If a device has the SR-IOV capability, initialize it (set the ARI
Capable Hierarchy in the lowest numbered PF if necessary; calculate
the System Page Size for the VF MMIO, probe the VF Offset, Stride
and BARs). A lock for the VF bus allocation is also initialized if
a PF is the lowest numbered PF.
Signed-off-by: Yu Zhao <yu.zhao@xxxxxxxxx>
---
drivers/pci/Kconfig | 10 +++
drivers/pci/Makefile | 2 +
drivers/pci/iov.c | 182 ++++++++++++++++++++++++++++++++++++++++++++++
drivers/pci/pci.c | 7 ++
drivers/pci/pci.h | 37 +++++++++
drivers/pci/probe.c | 4 +
include/linux/pci.h | 9 ++
include/linux/pci_regs.h | 33 ++++++++
8 files changed, 284 insertions(+), 0 deletions(-)
create mode 100644 drivers/pci/iov.c
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 2a4501d..25cf360 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -59,3 +59,13 @@ config HT_IRQ
This allows native hypertransport devices to use interrupts.
If unsure say Y.
+
+config PCI_IOV
+ bool "PCI IOV support"
+ depends on PCI
+ help
+ PCI-SIG I/O Virtualization (IOV) Specifications support.
+ Single Root IOV: allows the creation of virtual PCI devices
+ that share the physical resources from a real device.
+
+ When in doubt, say N.
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 3d07ce2..ba6af16 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -29,6 +29,8 @@ obj-$(CONFIG_DMAR) += dmar.o iova.o intel-iommu.o
obj-$(CONFIG_INTR_REMAP) += dmar.o intr_remapping.o
+obj-$(CONFIG_PCI_IOV) += iov.o
+
#
# Some architectures use the generic PCI setup functions
#
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
new file mode 100644
index 0000000..656216c
--- /dev/null
+++ b/drivers/pci/iov.c
@@ -0,0 +1,182 @@
+/*
+ * drivers/pci/iov.c
+ *
+ * Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@xxxxxxxxx>
+ *
+ * PCI Express I/O Virtualization (IOV) support.
+ * Single Root IOV 1.0
+ */
+
+#include <linux/pci.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include "pci.h"
+
+
+static int sriov_init(struct pci_dev *dev, int pos)
+{
+ int i;
+ int rc;
+ int nres;
+ u32 pgsz;
+ u16 ctrl, total, offset, stride;
+ struct pci_sriov *iov;
+ struct resource *res;
+ struct pci_dev *pdev;
+
+ if (dev->pcie_type != PCI_EXP_TYPE_RC_END &&
+ dev->pcie_type != PCI_EXP_TYPE_ENDPOINT)
+ return -ENODEV;
+
+ pci_read_config_word(dev, pos + PCI_SRIOV_CTRL, &ctrl);
+ if (ctrl & PCI_SRIOV_CTRL_VFE) {
+ pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, 0);
+ ssleep(1);
+ }
+
+ pci_read_config_word(dev, pos + PCI_SRIOV_TOTAL_VF, &total);
+ if (!total)
+ return 0;
+
+ list_for_each_entry(pdev, &dev->bus->devices, bus_list)
+ if (pdev->is_physfn)
+ break;
+ if (list_empty(&dev->bus->devices) || !pdev->is_physfn)
+ pdev = NULL;
+
+ ctrl = 0;
+ if (!pdev && pci_ari_enabled(dev->bus))
+ ctrl |= PCI_SRIOV_CTRL_ARI;
+
+ pci_write_config_word(dev, pos + PCI_SRIOV_CTRL, ctrl);
+ pci_write_config_word(dev, pos + PCI_SRIOV_NUM_VF, total);
+ pci_read_config_word(dev, pos + PCI_SRIOV_VF_OFFSET, &offset);
+ pci_read_config_word(dev, pos + PCI_SRIOV_VF_STRIDE, &stride);
+ if (!offset || (total > 1 && !stride))
+ return -EIO;
+
+ pci_read_config_dword(dev, pos + PCI_SRIOV_SUP_PGSIZE, &pgsz);
+ i = PAGE_SHIFT > 12 ? PAGE_SHIFT - 12 : 0;
+ pgsz &= ~((1 << i) - 1);
+ if (!pgsz)
+ return -EIO;
+
+ pgsz &= ~(pgsz - 1);
+ pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz);
+
+ nres = 0;
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ res = dev->resource + PCI_IOV_RESOURCES + i;
+ i += __pci_read_base(dev, pci_bar_unknown, res,
+ pos + PCI_SRIOV_BAR + i * 4);
+ if (!res->flags)
+ continue;
+ if (resource_size(res) & (PAGE_SIZE - 1)) {
+ rc = -EIO;
+ goto failed;
+ }
+ res->end = res->start + resource_size(res) * total - 1;
+ nres++;
+ }
+
+ iov = kzalloc(sizeof(*iov), GFP_KERNEL);
+ if (!iov) {
+ rc = -ENOMEM;
+ goto failed;
+ }
+
+ iov->pos = pos;
+ iov->nres = nres;
+ iov->ctrl = ctrl;
+ iov->total = total;
+ iov->offset = offset;
+ iov->stride = stride;
+ iov->pgsz = pgsz;
+ iov->self = dev;
+ pci_read_config_dword(dev, pos + PCI_SRIOV_CAP, &iov->cap);
+ pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link);
+
+ if (pdev)
+ iov->dev = pci_dev_get(pdev);
+ else {
+ iov->dev = dev;
+ mutex_init(&iov->lock);
+ }
+
+ dev->sriov = iov;
+ dev->is_physfn = 1;
+
+ return 0;
+
+failed:
+ for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+ res = dev->resource + PCI_IOV_RESOURCES + i;
+ res->flags = 0;
+ }
+
+ return rc;
+}
+
+static void sriov_release(struct pci_dev *dev)
+{
+ if (dev == dev->sriov->dev)
+ mutex_destroy(&dev->sriov->lock);
+ else
+ pci_dev_put(dev->sriov->dev);
+
+ kfree(dev->sriov);
+ dev->sriov = NULL;
+}
+
+/**
+ * pci_iov_init - initialize the IOV capability
+ * @dev: the PCI device
+ *
+ * Returns 0 on success, or negative on failure.
+ */
+int pci_iov_init(struct pci_dev *dev)
+{
+ int pos;
+
+ if (!dev->is_pcie)
+ return -ENODEV;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_SRIOV);
+ if (pos)
+ return sriov_init(dev, pos);
+
+ return -ENODEV;
+}
+
+/**
+ * pci_iov_release - release resources used by the IOV capability
+ * @dev: the PCI device
+ */
+void pci_iov_release(struct pci_dev *dev)
+{
+ if (dev->is_physfn)
+ sriov_release(dev);
+}
+
+/**
+ * pci_iov_resource_bar - get position of the SR-IOV BAR
+ * @dev: the PCI device
+ * @resno: the resource number
+ * @type: the BAR type to be filled in
+ *
+ * Returns position of the BAR encapsulated in the SR-IOV capability.
+ */
+int pci_iov_resource_bar(struct pci_dev *dev, int resno,
+ enum pci_bar_type *type)
+{
+ if (resno < PCI_IOV_RESOURCES || resno > PCI_IOV_RESOURCE_END)
+ return 0;
+
+ BUG_ON(!dev->is_physfn);
+
+ *type = pci_bar_unknown;
+
+ return dev->sriov->pos + PCI_SRIOV_BAR +
+ 4 * (resno - PCI_IOV_RESOURCES);
+}
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6d61200..2eba2a5 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2346,12 +2346,19 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags)
*/
int pci_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type)
{
+ int reg;
+
if (resno < PCI_ROM_RESOURCE) {
*type = pci_bar_unknown;
return PCI_BASE_ADDRESS_0 + 4 * resno;
} else if (resno == PCI_ROM_RESOURCE) {
*type = pci_bar_mem32;
return dev->rom_base_reg;
+ } else if (resno < PCI_BRIDGE_RESOURCES) {
+ /* device specific resource */
+ reg = pci_iov_resource_bar(dev, resno, type);
+ if (reg)
+ return reg;
}
dev_err(&dev->dev, "BAR: invalid resource #%d\n", resno);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 07c0aa5..196be5e 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -195,4 +195,41 @@ static inline int pci_ari_enabled(struct pci_bus *bus)
return bus->self && bus->self->ari_enabled;
}
+/* Single Root I/O Virtualization */
+struct pci_sriov {
+ int pos; /* capability position */
+ int nres; /* number of resources */
+ u32 cap; /* SR-IOV Capabilities */
+ u16 ctrl; /* SR-IOV Control */
+ u16 total; /* total VFs associated with the PF */
+ u16 offset; /* first VF Routing ID offset */
+ u16 stride; /* following VF stride */
+ u32 pgsz; /* page size for BAR alignment */
+ u8 link; /* Function Dependency Link */
+ struct pci_dev *dev; /* lowest numbered PF */
+ struct pci_dev *self; /* this PF */
+ struct mutex lock; /* lock for VF bus */
+};
+
+#ifdef CONFIG_PCI_IOV
+extern int pci_iov_init(struct pci_dev *dev);
+extern void pci_iov_release(struct pci_dev *dev);
+extern int pci_iov_resource_bar(struct pci_dev *dev, int resno,
+ enum pci_bar_type *type);
+#else
+static inline int pci_iov_init(struct pci_dev *dev)
+{
+ return -ENODEV;
+}
+static inline void pci_iov_release(struct pci_dev *dev)
+
+{
+}
+static inline int pci_iov_resource_bar(struct pci_dev *dev, int resno,
+ enum pci_bar_type *type)
+{
+ return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
#endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 55ec44a..03b6f29 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -785,6 +785,7 @@ static int pci_setup_device(struct pci_dev * dev)
static void pci_release_capabilities(struct pci_dev *dev)
{
pci_vpd_release(dev);
+ pci_iov_release(dev);
}
/**
@@ -972,6 +973,9 @@ static void pci_init_capabilities(struct pci_dev *dev)
/* Alternative Routing-ID Forwarding */
pci_enable_ari(dev);
+
+ /* Single Root I/O Virtualization */
+ pci_iov_init(dev);
}
void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7bd624b..8eba820 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -93,6 +93,12 @@ enum {
/* #6: expansion ROM resource */
PCI_ROM_RESOURCE,
+ /* device specific resources */
+#ifdef CONFIG_PCI_IOV
+ PCI_IOV_RESOURCES,
+ PCI_IOV_RESOURCE_END = PCI_IOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1,
+#endif
+
/* resources assigned to buses behind the bridge */
#define PCI_BRIDGE_RESOURCE_NUM 4
@@ -180,6 +186,7 @@ struct pci_cap_saved_state {
struct pcie_link_state;
struct pci_vpd;
+struct pci_sriov;
/*
* The pci_dev structure is used to describe PCI devices.
@@ -257,6 +264,7 @@ struct pci_dev {
unsigned int is_managed:1;
unsigned int is_pcie:1;
unsigned int state_saved:1;
+ unsigned int is_physfn:1;
pci_dev_flags_t dev_flags;
atomic_t enable_cnt; /* pci_enable_device has been called */
@@ -270,6 +278,7 @@ struct pci_dev {
struct list_head msi_list;
#endif
struct pci_vpd *vpd;
+ struct pci_sriov *sriov; /* SR-IOV capability related */
};
extern struct pci_dev *alloc_pci_dev(void);
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index 027815b..4ce5eb0 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -375,6 +375,7 @@
#define PCI_EXP_TYPE_UPSTREAM 0x5 /* Upstream Port */
#define PCI_EXP_TYPE_DOWNSTREAM 0x6 /* Downstream Port */
#define PCI_EXP_TYPE_PCI_BRIDGE 0x7 /* PCI/PCI-X Bridge */
+#define PCI_EXP_TYPE_RC_END 0x9 /* Root Complex Integrated Endpoint */
#define PCI_EXP_FLAGS_SLOT 0x0100 /* Slot implemented */
#define PCI_EXP_FLAGS_IRQ 0x3e00 /* Interrupt message number */
#define PCI_EXP_DEVCAP 4 /* Device capabilities */
@@ -498,6 +499,7 @@
#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_SRIOV 16
/* Advanced Error Reporting */
#define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */
@@ -615,4 +617,35 @@
#define PCI_ARI_CTRL_ACS 0x0002 /* ACS Function Groups Enable */
#define PCI_ARI_CTRL_FG(x) (((x) >> 4) & 7) /* Function Group */
+/* Single Root I/O Virtualization */
+#define PCI_SRIOV_CAP 0x04 /* SR-IOV Capabilities */
+#define PCI_SRIOV_CAP_VFM 0x01 /* VF Migration Capable */
+#define PCI_SRIOV_CAP_INTR(x) ((x) >> 21) /* Interrupt Message Number */
+#define PCI_SRIOV_CTRL 0x08 /* SR-IOV Control */
+#define PCI_SRIOV_CTRL_VFE 0x01 /* VF Enable */
+#define PCI_SRIOV_CTRL_VFM 0x02 /* VF Migration Enable */
+#define PCI_SRIOV_CTRL_INTR 0x04 /* VF Migration Interrupt Enable */
+#define PCI_SRIOV_CTRL_MSE 0x08 /* VF Memory Space Enable */
+#define PCI_SRIOV_CTRL_ARI 0x10 /* ARI Capable Hierarchy */
+#define PCI_SRIOV_STATUS 0x0a /* SR-IOV Status */
+#define PCI_SRIOV_STATUS_VFM 0x01 /* VF Migration Status */
+#define PCI_SRIOV_INITIAL_VF 0x0c /* Initial VFs */
+#define PCI_SRIOV_TOTAL_VF 0x0e /* Total VFs */
+#define PCI_SRIOV_NUM_VF 0x10 /* Number of VFs */
+#define PCI_SRIOV_FUNC_LINK 0x12 /* Function Dependency Link */
+#define PCI_SRIOV_VF_OFFSET 0x14 /* First VF Offset */
+#define PCI_SRIOV_VF_STRIDE 0x16 /* Following VF Stride */
+#define PCI_SRIOV_VF_DID 0x1a /* VF Device ID */
+#define PCI_SRIOV_SUP_PGSIZE 0x1c /* Supported Page Sizes */
+#define PCI_SRIOV_SYS_PGSIZE 0x20 /* System Page Size */
+#define PCI_SRIOV_BAR 0x24 /* VF BAR0 */
+#define PCI_SRIOV_NUM_BARS 6 /* Number of VF BARs */
+#define PCI_SRIOV_VFM 0x3c /* VF Migration State Array Offset*/
+#define PCI_SRIOV_VFM_BIR(x) ((x) & 7) /* State BIR */
+#define PCI_SRIOV_VFM_OFFSET(x) ((x) & ~7) /* State Offset */
+#define PCI_SRIOV_VFM_UA 0x0 /* Inactive.Unavailable */
+#define PCI_SRIOV_VFM_MI 0x1 /* Dormant.MigrateIn */
+#define PCI_SRIOV_VFM_MO 0x2 /* Active.MigrateOut */
+#define PCI_SRIOV_VFM_AV 0x3 /* Active.Available */
+
#endif /* LINUX_PCI_REGS_H */
--
1.6.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
