Patch "cxgb4: fix BUG() on interrupt deallocating path of ULD" has been added to the 4.12-stable tree

[<gregkh@linuxfoundation.org>]

This is a note to let you know that I've just added the patch titled

    cxgb4: fix BUG() on interrupt deallocating path of ULD

to the 4.12-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     cxgb4-fix-bug-on-interrupt-deallocating-path-of-uld.patch
and it can be found in the queue-4.12 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


>From foo@baz Mon Jul 17 18:46:41 CEST 2017
From: "Guilherme G. Piccoli" <gpiccoli@linux.vnet.ibm.com>
Date: Mon, 10 Jul 2017 10:55:46 -0300
Subject: cxgb4: fix BUG() on interrupt deallocating path of ULD

From: "Guilherme G. Piccoli" <gpiccoli@linux.vnet.ibm.com>


[ Upstream commit 6a146f3a5894b751cef16feb3d7903e45e3c445c ]

Since the introduction of ULD (Upper-Layer Drivers), the MSI-X
deallocating path changed in cxgb4: the driver frees the interrupts
of ULD when unregistering it or on shutdown PCI handler.

Problem is that if a MSI-X is not freed before deallocated in the PCI
layer, it will trigger a BUG() due to still "alive" interrupt being
tentatively quiesced.

The below trace was observed when doing a simple unbind of Chelsio's
adapter PCI function, like:
  "echo 001e:80:00.4 > /sys/bus/pci/drivers/cxgb4/unbind"

Trace:

  kernel BUG at drivers/pci/msi.c:352!
  Oops: Exception in kernel mode, sig: 5 [#1]
  ...
  NIP [c0000000005a5e60] free_msi_irqs+0xa0/0x250
  LR [c0000000005a5e50] free_msi_irqs+0x90/0x250
  Call Trace:
  [c0000000005a5e50] free_msi_irqs+0x90/0x250 (unreliable)
  [c0000000005a72c4] pci_disable_msix+0x124/0x180
  [d000000011e06708] disable_msi+0x88/0xb0 [cxgb4]
  [d000000011e06948] free_some_resources+0xa8/0x160 [cxgb4]
  [d000000011e06d60] remove_one+0x170/0x3c0 [cxgb4]
  [c00000000058a910] pci_device_remove+0x70/0x110
  [c00000000064ef04] device_release_driver_internal+0x1f4/0x2c0
  ...

This patch fixes the issue by refactoring the shutdown path of ULD on
cxgb4 driver, by properly freeing and disabling interrupts on PCI
remove handler too.

Fixes: 0fbc81b3ad51 ("Allocate resources dynamically for all cxgb4 ULD's")
Reported-by: Harsha Thyagaraja <hathyaga@in.ibm.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c |   16 ++++++---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c  |   42 ++++++++++++++----------
 2 files changed, 36 insertions(+), 22 deletions(-)

--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2055,12 +2055,12 @@ static void detach_ulds(struct adapter *
 
 	mutex_lock(&uld_mutex);
 	list_del(&adap->list_node);
+
 	for (i = 0; i < CXGB4_ULD_MAX; i++)
-		if (adap->uld && adap->uld[i].handle) {
+		if (adap->uld && adap->uld[i].handle)
 			adap->uld[i].state_change(adap->uld[i].handle,
 					     CXGB4_STATE_DETACH);
-			adap->uld[i].handle = NULL;
-		}
+
 	if (netevent_registered && list_empty(&adapter_list)) {
 		unregister_netevent_notifier(&cxgb4_netevent_nb);
 		netevent_registered = false;
@@ -5086,8 +5086,10 @@ static void remove_one(struct pci_dev *p
 		 */
 		destroy_workqueue(adapter->workq);
 
-		if (is_uld(adapter))
+		if (is_uld(adapter)) {
 			detach_ulds(adapter);
+			t4_uld_clean_up(adapter);
+		}
 
 		disable_interrupts(adapter);
 
@@ -5164,7 +5166,11 @@ static void shutdown_one(struct pci_dev
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				cxgb_close(adapter->port[i]);
 
-		t4_uld_clean_up(adapter);
+		if (is_uld(adapter)) {
+			detach_ulds(adapter);
+			t4_uld_clean_up(adapter);
+		}
+
 		disable_interrupts(adapter);
 		disable_msi(adapter);
 
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -589,22 +589,37 @@ void t4_uld_mem_free(struct adapter *ada
 	kfree(adap->uld);
 }
 
+/* This function should be called with uld_mutex taken. */
+static void cxgb4_shutdown_uld_adapter(struct adapter *adap, enum cxgb4_uld type)
+{
+	if (adap->uld[type].handle) {
+		adap->uld[type].handle = NULL;
+		adap->uld[type].add = NULL;
+		release_sge_txq_uld(adap, type);
+
+		if (adap->flags & FULL_INIT_DONE)
+			quiesce_rx_uld(adap, type);
+
+		if (adap->flags & USING_MSIX)
+			free_msix_queue_irqs_uld(adap, type);
+
+		free_sge_queues_uld(adap, type);
+		free_queues_uld(adap, type);
+	}
+}
+
 void t4_uld_clean_up(struct adapter *adap)
 {
 	unsigned int i;
 
-	if (!adap->uld)
-		return;
+	mutex_lock(&uld_mutex);
 	for (i = 0; i < CXGB4_ULD_MAX; i++) {
 		if (!adap->uld[i].handle)
 			continue;
-		if (adap->flags & FULL_INIT_DONE)
-			quiesce_rx_uld(adap, i);
-		if (adap->flags & USING_MSIX)
-			free_msix_queue_irqs_uld(adap, i);
-		free_sge_queues_uld(adap, i);
-		free_queues_uld(adap, i);
+
+		cxgb4_shutdown_uld_adapter(adap, i);
 	}
+	mutex_unlock(&uld_mutex);
 }
 
 static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
@@ -782,15 +797,8 @@ int cxgb4_unregister_uld(enum cxgb4_uld
 			continue;
 		if (type == CXGB4_ULD_ISCSIT && is_t4(adap->params.chip))
 			continue;
-		adap->uld[type].handle = NULL;
-		adap->uld[type].add = NULL;
-		release_sge_txq_uld(adap, type);
-		if (adap->flags & FULL_INIT_DONE)
-			quiesce_rx_uld(adap, type);
-		if (adap->flags & USING_MSIX)
-			free_msix_queue_irqs_uld(adap, type);
-		free_sge_queues_uld(adap, type);
-		free_queues_uld(adap, type);
+
+		cxgb4_shutdown_uld_adapter(adap, type);
 	}
 	mutex_unlock(&uld_mutex);
 


Patches currently in stable-queue which might be from gpiccoli@linux.vnet.ibm.com are

queue-4.12/cxgb4-fix-bug-on-interrupt-deallocating-path-of-uld.patch