc_stats); - efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, - mask, stats, nic_data->mc_stats, false); + /* If NIC was fini'd (probably resetting), then we can't read + * updated stats right now. + */ + if (nic_data->mc_stats) { + efx_nic_copy_stats(efx, nic_data->mc_stats); + efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, + mask, stats, nic_data->mc_stats, false); + } /* Update derived statistics */ efx_nic_fix_nodesc_drop_stat(efx, -- cgit v1.2.3-58-ga151 From 6709d4b7bc2e079241fdef15d1160581c5261c10 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Sun, 25 Jun 2023 17:10:07 +0800 Subject: net: nfc: Fix use-after-free caused by nfc_llcp_find_local This commit fixes several use-after-free that caused by function nfc_llcp_find_local(). For example, one UAF can happen when below buggy time window occurs. // nfc_genl_llc_get_params | // nfc_unregister_device | dev = nfc_get_device(idx); | device_lock(...) if (!dev) | dev->shutting_down = true; return -ENODEV; | device_unlock(...); | device_lock(...); | // nfc_llcp_unregister_device | nfc_llcp_find_local() nfc_llcp_find_local(...); | | local_cleanup() if (!local) { | rc = -ENODEV; | // nfc_llcp_local_put goto exit; | kref_put(.., local_release) } | | // local_release | list_del(&local->list) // nfc_genl_send_params | kfree() local->dev->idx !!!UAF!!! | | and the crash trace for the one of the discussed UAF like: BUG: KASAN: slab-use-after-free in nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 Read of size 8 at addr ffff888105b0e410 by task 20114 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x72/0xa0 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:319 [inline] print_report+0xcc/0x620 mm/kasan/report.c:430 kasan_report+0xb2/0xe0 mm/kasan/report.c:536 nfc_genl_send_params net/nfc/netlink.c:999 [inline] nfc_genl_llc_get_params+0x72f/0x780 net/nfc/netlink.c:1045 genl_family_rcv_msg_doit.isra.0+0x1ee/0x2e0 net/netlink/genetlink.c:968 genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x503/0x7d0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x161/0x430 net/netlink/af_netlink.c:2548 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x644/0x900 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x934/0xe70 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b6/0x200 net/socket.c:747 ____sys_sendmsg+0x6e9/0x890 net/socket.c:2501 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2555 __sys_sendmsg+0xf7/0x1d0 net/socket.c:2584 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7f34640a2389 RSP: 002b:00007f3463415168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f34641c1f80 RCX: 00007f34640a2389 RDX: 0000000000000000 RSI: 0000000020000240 RDI: 0000000000000006 RBP: 00007f34640ed493 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe38449ecf R14: 00007f3463415300 R15: 0000000000022000 Allocated by task 20116: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc+0x7f/0x90 mm/kasan/common.c:383 kmalloc include/linux/slab.h:580 [inline] kzalloc include/linux/slab.h:720 [inline] nfc_llcp_register_device+0x49/0xa40 net/nfc/llcp_core.c:1567 nfc_register_device+0x61/0x260 net/nfc/core.c:1124 nci_register_device+0x776/0xb20 net/nfc/nci/core.c:1257 virtual_ncidev_open+0x147/0x230 drivers/nfc/virtual_ncidev.c:148 misc_open+0x379/0x4a0 drivers/char/misc.c:165 chrdev_open+0x26c/0x780 fs/char_dev.c:414 do_dentry_open+0x6c4/0x12a0 fs/open.c:920 do_open fs/namei.c:3560 [inline] path_openat+0x24fe/0x37e0 fs/namei.c:3715 do_filp_open+0x1ba/0x410 fs/namei.c:3742 do_sys_openat2+0x171/0x4c0 fs/open.c:1356 do_sys_open fs/open.c:1372 [inline] __do_sys_openat fs/open.c:1388 [inline] __se_sys_openat fs/open.c:1383 [inline] __x64_sys_openat+0x143/0x200 fs/open.c:1383 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc Freed by task 20115: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x50 mm/kasan/generic.c:521 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free mm/kasan/common.c:200 [inline] __kasan_slab_free+0x10a/0x190 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:162 [inline] slab_free_hook mm/slub.c:1781 [inline] slab_free_freelist_hook mm/slub.c:1807 [inline] slab_free mm/slub.c:3787 [inline] __kmem_cache_free+0x7a/0x190 mm/slub.c:3800 local_release net/nfc/llcp_core.c:174 [inline] kref_put include/linux/kref.h:65 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:182 [inline] nfc_llcp_local_put net/nfc/llcp_core.c:177 [inline] nfc_llcp_unregister_device+0x206/0x290 net/nfc/llcp_core.c:1620 nfc_unregister_device+0x160/0x1d0 net/nfc/core.c:1179 virtual_ncidev_close+0x52/0xa0 drivers/nfc/virtual_ncidev.c:163 __fput+0x252/0xa20 fs/file_table.c:321 task_work_run+0x174/0x270 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x108/0x110 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x21/0x50 kernel/entry/common.c:297 do_syscall_64+0x4c/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc Last potentially related work creation: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 __kasan_record_aux_stack+0x95/0xb0 mm/kasan/generic.c:491 kvfree_call_rcu+0x29/0xa80 kernel/rcu/tree.c:3328 drop_sysctl_table+0x3be/0x4e0 fs/proc/proc_sysctl.c:1735 unregister_sysctl_table.part.0+0x9c/0x190 fs/proc/proc_sysctl.c:1773 unregister_sysctl_table+0x24/0x30 fs/proc/proc_sysctl.c:1753 neigh_sysctl_unregister+0x5f/0x80 net/core/neighbour.c:3895 addrconf_notify+0x140/0x17b0 net/ipv6/addrconf.c:3684 notifier_call_chain+0xbe/0x210 kernel/notifier.c:87 call_netdevice_notifiers_info+0xb5/0x150 net/core/dev.c:1937 call_netdevice_notifiers_extack net/core/dev.c:1975 [inline] call_netdevice_notifiers net/core/dev.c:1989 [inline] dev_change_name+0x3c3/0x870 net/core/dev.c:1211 dev_ifsioc+0x800/0xf70 net/core/dev_ioctl.c:376 dev_ioctl+0x3d9/0xf80 net/core/dev_ioctl.c:542 sock_do_ioctl+0x160/0x260 net/socket.c:1213 sock_ioctl+0x3f9/0x670 net/socket.c:1316 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl fs/ioctl.c:856 [inline] __x64_sys_ioctl+0x19e/0x210 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3f/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc The buggy address belongs to the object at ffff888105b0e400 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 16 bytes inside of freed 1024-byte region [ffff888105b0e400, ffff888105b0e800) The buggy address belongs to the physical page: head:ffffea000416c200 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0x200000000010200(slab|head|node=0|zone=2) raw: 0200000000010200 ffff8881000430c0 ffffea00044c7010 ffffea0004510e10 raw: 0000000000000000 00000000000a000a 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888105b0e300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888105b0e380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888105b0e400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888105b0e480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888105b0e500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb In summary, this patch solves those use-after-free by 1. Re-implement the nfc_llcp_find_local(). The current version does not grab the reference when getting the local from the linked list. For example, the llcp_sock_bind() gets the reference like below: // llcp_sock_bind() local = nfc_llcp_find_local(dev); // A ..... \ | raceable ..... / llcp_sock->local = nfc_llcp_local_get(local); // B There is an apparent race window that one can drop the reference and free the local object fetched in (A) before (B) gets the reference. 2. Some callers of the nfc_llcp_find_local() do not grab the reference at all. For example, the nfc_genl_llc_{{get/set}_params/sdreq} functions. We add the nfc_llcp_local_put() for them. Moreover, we add the necessary error handling function to put the reference. 3. Add the nfc_llcp_remove_local() helper. The local object is removed from the linked list in local_release() when all reference is gone. This patch removes it when nfc_llcp_unregister_device() is called. Therefore, every caller of nfc_llcp_find_local() will get a reference even when the nfc_llcp_unregister_device() is called. This promises no use-after-free for the local object is ever possible. Fixes: 52feb444a903 ("NFC: Extend netlink interface for LTO, RW, and MIUX parameters support") Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket") Signed-off-by: Lin Ma Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/nfc/llcp.h | 1 - net/nfc/llcp_commands.c | 12 +++++++++--- net/nfc/llcp_core.c | 49 ++++++++++++++++++++++++++++++++++++++++++------- net/nfc/llcp_sock.c | 18 ++++++++++-------- net/nfc/netlink.c | 20 +++++++++++++++----- net/nfc/nfc.h | 1 + 6 files changed, 77 insertions(+), 24 deletions(-) diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index c1d9be636933..d8345ed57c95 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -201,7 +201,6 @@ void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *s); void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local); int nfc_llcp_local_put(struct nfc_llcp_local *local); u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 41e3a20c8935..5d2d4bc26ef9 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -359,6 +359,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) struct sk_buff *skb; struct nfc_llcp_local *local; u16 size = 0; + int err; local = nfc_llcp_find_local(dev); if (local == NULL) @@ -368,8 +369,10 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) size += dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = alloc_skb(size, GFP_KERNEL); - if (skb == NULL) - return -ENOMEM; + if (skb == NULL) { + err = -ENOMEM; + goto out; + } skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); @@ -379,8 +382,11 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); - return nfc_data_exchange(dev, local->target_idx, skb, + err = nfc_data_exchange(dev, local->target_idx, skb, nfc_llcp_recv, local); +out: + nfc_llcp_local_put(local); + return err; } int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index a27e1842b2a0..f60e424e0607 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -17,6 +17,8 @@ static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; static LIST_HEAD(llcp_devices); +/* Protects llcp_devices list */ +static DEFINE_SPINLOCK(llcp_devices_lock); static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb); @@ -141,7 +143,7 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, write_unlock(&local->raw_sockets.lock); } -struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) +static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { kref_get(&local->ref); @@ -169,7 +171,6 @@ static void local_release(struct kref *ref) local = container_of(ref, struct nfc_llcp_local, ref); - list_del(&local->list); local_cleanup(local); kfree(local); } @@ -282,12 +283,33 @@ static void nfc_llcp_sdreq_timer(struct timer_list *t) struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) { struct nfc_llcp_local *local; + struct nfc_llcp_local *res = NULL; + spin_lock(&llcp_devices_lock); list_for_each_entry(local, &llcp_devices, list) - if (local->dev == dev) + if (local->dev == dev) { + res = nfc_llcp_local_get(local); + break; + } + spin_unlock(&llcp_devices_lock); + + return res; +} + +static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) +{ + struct nfc_llcp_local *local, *tmp; + + spin_lock(&llcp_devices_lock); + list_for_each_entry_safe(local, tmp, &llcp_devices, list) + if (local->dev == dev) { + list_del(&local->list); + spin_unlock(&llcp_devices_lock); return local; + } + spin_unlock(&llcp_devices_lock); - pr_debug("No device found\n"); + pr_warn("Shutting down device not found\n"); return NULL; } @@ -608,12 +630,15 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) *general_bytes_len = local->gb_len; + nfc_llcp_local_put(local); + return local->gb; } int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; + int err; if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN) return -EINVAL; @@ -630,12 +655,16 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) if (memcmp(local->remote_gb, llcp_magic, 3)) { pr_err("MAC does not support LLCP\n"); - return -EINVAL; + err = -EINVAL; + goto out; } - return nfc_llcp_parse_gb_tlv(local, + err = nfc_llcp_parse_gb_tlv(local, &local->remote_gb[3], local->remote_gb_len - 3); +out: + nfc_llcp_local_put(local); + return err; } static u8 nfc_llcp_dsap(const struct sk_buff *pdu) @@ -1517,6 +1546,8 @@ int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) __nfc_llcp_recv(local, skb); + nfc_llcp_local_put(local); + return 0; } @@ -1533,6 +1564,8 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev) /* Close and purge all existing sockets */ nfc_llcp_socket_release(local, true, 0); + + nfc_llcp_local_put(local); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, @@ -1558,6 +1591,8 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(local->remote_lto)); } + + nfc_llcp_local_put(local); } int nfc_llcp_register_device(struct nfc_dev *ndev) @@ -1608,7 +1643,7 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) void nfc_llcp_unregister_device(struct nfc_dev *dev) { - struct nfc_llcp_local *local = nfc_llcp_find_local(dev); + struct nfc_llcp_local *local = nfc_llcp_remove_local(dev); if (local == NULL) { pr_debug("No such device\n"); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 77642d18a3b4..645677f84dba 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -99,7 +99,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; llcp_sock->service_name_len = min_t(unsigned int, llcp_addr.service_name_len, @@ -186,7 +186,7 @@ static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->nfc_protocol = llcp_addr.nfc_protocol; nfc_llcp_sock_link(&local->raw_sockets, sk); @@ -696,22 +696,22 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, if (dev->dep_link_up == false) { ret = -ENOLINK; device_unlock(&dev->dev); - goto put_dev; + goto sock_llcp_put_local; } device_unlock(&dev->dev); if (local->rf_mode == NFC_RF_INITIATOR && addr->target_idx != local->target_idx) { ret = -ENOLINK; - goto put_dev; + goto sock_llcp_put_local; } llcp_sock->dev = dev; - llcp_sock->local = nfc_llcp_local_get(local); + llcp_sock->local = local; llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { ret = -ENOMEM; - goto sock_llcp_put_local; + goto sock_llcp_nullify; } llcp_sock->reserved_ssap = llcp_sock->ssap; @@ -757,11 +757,13 @@ sock_unlink: sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); -sock_llcp_put_local: - nfc_llcp_local_put(llcp_sock->local); +sock_llcp_nullify: llcp_sock->local = NULL; llcp_sock->dev = NULL; +sock_llcp_put_local: + nfc_llcp_local_put(local); + put_dev: nfc_put_device(dev); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index b9264e730fd9..e9ac6a6f934e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1039,11 +1039,14 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { rc = -ENOMEM; - goto exit; + goto put_local; } rc = nfc_genl_send_params(msg, local, info->snd_portid, info->snd_seq); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1105,7 +1108,7 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_LTO]) { if (dev->dep_link_up) { rc = -EINPROGRESS; - goto exit; + goto put_local; } local->lto = nla_get_u8(info->attrs[NFC_ATTR_LLC_PARAM_LTO]); @@ -1117,6 +1120,9 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NFC_ATTR_LLC_PARAM_MIUX]) local->miux = cpu_to_be16(miux); +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); @@ -1172,7 +1178,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (rc != 0) { rc = -EINVAL; - goto exit; + goto put_local; } if (!sdp_attrs[NFC_SDP_ATTR_URI]) @@ -1191,7 +1197,7 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) sdreq = nfc_llcp_build_sdreq_tlv(tid, uri, uri_len); if (sdreq == NULL) { rc = -ENOMEM; - goto exit; + goto put_local; } tlvs_len += sdreq->tlv_len; @@ -1201,10 +1207,14 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) if (hlist_empty(&sdreq_list)) { rc = -EINVAL; - goto exit; + goto put_local; } rc = nfc_llcp_send_snl_sdreq(local, &sdreq_list, tlvs_len); + +put_local: + nfc_llcp_local_put(local); + exit: device_unlock(&dev->dev); diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index de2ec66d7e83..0b1e6466f4fb 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -52,6 +52,7 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); +int nfc_llcp_local_put(struct nfc_llcp_local *local); int __init nfc_llcp_init(void); void nfc_llcp_exit(void); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); -- cgit v1.2.3-58-ga151 From 6f67fbf8192da80c4db01a1800c7fceaca9cf1f9 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Mon, 19 Jun 2023 20:06:57 +0100 Subject: lib/ts_bm: reset initial match offset for every block of text The `shift` variable which indicates the offset in the string at which to start matching the pattern is initialized to `bm->patlen - 1`, but it is not reset when a new block is retrieved. This means the implemen- tation may start looking at later and later positions in each successive block and miss occurrences of the pattern at the beginning. E.g., consider a HTTP packet held in a non-linear skb, where the HTTP request line occurs in the second block: [... 52 bytes of packet headers ...] GET /bmtest HTTP/1.1\r\nHost: www.example.com\r\n\r\n and the pattern is "GET /bmtest". Once the first block comprising the packet headers has been examined, `shift` will be pointing to somewhere near the end of the block, and so when the second block is examined the request line at the beginning will be missed. Reinitialize the variable for each new block. Fixes: 8082e4ed0a61 ("[LIB]: Boyer-Moore extension for textsearch infrastructure strike #2") Link: https://bugzilla.netfilter.org/show_bug.cgi?id=1390 Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- lib/ts_bm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/lib/ts_bm.c b/lib/ts_bm.c index 1f2234221dd1..c8ecbf74ef29 100644 --- a/lib/ts_bm.c +++ b/lib/ts_bm.c @@ -60,10 +60,12 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state) struct ts_bm *bm = ts_config_priv(conf); unsigned int i, text_len, consumed = state->offset; const u8 *text; - int shift = bm->patlen - 1, bs; + int bs; const u8 icase = conf->flags & TS_IGNORECASE; for (;;) { + int shift = bm->patlen - 1; + text_len = conf->get_next_block(consumed, &text, conf, state); if (unlikely(text_len == 0)) -- cgit v1.2.3-58-ga151 From ff0a3a7d52ff7282dbd183e7fc29a1fe386b0c30 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 21 Jun 2023 17:56:53 +0200 Subject: netfilter: conntrack: dccp: copy entire header to stack buffer, not just basic one Eric Dumazet says: nf_conntrack_dccp_packet() has an unique: dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); And nothing more is 'pulled' from the packet, depending on the content. dh->dccph_doff, and/or dh->dccph_x ...) So dccp_ack_seq() is happily reading stuff past the _dh buffer. BUG: KASAN: stack-out-of-bounds in nf_conntrack_dccp_packet+0x1134/0x11c0 Read of size 4 at addr ffff000128f66e0c by task syz-executor.2/29371 [..] Fix this by increasing the stack buffer to also include room for the extra sequence numbers and all the known dccp packet type headers, then pull again after the initial validation of the basic header. While at it, mark packets invalid that lack 48bit sequence bit but where RFC says the type MUST use them. Compile tested only. v2: first skb_header_pointer() now needs to adjust the size to only pull the generic header. (Eric) Heads-up: I intend to remove dccp conntrack support later this year. Fixes: 2bc780499aa3 ("[NETFILTER]: nf_conntrack: add DCCP protocol support") Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_dccp.c | 52 +++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index c1557d47ccd1..d4fd626d2b8c 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -432,9 +432,19 @@ static bool dccp_error(const struct dccp_hdr *dh, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { + static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST | + 1 << DCCP_PKT_RESPONSE | + 1 << DCCP_PKT_CLOSEREQ | + 1 << DCCP_PKT_CLOSE | + 1 << DCCP_PKT_RESET | + 1 << DCCP_PKT_SYNC | + 1 << DCCP_PKT_SYNCACK; unsigned int dccp_len = skb->len - dataoff; unsigned int cscov; const char *msg; + u8 type; + + BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG); if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) || dh->dccph_doff * 4 > dccp_len) { @@ -459,34 +469,70 @@ static bool dccp_error(const struct dccp_hdr *dh, goto out_invalid; } - if (dh->dccph_type >= DCCP_PKT_INVALID) { + type = dh->dccph_type; + if (type >= DCCP_PKT_INVALID) { msg = "nf_ct_dccp: reserved packet type "; goto out_invalid; } + + if (test_bit(type, &require_seq48) && !dh->dccph_x) { + msg = "nf_ct_dccp: type lacks 48bit sequence numbers"; + goto out_invalid; + } + return false; out_invalid: nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg); return true; } +struct nf_conntrack_dccp_buf { + struct dccp_hdr dh; /* generic header part */ + struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */ + union { /* depends on header type */ + struct dccp_hdr_ack_bits ack; + struct dccp_hdr_request req; + struct dccp_hdr_response response; + struct dccp_hdr_reset rst; + } u; +}; + +static struct dccp_hdr * +dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh, + struct nf_conntrack_dccp_buf *buf) +{ + unsigned int hdrlen = __dccp_hdr_len(dh); + + if (hdrlen > sizeof(*buf)) + return NULL; + + return skb_header_pointer(skb, offset, hdrlen, buf); +} + int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - struct dccp_hdr _dh, *dh; + struct nf_conntrack_dccp_buf _dh; u_int8_t type, old_state, new_state; enum ct_dccp_roles role; unsigned int *timeouts; + struct dccp_hdr *dh; - dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh); + dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh); if (!dh) return NF_DROP; if (dccp_error(dh, skb, dataoff, state)) return -NF_ACCEPT; + /* pull again, including possible 48 bit sequences and subtype header */ + dh = dccp_header_pointer(skb, dataoff, dh, &_dh); + if (!dh) + return NF_DROP; + type = dh->dccph_type; if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) return -NF_ACCEPT; -- cgit v1.2.3-58-ga151 From f18e7122cc73d9218930156fa38f050a2e37de57 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 22 Jun 2023 23:11:01 -0700 Subject: linux/netfilter.h: fix kernel-doc warnings kernel-doc does not support DECLARE_PER_CPU(), so don't mark it with kernel-doc notation. One comment block is not kernel-doc notation, so just use "/*" to begin the comment. Quietens these warnings: netfilter.h:493: warning: Function parameter or member 'bool' not described in 'DECLARE_PER_CPU' netfilter.h:493: warning: Function parameter or member 'nf_skb_duplicated' not described in 'DECLARE_PER_CPU' netfilter.h:493: warning: expecting prototype for nf_skb_duplicated(). Prototype was for DECLARE_PER_CPU() instead netfilter.h:496: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Contains bitmask of ctnetlink event subscribers, if any. Fixes: e7c8899f3e6f ("netfilter: move tee_active to core") Fixes: fdf6491193e4 ("netfilter: ctnetlink: make event listener tracking global") Signed-off-by: Randy Dunlap Reviewed-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0762444e3767..d4fed4c508ca 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -481,7 +481,7 @@ struct nfnl_ct_hook { }; extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; -/** +/* * nf_skb_duplicated - TEE target has sent a packet * * When a xtables target sends a packet, the OUTPUT and POSTROUTING @@ -492,7 +492,7 @@ extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; */ DECLARE_PER_CPU(bool, nf_skb_duplicated); -/** +/* * Contains bitmask of ctnetlink event subscribers, if any. * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. */ -- cgit v1.2.3-58-ga151 From f188d30087480eab421cd8ca552fb15f55d57f4d Mon Sep 17 00:00:00 2001 From: "Ilia.Gavrilov" Date: Fri, 23 Jun 2023 11:23:46 +0000 Subject: netfilter: nf_conntrack_sip: fix the ct_sip_parse_numerical_param() return value. ct_sip_parse_numerical_param() returns only 0 or 1 now. But process_register_request() and process_register_response() imply checking for a negative value if parsing of a numerical header parameter failed. The invocation in nf_nat_sip() looks correct: if (ct_sip_parse_numerical_param(...) > 0 && ...) { ... } Make the return value of the function ct_sip_parse_numerical_param() a tristate to fix all the cases a) return 1 if value is found; *val is set b) return 0 if value is not found; *val is unchanged c) return -1 on error; *val is undefined Found by InfoTeCS on behalf of Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0f32a40fc91a ("[NETFILTER]: nf_conntrack_sip: create signalling expectations") Signed-off-by: Ilia.Gavrilov Reviewed-by: Simon Horman Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_sip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 77f5e82d8e3f..d0eac27f6ba0 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -611,7 +611,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, start += strlen(name); *val = simple_strtoul(start, &end, 0); if (start == end) - return 0; + return -1; if (matchoff && matchlen) { *matchoff = start - dptr; *matchlen = end - start; -- cgit v1.2.3-58-ga151 From 3e70489721b6c870252c9082c496703677240f53 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 26 Jun 2023 00:42:18 +0200 Subject: netfilter: nf_tables: unbind non-anonymous set if rule construction fails Otherwise a dangling reference to a rule object that is gone remains in the set binding list. Fixes: 26b5a5712eb8 ("netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4c7937fd803f..1d64c163076a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5343,6 +5343,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); + else + list_del_rcu(&binding->list); set->use--; break; -- cgit v1.2.3-58-ga151 From b389139f12f287b8ed2e2628b72df89a081f0b59 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 26 Jun 2023 00:42:19 +0200 Subject: netfilter: nf_tables: fix underflow in chain reference counter Set element addition error path decrements reference counter on chains twice: once on element release and again via nft_data_release(). Then, d6b478666ffa ("netfilter: nf_tables: fix underflow in object reference counter") incorrectly fixed this by removing the stateful object reference count decrement. Restore the stateful object decrement as in b91d90368837 ("netfilter: nf_tables: fix leaking object reference count") and let nft_data_release() decrement the chain reference counter, so this is done only once. Fixes: d6b478666ffa ("netfilter: nf_tables: fix underflow in object reference counter") Fixes: 628bd3e49cba ("netfilter: nf_tables: drop map element references from preparation phase") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1d64c163076a..c742918f22a4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6771,7 +6771,9 @@ err_set_full: err_element_clash: kfree(trans); err_elem_free: - nft_set_elem_destroy(set, elem.priv, true); + nf_tables_set_elem_destroy(ctx, set, elem.priv); + if (obj) + obj->use--; err_parse_data: if (nla[NFTA_SET_ELEM_DATA] != NULL) nft_data_release(&elem.data.val, desc.type); -- cgit v1.2.3-58-ga151 From 8a9922e7be6d042fa00f894c376473b17a162b66 Mon Sep 17 00:00:00 2001 From: Cambda Zhu Date: Mon, 26 Jun 2023 17:33:47 +0800 Subject: ipvlan: Fix return value of ipvlan_queue_xmit() ipvlan_queue_xmit() should return NET_XMIT_XXX, but ipvlan_xmit_mode_l2/l3() returns rx_handler_result_t or NET_RX_XXX in some cases. ipvlan_rcv_frame() will only return RX_HANDLER_CONSUMED in ipvlan_xmit_mode_l2/l3() because 'local' is true. It's equal to NET_XMIT_SUCCESS. But dev_forward_skb() can return NET_RX_SUCCESS or NET_RX_DROP, and returning NET_RX_DROP(NET_XMIT_DROP) will increase both ipvlan and ipvlan->phy_dev drops counter. The skb to forward can be treated as xmitted successfully. This patch makes ipvlan_queue_xmit() return NET_XMIT_SUCCESS for forward skb. Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: Cambda Zhu Link: https://lore.kernel.org/r/20230626093347.7492-1-cambda@linux.alibaba.com Signed-off-by: Paolo Abeni --- drivers/net/ipvlan/ipvlan_core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index ab5133eb1d51..e45817caaee8 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -585,7 +585,8 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); return NET_XMIT_DROP; } - return ipvlan_rcv_frame(addr, &skb, true); + ipvlan_rcv_frame(addr, &skb, true); + return NET_XMIT_SUCCESS; } } out: @@ -611,7 +612,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); return NET_XMIT_DROP; } - return ipvlan_rcv_frame(addr, &skb, true); + ipvlan_rcv_frame(addr, &skb, true); + return NET_XMIT_SUCCESS; } } skb = skb_share_check(skb, GFP_ATOMIC); @@ -623,7 +625,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) * the skb for the main-dev. At the RX side we just return * RX_PASS for it to be processed further on the stack. */ - return dev_forward_skb(ipvlan->phy_dev, skb); + dev_forward_skb(ipvlan->phy_dev, skb); + return NET_XMIT_SUCCESS; } else if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); -- cgit v1.2.3-58-ga151 From eaaacb085144e7e950061bfd6d097eb87f7513d7 Mon Sep 17 00:00:00 2001 From: Davide Tronchin Date: Mon, 26 Jun 2023 14:53:36 +0200 Subject: net: usb: qmi_wwan: add u-blox 0x1312 composition Add RmNet support for LARA-R6 01B. The new LARA-R6 product variant identified by the "01B" string can be configured (by AT interface) in three different USB modes: * Default mode (Vendor ID: 0x1546 Product ID: 0x1311) with 4 serial interfaces * RmNet mode (Vendor ID: 0x1546 Product ID: 0x1312) with 4 serial interfaces and 1 RmNet virtual network interface * CDC-ECM mode (Vendor ID: 0x1546 Product ID: 0x1313) with 4 serial interface and 1 CDC-ECM virtual network interface The first 4 interfaces of all the 3 configurations (default, RmNet, ECM) are the same. In RmNet mode LARA-R6 01B exposes the following interfaces: If 0: Diagnostic If 1: AT parser If 2: AT parser If 3: AT parset/alternative functions If 4: RMNET interface Signed-off-by: Davide Tronchin Link: https://lore.kernel.org/r/20230626125336.3127-1-davide.tronchin.94@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 2e7c7b0cdc54..417f7ea1fffa 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1427,6 +1427,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ + {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ /* 4. Gobi 1000 devices */ -- cgit v1.2.3-58-ga151 From d06f925f13976ab82167c93467c70a337a0a3cda Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 26 Jun 2023 18:44:02 +0300 Subject: net: dsa: avoid suspicious RCU usage for synced VLAN-aware MAC addresses When using the felix driver (the only one which supports UC filtering and MC filtering) as a DSA master for a random other DSA switch, one can see the following stack trace when the downstream switch ports join a VLAN-aware bridge: ============================= WARNING: suspicious RCU usage ----------------------------- net/8021q/vlan_core.c:238 suspicious rcu_dereference_protected() usage! stack backtrace: Workqueue: dsa_ordered dsa_slave_switchdev_event_work Call trace: lockdep_rcu_suspicious+0x170/0x210 vlan_for_each+0x8c/0x188 dsa_slave_sync_uc+0x128/0x178 __hw_addr_sync_dev+0x138/0x158 dsa_slave_set_rx_mode+0x58/0x70 __dev_set_rx_mode+0x88/0xa8 dev_uc_add+0x74/0xa0 dsa_port_bridge_host_fdb_add+0xec/0x180 dsa_slave_switchdev_event_work+0x7c/0x1c8 process_one_work+0x290/0x568 What it's saying is that vlan_for_each() expects rtnl_lock() context and it's not getting it, when it's called from the DSA master's ndo_set_rx_mode(). The caller of that - dsa_slave_set_rx_mode() - is the slave DSA interface's dsa_port_bridge_host_fdb_add() which comes from the deferred dsa_slave_switchdev_event_work(). We went to great lengths to avoid the rtnl_lock() context in that call path in commit 0faf890fc519 ("net: dsa: drop rtnl_lock from dsa_slave_switchdev_event_work"), and calling rtnl_lock() is simply not an option due to the possibility of deadlocking when calling dsa_flush_workqueue() from the call paths that do hold rtnl_lock() - basically all of them. So, when the DSA master calls vlan_for_each() from its ndo_set_rx_mode(), the state of the 8021q driver on this device is really not protected from concurrent access by anything. Looking at net/8021q/, I don't think that vlan_info->vid_list was particularly designed with RCU traversal in mind, so introducing an RCU read-side form of vlan_for_each() - vlan_for_each_rcu() - won't be so easy, and it also wouldn't be exactly what we need anyway. In general I believe that the solution isn't in net/8021q/ anyway; vlan_for_each() is not cut out for this task. DSA doesn't need rtnl_lock() to be held per se - since it's not a netdev state change that we're blocking, but rather, just concurrent additions/removals to a VLAN list. We don't even need sleepable context - the callback of vlan_for_each() just schedules deferred work. The proposed escape is to remove the dependency on vlan_for_each() and to open-code a non-sleepable, rtnl-free alternative to that, based on copies of the VLAN list modified from .ndo_vlan_rx_add_vid() and .ndo_vlan_rx_kill_vid(). Fixes: 64fdc5f341db ("net: dsa: sync unicast and multicast addresses for VLAN filters too") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20230626154402.3154454-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 12 ++++++-- net/dsa/dsa.c | 2 +- net/dsa/slave.c | 84 ++++++++++++++++++++++++++++++++++++++----------------- net/dsa/switch.c | 4 +-- net/dsa/switch.h | 3 ++ 5 files changed, 74 insertions(+), 31 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index ab0f0a5b0860..197c5a6ca8f7 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -314,9 +314,17 @@ struct dsa_port { struct list_head fdbs; struct list_head mdbs; - /* List of VLANs that CPU and DSA ports are members of. */ struct mutex vlans_lock; - struct list_head vlans; + union { + /* List of VLANs that CPU and DSA ports are members of. + * Access to this is serialized by the sleepable @vlans_lock. + */ + struct list_head vlans; + /* List of VLANs that user ports are members of. + * Access to this is serialized by netif_addr_lock_bh(). + */ + struct list_head user_vlans; + }; }; /* TODO: ideally DSA ports would have a single dp->link_dp member, diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1afed89e03c0..ccbdb98109f8 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1106,7 +1106,7 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) mutex_init(&dp->vlans_lock); INIT_LIST_HEAD(&dp->fdbs); INIT_LIST_HEAD(&dp->mdbs); - INIT_LIST_HEAD(&dp->vlans); + INIT_LIST_HEAD(&dp->vlans); /* also initializes &dp->user_vlans */ INIT_LIST_HEAD(&dp->list); list_add_tail(&dp->list, &dst->ports); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 165bb2cb8431..527b1d576460 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -27,6 +27,7 @@ #include "master.h" #include "netlink.h" #include "slave.h" +#include "switch.h" #include "tag.h" struct dsa_switchdev_event_work { @@ -161,8 +162,7 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, return 0; } -static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid, - void *arg) +static int dsa_slave_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; @@ -170,6 +170,28 @@ static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid, ctx->addr, vid); } +static int dsa_slave_vlan_for_each(struct net_device *dev, + int (*cb)(void *arg, int vid), void *arg) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_vlan *v; + int err; + + lockdep_assert_held(&dev->addr_list_lock); + + err = cb(arg, 0); + if (err) + return err; + + list_for_each_entry(v, &dp->user_vlans, list) { + err = cb(arg, v->vid); + if (err) + return err; + } + + return 0; +} + static int dsa_slave_sync_uc(struct net_device *dev, const unsigned char *addr) { @@ -180,18 +202,14 @@ static int dsa_slave_sync_uc(struct net_device *dev, .addr = addr, .event = DSA_UC_ADD, }; - int err; dev_uc_add(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } static int dsa_slave_unsync_uc(struct net_device *dev, @@ -204,18 +222,14 @@ static int dsa_slave_unsync_uc(struct net_device *dev, .addr = addr, .event = DSA_UC_DEL, }; - int err; dev_uc_del(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } static int dsa_slave_sync_mc(struct net_device *dev, @@ -228,18 +242,14 @@ static int dsa_slave_sync_mc(struct net_device *dev, .addr = addr, .event = DSA_MC_ADD, }; - int err; dev_mc_add(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } static int dsa_slave_unsync_mc(struct net_device *dev, @@ -252,18 +262,14 @@ static int dsa_slave_unsync_mc(struct net_device *dev, .addr = addr, .event = DSA_MC_DEL, }; - int err; dev_mc_del(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - err = dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0); - if (err) - return err; - - return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); + return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + &ctx); } void dsa_slave_sync_ha(struct net_device *dev) @@ -1759,6 +1765,7 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; + struct dsa_vlan *v; int ret; /* User port... */ @@ -1782,8 +1789,17 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, !dsa_switch_supports_mc_filtering(ds)) return 0; + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) { + ret = -ENOMEM; + goto rollback; + } + netif_addr_lock_bh(dev); + v->vid = vid; + list_add_tail(&v->list, &dp->user_vlans); + if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, @@ -1803,6 +1819,12 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, dsa_flush_workqueue(); return 0; + +rollback: + dsa_port_host_vlan_del(dp, &vlan); + dsa_port_vlan_del(dp, &vlan); + + return ret; } static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, @@ -1816,6 +1838,7 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; + struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); @@ -1832,6 +1855,15 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, netif_addr_lock_bh(dev); + v = dsa_vlan_find(&dp->user_vlans, &vlan); + if (!v) { + netif_addr_unlock_bh(dev); + return -ENOENT; + } + + list_del(&v->list); + kfree(v); + if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 8c9a9f94b756..1a42f9317334 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -673,8 +673,8 @@ static bool dsa_port_host_vlan_match(struct dsa_port *dp, return false; } -static struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, - const struct switchdev_obj_port_vlan *vlan) +struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, + const struct switchdev_obj_port_vlan *vlan) { struct dsa_vlan *v; diff --git a/net/dsa/switch.h b/net/dsa/switch.h index 15e67b95eb6e..ea034677da15 100644 --- a/net/dsa/switch.h +++ b/net/dsa/switch.h @@ -111,6 +111,9 @@ struct dsa_notifier_master_state_info { bool operational; }; +struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, + const struct switchdev_obj_port_vlan *vlan); + int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); int dsa_broadcast(unsigned long e, void *v); -- cgit v1.2.3-58-ga151 From 25a9c8a4431c364f97f75558cb346d2ad3f53fbb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 26 Jun 2023 09:43:13 -0700 Subject: netlink: Add __sock_i_ino() for __netlink_diag_dump(). syzbot reported a warning in __local_bh_enable_ip(). [0] Commit 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") converted read_lock(&nl_table_lock) to read_lock_irqsave() in __netlink_diag_dump() to prevent a deadlock. However, __netlink_diag_dump() calls sock_i_ino() that uses read_lock_bh() and read_unlock_bh(). If CONFIG_TRACE_IRQFLAGS=y, read_unlock_bh() finally enables IRQ even though it should stay disabled until the following read_unlock_irqrestore(). Using read_lock() in sock_i_ino() would trigger a lockdep splat in another place that was fixed in commit f064af1e500a ("net: fix a lockdep splat"), so let's add __sock_i_ino() that would be safe to use under BH disabled. [0]: WARNING: CPU: 0 PID: 5012 at kernel/softirq.c:376 __local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Modules linked in: CPU: 0 PID: 5012 Comm: syz-executor487 Not tainted 6.4.0-rc7-syzkaller-00202-g6f68fc395f49 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/27/2023 RIP: 0010:__local_bh_enable_ip+0xbe/0x130 kernel/softirq.c:376 Code: 45 bf 01 00 00 00 e8 91 5b 0a 00 e8 3c 15 3d 00 fb 65 8b 05 ec e9 b5 7e 85 c0 74 58 5b 5d c3 65 8b 05 b2 b6 b4 7e 85 c0 75 a2 <0f> 0b eb 9e e8 89 15 3d 00 eb 9f 48 89 ef e8 6f 49 18 00 eb a8 0f RSP: 0018:ffffc90003a1f3d0 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000201 RCX: 1ffffffff1cf5996 RDX: 0000000000000000 RSI: 0000000000000201 RDI: ffffffff8805c6f3 RBP: ffffffff8805c6f3 R08: 0000000000000001 R09: ffff8880152b03a3 R10: ffffed1002a56074 R11: 0000000000000005 R12: 00000000000073e4 R13: dffffc0000000000 R14: 0000000000000002 R15: 0000000000000000 FS: 0000555556726300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000045ad50 CR3: 000000007c646000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: sock_i_ino+0x83/0xa0 net/core/sock.c:2559 __netlink_diag_dump+0x45c/0x790 net/netlink/diag.c:171 netlink_diag_dump+0xd6/0x230 net/netlink/diag.c:207 netlink_dump+0x570/0xc50 net/netlink/af_netlink.c:2269 __netlink_dump_start+0x64b/0x910 net/netlink/af_netlink.c:2374 netlink_dump_start include/linux/netlink.h:329 [inline] netlink_diag_handler_dump+0x1ae/0x250 net/netlink/diag.c:238 __sock_diag_cmd net/core/sock_diag.c:238 [inline] sock_diag_rcv_msg+0x31e/0x440 net/core/sock_diag.c:269 netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2547 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:280 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x925/0xe30 net/netlink/af_netlink.c:1914 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0xde/0x190 net/socket.c:747 ____sys_sendmsg+0x71c/0x900 net/socket.c:2503 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2557 __sys_sendmsg+0xf7/0x1c0 net/socket.c:2586 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5303aaabb9 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 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 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc7506e548 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f5303aaabb9 RDX: 0000000000000000 RSI: 0000000020000180 RDI: 0000000000000003 RBP: 00007f5303a6ed60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f5303a6edf0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Fixes: 8d61f926d420 ("netlink: fix potential deadlock in netlink_set_err()") Reported-by: syzbot+5da61cf6a9bc1902d422@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=5da61cf6a9bc1902d422 Suggested-by: Eric Dumazet Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230626164313.52528-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 1 + net/core/sock.c | 17 ++++++++++++++--- net/netlink/diag.c | 2 +- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 6f428a7f3567..ad468fe71413 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2100,6 +2100,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) } kuid_t sock_i_uid(struct sock *sk); +unsigned long __sock_i_ino(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) diff --git a/net/core/sock.c b/net/core/sock.c index 6e5662ca00fe..4a0edccf8606 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2550,13 +2550,24 @@ kuid_t sock_i_uid(struct sock *sk) } EXPORT_SYMBOL(sock_i_uid); -unsigned long sock_i_ino(struct sock *sk) +unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock_bh(&sk->sk_callback_lock); + read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock_bh(&sk->sk_callback_lock); + read_unlock(&sk->sk_callback_lock); + return ino; +} +EXPORT_SYMBOL(__sock_i_ino); + +unsigned long sock_i_ino(struct sock *sk) +{ + unsigned long ino; + + local_bh_disable(); + ino = __sock_i_ino(sk); + local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 4143b2ea4195..e4f21b1067bc 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -168,7 +168,7 @@ mc_list: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - sock_i_ino(sk)) < 0) { + __sock_i_ino(sk)) < 0) { ret = 1; break; } -- cgit v1.2.3-58-ga151