From mboxrd@z Thu Jan  1 00:00:00 1970
From: Stephen Hemminger <stephen-OTpzqLSitTUnbdJkjeBofR2eb7JE58TQ@public.gmane.org>
Subject: [PATCH 2/2] igb_uio: handle no IRQ fallback
Date: Fri, 25 Jul 2014 10:37:54 -0700
Message-ID: <20140725103754.5fbec494@haswell.linuxnetplumber.net>
References: <20140725103627.4ca989b7@haswell.linuxnetplumber.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Cc: dev-VfR2kkLFssw@public.gmane.org
To: Thomas Monjalon <thomas.monjalon-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>, Yerden Zhumabekov
 <e_zhumabekov-8EHiFRVJVgQ@public.gmane.org>
Return-path: <dev-bounces-VfR2kkLFssw@public.gmane.org>
In-Reply-To: <20140725103627.4ca989b7-a7a0dvSY7KrRI77zikRAJc56i+j3xesD0e7PPNI6Mm0@public.gmane.org>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev-VfR2kkLFssw@public.gmane.org>
List-Help: <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request-VfR2kkLFssw@public.gmane.org?subject=subscribe>
Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org
Sender: "dev" <dev-bounces-VfR2kkLFssw@public.gmane.org>

Fix a couple of issues with my earlier igb_uio stuff:
1. With MSI (like MSI-X) actual IRQ number is not known until
   after the pci_enable_msi() is done.
2. If INTX fails, fall back to running without IRQ.
   This allows usermode PCI to recover and run without out IRQ
   for cases where PCI INTX support is broken (aka VMWare).

Signed-off-by: Stephen Hemminger <stephen-OTpzqLSitTUnbdJkjeBofR2eb7JE58TQ@public.gmane.org>


--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c	2014-07-25 10:30:07.740159856 -0700
+++ b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c	2014-07-25 10:30:07.736159842 -0700
@@ -506,7 +506,6 @@ igbuio_pci_probe(struct pci_dev *dev, co
 	udev->info.version = "0.1";
 	udev->info.handler = igbuio_pci_irqhandler;
 	udev->info.irqcontrol = igbuio_pci_irqcontrol;
-	udev->info.irq = dev->irq;
 #ifdef CONFIG_XEN_DOM0
 	/* check if the driver run on Xen Dom0 */
 	if (xen_initial_domain())
@@ -516,9 +515,6 @@ igbuio_pci_probe(struct pci_dev *dev, co
 	udev->pdev = dev;
 
 	switch (igbuio_intr_mode_preferred) {
-	case RTE_INTR_MODE_NONE:
-		udev->info.irq = 0;
-		break;
 	case RTE_INTR_MODE_MSIX:
 		/* Only 1 msi-x vector needed */
 		msix_entry.entry = 0;
@@ -532,6 +528,7 @@ igbuio_pci_probe(struct pci_dev *dev, co
 	case RTE_INTR_MODE_MSI:
 		if (pci_enable_msi(dev) == 0) {
 			dev_dbg(&dev->dev, "using MSI");
+			udev->info.irq = dev->irq;
 			udev->mode = RTE_INTR_MODE_MSI;
 			break;
 		}
@@ -540,13 +537,17 @@ igbuio_pci_probe(struct pci_dev *dev, co
 		if (pci_intx_mask_supported(dev)) {
 			dev_dbg(&dev->dev, "using INTX");
 			udev->info.irq_flags = IRQF_SHARED;
+			udev->info.irq = dev->irq;
 			udev->mode = RTE_INTR_MODE_LEGACY;
-		} else {
-			dev_err(&dev->dev, "PCI INTX mask not supported\n");
-			err = -EIO;
-			goto fail_release_iomem;
+			break;
 		}
+		dev_notice(&dev->dev, "PCI INTX mask not supported\n");
+		/* fall back to no IRQ */
+	case RTE_INTR_MODE_NONE:
+		udev->mode = RTE_INTR_MODE_NONE;
+		udev->info.irq = 0;
 		break;
+
 	default:
 		dev_err(&dev->dev, "invalid IRQ mode %u",
 			igbuio_intr_mode_preferred);