PCI: Add sysfs sriov_drivers_autoprobe to control VF driver binding

Sometimes it is not desirable to bind SR-IOV VFs to drivers.  This can save
host side resource usage by VF instances that will be assigned to VMs.

Add a new PCI sysfs interface "sriov_drivers_autoprobe" to control that
from the PF.  To modify it, echo 0/n/N (disable probe) or 1/y/Y (enable
probe) to:

  /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_drivers_autoprobe

Note that this must be done before enabling VFs.  The change will not take
effect if VFs are already enabled.  Simply, one can disable VFs by setting
sriov_numvfs to 0, choose whether to probe or not, and then re-enable the
VFs by restoring sriov_numvfs.

[bhelgaas: changelog, ABI doc]
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>

6 files changed, 82 insertions, 4 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index 5a1732b78707..b728f700340d 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -301,3 +301,25 @@ Contact:	Emil Velikov <emil.l.velikov@gmail.com>
 Description:
 		This file contains the revision field of the the PCI device.
 		The value comes from device config space. The file is read only.
+
+What:		/sys/bus/pci/devices/.../sriov_drivers_autoprobe
+Date:		April 2017
+Contact:	Bodong Wang<bodong@mellanox.com>
+Description:
+		This file is associated with the PF of a device that
+		supports SR-IOV.  It determines whether newly-enabled VFs
+		are immediately bound to a driver.  It initially contains
+		1, which means the kernel automatically binds VFs to a
+		compatible driver immediately after they are enabled.  If
+		an application writes 0 to the file before enabling VFs,
+		the kernel will not bind VFs to a driver.
+
+		A typical use case is to write 0 to this file, then enable
+		VFs, then assign the newly-created VFs to virtual machines.
+		Note that changing this file does not affect already-
+		enabled VFs.  In this scenario, the user must first disable
+		the VFs, write 0 to sriov_drivers_autoprobe, then re-enable
+		the VFs.
+
+		This is similar to /sys/bus/pci/drivers_autoprobe, but
+		affects only the VFs associated with a specific PF.
diff --git a/Documentation/PCI/pci-iov-howto.txt b/Documentation/PCI/pci-iov-howto.txt
index 2d91ae251982..d2a84151e99c 100644
--- a/Documentation/PCI/pci-iov-howto.txt
+++ b/Documentation/PCI/pci-iov-howto.txt
@@ -68,6 +68,18 @@ To disable SR-IOV capability:
 	echo  0 > \
         /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_numvfs
 
+To enable auto probing VFs by a compatible driver on the host, run
+command below before enabling SR-IOV capabilities. This is the
+default behavior.
+	echo 1 > \
+        /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_drivers_autoprobe
+
+To disable auto probing VFs by a compatible driver on the host, run
+command below before enabling SR-IOV capabilities. Updating this
+entry will not affect VFs which are already probed.
+	echo  0 > \
+        /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_drivers_autoprobe
+
 3.2 Usage example
 
 Following piece of code illustrates the usage of the SR-IOV API.
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 2479ae876482..d9dc7363ac77 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -450,6 +450,7 @@ found:
 	iov->total_VFs = total;
 	iov->pgsz = pgsz;
 	iov->self = dev;
+	iov->drivers_autoprobe = true;
 	pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap);
 	pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
 	if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index afa72717a979..f99f7fe749b8 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -394,6 +394,18 @@ void __weak pcibios_free_irq(struct pci_dev *dev)
 {
 }
 
+#ifdef CONFIG_PCI_IOV
+static inline bool pci_device_can_probe(struct pci_dev *pdev)
+{
+	return (!pdev->is_virtfn || pdev->physfn->sriov->drivers_autoprobe);
+}
+#else
+static inline bool pci_device_can_probe(struct pci_dev *pdev)
+{
+	return true;
+}
+#endif
+
 static int pci_device_probe(struct device *dev)
 {
 	int error;
@@ -405,10 +417,12 @@ static int pci_device_probe(struct device *dev)
 		return error;
 
 	pci_dev_get(pci_dev);
-	error = __pci_device_probe(drv, pci_dev);
-	if (error) {
-		pcibios_free_irq(pci_dev);
-		pci_dev_put(pci_dev);
+	if (pci_device_can_probe(pci_dev)) {
+		error = __pci_device_probe(drv, pci_dev);
+		if (error) {
+			pcibios_free_irq(pci_dev);
+			pci_dev_put(pci_dev);
+		}
 	}
 
 	return error;
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 25d010d449a3..369c999683ca 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -526,10 +526,37 @@ exit:
 	return count;
 }
 
+static ssize_t sriov_drivers_autoprobe_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	return sprintf(buf, "%u\n", pdev->sriov->drivers_autoprobe);
+}
+
+static ssize_t sriov_drivers_autoprobe_store(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t count)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	bool drivers_autoprobe;
+
+	if (kstrtobool(buf, &drivers_autoprobe) < 0)
+		return -EINVAL;
+
+	pdev->sriov->drivers_autoprobe = drivers_autoprobe;
+
+	return count;
+}
+
 static struct device_attribute sriov_totalvfs_attr = __ATTR_RO(sriov_totalvfs);
 static struct device_attribute sriov_numvfs_attr =
 		__ATTR(sriov_numvfs, (S_IRUGO|S_IWUSR|S_IWGRP),
 		       sriov_numvfs_show, sriov_numvfs_store);
+static struct device_attribute sriov_drivers_autoprobe_attr =
+		__ATTR(sriov_drivers_autoprobe, (S_IRUGO|S_IWUSR|S_IWGRP),
+		       sriov_drivers_autoprobe_show, sriov_drivers_autoprobe_store);
 #endif /* CONFIG_PCI_IOV */
 
 static ssize_t driver_override_store(struct device *dev,
@@ -1549,6 +1576,7 @@ static struct attribute_group pci_dev_hp_attr_group = {
 static struct attribute *sriov_dev_attrs[] = {
 	&sriov_totalvfs_attr.attr,
 	&sriov_numvfs_attr.attr,
+	&sriov_drivers_autoprobe_attr.attr,
 	NULL,
 };
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 8dd38e69d6f2..3ba7d586f522 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -272,6 +272,7 @@ struct pci_sriov {
 	struct pci_dev *self;	/* this PF */
 	struct mutex lock;	/* lock for setting sriov_numvfs in sysfs */
 	resource_size_t barsz[PCI_SRIOV_NUM_BARS];	/* VF BAR size */
+	bool drivers_autoprobe;	/* auto probing of VFs by driver */
 };
 
 #ifdef CONFIG_PCI_ATS