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>
This commit is contained in:
parent
f114040e3e
commit
63692df103
|
@ -281,3 +281,16 @@ Description:
|
|||
opt-out of driver binding using a driver_override name such as
|
||||
"none". Only a single driver may be specified in the override,
|
||||
there is no support for parsing delimiters.
|
||||
|
||||
What: /sys/bus/pci/devices/.../numa_node
|
||||
Date: Oct 2014
|
||||
Contact: Prarit Bhargava <prarit@redhat.com>
|
||||
Description:
|
||||
This file contains the NUMA node to which the PCI device is
|
||||
attached, or -1 if the node is unknown. The initial value
|
||||
comes from an ACPI _PXM method or a similar firmware
|
||||
source. If that is missing or incorrect, this file can be
|
||||
written to override the node. In that case, please report
|
||||
a firmware bug to the system vendor. Writing to this file
|
||||
taints the kernel with TAINT_FIRMWARE_WORKAROUND, which
|
||||
reduces the supportability of your system.
|
||||
|
|
|
@ -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,
|
||||
|
|
Loading…
Reference in a new issue