diff mbox series

[net,v2,1/7] eth: tg3: fix calling napi_enable() in atomic context

Message ID 20250123004520.806855-2-kuba@kernel.org (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series eth: fix calling napi_enable() in atomic context | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag present in non-next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 9 of 9 maintainers
netdev/build_clang success Errors and warnings before: 1 this patch: 1
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 179 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 2 this patch: 2
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2025-01-23--12-00 (tests: 878)

Commit Message

Jakub Kicinski Jan. 23, 2025, 12:45 a.m. UTC
tg3 has a spin lock protecting most of the config,
switch to taking netdev_lock() explicitly on enable/start
paths. Disable/stop paths seem to not be under the spin
lock (since napi_disable() already needs to sleep),
so leave that side as is.

tg3_restart_hw() releases and re-takes the spin lock,
we need to do the same because dev_close() needs to
take netdev_lock().

Fixes: 413f0271f396 ("net: protect NAPI enablement with netdev_lock()")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/dcfd56bc-de32-4b11-9e19-d8bd1543745d@stanley.mountain
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
v2:
 - correct commit msg (can't sleep -> needs to sleep)
 - add re-locking annotation to tg3_irq_quiesce()
v1: https://lore.kernel.org/20250121221519.392014-2-kuba@kernel.org

CC: pavan.chebbi@broadcom.com
CC: mchan@broadcom.com
CC: kuniyu@amazon.com
CC: romieu@fr.zoreil.com
---
 drivers/net/ethernet/broadcom/tg3.c | 35 +++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 4 deletions(-)

Comments

Michael Chan Jan. 23, 2025, 7:23 a.m. UTC | #1
On Wed, Jan 22, 2025 at 4:45 PM Jakub Kicinski <kuba@kernel.org> wrote:
>
> tg3 has a spin lock protecting most of the config,
> switch to taking netdev_lock() explicitly on enable/start
> paths. Disable/stop paths seem to not be under the spin
> lock (since napi_disable() already needs to sleep),
> so leave that side as is.
>
> tg3_restart_hw() releases and re-takes the spin lock,
> we need to do the same because dev_close() needs to
> take netdev_lock().
>
> Fixes: 413f0271f396 ("net: protect NAPI enablement with netdev_lock()")
> Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
> Link: https://lore.kernel.org/dcfd56bc-de32-4b11-9e19-d8bd1543745d@stanley.mountain
> Reviewed-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>

The relocking annotation seems to be in the wrong function.  It should
be in tg3_restart_hw().  Other than that,

Reviewed-by: Michael Chan <michael.chan@broadcom.com>
diff mbox series

Patch

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9cc8db10a8d6..57a09107b0dc 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7424,7 +7424,7 @@  static void tg3_napi_enable(struct tg3 *tp)
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		tnapi = &tp->napi[i];
-		napi_enable(&tnapi->napi);
+		napi_enable_locked(&tnapi->napi);
 		if (tnapi->tx_buffers) {
 			netif_queue_set_napi(tp->dev, txq_idx,
 					     NETDEV_QUEUE_TYPE_TX,
@@ -7445,9 +7445,10 @@  static void tg3_napi_init(struct tg3 *tp)
 	int i;
 
 	for (i = 0; i < tp->irq_cnt; i++) {
-		netif_napi_add(tp->dev, &tp->napi[i].napi,
-			       i ? tg3_poll_msix : tg3_poll);
-		netif_napi_set_irq(&tp->napi[i].napi, tp->napi[i].irq_vec);
+		netif_napi_add_locked(tp->dev, &tp->napi[i].napi,
+				      i ? tg3_poll_msix : tg3_poll);
+		netif_napi_set_irq_locked(&tp->napi[i].napi,
+					  tp->napi[i].irq_vec);
 	}
 }
 
@@ -7489,6 +7490,8 @@  static inline void tg3_netif_start(struct tg3 *tp)
 static void tg3_irq_quiesce(struct tg3 *tp)
 	__releases(tp->lock)
 	__acquires(tp->lock)
+	__releases(tp->dev->lock)
+	__acquires(tp->dev->lock)
 {
 	int i;
 
@@ -11271,7 +11274,9 @@  static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 		tg3_timer_stop(tp);
 		tp->irq_sync = 0;
 		tg3_napi_enable(tp);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
+		netdev_lock(tp->dev);
 		tg3_full_lock(tp, 0);
 	}
 	return err;
@@ -11299,6 +11304,7 @@  static void tg3_reset_task(struct work_struct *work)
 
 	tg3_netif_stop(tp);
 
+	netdev_lock(tp->dev);
 	tg3_full_lock(tp, 1);
 
 	if (tg3_flag(tp, TX_RECOVERY_PENDING)) {
@@ -11318,12 +11324,14 @@  static void tg3_reset_task(struct work_struct *work)
 		 * call cancel_work_sync() and wait forever.
 		 */
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
 		goto out;
 	}
 
 	tg3_netif_start(tp);
 	tg3_full_unlock(tp);
+	netdev_unlock(tp->dev);
 	tg3_phy_start(tp);
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
 out:
@@ -11683,9 +11691,11 @@  static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
 	if (err)
 		goto out_ints_fini;
 
+	netdev_lock(dev);
 	tg3_napi_init(tp);
 
 	tg3_napi_enable(tp);
+	netdev_unlock(dev);
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		err = tg3_request_irq(tp, i);
@@ -12569,6 +12579,7 @@  static int tg3_set_ringparam(struct net_device *dev,
 		irq_sync = 1;
 	}
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, irq_sync);
 
 	tp->rx_pending = ering->rx_pending;
@@ -12597,6 +12608,7 @@  static int tg3_set_ringparam(struct net_device *dev,
 	}
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (irq_sync && !err)
 		tg3_phy_start(tp);
@@ -12678,6 +12690,7 @@  static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 			irq_sync = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, irq_sync);
 
 		if (epause->autoneg)
@@ -12707,6 +12720,7 @@  static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 	}
 
 	tp->phy_flags |= TG3_PHYFLG_USER_CONFIGURED;
@@ -13911,6 +13925,7 @@  static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 			data[TG3_INTERRUPT_TEST] = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, 0);
 
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -13922,6 +13937,7 @@  static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 
 		if (irq_sync && !err2)
 			tg3_phy_start(tp);
@@ -14365,6 +14381,7 @@  static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 
 	tg3_set_mtu(dev, tp, new_mtu);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 1);
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -14384,6 +14401,7 @@  static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 		tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18164,6 +18182,7 @@  static int tg3_resume(struct device *device)
 
 	netif_device_attach(dev);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 0);
 
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
@@ -18180,6 +18199,7 @@  static int tg3_resume(struct device *device)
 
 out:
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18260,7 +18280,9 @@  static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 done:
 	if (state == pci_channel_io_perm_failure) {
 		if (netdev) {
+			netdev_lock(netdev);
 			tg3_napi_enable(tp);
+			netdev_unlock(netdev);
 			dev_close(netdev);
 		}
 		err = PCI_ERS_RESULT_DISCONNECT;
@@ -18314,7 +18336,9 @@  static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 
 done:
 	if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) {
+		netdev_lock(netdev);
 		tg3_napi_enable(tp);
+		netdev_unlock(netdev);
 		dev_close(netdev);
 	}
 	rtnl_unlock();
@@ -18340,12 +18364,14 @@  static void tg3_io_resume(struct pci_dev *pdev)
 	if (!netdev || !netif_running(netdev))
 		goto done;
 
+	netdev_lock(netdev);
 	tg3_full_lock(tp, 0);
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
 	tg3_flag_set(tp, INIT_COMPLETE);
 	err = tg3_restart_hw(tp, true);
 	if (err) {
 		tg3_full_unlock(tp);
+		netdev_unlock(netdev);
 		netdev_err(netdev, "Cannot restart hardware after reset.\n");
 		goto done;
 	}
@@ -18357,6 +18383,7 @@  static void tg3_io_resume(struct pci_dev *pdev)
 	tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(netdev);
 
 	tg3_phy_start(tp);