From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from linux.microsoft.com (linux.microsoft.com [13.77.154.182]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 114FC49C4BB; Wed, 2 Sep 2026 11:59:15 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=13.77.154.182 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788350372; cv=none; b=RTRE/b/Tht0BlQKeofbCq+b8i+tDT3xJyWQK6Y7bdq3suBJDBWKxbCoCxPd9p+y5OBovo+ioCsKPZt+zgfK2rhdy+LR5iF24qiEG6k/FiPC3DMgp3gg/9Ug65Mux1x0br2YlnxnKS0U26toEZrgZ4j6WXoWVTdZV5vhllwqvMPM= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788350372; c=relaxed/simple; bh=WQgZINIb4cT81Qa+2S8JCeILW5BK0Ti2MUqMysl2vTk=; h=From:To:Subject:Date:Message-ID:MIME-Version; b=ZBUrlBfmRtR/65Y5RBfyC+mDDtPa7+BNGgneHgWd98rx+I+eVSfEKT5BLxIIeItnEnZJkUK7aJ8mMMPFMgJn1NGM8+af2CtKWzxhVBA2+uhAkusScWq19efZjSMu17SqyeaRU5g0M7E23GUIfsfhJEc7FGLB/Hhq6iFHwUANKhs= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.microsoft.com; spf=pass smtp.mailfrom=linux.microsoft.com; dkim=pass (1024-bit key) header.d=linux.microsoft.com header.i=@linux.microsoft.com header.b=Eil+nx/n; arc=none smtp.client-ip=13.77.154.182 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.microsoft.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.microsoft.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.microsoft.com header.i=@linux.microsoft.com header.b="Eil+nx/n" Received: from sahil.mshome.net (unknown [4.213.232.23]) by linux.microsoft.com (Postfix) with ESMTPSA id 5637020B712D; Wed, 2 Sep 2026 04:58:25 -0700 (PDT) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 5637020B712D DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1788350309; bh=NbTpxWy4eTngSJB5iCZ1UgAbNhWcWwhmt9T2M+RrWzM=; h=From:To:Subject:Date:From; b=Eil+nx/n2+lN5Bbx33eo53U4es1T8TEK/1drmpTThnGNOtqyJm0LAteUUC4THyrBG JAL8lYrM3DNkCpmFjafnydCdTurgXaVQfk9abgt4TPqMvgOLg1TinTQPZVUo0/3fcR 9h5IuPHZywpcWWTUU2vjTpB5uN5aQigyvClvg54A= From: Sahil Chandna To: kys@microsoft.com, haiyangz@microsoft.com, namjain@linux.microsoft.com, mhklinux@outlook.com, hamzamahfooz@linux.microsoft.com, wei.liu@kernel.org, decui@microsoft.com, longli@microsoft.com, lpieralisi@kernel.org, kwilczynski@kernel.org, mani@kernel.org, robh@kernel.org, bhelgaas@google.com, linux-hyperv@vger.kernel.org, linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH v2] PCI: hv: warn when wait_for_response() waits indefinitely Date: Wed, 2 Sep 2026 04:58:51 -0700 Message-ID: <20260902115854.2629164-1-sahilchandna@linux.microsoft.com> X-Mailer: git-send-email 2.53.0 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit A guest can wait indefinitely in wait_for_response() for the host to send either a rescind message or a packet completion. If the host does not send either, the guest can remain blocked with no diagnostic indicating a reason. This was observed during a guest kernel upgrade in which the host-side application handling the PCI channel faulted, causing the guest to never receive the completion request. Add a warning in wait_for_response() when the wait exceeds a timeout so that such a hang is visible in the guest's kernel log and can be correlated with host-side state. Suggested-by: Hamza Mahfooz Suggested-by: Naman Jain Suggested-by: Michael Kelley Signed-off-by: Sahil Chandna --- Changes since v1: - Removed periodic warning to one time warning in 2 minutes - Include vmbus relid and stuck PCI msg. Link to v1: https://lore.kernel.org/all/20260825051850.2438816-1-sahilchandna@linux.microsoft.com/ --- drivers/pci/controller/pci-hyperv.c | 48 +++++++++++++++++++++++------ 1 file changed, 38 insertions(+), 10 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 89816a2bd7cd..ca9d8efd748c 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1040,19 +1040,40 @@ static void put_pcichild(struct hv_pci_dev *hpdev) /* * There is no good way to get notified from vmbus_onoffer_rescind(), - * so let's use polling here, since this is not a hot path. + * so let's use polling here, since this is not a hot path. If + * wait_for_response() has been polling for PCI_RESPONSE_HANG_TIMEOUT_SEC + * without either a rescind or completion, add a warning. */ +#define PCI_RESPONSE_HANG_TIMEOUT_SEC 120 + static int wait_for_response(struct hv_device *hdev, - struct completion *comp) + struct completion *comp, + const char *msg_type) { + unsigned long delay = secs_to_jiffies(PCI_RESPONSE_HANG_TIMEOUT_SEC); + u64 timeout = get_jiffies_64() + delay; + bool warned = false; + while (true) { if (hdev->channel->rescind) { dev_warn_once(&hdev->device, "The device is gone.\n"); return -ENODEV; } - if (wait_for_completion_timeout(comp, HZ / 10)) + if (wait_for_completion_timeout(comp, HZ / 10)) { + if (warned) + dev_warn(&hdev->device, + "Late %s completion arrived.\n", msg_type); break; + } + + if (!warned && time_after64(get_jiffies_64(), timeout)) { + dev_err(&hdev->device, + "%s stuck waiting for response, relid = %u\n", + msg_type, hdev->channel->offermsg.child_relid); + + warned = true; + } } return 0; @@ -1518,7 +1539,8 @@ static int hv_read_config_block(struct pci_dev *pdev, void *buf, if (ret) return ret; - ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event); + ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event, + "PCI_READ_BLOCK"); if (ret) return ret; @@ -1607,7 +1629,8 @@ static int hv_write_config_block(struct pci_dev *pdev, void *buf, if (ret) return ret; - ret = wait_for_response(hbus->hdev, &comp_pkt.host_event); + ret = wait_for_response(hbus->hdev, &comp_pkt.host_event, + "PCI_WRITE_BLOCK"); if (ret) return ret; @@ -2624,7 +2647,8 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, if (ret) goto error; - if (wait_for_response(hbus->hdev, &comp_pkt.host_event)) + if (wait_for_response(hbus->hdev, &comp_pkt.host_event, + "PCI_QUERY_RESOURCE_REQUIREMENTS")) goto error; hpdev->desc = *desc; @@ -3256,7 +3280,8 @@ static int hv_pci_protocol_negotiation(struct hv_device *hdev, (unsigned long)pkt, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (!ret) - ret = wait_for_response(hdev, &comp_pkt.host_event); + ret = wait_for_response(hdev, &comp_pkt.host_event, + "PCI_QUERY_PROTOCOL_VERSION"); if (ret) { dev_err(&hdev->device, @@ -3476,7 +3501,8 @@ static int hv_pci_enter_d0(struct hv_device *hdev) (unsigned long)pkt, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (!ret) - ret = wait_for_response(hdev, &comp_pkt.host_event); + ret = wait_for_response(hdev, &comp_pkt.host_event, + "PCI_BUS_D0ENTRY"); if (ret) goto exit; @@ -3553,7 +3579,8 @@ static int hv_pci_query_relations(struct hv_device *hdev) ret = vmbus_sendpacket(hdev->channel, &message, sizeof(message), 0, VM_PKT_DATA_INBAND, 0); if (!ret) - ret = wait_for_response(hdev, &comp); + ret = wait_for_response(hdev, &comp, + "PCI_QUERY_BUS_RELATIONS"); /* * In the case of fast device addition/removal, it's possible that @@ -3644,7 +3671,8 @@ static int hv_send_resources_allocated(struct hv_device *hdev) VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (!ret) - ret = wait_for_response(hdev, &comp_pkt.host_event); + ret = wait_for_response(hdev, &comp_pkt.host_event, + "PCI_RESOURCE_ASSIGNED"); if (ret) break; -- 2.53.0