From patchwork Wed Sep 26 03:16:50 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jason Wang X-Patchwork-Id: 974800 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=nongnu.org (client-ip=2001:4830:134:3::11; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=redhat.com Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 42KjzS4pfFz9s4s for ; Wed, 26 Sep 2018 13:26:59 +1000 (AEST) Received: from localhost ([::1]:56207 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1g50TX-0004h9-3i for incoming@patchwork.ozlabs.org; Tue, 25 Sep 2018 23:26:55 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:55718) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1g50Sd-0004dn-TM for qemu-devel@nongnu.org; Tue, 25 Sep 2018 23:26:00 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1g50LF-0002lY-St for qemu-devel@nongnu.org; Tue, 25 Sep 2018 23:18:23 -0400 Received: from mx1.redhat.com ([209.132.183.28]:59470) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1g50LE-0002l0-C7 for qemu-devel@nongnu.org; Tue, 25 Sep 2018 23:18:20 -0400 Received: from smtp.corp.redhat.com (int-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.12]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 660E7550B0; Wed, 26 Sep 2018 03:18:19 +0000 (UTC) Received: from jason-ThinkPad-T450s.redhat.com (ovpn-12-161.pek2.redhat.com [10.72.12.161]) by smtp.corp.redhat.com (Postfix) with ESMTP id CBE6860BE1; Wed, 26 Sep 2018 03:18:17 +0000 (UTC) From: Jason Wang To: qemu-devel@nongnu.org Date: Wed, 26 Sep 2018 11:16:50 +0800 Message-Id: <20180926031650.8892-26-jasowang@redhat.com> In-Reply-To: <20180926031650.8892-1-jasowang@redhat.com> References: <20180926031650.8892-1-jasowang@redhat.com> X-Scanned-By: MIMEDefang 2.79 on 10.5.11.12 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.29]); Wed, 26 Sep 2018 03:18:19 +0000 (UTC) X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PULL 25/25] e1000: indicate dropped packets in HW counters X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: peter.maydell@linaro.org, Martin Wilck Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" From: Martin Wilck The e1000 emulation silently discards RX packets if there's insufficient space in the ring buffer. This leads to errors on higher-level protocols in the guest, with no indication about the error cause. This patch increments the "Missed Packets Count" (MPC) and "Receive No Buffers Count" (RNBC) HW counters in this case. As the emulation has no FIFO for buffering packets that can't immediately be pushed to the guest, these two registers are practically equivalent (see 10.2.7.4, 10.2.7.33 in https://www.intel.com/content/www/us/en/embedded/products/networking/82574l-gbe-controller-datasheet.html). On a Linux guest, the register content will be reflected in the "rx_missed_errors" and "rx_no_buffer_count" stats from "ethtool -S", and in the "missed" stat from "ip -s -s link show", giving at least some hint about the error cause inside the guest. If the cause is known, problems like this can often be avoided easily, by increasing the number of RX descriptors in the guest e1000 driver (e.g under Linux, "e1000.RxDescriptors=1024"). The patch also adds a qemu trace message for this condition. Signed-off-by: Martin Wilck --- hw/net/e1000.c | 16 +++++++++++++--- hw/net/trace-events | 3 +++ 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/hw/net/e1000.c b/hw/net/e1000.c index 13a9494a8d..5e144cb4e4 100644 --- a/hw/net/e1000.c +++ b/hw/net/e1000.c @@ -36,6 +36,7 @@ #include "qemu/range.h" #include "e1000x_common.h" +#include "trace.h" static const uint8_t bcast[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; @@ -847,6 +848,15 @@ static uint64_t rx_desc_base(E1000State *s) return (bah << 32) + bal; } +static void +e1000_receiver_overrun(E1000State *s, size_t size) +{ + trace_e1000_receiver_overrun(size, s->mac_reg[RDH], s->mac_reg[RDT]); + e1000x_inc_reg_if_not_full(s->mac_reg, RNBC); + e1000x_inc_reg_if_not_full(s->mac_reg, MPC); + set_ics(s, 0, E1000_ICS_RXO); +} + static ssize_t e1000_receive_iov(NetClientState *nc, const struct iovec *iov, int iovcnt) { @@ -916,8 +926,8 @@ e1000_receive_iov(NetClientState *nc, const struct iovec *iov, int iovcnt) desc_offset = 0; total_size = size + e1000x_fcs_len(s->mac_reg); if (!e1000_has_rxbufs(s, total_size)) { - set_ics(s, 0, E1000_ICS_RXO); - return -1; + e1000_receiver_overrun(s, total_size); + return -1; } do { desc_size = total_size - desc_offset; @@ -969,7 +979,7 @@ e1000_receive_iov(NetClientState *nc, const struct iovec *iov, int iovcnt) rdh_start >= s->mac_reg[RDLEN] / sizeof(desc)) { DBGOUT(RXERR, "RDH wraparound @%x, RDT %x, RDLEN %x\n", rdh_start, s->mac_reg[RDT], s->mac_reg[RDLEN]); - set_ics(s, 0, E1000_ICS_RXO); + e1000_receiver_overrun(s, total_size); return -1; } } while (desc_offset < total_size); diff --git a/hw/net/trace-events b/hw/net/trace-events index c1dea4b156..bdf63cf3f8 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -98,6 +98,9 @@ net_rx_pkt_rss_ip6_ex(void) "Calculating IPv6/EX RSS hash" net_rx_pkt_rss_hash(size_t rss_length, uint32_t rss_hash) "RSS hash for %zu bytes: 0x%X" net_rx_pkt_rss_add_chunk(void* ptr, size_t size, size_t input_offset) "Add RSS chunk %p, %zu bytes, RSS input offset %zu bytes" +# hw/net/e1000.c +e1000_receiver_overrun(size_t s, uint32_t rdh, uint32_t rdt) "Receiver overrun: dropped packet of %lu bytes, RDH=%u, RDT=%u" + # hw/net/e1000x_common.c e1000x_rx_can_recv_disabled(bool link_up, bool rx_enabled, bool pci_master) "link_up: %d, rx_enabled %d, pci_master %d" e1000x_vlan_is_vlan_pkt(bool is_vlan_pkt, uint16_t eth_proto, uint16_t vet) "Is VLAN packet: %d, ETH proto: 0x%X, VET: 0x%X"