linux-kernel - [PATCH 4.9 092/138] e1000e: Avoid receiver overrun interrupt bursts

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 28 Nov 2017 11:23:13 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org,
        Lennart Sorensen <lsorense@...lub.uwaterloo.ca>,
        Benjamin Poirier <bpoirier@...e.com>,
        Aaron Brown <aaron.f.brown@...el.com>,
        Jeff Kirsher <jeffrey.t.kirsher@...el.com>,
        Amit Pundir <amit.pundir@...aro.org>
Subject: [PATCH 4.9 092/138] e1000e: Avoid receiver overrun interrupt bursts

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Benjamin Poirier <bpoirier@...e.com>

commit 4aea7a5c5e940c1723add439f4088844cd26196d upstream.

When e1000e_poll() is not fast enough to keep up with incoming traffic, the
adapter (when operating in msix mode) raises the Other interrupt to signal
Receiver Overrun.

This is a double problem because 1) at the moment e1000_msix_other()
assumes that it is only called in case of Link Status Change and 2) if the
condition persists, the interrupt is repeatedly raised again in quick
succession.

Ideally we would configure the Other interrupt to not be raised in case of
receiver overrun but this doesn't seem possible on this adapter. Instead,
we handle the first part of the problem by reverting to the practice of
reading ICR in the other interrupt handler, like before commit 16ecba59bc33
("e1000e: Do not read ICR in Other interrupt"). Thanks to commit
0a8047ac68e5 ("e1000e: Fix msi-x interrupt automask") which cleared IAME
from CTRL_EXT, reading ICR doesn't interfere with RxQ0, TxQ0 interrupts
anymore. We handle the second part of the problem by not re-enabling the
Other interrupt right away when there is overrun. Instead, we wait until
traffic subsides, napi polling mode is exited and interrupts are
re-enabled.

Reported-by: Lennart Sorensen <lsorense@...lub.uwaterloo.ca>
Fixes: 16ecba59bc33 ("e1000e: Do not read ICR in Other interrupt")
Signed-off-by: Benjamin Poirier <bpoirier@...e.com>
Tested-by: Aaron Brown <aaron.f.brown@...el.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
Signed-off-by: Amit Pundir <amit.pundir@...aro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 drivers/net/ethernet/intel/e1000e/defines.h |    1 
 drivers/net/ethernet/intel/e1000e/netdev.c  |   31 +++++++++++++++++++++-------
 2 files changed, 25 insertions(+), 7 deletions(-)

--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -398,6 +398,7 @@
 #define E1000_ICR_LSC           0x00000004 /* Link Status Change */
 #define E1000_ICR_RXSEQ         0x00000008 /* Rx sequence error */
 #define E1000_ICR_RXDMT0        0x00000010 /* Rx desc min. threshold (0) */
+#define E1000_ICR_RXO           0x00000040 /* Receiver Overrun */
 #define E1000_ICR_RXT0          0x00000080 /* Rx timer intr (ring 0) */
 #define E1000_ICR_ECCER         0x00400000 /* Uncorrectable ECC Error */
 /* If this bit asserted, the driver should claim the interrupt */
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1905,14 +1905,30 @@ static irqreturn_t e1000_msix_other(int
 	struct net_device *netdev = data;
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	u32 icr;
+	bool enable = true;
 
-	hw->mac.get_link_status = true;
+	icr = er32(ICR);
+	if (icr & E1000_ICR_RXO) {
+		ew32(ICR, E1000_ICR_RXO);
+		enable = false;
+		/* napi poll will re-enable Other, make sure it runs */
+		if (napi_schedule_prep(&adapter->napi)) {
+			adapter->total_rx_bytes = 0;
+			adapter->total_rx_packets = 0;
+			__napi_schedule(&adapter->napi);
+		}
+	}
+	if (icr & E1000_ICR_LSC) {
+		ew32(ICR, E1000_ICR_LSC);
+		hw->mac.get_link_status = true;
+		/* guard against interrupt when we're going down */
+		if (!test_bit(__E1000_DOWN, &adapter->state))
+			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	}
 
-	/* guard against interrupt when we're going down */
-	if (!test_bit(__E1000_DOWN, &adapter->state)) {
-		mod_timer(&adapter->watchdog_timer, jiffies + 1);
+	if (enable && !test_bit(__E1000_DOWN, &adapter->state))
 		ew32(IMS, E1000_IMS_OTHER);
-	}
 
 	return IRQ_HANDLED;
 }
@@ -2683,7 +2699,8 @@ static int e1000e_poll(struct napi_struc
 		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->state)) {
 			if (adapter->msix_entries)
-				ew32(IMS, adapter->rx_ring->ims_val);
+				ew32(IMS, adapter->rx_ring->ims_val |
+				     E1000_IMS_OTHER);
 			else
 				e1000_irq_enable(adapter);
 		}
@@ -4178,7 +4195,7 @@ static void e1000e_trigger_lsc(struct e1
 	struct e1000_hw *hw = &adapter->hw;
 
 	if (adapter->msix_entries)
-		ew32(ICS, E1000_ICS_OTHER);
+		ew32(ICS, E1000_ICS_LSC | E1000_ICS_OTHER);
 	else
 		ew32(ICS, E1000_ICS_LSC);
 }