All of lore.kernel.org
 help / color / mirror / Atom feed
From: Brice Goglin <brice@myri.com>
To: linux-pci@atrey.karlin.mff.cuni.cz
Cc: linux-kernel@vger.kernel.org, Dave Olson <olson@unixfolk.com>
Subject: [PATCH 3/6 v4] Blacklist PCI-E chipsets depending on Hypertransport MSI capabality
Date: Thu, 22 Jun 2006 09:56:01 -0400	[thread overview]
Message-ID: <20060622135601.GA2416@myri.com> (raw)
In-Reply-To: <20060621023224.GC16292@myri.com>

[PATCH 3/6] Blacklist PCI-E chipsets depending on Hypertransport MSI capabality

Introduce msi_ht_cap_enabled() to check the MSI capability in the
Hypertransport configuration space.
It is used in a generic quirk quirk_msi_ht_cap() to check whether
MSI is enabled on hypertransport chipset, and a nVidia specific quirk
quirk_nvidia_ck804_msi_ht_cap() where two 2 HT MSI mappings have to
be checked.
Both quirks set the PCI_BUS_FLAGS_NO_MSI flags when MSI is disabled.

Signed-off-by: Brice Goglin <brice@myri.com>
---
We now use pci_find_next_capability() to simplify the HT MSI check.
And this patch does not define PCI_DEVICE_ID_NVIDIA_CK804_PCIE anymore
since a patch defining it has been merged meanwhile.

 drivers/pci/quirks.c    |   58 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci_ids.h |    1 
 2 files changed, 59 insertions(+)

Index: linux-mm/drivers/pci/quirks.c
===================================================================
--- linux-mm.orig/drivers/pci/quirks.c	2006-06-22 09:38:57.000000000 -0400
+++ linux-mm/drivers/pci/quirks.c	2006-06-22 09:47:46.000000000 -0400
@@ -1603,6 +1603,64 @@
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_disable_msi);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_GCNB_LE,
 			quirk_disable_msi);
+
+/* Go through the list of Hypertransport capabilities and
+ * return 1 if a HT MSI capability is found and enabled */
+static pci_bus_flags_t __devinit msi_ht_cap_enabled(struct pci_dev *dev)
+{
+	u8 pos;
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_HT);
+	     pos;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_HT)) {
+		u32 cap_hdr;
+		/* MSI mapping section according to Hypertransport spec */
+		if (pci_read_config_dword(dev, pos, &cap_hdr) == 0
+		    && (cap_hdr & 0xf8000000) == 0xa8000000 /* MSI mapping */) {
+			printk(KERN_INFO "PCI: Found HT MSI mapping on %s with capability %s\n",
+			       pci_name(dev), cap_hdr & 0x10000 ? "enabled" : "disabled");
+			return (cap_hdr & 0x10000) != 0; /* MSI mapping cap enabled */
+		}
+	}
+	return 0;
+}
+
+/* Check the hypertransport MSI mapping to know whether MSI is enabled or not */
+static void __devinit quirk_msi_ht_cap(struct pci_dev *dev)
+{
+	if (!dev->subordinate)
+		return;
+
+	if (!msi_ht_cap_enabled(dev)) {
+		printk(KERN_WARNING "PCI: MSI quirk detected. "
+		       "PCI_BUS_FLAGS_NO_MSI set for %s subordinate bus.\n",
+		       pci_name(dev));
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_HT2000_PCIE, quirk_msi_ht_cap);
+
+/* The nVidia CK804 chipset may have 2 HT MSI mappings.
+ * MSI are supported if the MSI capability set in any of these mappings.
+ */
+static void __devinit quirk_nvidia_ck804_msi_ht_cap(struct pci_dev *dev)
+{
+	struct pci_dev *pdev;
+
+	if (!dev->subordinate)
+		return;
+
+	/* check HT MSI cap on this chipset and the root one.
+	 * a single one having MSI is enough to be sure that MSI are supported.
+	 */
+	pdev = pci_find_slot(dev->bus->number, 0);
+	if (!msi_ht_cap_enabled(dev) && !msi_ht_cap_enabled(pdev)) {
+		printk(KERN_WARNING "PCI: MSI quirk detected. "
+		       "PCI_BUS_FLAGS_NO_MSI set for %s subordinate bus.\n",
+		       pci_name(dev));
+		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_CK804_PCIE, quirk_nvidia_ck804_msi_ht_cap);
 #endif /* CONFIG_PCI_MSI */
 
 EXPORT_SYMBOL(pcie_mch_quirk);
Index: linux-mm/include/linux/pci_ids.h
===================================================================
--- linux-mm.orig/include/linux/pci_ids.h	2006-06-21 08:16:06.000000000 -0400
+++ linux-mm/include/linux/pci_ids.h	2006-06-22 09:39:23.000000000 -0400
@@ -1406,6 +1406,7 @@
 #define PCI_DEVICE_ID_SERVERWORKS_LE	  0x0009
 #define PCI_DEVICE_ID_SERVERWORKS_GCNB_LE 0x0017
 #define PCI_DEVICE_ID_SERVERWORKS_EPB	  0x0103
+#define PCI_DEVICE_ID_SERVERWORKS_HT2000_PCIE	0x0132
 #define PCI_DEVICE_ID_SERVERWORKS_OSB4	  0x0200
 #define PCI_DEVICE_ID_SERVERWORKS_CSB5	  0x0201
 #define PCI_DEVICE_ID_SERVERWORKS_CSB6    0x0203

  reply	other threads:[~2006-06-22 13:56 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-06-21  2:31 [PATCH 0/6] Improve MSI detection v3 Brice Goglin
2006-06-21  2:31 ` [PATCH 1/6] Merge existing MSI disabling quirks Brice Goglin
2006-06-21  2:32 ` [PATCH 2/6] Rename PCI_CAP_ID_HT_IRQCONF into PCI_CAP_ID_HT Brice Goglin
2006-06-21  2:32 ` [PATCH 3/6] Blacklist PCI-E chipsets depending on Hypertransport MSI capabality Brice Goglin
2006-06-22 13:56   ` Brice Goglin [this message]
2006-06-21  2:32 ` [PATCH 4/6] Factorize common MSI detection code from pci_enable_msi() and msix() Brice Goglin
2006-06-21  2:32 ` [PATCH 5/6] Stop inheriting bus flags and check root chipset bus flags instead Brice Goglin
2006-06-21  2:33 ` [PATCH 6/6] Drop pci_msi_quirk Brice Goglin

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=20060622135601.GA2416@myri.com \
    --to=brice@myri.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@atrey.karlin.mff.cuni.cz \
    --cc=olson@unixfolk.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.