summaryrefslogtreecommitdiffstats
path: root/drivers/pci/pci-sysfs.c
diff options
context:
space:
mode:
authorPrarit Bhargava <prarit@redhat.com>2014-10-23 14:22:12 -0400
committerBjorn Helgaas <bhelgaas@google.com>2014-11-06 15:10:06 -0700
commit63692df103e9c76b26c382ce8079283b7df9a99a (patch)
tree677204f229cd7ad3dcf072d8d7eb44ce01018e9e /drivers/pci/pci-sysfs.c
parentf114040e3ea6e07372334ade75d1ee0775c355e1 (diff)
downloadop-kernel-dev-63692df103e9c76b26c382ce8079283b7df9a99a.zip
op-kernel-dev-63692df103e9c76b26c382ce8079283b7df9a99a.tar.gz
PCI: Allow numa_node override via sysfs
NUMA systems with ACPI normally describe the physical topology via _PXM methods. But many BIOSes don't implement _PXM, which leaves the kernel with no way to discover the device topology, which reduces performance because we can't put memory and processes close to the device. The NUMA node of a PCI device is already exported in the sysfs "numa_node" file. Make that file writable so users can workaround the lack of _PXM methods in the BIOS. For example: echo 3 > /sys/devices/pci0000:ff/0000:03:1f.3/numa_node sets the node for PCI device 0000:03:1f.3. Writing the file emits a FW_BUG warning to encourage users to request firmware updates. It also taints the kernel with TAINT_FIRMWARE_WORKAROUND because overriding the node incorrectly can cause performance issues. [bhelgaas: changelog, documentation text] Signed-off-by: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> CC: Myron Stowe <mstowe@redhat.com> CC: Alexander Ducyk <alexander.h.duyck@redhat.com> CC: Jiang Liu <jiang.liu@linux.intel.com>
Diffstat (limited to 'drivers/pci/pci-sysfs.c')
-rw-r--r--drivers/pci/pci-sysfs.c27
1 files changed, 26 insertions, 1 deletions
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 92b6d9a..91e760f 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -221,12 +221,37 @@ static ssize_t enabled_show(struct device *dev, struct device_attribute *attr,
static DEVICE_ATTR_RW(enabled);
#ifdef CONFIG_NUMA
+static ssize_t numa_node_store(struct device *dev,
+ struct device_attribute *attr, const char *buf,
+ size_t count)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ int node, ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ret = kstrtoint(buf, 0, &node);
+ if (ret)
+ return ret;
+
+ if (!node_online(node))
+ return -EINVAL;
+
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+ dev_alert(&pdev->dev, FW_BUG "Overriding NUMA node to %d. Contact your vendor for updates.",
+ node);
+
+ dev->numa_node = node;
+ return count;
+}
+
static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "%d\n", dev->numa_node);
}
-static DEVICE_ATTR_RO(numa_node);
+static DEVICE_ATTR_RW(numa_node);
#endif
static ssize_t dma_mask_bits_show(struct device *dev,
OpenPOWER on IntegriCloud