PCI: support the ATS capability
The PCIe ATS capability makes the Endpoint be able to request the
DMA address translation from the IOMMU and cache the translation
in the device side, thus alleviate IOMMU pressure and improve the
hardware performance in the I/O virtualization environment.
Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index b497daa..0a7a1b4 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -5,6 +5,7 @@
*
* PCI Express I/O Virtualization (IOV) support.
* Single Root IOV 1.0
+ * Address Translation Service 1.0
*/
#include <linux/pci.h>
@@ -679,3 +680,107 @@
return sriov_migration(dev) ? IRQ_HANDLED : IRQ_NONE;
}
EXPORT_SYMBOL_GPL(pci_sriov_migration);
+
+static int ats_alloc_one(struct pci_dev *dev, int ps)
+{
+ int pos;
+ u16 cap;
+ struct pci_ats *ats;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
+ if (!pos)
+ return -ENODEV;
+
+ ats = kzalloc(sizeof(*ats), GFP_KERNEL);
+ if (!ats)
+ return -ENOMEM;
+
+ ats->pos = pos;
+ ats->stu = ps;
+ pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
+ ats->qdep = PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
+ PCI_ATS_MAX_QDEP;
+ dev->ats = ats;
+
+ return 0;
+}
+
+static void ats_free_one(struct pci_dev *dev)
+{
+ kfree(dev->ats);
+ dev->ats = NULL;
+}
+
+/**
+ * pci_enable_ats - enable the ATS capability
+ * @dev: the PCI device
+ * @ps: the IOMMU page shift
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_enable_ats(struct pci_dev *dev, int ps)
+{
+ int rc;
+ u16 ctrl;
+
+ BUG_ON(dev->ats);
+
+ if (ps < PCI_ATS_MIN_STU)
+ return -EINVAL;
+
+ rc = ats_alloc_one(dev, ps);
+ if (rc)
+ return rc;
+
+ ctrl = PCI_ATS_CTRL_ENABLE;
+ ctrl |= PCI_ATS_CTRL_STU(ps - PCI_ATS_MIN_STU);
+ pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
+
+ return 0;
+}
+
+/**
+ * pci_disable_ats - disable the ATS capability
+ * @dev: the PCI device
+ */
+void pci_disable_ats(struct pci_dev *dev)
+{
+ u16 ctrl;
+
+ BUG_ON(!dev->ats);
+
+ pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl);
+ ctrl &= ~PCI_ATS_CTRL_ENABLE;
+ pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
+
+ ats_free_one(dev);
+}
+
+/**
+ * pci_ats_queue_depth - query the ATS Invalidate Queue Depth
+ * @dev: the PCI device
+ *
+ * Returns the queue depth on success, or negative on failure.
+ *
+ * The ATS spec uses 0 in the Invalidate Queue Depth field to
+ * indicate that the function can accept 32 Invalidate Request.
+ * But here we use the `real' values (i.e. 1~32) for the Queue
+ * Depth.
+ */
+int pci_ats_queue_depth(struct pci_dev *dev)
+{
+ int pos;
+ u16 cap;
+
+ if (dev->ats)
+ return dev->ats->qdep;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ATS);
+ if (!pos)
+ return -ENODEV;
+
+ pci_read_config_word(dev, pos + PCI_ATS_CAP, &cap);
+
+ return PCI_ATS_CAP_QDEP(cap) ? PCI_ATS_CAP_QDEP(cap) :
+ PCI_ATS_MAX_QDEP;
+}
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index d03f6b9..3c2ec64 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -229,6 +229,13 @@
u8 __iomem *mstate; /* VF Migration State Array */
};
+/* Address Translation Service */
+struct pci_ats {
+ int pos; /* capability position */
+ int stu; /* Smallest Translation Unit */
+ int qdep; /* Invalidate Queue Depth */
+};
+
#ifdef CONFIG_PCI_IOV
extern int pci_iov_init(struct pci_dev *dev);
extern void pci_iov_release(struct pci_dev *dev);
@@ -236,6 +243,20 @@
enum pci_bar_type *type);
extern void pci_restore_iov_state(struct pci_dev *dev);
extern int pci_iov_bus_range(struct pci_bus *bus);
+
+extern int pci_enable_ats(struct pci_dev *dev, int ps);
+extern void pci_disable_ats(struct pci_dev *dev);
+extern int pci_ats_queue_depth(struct pci_dev *dev);
+/**
+ * pci_ats_enabled - query the ATS status
+ * @dev: the PCI device
+ *
+ * Returns 1 if ATS capability is enabled, or 0 if not.
+ */
+static inline int pci_ats_enabled(struct pci_dev *dev)
+{
+ return !!dev->ats;
+}
#else
static inline int pci_iov_init(struct pci_dev *dev)
{
@@ -257,6 +278,22 @@
{
return 0;
}
+
+static inline int pci_enable_ats(struct pci_dev *dev, int ps)
+{
+ return -ENODEV;
+}
+static inline void pci_disable_ats(struct pci_dev *dev)
+{
+}
+static inline int pci_ats_queue_depth(struct pci_dev *dev)
+{
+ return -ENODEV;
+}
+static inline int pci_ats_enabled(struct pci_dev *dev)
+{
+ return 0;
+}
#endif /* CONFIG_PCI_IOV */
#endif /* DRIVERS_PCI_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 72698d8..bd3e4a7 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -188,6 +188,7 @@
struct pcie_link_state;
struct pci_vpd;
struct pci_sriov;
+struct pci_ats;
/*
* The pci_dev structure is used to describe PCI devices.
@@ -285,6 +286,7 @@
struct pci_sriov *sriov; /* SR-IOV capability related */
struct pci_dev *physfn; /* the PF this VF is associated with */
};
+ struct pci_ats *ats; /* Address Translation Service */
#endif
};
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index e4d08c1..c03189c 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -501,6 +501,7 @@
#define PCI_EXT_CAP_ID_DSN 3
#define PCI_EXT_CAP_ID_PWR 4
#define PCI_EXT_CAP_ID_ARI 14
+#define PCI_EXT_CAP_ID_ATS 15
#define PCI_EXT_CAP_ID_SRIOV 16
/* Advanced Error Reporting */
@@ -619,6 +620,15 @@
#define PCI_ARI_CTRL_ACS 0x0002 /* ACS Function Groups Enable */
#define PCI_ARI_CTRL_FG(x) (((x) >> 4) & 7) /* Function Group */
+/* Address Translation Service */
+#define PCI_ATS_CAP 0x04 /* ATS Capability Register */
+#define PCI_ATS_CAP_QDEP(x) ((x) & 0x1f) /* Invalidate Queue Depth */
+#define PCI_ATS_MAX_QDEP 32 /* Max Invalidate Queue Depth */
+#define PCI_ATS_CTRL 0x06 /* ATS Control Register */
+#define PCI_ATS_CTRL_ENABLE 0x8000 /* ATS Enable */
+#define PCI_ATS_CTRL_STU(x) ((x) & 0x1f) /* Smallest Translation Unit */
+#define PCI_ATS_MIN_STU 12 /* shift of minimum STU block */
+
/* Single Root I/O Virtualization */
#define PCI_SRIOV_CAP 0x04 /* SR-IOV Capabilities */
#define PCI_SRIOV_CAP_VFM 0x01 /* VF Migration Capable */