PCI: handle SR-IOV Virtual Function Migration

Add or remove a Virtual Function after receiving a Migrate In or Out
Request.

Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>

3 files changed, 129 insertions, 0 deletions

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index d0ff8ad8f7b..7227efc760d 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -179,6 +179,97 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset)
 	pci_dev_put(dev);
 }
 
+static int sriov_migration(struct pci_dev *dev)
+{
+	u16 status;
+	struct pci_sriov *iov = dev->sriov;
+
+	if (!iov->nr_virtfn)
+		return 0;
+
+	if (!(iov->cap & PCI_SRIOV_CAP_VFM))
+		return 0;
+
+	pci_read_config_word(dev, iov->pos + PCI_SRIOV_STATUS, &status);
+	if (!(status & PCI_SRIOV_STATUS_VFM))
+		return 0;
+
+	schedule_work(&iov->mtask);
+
+	return 1;
+}
+
+static void sriov_migration_task(struct work_struct *work)
+{
+	int i;
+	u8 state;
+	u16 status;
+	struct pci_sriov *iov = container_of(work, struct pci_sriov, mtask);
+
+	for (i = iov->initial; i < iov->nr_virtfn; i++) {
+		state = readb(iov->mstate + i);
+		if (state == PCI_SRIOV_VFM_MI) {
+			writeb(PCI_SRIOV_VFM_AV, iov->mstate + i);
+			state = readb(iov->mstate + i);
+			if (state == PCI_SRIOV_VFM_AV)
+				virtfn_add(iov->self, i, 1);
+		} else if (state == PCI_SRIOV_VFM_MO) {
+			virtfn_remove(iov->self, i, 1);
+			writeb(PCI_SRIOV_VFM_UA, iov->mstate + i);
+			state = readb(iov->mstate + i);
+			if (state == PCI_SRIOV_VFM_AV)
+				virtfn_add(iov->self, i, 0);
+		}
+	}
+
+	pci_read_config_word(iov->self, iov->pos + PCI_SRIOV_STATUS, &status);
+	status &= ~PCI_SRIOV_STATUS_VFM;
+	pci_write_config_word(iov->self, iov->pos + PCI_SRIOV_STATUS, status);
+}
+
+static int sriov_enable_migration(struct pci_dev *dev, int nr_virtfn)
+{
+	int bir;
+	u32 table;
+	resource_size_t pa;
+	struct pci_sriov *iov = dev->sriov;
+
+	if (nr_virtfn <= iov->initial)
+		return 0;
+
+	pci_read_config_dword(dev, iov->pos + PCI_SRIOV_VFM, &table);
+	bir = PCI_SRIOV_VFM_BIR(table);
+	if (bir > PCI_STD_RESOURCE_END)
+		return -EIO;
+
+	table = PCI_SRIOV_VFM_OFFSET(table);
+	if (table + nr_virtfn > pci_resource_len(dev, bir))
+		return -EIO;
+
+	pa = pci_resource_start(dev, bir) + table;
+	iov->mstate = ioremap(pa, nr_virtfn);
+	if (!iov->mstate)
+		return -ENOMEM;
+
+	INIT_WORK(&iov->mtask, sriov_migration_task);
+
+	iov->ctrl |= PCI_SRIOV_CTRL_VFM | PCI_SRIOV_CTRL_INTR;
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+
+	return 0;
+}
+
+static void sriov_disable_migration(struct pci_dev *dev)
+{
+	struct pci_sriov *iov = dev->sriov;
+
+	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFM | PCI_SRIOV_CTRL_INTR);
+	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
+
+	cancel_work_sync(&iov->mtask);
+	iounmap(iov->mstate);
+}
+
 static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 {
 	int rc;
@@ -261,6 +352,12 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 			goto failed;
 	}
 
+	if (iov->cap & PCI_SRIOV_CAP_VFM) {
+		rc = sriov_enable_migration(dev, nr_virtfn);
+		if (rc)
+			goto failed;
+	}
+
 	kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE);
 	iov->nr_virtfn = nr_virtfn;
 
@@ -290,6 +387,9 @@ static void sriov_disable(struct pci_dev *dev)
 	if (!iov->nr_virtfn)
 		return;
 
+	if (iov->cap & PCI_SRIOV_CAP_VFM)
+		sriov_disable_migration(dev);
+
 	for (i = 0; i < iov->nr_virtfn; i++)
 		virtfn_remove(dev, i, 0);
 
@@ -559,3 +659,22 @@ void pci_disable_sriov(struct pci_dev *dev)
 	sriov_disable(dev);
 }
 EXPORT_SYMBOL_GPL(pci_disable_sriov);
+
+/**
+ * pci_sriov_migration - notify SR-IOV core of Virtual Function Migration
+ * @dev: the PCI device
+ *
+ * Returns IRQ_HANDLED if the IRQ is handled, or IRQ_NONE if not.
+ *
+ * Physical Function driver is responsible to register IRQ handler using
+ * VF Migration Interrupt Message Number, and call this function when the
+ * interrupt is generated by the hardware.
+ */
+irqreturn_t pci_sriov_migration(struct pci_dev *dev)
+{
+	if (!dev->is_physfn)
+		return IRQ_NONE;
+
+	return sriov_migration(dev) ? IRQ_HANDLED : IRQ_NONE;
+}
+EXPORT_SYMBOL_GPL(pci_sriov_migration);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 0f1c7d10350..22dcfdb75d9 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -1,6 +1,8 @@
 #ifndef DRIVERS_PCI_H
 #define DRIVERS_PCI_H
 
+#include <linux/workqueue.h>
+
 #define PCI_CFG_SPACE_SIZE	256
 #define PCI_CFG_SPACE_EXP_SIZE	4096
 
@@ -218,6 +220,8 @@ struct pci_sriov {
 	struct pci_dev *dev;	/* lowest numbered PF */
 	struct pci_dev *self;	/* this PF */
 	struct mutex lock;	/* lock for VF bus */
+	struct work_struct mtask; /* VF Migration task */
+	u8 __iomem *mstate;	/* VF Migration State Array */
 };
 
 #ifdef CONFIG_PCI_IOV
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c2e491e0406..1216843412d 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -52,6 +52,7 @@
 #include <asm/atomic.h>
 #include <linux/device.h>
 #include <linux/io.h>
+#include <linux/irqreturn.h>
 
 /* Include the ID list */
 #include <linux/pci_ids.h>
@@ -1219,6 +1220,7 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
 #ifdef CONFIG_PCI_IOV
 extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 extern void pci_disable_sriov(struct pci_dev *dev);
+extern irqreturn_t pci_sriov_migration(struct pci_dev *dev);
 #else
 static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
 {
@@ -1227,6 +1229,10 @@ static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
 static inline void pci_disable_sriov(struct pci_dev *dev)
 {
 }
+static inline irqreturn_t pci_sriov_migration(struct pci_dev *dev)
+{
+	return IRQ_NONE;
+}
 #endif
 
 #endif /* __KERNEL__ */