DPDK patches and discussions
 help / color / mirror / Atom feed
From: Stephen Hemminger <stephen@networkplumber.org>
To: Thomas Monjalon <thomas.monjalon@6wind.com>
Cc: dev@dpdk.org
Subject: [dpdk-dev] [PATCH 09/10] igb_uio: allow msi mode
Date: Fri, 18 Jul 2014 09:14:56 -0700	[thread overview]
Message-ID: <20140718161526.944177421@networkplumber.org> (raw)
In-Reply-To: <20140718161447.020882834@networkplumber.org>

[-- Attachment #1: igb_uio_msi_mode.patch --]
[-- Type: text/plain, Size: 2147 bytes --]

Allows msi to be selected as a preferred mode.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>

--- a/lib/librte_eal/linuxapp/igb_uio/igb_uio.c	2014-07-18 08:47:24.713604900 -0700
+++ b/lib/librte_eal/linuxapp/igb_uio/igb_uio.c	2014-07-18 08:47:24.709604886 -0700
@@ -646,7 +646,7 @@ fail_release_iomem:
 	igbuio_pci_release_iomem(&udev->info);
 	if (udev->mode == RTE_INTR_MODE_MSIX)
 		pci_disable_msix(udev->pdev);
-	if (udev->mode == RTE_INTR_MODE_MSI)
+	else if (udev->mode == RTE_INTR_MODE_MSI)
 		pci_disable_msi(udev->pdev);
 	pci_release_regions(dev);
 fail_disable:
@@ -661,6 +661,7 @@ static void
 igbuio_pci_remove(struct pci_dev *dev)
 {
 	struct uio_info *info = pci_get_drvdata(dev);
+	struct rte_uio_pci_dev *udev = igbuio_get_uio_pci_dev(info);
 
 	if (info->priv == NULL) {
 		pr_notice("Not igbuio device\n");
@@ -670,9 +671,10 @@ igbuio_pci_remove(struct pci_dev *dev)
 	sysfs_remove_group(&dev->dev.kobj, &dev_attr_grp);
 	uio_unregister_device(info);
 	igbuio_pci_release_iomem(info);
-	if (((struct rte_uio_pci_dev *)info->priv)->mode ==
-			RTE_INTR_MODE_MSIX)
+	if (udev->mode == RTE_INTR_MODE_MSIX)
 		pci_disable_msix(dev);
+	else if (udev->mode == RTE_INTR_MODE_MSI)
+		pci_disable_msi(dev);
 	pci_release_regions(dev);
 	pci_disable_device(dev);
 	pci_set_drvdata(dev, NULL);
@@ -690,6 +692,9 @@ igbuio_config_intr_mode(char *intr_str)
 	if (!strcmp(intr_str, RTE_INTR_MODE_MSIX_NAME)) {
 		igbuio_intr_mode_preferred = RTE_INTR_MODE_MSIX;
 		pr_info("Use MSIX interrupt\n");
+	} else if (!strcmp(intr_str, RTE_INTR_MODE_MSI_NAME)) {
+		igbuio_intr_mode_preferred = RTE_INTR_MODE_MSI;
+		pr_info("Use MSI interrupt\n");
 	} else if (!strcmp(intr_str, RTE_INTR_MODE_LEGACY_NAME)) {
 		igbuio_intr_mode_preferred = RTE_INTR_MODE_LEGACY;
 		pr_info("Use legacy interrupt\n");
@@ -733,6 +738,7 @@ module_param(intr_mode, charp, S_IRUGO);
 MODULE_PARM_DESC(intr_mode,
 "igb_uio interrupt mode (default=msix):\n"
 "    " RTE_INTR_MODE_MSIX_NAME "       Use MSIX interrupt\n"
+"    " RTE_INTR_MODE_MSI_NAME "       Use MSI interrupt\n"
 "    " RTE_INTR_MODE_LEGACY_NAME "     Use Legacy interrupt\n"
 "\n");
 

  parent reply	other threads:[~2014-07-18 16:14 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-18 16:14 [dpdk-dev] [PATCH 00/10] igb_uio related patches Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 01/10] igb_uio: use kernel standard log message Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 02/10] igb_uio: use standard uio naming Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 03/10] igb_uio: dont wrap pci_num_vf function needlessly Stephen Hemminger
2014-07-23  8:20   ` Thomas Monjalon
2014-07-18 16:14 ` [dpdk-dev] [PATCH 04/10] igb_uio: msix cleanups Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 05/10] igb_uio: propogate error numbers in probe code Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 06/10] igb_uio: make irq mode param read-only Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 07/10] igb_uio: fix IRQ mode handling Stephen Hemminger
2014-07-18 16:14 ` [dpdk-dev] [PATCH 08/10] igb_uio: add missing locking to config access Stephen Hemminger
2014-07-18 16:14 ` Stephen Hemminger [this message]
2014-07-18 16:14 ` [dpdk-dev] [PATCH 10/10] igb_uio: fix check patch warnings Stephen Hemminger
2014-07-19  0:16 ` [dpdk-dev] [PATCH 00/10] igb_uio related patches Thomas Monjalon
2014-07-20  8:14   ` Yerden Zhumabekov
2014-07-21 10:28     ` Thomas Monjalon
2014-07-21 12:03       ` [dpdk-dev] [igb_uio PATCH 0/3] igb_uio: fixed typos and pci lock/unlock calls Yerden Zhumabekov
2014-07-21 12:03         ` [dpdk-dev] [igb_uio PATCH 1/3] igb_uio: fixed typos Yerden Zhumabekov
2014-07-21 12:03         ` [dpdk-dev] [igb_uio PATCH 2/3] igb_uio: pci_config_lock/pci_config_unlock wrappers Yerden Zhumabekov
2014-07-21 20:42           ` Stephen Hemminger
2014-07-21 20:50             ` Thomas Monjalon
2014-07-22 12:57             ` Thomas Monjalon
2014-07-21 12:03         ` [dpdk-dev] [igb_uio PATCH 3/3] igb_uio: renaming pci config lock/unlock functions Yerden Zhumabekov
2014-07-21 19:51         ` [dpdk-dev] [igb_uio PATCH 0/3] igb_uio: fixed typos and pci lock/unlock calls Thomas Monjalon
2014-07-22 13:07         ` Thomas Monjalon
2014-07-24 21:50           ` Thomas Monjalon
2014-07-25 16:51             ` Stephen Hemminger
2014-07-21 15:38       ` [dpdk-dev] [PATCH " Yerden Zhumabekov
2014-07-21 15:38         ` [dpdk-dev] [PATCH 1/3] igb_uio: fixed typos Yerden Zhumabekov
2014-07-21 15:38         ` [dpdk-dev] [PATCH 2/3] igb_uio: pci_config_lock/pci_config_unlock wrappers Yerden Zhumabekov
2014-07-21 15:38         ` [dpdk-dev] [PATCH 3/3] igb_uio: renaming pci config lock/unlock functions Yerden Zhumabekov
2014-07-21 19:54         ` [dpdk-dev] [PATCH 0/3] igb_uio: fixed typos and pci lock/unlock calls Thomas Monjalon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140718161526.944177421@networkplumber.org \
    --to=stephen@networkplumber.org \
    --cc=dev@dpdk.org \
    --cc=thomas.monjalon@6wind.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).