tg3: add napi_enabled flag to track napi_enable/napi_disable calls

patches-sonic/driver-arista-net-tg3-napi-enable-called-flag.patch

@@ -0,0 +1,123 @@
+From 821f6d79ad2773e0ff1537c0bb3c7af93a694709 Mon Sep 17 00:00:00 2001
+From: Yury Murashka <yurypm@arista.com>
+Date: Thu, 8 May 2026 00:00:00 +0000
+Subject: net: tg3: guard napi_disable and pci_disable_device calls
+
+We need this patch to fix a soft lockup in the Linux kernel on Arista
+modular chassis in the 202511 branch.
+
+During PCIe hot-plug events, uncorrectable errors can be reported and
+AER recovery for the tg3 device is initiated by the AER kernel driver.
+The tg3_io_error_detected function is the AER error recovery handler.
+
+From tg3_io_error_detected, we call tg3_netif_stop->tg3_napi_disable->
+napi_disable and return PCI_ERS_RESULT_NEED_RESET on non-fatal error.
+We expect that during AER recovery tg3_io_slot_reset and tg3_io_resume
+will be called. But AER error recovery can fail. For example, when one
+of PCIe devices on the same bus reports PCI_ERS_RESULT_NO_AER_DRIVER.
+As a result, tg3_io_slot_reset and tg3_io_resume are not called, PCIe
+device is disabled and NAPI is disabled (pci_disable_device and
+napi_disable are called from tg3_io_error_detected). Then we can try to
+disable PCIe link and napi_disable will be called again:
+
+  napi_disable+0x1b/0x1b0
+  tg3_napi_disable+0x89/0xa0 [tg3]
+  tg3_netif_stop+0x37/0xe3 [tg3]
+  tg3_stop+0x30/0x160 [tg3]
+  tg3_close+0x2a/0x60 [tg3]
+  __dev_close_many+0xad/0x130
+  dev_close_many+0xb2/0x190
+  unregister_netdevice_many_notify+0x19d/0xa00
+  unregister_netdevice_queue+0xf8/0x140
+  unregister_netdev+0x1c/0x30
+  tg3_remove_one+0xaa/0x150 [tg3]
+  pci_device_remove+0x42/0xb0
+  device_release_driver_internal+0x19c/0x200
+  pci_stop_bus_device+0x85/0xb0
+  pci_stop_bus_device+0x2c/0xb0
+  pci_stop_bus_device+0x2c/0xb0
+  pci_stop_and_remove_bus_device+0x12/0x20
+  pciehp_unconfigure_device+0x9f/0x160
+  pciehp_disable_slot+0x67/0x100
+  pciehp_handle_presence_or_link_change+0x77/0x350
+
+This is not expected by napi_disable and a thread can be locked in
+napi_disable forever. We have pcierr_recovery to cover a similar issue,
+but for fatal errors. We cannot reuse this flag because it is reset in
+tg3_io_resume, but it is not called when AER recovery fails.
+
+Similarly, if an AER error is reported and tg3_io_error_detected calls
+pci_disable_device, a subsequent device removal via tg3_remove_one or
+tg3_shutdown will call pci_disable_device again for the already-disabled
+device.
+
+Add a napi_enabled flag to struct tg3 to track whether napi_enable has
+been called. Guard tg3_napi_disable() so it returns early if NAPI was
+not previously enabled. Also guard pci_disable_device() calls in
+tg3_remove_one() and tg3_shutdown() with pci_is_enabled() to avoid
+disabling an already-disabled device.
+
+Fixes: b45aa2f6192e ("tg3: Add EEH support")
+Signed-off-by: Yury Murashka <yurypm@arista.com>
+
+--- a/drivers/net/ethernet/broadcom/tg3.c
++++ b/drivers/net/ethernet/broadcom/tg3.c
+@@ -7415,6 +7415,11 @@ static void tg3_napi_disable(struct tg3
+ {
+ 	int i;
+
++	if (!tp->napi_enabled)
++		return;
++
++	tp->napi_enabled = false;
++
+ 	for (i = tp->irq_cnt - 1; i >= 0; i--)
+ 		napi_disable(&tp->napi[i].napi);
+ }
+@@ -7423,6 +7428,8 @@ static void tg3_napi_enable(struct tg3 *
+ {
+ 	int i;
+
++	tp->napi_enabled = true;
++
+ 	for (i = 0; i < tp->irq_cnt; i++)
+ 		napi_enable(&tp->napi[i].napi);
+ }
+@@ -17715,6 +17722,7 @@ static int tg3_init_one(struct pci_dev *
+ 	tp->tx_mode = TG3_DEF_TX_MODE;
+ 	tp->irq_sync = 1;
+ 	tp->pcierr_recovery = false;
++	tp->napi_enabled = false;
+
+ 	if (tg3_debug > 0)
+ 		tp->msg_enable = tg3_debug;
+@@ -18096,7 +18104,8 @@ static void tg3_remove_one(struct pci_de
+ 		}
+ 		free_netdev(dev);
+ 		pci_release_regions(pdev);
+-		pci_disable_device(pdev);
++		if (pci_is_enabled(pdev))
++			pci_disable_device(pdev);
+ 	}
+ }
+
+@@ -18252,7 +18261,8 @@ static void tg3_shutdown(struct pci_dev
+
+ 	rtnl_unlock();
+
+-	pci_disable_device(pdev);
++	if (pci_is_enabled(pdev))
++		pci_disable_device(pdev);
+ }
+
+ /**
+--- a/drivers/net/ethernet/broadcom/tg3.h
++++ b/drivers/net/ethernet/broadcom/tg3.h
+@@ -3430,6 +3430,7 @@ struct tg3 {
+ 	struct device			*hwmon_dev;
+ 	bool				link_up;
+ 	bool				pcierr_recovery;
++	bool				napi_enabled;
+
+ 	u32                             ape_hb;
+ 	unsigned long                   ape_hb_interval;

patches-sonic/series

@@ -7,6 +7,7 @@
 driver-arista-net-tg3-dma-mask-4g-sb800.patch
 driver-arista-net-tg3-disallow-broadcom-default-mac.patch
 driver-arista-net-tg3-access-regs-indirectly.patch
+driver-arista-net-tg3-napi-enable-called-flag.patch
 driver-arista-pci-reassign-pref-mem.patch
 driver-arista-mmcblk-not-working-on-AMD-platforms.patch
 driver-arista-restrict-eMMC-drive-to-50Mhz-from-userland.patch