Skip to contentSkip to conversation

i40e: fix races in PTP external timestamp work handling

PATCH In review [email protected] 3 participants 6 messages Jul 24 – Aug 5

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 i40e: fix races in PTP external timestamp work handling

From: Xuanqiang Luo <[email protected]>

The time sync interrupt queues ptp_extts0_work, which reads device registers and reports events through pf->ptp_clock.

i40e_ptp_stop() unregisters the PHC without first disabling the event source or draining the work. The worker can therefore access the clock or PF after either has been freed, causing a use-after-free. Disable external timestamp events and call disable_work_sync() before unregistering the PHC. Disabling the work also prevents an interrupt already in progress from queuing it after the drain.

INIT_WORK() is called from i40e_ptp_set_timestamp_mode(), which runs on reset and whenever timestamping is reconfigured. Reinitializing pending or running work can corrupt its workqueue state. Initialize the work once from i40e_sw_init() instead.

Also exclude reset recovery before stopping PTP so a concurrent rebuild cannot re-enable timestamp events or recreate the PHC during removal.

Fixes 1050713026a0 ("i40e: add support for PTP external synchronization clock")
---
 drivers/net/ethernet/intel/i40e/i40e.h      |  1 +
 drivers/net/ethernet/intel/i40e/i40e_main.c | 17 +++++++-------
 drivers/net/ethernet/intel/i40e/i40e_ptp.c  | 25 +++++++++++++++------
 3 files changed, 28 insertions(+), 15 deletions(-)
drivers/net/ethernet/intel/i40e/i40e.h +1 -0
index 83e780919ac97..e2ae61bc38786 100644
@@ -1315,6 +1315,7 @@ int i40e_ptp_hwtstamp_set(struct net_device *netdev,
 			  struct netlink_ext_ack *extack);
 void i40e_ptp_save_hw_time(struct i40e_pf *pf);
 void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
+void i40e_ptp_init_work(struct i40e_pf *pf);
 void i40e_ptp_init(struct i40e_pf *pf);
 void i40e_ptp_stop(struct i40e_pf *pf);
 int i40e_ptp_alloc_pins(struct i40e_pf *pf);
drivers/net/ethernet/intel/i40e/i40e_main.c +9 -8
index a04683004a567..2909a58d57562 100644
@@ -12819,6 +12819,7 @@ static int i40e_sw_init(struct i40e_pf *pf)
 			 "total-port-shutdown was enabled, link-down-on-close is forced on\n");
 	}
 	mutex_init(&pf->switch_mutex);
+	i40e_ptp_init_work(pf);
 
 sw_init_done:
 	return err;
@@ -16157,14 +16158,6 @@ static void i40e_remove(struct pci_dev *pdev)
 
 	i40e_devlink_unregister(pf);
 
-	i40e_dbg_pf_exit(pf);
-
-	i40e_ptp_stop(pf);
-
-	/* Disable RSS in hw */
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
-
 	/* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE
 	 * flags, once they are set, i40e_rebuild should not be called as
 	 * i40e_prep_for_reset always returns early.
@@ -16173,6 +16166,14 @@ static void i40e_remove(struct pci_dev *pdev)
 		usleep_range(1000, 2000);
 	set_bit(__I40E_IN_REMOVE, pf->state);
 
+	i40e_dbg_pf_exit(pf);
+
+	i40e_ptp_stop(pf);
+
+	/* Disable RSS in hw */
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
+
 	if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags)) {
 		set_bit(__I40E_VF_RESETS_DISABLED, pf->state);
 		i40e_free_vfs(pf);
drivers/net/ethernet/intel/i40e/i40e_ptp.c +18 -7
index ff62b5f2c8150..fd51ab8c10c20 100644
@@ -169,6 +169,17 @@ static void i40e_ptp_extts0_work(struct work_struct *work)
 	ptp_clock_event(pf->ptp_clock, &event);
 }
 
+/**
+ * i40e_ptp_init_work - Initialize PTP work for a PF
+ * @pf: Board private structure
+ *
+ * Initialize work which must remain valid for the lifetime of the PF.
+ */
+void i40e_ptp_init_work(struct i40e_pf *pf)
+{
+	INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
+}
+
 /**
  * i40e_is_ptp_pin_dev - check if device supports PTP pins
  * @hw: pointer to the hardware structure
@@ -1186,8 +1197,6 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 	regval |= 1 << I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT;
 	wr32(hw, I40E_PRTTSYN_CTL0, regval);
 
-	INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
-
 	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		pf->ptp_tx = false;
@@ -1541,6 +1550,13 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 	struct i40e_hw *hw = &pf->hw;
 	u32 regval;
 
+	/* Stop external timestamp events before unregistering the clock. */
+	regval = rd32(hw, I40E_PRTTSYN_CTL0);
+	regval &= ~I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK;
+	wr32(hw, I40E_PRTTSYN_CTL0, regval);
+
+	disable_work_sync(&pf->ptp_extts0_work);
+
 	clear_bit(I40E_FLAG_PTP_ENA, pf->flags);
 	pf->ptp_tx = false;
 	pf->ptp_rx = false;
@@ -1570,10 +1586,5 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 	regval &= ~I40E_PRTTSYN_AUX_0_PTPFLAG_MASK;
 	wr32(hw, I40E_PRTTSYN_AUX_0(0), regval);
 
-	/* Disable interrupts */
-	regval = rd32(hw, I40E_PRTTSYN_CTL0);
-	regval &= ~I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK;
-	wr32(hw, I40E_PRTTSYN_CTL0, regval);
-
 	i40e_ptp_free_pins(pf);
 }
Signature · 1 line
2.43.0
reviewer
#1 lore raw

This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
Full review at: https://sashiko.dev/#/patchset/[email protected]?part=1
---
--- Patch [1]: [PATCH iwl-net v1] i40e: fix races in PTP external timestamp work handling --- commit 4359cf206cb2602e153fdeac3151f8d4bacf9195
Author: Xuanqiang Luo <[email protected]>

i40e: fix races in PTP external timestamp work handling

This commit disables external timestamp events and drains the work queue before unregistering the PHC to fix a use-after-free, and moves the work initialization to device init instead of reset. It also excludes reset recovery during teardown to avoid concurrent rebuilds.

Quoted 4 lines
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -0
index a04683004a567..2909a58d57562 100644

[ ... ]

Quoted 16 lines
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -8
@@ -16157,14 +16158,6 @@ static void i40e_remove(struct pci_dev *pdev)
 
 	i40e_devlink_unregister(pf);
 
-	i40e_dbg_pf_exit(pf);
-
-	i40e_ptp_stop(pf);
-
-	/* Disable RSS in hw */
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
-
 	/* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE
 	 * flags, once they are set, i40e_rebuild should not be called as
 	 * i40e_prep_for_reset always returns early.

drivers/net/ethernet/intel/i40e/i40e_main.c static void i40e_remove(struct pci_dev *pdev) · line 16166

Quoted 1 line
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -0
@@ -16173,6 +16166,14 @@ static void i40e_remove(struct pci_dev *pdev)
 		usleep_range(1000, 2000);

Simon says: I think the issue flagged below is somewhat orthogonal to
this patch and can be considered in the context of possible follow-up.

[Severity: High]
This is a pre-existing issue, but does this ad-hoc polling loop violate core networking synchronization rules?

The subsystem guidelines state that using retry/poll loops on flags to guard code sections is a bug, as it evades lockdep deadlock detection and lacks proper memory ordering guarantees.

i40e_remove() spins on __I40E_RESET_RECOVERY_PENDING with a sleep instead of using a standard lock or workqueue synchronization, which exposes the teardown path to races during hotplug or PCIe AER unbinds.

Quoted 5 lines
drivers/net/ethernet/intel/i40e/i40e_main.c +3 -0
 	set_bit(__I40E_IN_REMOVE, pf->state);
 
+	i40e_dbg_pf_exit(pf);
+
+	i40e_ptp_stop(pf);

[ ... ]

Quoted 4 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
index ff62b5f2c8150..fd51ab8c10c20 100644

[ ... ]

drivers/net/ethernet/intel/i40e/i40e_ptp.c void i40e_ptp_stop(struct i40e_pf *pf) · line 1559

Quoted 11 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +7 -0
@@ -1541,6 +1550,13 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 	struct i40e_hw *hw = &pf->hw;
 	u32 regval;
 
+	/* Stop external timestamp events before unregistering the clock. */
+	regval = rd32(hw, I40E_PRTTSYN_CTL0);
+	regval &= ~I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK;
+	wr32(hw, I40E_PRTTSYN_CTL0, regval);
+
+	disable_work_sync(&pf->ptp_extts0_work);
+

[Severity: Medium]
Does this reordering introduce a TOCTOU race condition with the PTP ioctl?

The flag I40E_FLAG_PTP_ENA is still set here while we disable the workqueue. Because i40e_remove() does not hold the rtnl_lock(), a concurrent SIOCSHWTSTAMP ioctl could execute i40e_ptp_hwtstamp_set().

Since the ioctl checks I40E_FLAG_PTP_ENA, it might observe it as still set and call i40e_ptp_set_timestamp_mode(). This would overwrite I40E_PRTTSYN_CTL0 and re-enable hardware interrupts immediately after i40e_ptp_stop() just disabled them, leaving the device generating events for a disabled workqueue.

drivers/net/ethernet/intel/i40e/i40e_ptp.c

Quoted 11 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
 	clear_bit(I40E_FLAG_PTP_ENA, pf->flags);
 	pf->ptp_tx = false;
 	pf->ptp_rx = false;
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
 	if (pf->ptp_tx_skb) {
 		struct sk_buff *skb = pf->ptp_tx_skb;
 
 		pf->ptp_tx_skb = NULL;
 		clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state);
 		dev_kfree_skb_any(skb);
 	}

Simon says: Although the issue flagged below is flagged as pre-existing
I am concerned that it is exacerbated by this patch.

[Severity: High]
This is a pre-existing issue, but could this freeing pattern result in a double-free or use-after-free?

A user configuring PTP and transmitting a packet sets pf->ptp_tx_skb. The watchdog task in i40e_ptp_tx_hang() checks the timeout and reads pf->ptp_tx_skb without an atomic test-and-set claim.

If a hardware interrupt arrives at this exact time, i40e_ptp_tx_hwtstamp() can preempt the watchdog, read the exact same pointer, set it to NULL, call skb_tstamp_tx() and then dev_kfree_skb_any().

When the interrupt returns, the watchdog task resumes and frees the exact same SKB pointer again. This teardown path in i40e_ptp_stop() also forcibly frees ptp_tx_skb without atomic protections against the interrupt handler, compounding the race.

[ ... ]

#2 lore raw

Thanks Simon for the review and Sashiko for the detailed findings!

I have posted v2 addressing these concerns as follows.

Quoted 45 lines · Simon Horman

This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
Full review at:https://sashiko.dev/#/patchset/[email protected]?part=1
---
--- Patch [1]: [PATCH iwl-net v1] i40e: fix races in PTP external timestamp work handling --- commit 4359cf206cb2602e153fdeac3151f8d4bacf9195
Author: Xuanqiang Luo<[email protected]>

i40e: fix races in PTP external timestamp work handling

This commit disables external timestamp events and drains the work queue before unregistering the PHC to fix a use-after-free, and moves the work initialization to device init instead of reset. It also excludes reset recovery during teardown to avoid concurrent rebuilds.

Quoted 4 lines
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -0
index a04683004a567..2909a58d57562 100644

[ ... ]

Quoted 16 lines
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -8
@@ -16157,14 +16158,6 @@ static void i40e_remove(struct pci_dev *pdev)
 
  	i40e_devlink_unregister(pf);
 
-	i40e_dbg_pf_exit(pf);
-
-	i40e_ptp_stop(pf);
-
-	/* Disable RSS in hw */
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
-
  	/* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE
  	 * flags, once they are set, i40e_rebuild should not be called as
  	 * i40e_prep_for_reset always returns early.

drivers/net/ethernet/intel/i40e/i40e_main.c static void i40e_remove(struct pci_dev *pdev) · line 16166

Quoted 1 line
drivers/net/ethernet/intel/i40e/i40e_main.c +0 -0
@@ -16173,6 +16166,14 @@ static void i40e_remove(struct pci_dev *pdev)
  		usleep_range(1000, 2000);

Simon says: I think the issue flagged below is somewhat orthogonal to
this patch and can be considered in the context of possible
follow-up.

[Severity: High]
This is a pre-existing issue, but does this ad-hoc polling loop violate core networking synchronization rules?

Quoted 7 lines

The subsystem guidelines state that using retry/poll loops on flags to guard code sections is a bug, as it evades lockdep deadlock detection and lacks proper memory ordering guarantees.

i40e_remove() spins on __I40E_RESET_RECOVERY_PENDING with a sleep instead of using a standard lock or workqueue synchronization, which exposes the teardown path to races during hotplug or PCIe AER unbinds.

For this pre-existing issue, I included a wait-bit based fix in v2 as Patch 4.

Quoted 25 lines
Quoted 5 lines
drivers/net/ethernet/intel/i40e/i40e_main.c +3 -0
  	set_bit(__I40E_IN_REMOVE, pf->state);
 
+	i40e_dbg_pf_exit(pf);
+
+	i40e_ptp_stop(pf);

[ ... ]

Quoted 4 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
index ff62b5f2c8150..fd51ab8c10c20 100644

[ ... ]

drivers/net/ethernet/intel/i40e/i40e_ptp.c void i40e_ptp_stop(struct i40e_pf *pf) · line 1559

Quoted 11 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +7 -0
@@ -1541,6 +1550,13 @@ void i40e_ptp_stop(struct i40e_pf *pf)
  	struct i40e_hw *hw = &pf->hw;
  	u32 regval;
 
+	/* Stop external timestamp events before unregistering the clock. */
+	regval = rd32(hw, I40E_PRTTSYN_CTL0);
+	regval &= ~I40E_PRTTSYN_CTL0_EVENT_INT_ENA_MASK;
+	wr32(hw, I40E_PRTTSYN_CTL0, regval);
+
+	disable_work_sync(&pf->ptp_extts0_work);
+

[Severity: Medium]
Does this reordering introduce a TOCTOU race condition with the PTP ioctl?

Quoted 8 lines

The flag I40E_FLAG_PTP_ENA is still set here while we disable the workqueue. Because i40e_remove() does not hold the rtnl_lock(), a concurrent SIOCSHWTSTAMP ioctl could execute i40e_ptp_hwtstamp_set().

Since the ioctl checks I40E_FLAG_PTP_ENA, it might observe it as still set and call i40e_ptp_set_timestamp_mode(). This would overwrite I40E_PRTTSYN_CTL0 and re-enable hardware interrupts immediately after i40e_ptp_stop() just disabled them, leaving the device generating events for a disabled workqueue.

I agree. Patch 2 serializes timestamp configuration and PTP teardown with ptp_config_lock.

Quoted 26 lines
Quoted 11 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
  	clear_bit(I40E_FLAG_PTP_ENA, pf->flags);
  	pf->ptp_tx = false;
  	pf->ptp_rx = false;
  
  	if (pf->ptp_tx_skb) {
  		struct sk_buff *skb = pf->ptp_tx_skb;
  
  		pf->ptp_tx_skb = NULL;
  		clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state);
  		dev_kfree_skb_any(skb);
  	}

Simon says: Although the issue flagged below is flagged as pre-existing
I am concerned that it is exacerbated by this patch.

[Severity: High]
This is a pre-existing issue, but could this freeing pattern result in a double-free or use-after-free?

A user configuring PTP and transmitting a packet sets pf->ptp_tx_skb. The watchdog task in i40e_ptp_tx_hang() checks the timeout and reads pf->ptp_tx_skb without an atomic test-and-set claim.

If a hardware interrupt arrives at this exact time, i40e_ptp_tx_hwtstamp() can preempt the watchdog, read the exact same pointer, set it to NULL, call skb_tstamp_tx() and then dev_kfree_skb_any().

Quoted 6 lines

When the interrupt returns, the watchdog task resumes and frees the exact same SKB pointer again. This teardown path in i40e_ptp_stop() also forcibly frees ptp_tx_skb without atomic protections against the interrupt handler, compounding the race.

[ ... ]

I agree. Patch 1 adds ptp_tx_lock to protect the Tx timestamp slot across transmit, watchdog, interrupt, error, and stop paths.

The lock uses spin_lock_irqsave() for the hard IRQ path and is only taken for SKBTX_HW_TSTAMP packets.

Thanks,
Xuanqiang

#3 lore raw
In reply to [email protected]
Quoted 91 lines · On 24/07/2026 10:34, [email protected] wrote:

From: Xuanqiang Luo <[email protected]>

The time sync interrupt queues ptp_extts0_work, which reads device registers and reports events through pf->ptp_clock.

i40e_ptp_stop() unregisters the PHC without first disabling the event source or draining the work. The worker can therefore access the clock or PF after either has been freed, causing a use-after-free. Disable external timestamp events and call disable_work_sync() before unregistering the PHC. Disabling the work also prevents an interrupt already in progress from queuing it after the drain.

INIT_WORK() is called from i40e_ptp_set_timestamp_mode(), which runs on reset and whenever timestamping is reconfigured. Reinitializing pending or running work can corrupt its workqueue state. Initialize the work once from i40e_sw_init() instead.

Also exclude reset recovery before stopping PTP so a concurrent rebuild cannot re-enable timestamp events or recreate the PHC during removal.

Fixes 1050713026a0 ("i40e: add support for PTP external synchronization clock")
---
  drivers/net/ethernet/intel/i40e/i40e.h      |  1 +
  drivers/net/ethernet/intel/i40e/i40e_main.c | 17 +++++++-------
  drivers/net/ethernet/intel/i40e/i40e_ptp.c  | 25 +++++++++++++++------
  3 files changed, 28 insertions(+), 15 deletions(-)
drivers/net/ethernet/intel/i40e/i40e.h +1 -0
index 83e780919ac97..e2ae61bc38786 100644
@@ -1315,6 +1315,7 @@ int i40e_ptp_hwtstamp_set(struct net_device *netdev,
  			  struct netlink_ext_ack *extack);
  void i40e_ptp_save_hw_time(struct i40e_pf *pf);
  void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
+void i40e_ptp_init_work(struct i40e_pf *pf);
  void i40e_ptp_init(struct i40e_pf *pf);
  void i40e_ptp_stop(struct i40e_pf *pf);
  int i40e_ptp_alloc_pins(struct i40e_pf *pf);
drivers/net/ethernet/intel/i40e/i40e_main.c +9 -8
index a04683004a567..2909a58d57562 100644
@@ -12819,6 +12819,7 @@ static int i40e_sw_init(struct i40e_pf *pf)
  			 "total-port-shutdown was enabled, link-down-on-close is forced on\n");
  	}
  	mutex_init(&pf->switch_mutex);
+	i40e_ptp_init_work(pf);
 
  sw_init_done:
  	return err;
@@ -16157,14 +16158,6 @@ static void i40e_remove(struct pci_dev *pdev)
 
  	i40e_devlink_unregister(pf);
 
-	i40e_dbg_pf_exit(pf);
-
-	i40e_ptp_stop(pf);
-
-	/* Disable RSS in hw */
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
-	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
-
  	/* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE
  	 * flags, once they are set, i40e_rebuild should not be called as
  	 * i40e_prep_for_reset always returns early.
@@ -16173,6 +16166,14 @@ static void i40e_remove(struct pci_dev *pdev)
  		usleep_range(1000, 2000);
  	set_bit(__I40E_IN_REMOVE, pf->state);
 
+	i40e_dbg_pf_exit(pf);
+
+	i40e_ptp_stop(pf);
+
+	/* Disable RSS in hw */
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0);
+	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0);
+
  	if (test_bit(I40E_FLAG_SRIOV_ENA, pf->flags)) {
  		set_bit(__I40E_VF_RESETS_DISABLED, pf->state);
  		i40e_free_vfs(pf);
drivers/net/ethernet/intel/i40e/i40e_ptp.c +1 -0
index ff62b5f2c8150..fd51ab8c10c20 100644
@@ -169,6 +169,17 @@ static void i40e_ptp_extts0_work(struct work_struct *work)
  	ptp_clock_event(pf->ptp_clock, &event);
  }
 
+/**

drivers/net/ethernet/intel/i40e/i40e_ptp.c static void i40e_ptp_extts0_work(struct work_struct *work) · line 182

Quoted 10 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +10 -0
+ * i40e_ptp_init_work - Initialize PTP work for a PF
+ * @pf: Board private structure
+ *
+ * Initialize work which must remain valid for the lifetime of the PF.
+ */
+void i40e_ptp_init_work(struct i40e_pf *pf)
+{
+	INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
+}
+

why do you need extra function for a single line of code? why cannot you put it into i40e_ptp_init?

Quoted 12 lines
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -2
  /**
   * i40e_is_ptp_pin_dev - check if device supports PTP pins
   * @hw: pointer to the hardware structure
@@ -1186,8 +1197,6 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
  	regval |= 1 << I40E_PRTTSYN_CTL0_EVENT_INT_ENA_SHIFT;
  	wr32(hw, I40E_PRTTSYN_CTL0, regval);
 
-	INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
-
  	switch (config->tx_type) {
  	case HWTSTAMP_TX_OFF:
  		pf->ptp_tx = false;
#4 lore raw
Quoted 15 lines · Vadim Fedorenko
Quoted 14 lines · On 24/07/2026 10:34, [email protected] wrote:
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
index ff62b5f2c8150..fd51ab8c10c20 100644
@@ -169,6 +169,17 @@ static void i40e_ptp_extts0_work(struct 
 work_struct *work)
       ptp_clock_event(pf->ptp_clock, &event);
   }

  +/**
+ * i40e_ptp_init_work - Initialize PTP work for a PF
+ * @pf: Board private structure
+ *
+ * Initialize work which must remain valid for the lifetime of the PF.

Quoted 10 lines

drivers/net/ethernet/intel/i40e/i40e_ptp.c static void i40e_ptp_extts0_work(struct work_struct *work) · line 182

Quoted 6 lines

+ */

drivers/net/ethernet/intel/i40e/i40e_ptp.c +5 -0
+void i40e_ptp_init_work(struct i40e_pf *pf)
+{
+    INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
+}
+

why do you need extra function for a single line of code? why cannot you put it into i40e_ptp_init?

Thanks for pointing this out.

i40e_ptp_init() is also called from the reset/rebuild path:

i40e_service_task()

    -> i40e_reset_subtask()
      -> i40e_reset_and_rebuild()
        -> i40e_rebuild()
          -> i40e_setup_pf_switch()
            -> i40e_ptp_init()

Putting INIT_WORK() there would reinitialize the work item during reset or recovery. If the work is pending or running, this races with the workqueue, resets its bookkeeping, and breaks the workqueue's non-reentrance guarantee.

The work item is therefore initialized once per PF from i40e_sw_init(). The helper also keeps the work callback private to i40e_ptp.c.

#5 lore raw
Quoted 38 lines · luoxuanqiang
Quoted 15 lines · Vadim Fedorenko
Quoted 14 lines · On 24/07/2026 10:34, [email protected] wrote:
drivers/net/ethernet/intel/i40e/i40e_ptp.c +0 -0
index ff62b5f2c8150..fd51ab8c10c20 100644
@@ -169,6 +169,17 @@ static void i40e_ptp_extts0_work(struct 
 work_struct *work)
       ptp_clock_event(pf->ptp_clock, &event);
   }

  +/**
+ * i40e_ptp_init_work - Initialize PTP work for a PF
+ * @pf: Board private structure
+ *
+ * Initialize work which must remain valid for the lifetime of the PF.

Quoted 10 lines

drivers/net/ethernet/intel/i40e/i40e_ptp.c static void i40e_ptp_extts0_work(struct work_struct *work) · line 182

Quoted 6 lines

+ */

drivers/net/ethernet/intel/i40e/i40e_ptp.c +5 -0
+void i40e_ptp_init_work(struct i40e_pf *pf)
+{
+    INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work);
+}
+

why do you need extra function for a single line of code? why cannot you put it into i40e_ptp_init?

Thanks for pointing this out.

i40e_ptp_init() is also called from the reset/rebuild path:

  i40e_service_task()
    -> i40e_reset_subtask()
      -> i40e_reset_and_rebuild()
        -> i40e_rebuild()
          -> i40e_setup_pf_switch()
            -> i40e_ptp_init()

Quoted 4 lines

Putting INIT_WORK() there would reinitialize the work item during reset or recovery. If the work is pending or running, this races with the workqueue, resets its bookkeeping, and breaks the workqueue's non-reentrance guarantee.

ok, but then this driver has bigger problem. the same i40e_ptp_init() re-inits tmreg_lock mutex and ptp_rx_lock spinlock. While latter might be ok during reset (hopefully no traffic processed while the nic is in reset), tmreg_lock mutex can be used for adjfine/adjtime/gettimex64/ settime64 callbacks as ptp device is still visible to user space.

I believe ptp part of the driver has to be redesigned properly.

Quoted 3 lines

The work item is therefore initialized once per PF from i40e_sw_init(). The helper also keeps the work callback private to i40e_ptp.c.