# HG changeset patch
# User Keir Fraser <keir.fraser@xxxxxxxxxx>
# Date 1237376344 0
# Node ID fb46e5625c614ac086e852e3633f29309378812f
# Parent 6669e480cb59e70767d835bbd0294ed5266692a9
PCI: initialize and release SR-IOV capability
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 | 9 ++
drivers/pci/Makefile | 2
drivers/pci/iov.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++
drivers/pci/pci.c | 7 +
drivers/pci/pci.h | 37 +++++++++
drivers/pci/probe.c | 6 +
include/linux/pci.h | 14 +++
include/linux/pci_regs.h | 33 ++++++++
8 files changed, 282 insertions(+), 1 deletion(-)
diff -r 6669e480cb59 -r fb46e5625c61 drivers/pci/Kconfig
--- a/drivers/pci/Kconfig Tue Mar 17 14:27:31 2009 +0000
+++ b/drivers/pci/Kconfig Wed Mar 18 11:39:04 2009 +0000
@@ -37,3 +37,12 @@ config PCI_GUESTDEV
help
Say Y here if you want to reserve PCI device for passthrough.
+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 -r 6669e480cb59 -r fb46e5625c61 drivers/pci/Makefile
--- a/drivers/pci/Makefile Tue Mar 17 14:27:31 2009 +0000
+++ b/drivers/pci/Makefile Wed Mar 18 11:39:04 2009 +0000
@@ -15,6 +15,8 @@ obj-$(CONFIG_HOTPLUG) += hotplug.o
# Build the PCI Hotplug drivers if we were asked to
obj-$(CONFIG_HOTPLUG_PCI) += hotplug/
+
+obj-$(CONFIG_PCI_IOV) += iov.o
#
# Some architectures use the generic PCI setup functions
diff -r 6669e480cb59 -r fb46e5625c61 drivers/pci/iov.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/drivers/pci/iov.c Wed Mar 18 11:39:04 2009 +0000
@@ -0,0 +1,175 @@
+/*
+ * 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;
+
+ 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 ((res->end - res->start + 1) & (PAGE_SIZE - 1)) {
+ rc = -EIO;
+ goto failed;
+ }
+ res->end = res->start + (res->end - res->start + 1) * 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;
+
+ 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 -r 6669e480cb59 -r fb46e5625c61 drivers/pci/pci.c
--- a/drivers/pci/pci.c Tue Mar 17 14:27:31 2009 +0000
+++ b/drivers/pci/pci.c Wed Mar 18 11:39:04 2009 +0000
@@ -1048,12 +1048,19 @@ pci_set_consistent_dma_mask(struct pci_d
*/
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 -r 6669e480cb59 -r fb46e5625c61 drivers/pci/pci.h
--- a/drivers/pci/pci.h Tue Mar 17 14:27:31 2009 +0000
+++ b/drivers/pci/pci.h Wed Mar 18 11:39:04 2009 +0000
@@ -132,3 +132,40 @@ static inline int pci_ari_enabled(struct
{
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 */
diff -r 6669e480cb59 -r fb46e5625c61 drivers/pci/probe.c
--- a/drivers/pci/probe.c Tue Mar 17 14:27:31 2009 +0000
+++ b/drivers/pci/probe.c Wed Mar 18 11:39:04 2009 +0000
@@ -765,6 +765,9 @@ static void pci_release_dev(struct devic
struct pci_dev *pci_dev;
pci_dev = to_pci_dev(dev);
+
+ pci_iov_release(pci_dev);
+
kfree(pci_dev);
}
@@ -891,6 +894,9 @@ void __devinit pci_device_add(struct pci
/* Alternative Routing-ID Forwarding */
pci_enable_ari(dev);
+
+ /* Single Root I/O Virtualization */
+ pci_iov_init(dev);
/*
* Add the device to our list of discovered devices
diff -r 6669e480cb59 -r fb46e5625c61 include/linux/pci.h
--- a/include/linux/pci.h Tue Mar 17 14:27:31 2009 +0000
+++ b/include/linux/pci.h Wed Mar 18 11:39:04 2009 +0000
@@ -77,6 +77,12 @@ 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
@@ -127,6 +133,8 @@ struct pci_cap_saved_state {
char cap_nr;
u32 data[0];
};
+
+struct pci_sriov;
/*
* The pci_dev structure is used to describe PCI devices.
@@ -189,13 +197,17 @@ struct pci_dev {
unsigned int broken_parity_status:1; /* Device generates false
positive parity */
unsigned int msi_enabled:1;
unsigned int msix_enabled:1;
+ unsigned int ari_enabled:1; /* ARI forwarding */
+ unsigned int is_physfn:1;
u32 saved_config_space[16]; /* config space saved at
suspend time */
struct hlist_head saved_cap_space;
struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM
entry */
int rom_attr_enabled; /* has display of the rom attribute
been enabled? */
struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file
for resources */
- unsigned int ari_enabled:1; /* ARI forwarding */
+#ifdef CONFIG_PCI_IOV
+ struct pci_sriov *sriov; /* SR-IOV capability related */
+#endif
};
#define pci_dev_g(n) list_entry(n, struct pci_dev, global_list)
diff -r 6669e480cb59 -r fb46e5625c61 include/linux/pci_regs.h
--- a/include/linux/pci_regs.h Tue Mar 17 14:27:31 2009 +0000
+++ b/include/linux/pci_regs.h Wed Mar 18 11:39:04 2009 +0000
@@ -332,6 +332,7 @@
#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 */
@@ -393,6 +394,7 @@
#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 */
@@ -478,4 +480,35 @@
#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 */
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
Home