Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
---
drivers/xen/Kconfig | 18 +
drivers/xen/Makefile | 1 +
drivers/xen/pcifront/Makefile | 7 +
drivers/xen/pcifront/pci.c | 46 +++
drivers/xen/pcifront/pci_op.c | 666 +++++++++++++++++++++++++++++++++++++++
drivers/xen/pcifront/pcifront.h | 55 ++++
drivers/xen/pcifront/xenbus.c | 468 +++++++++++++++++++++++++++
include/xen/pcifront.h | 83 +++++
8 files changed, 1344 insertions(+), 0 deletions(-)
create mode 100644 drivers/xen/pcifront/Makefile
create mode 100644 drivers/xen/pcifront/pci.c
create mode 100644 drivers/xen/pcifront/pci_op.c
create mode 100644 drivers/xen/pcifront/pcifront.h
create mode 100644 drivers/xen/pcifront/xenbus.c
create mode 100644 include/xen/pcifront.h
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index bc6c3f4..d4a33b6 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -173,3 +173,21 @@ config ACPI_PROCESSOR_XEN
bool
depends on XEN_DOM0 && ACPI_PROCESSOR && CPU_FREQ
default y
+
+config XEN_PCIDEV_FRONTEND
+ bool "Xen PCI Frontend"
+ depends on PCI && X86_64
+ select HOTPLUG
+ default y
+ help
+ The PCI device frontend driver allows the kernel to import arbitrary
+ PCI devices from a PCI backend to support PCI driver domains.
+
+config XEN_PCIDEV_FE_DEBUG
+ bool "Xen PCI Frontend Debugging"
+ depends on XEN_PCIDEV_FRONTEND
+ default n
+ help
+ Enables some debug statements within the PCI Frontend.
+
+
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index cddfffb..0bba5f2 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_XEN_GNTDEV) += gntdev.o
obj-$(CONFIG_XEN_BLKDEV_BACKEND) += blkback/
obj-$(CONFIG_XEN_NETDEV_BACKEND) += netback/
obj-$(CONFIG_XEN_PCIDEV_BACKEND) += pciback/
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += pcifront/
obj-$(CONFIG_XENFS) += xenfs/
obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
obj-$(CONFIG_XEN_S3) += acpi.o
diff --git a/drivers/xen/pcifront/Makefile b/drivers/xen/pcifront/Makefile
new file mode 100644
index 0000000..621e988
--- /dev/null
+++ b/drivers/xen/pcifront/Makefile
@@ -0,0 +1,7 @@
+obj-y += pcifront.o
+
+pcifront-y := pci_op.o xenbus.o pci.o
+
+ifeq ($(CONFIG_XEN_PCIDEV_FE_DEBUG),y)
+EXTRA_CFLAGS += -DDEBUG
+endif
diff --git a/drivers/xen/pcifront/pci.c b/drivers/xen/pcifront/pci.c
new file mode 100644
index 0000000..4239f00
--- /dev/null
+++ b/drivers/xen/pcifront/pci.c
@@ -0,0 +1,46 @@
+/*
+ * PCI Frontend Operations - ensure only one PCI frontend runs at a time
+ *
+ * Author: Ryan Wilson <hap9@xxxxxxxxxxxxxx>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include "pcifront.h"
+
+DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev = NULL;
+
+int pcifront_connect(struct pcifront_device *pdev)
+{
+ int err = 0;
+
+ spin_lock(&pcifront_dev_lock);
+
+ if (!pcifront_dev) {
+ dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
+ pcifront_dev = pdev;
+ }
+ else {
+ dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+ err = -EEXIST;
+ }
+
+ spin_unlock(&pcifront_dev_lock);
+
+ return err;
+}
+
+void pcifront_disconnect(struct pcifront_device *pdev)
+{
+ spin_lock(&pcifront_dev_lock);
+
+ if (pdev == pcifront_dev) {
+ dev_info(&pdev->xdev->dev,
+ "Disconnecting PCI Frontend Buses\n");
+ pcifront_dev = NULL;
+ }
+
+ spin_unlock(&pcifront_dev_lock);
+}
diff --git a/drivers/xen/pcifront/pci_op.c b/drivers/xen/pcifront/pci_op.c
new file mode 100644
index 0000000..2034d20
--- /dev/null
+++ b/drivers/xen/pcifront/pci_op.c
@@ -0,0 +1,666 @@
+/*
+ * PCI Frontend Operations - Communicates with frontend
+ *
+ * Author: Ryan Wilson <hap9@xxxxxxxxxxxxxx>
+ */
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <asm/bitops.h>
+#include <linux/time.h>
+#include <xen/evtchn.h>
+#include "pcifront.h"
+
+static int verbose_request = 0;
+module_param(verbose_request, int, 0644);
+
+#ifdef __ia64__
+static void pcifront_init_sd(struct pcifront_sd *sd,
+ unsigned int domain, unsigned int bus,
+ struct pcifront_device *pdev)
+{
+ int err, i, j, k, len, root_num, res_count;
+ struct acpi_resource res;
+ unsigned int d, b, byte;
+ unsigned long magic;
+ char str[64], tmp[3];
+ unsigned char *buf, *bufp;
+ u8 *ptr;
+
+ memset(sd, 0, sizeof(*sd));
+
+ sd->segment = domain;
+ sd->node = -1; /* Revisit for NUMA */
+ sd->platform_data = pdev;
+
+ /* Look for resources for this controller in xenbus. */
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "root_num",
+ "%d", &root_num);
+ if (err != 1)
+ return;
+
+ for (i = 0; i < root_num; i++) {
+ len = snprintf(str, sizeof(str), "root-%d", i);
+ if (unlikely(len >= (sizeof(str) - 1)))
+ return;
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+ str, "%x:%x", &d, &b);
+ if (err != 2)
+ return;
+
+ if (d == domain && b == bus)
+ break;
+ }
+
+ if (i == root_num)
+ return;
+
+ len = snprintf(str, sizeof(str), "root-resource-magic");
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+ str, "%lx", &magic);
+
+ if (err != 1)
+ return; /* No resources, nothing to do */
+
+ if (magic != (sizeof(res) * 2) + 1) {
+ printk(KERN_WARNING "pcifront: resource magic mismatch\n");
+ return;
+ }
+
+ len = snprintf(str, sizeof(str), "root-%d-resources", i);
+ if (unlikely(len >= (sizeof(str) - 1)))
+ return;
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+ str, "%d", &res_count);
+
+ if (err != 1)
+ return; /* No resources, nothing to do */
+
+ sd->window = kzalloc(sizeof(*sd->window) * res_count, GFP_KERNEL);
+ if (!sd->window)
+ return;
+
+ /* magic is also the size of the byte stream in xenbus */
+ buf = kmalloc(magic, GFP_KERNEL);
+ if (!buf) {
+ kfree(sd->window);
+ sd->window = NULL;
+ return;
+ }
+
+ /* Read the resources out of xenbus */
+ for (j = 0; j < res_count; j++) {
+ memset(&res, 0, sizeof(res));
+ memset(buf, 0, magic);
+
+ len = snprintf(str, sizeof(str), "root-%d-resource-%d", i, j);
+ if (unlikely(len >= (sizeof(str) - 1)))
+ return;
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+ "%s", buf);
+ if (err != 1) {
+ printk(KERN_WARNING "pcifront: error reading "
+ "resource %d on bus %04x:%02x\n",
+ j, domain, bus);
+ continue;
+ }
+
+ bufp = buf;
+ ptr = (u8 *)&res;
+ memset(tmp, 0, sizeof(tmp));
+
+ /* Copy ASCII byte stream into structure */
+ for (k = 0; k < magic - 1; k += 2) {
+ memcpy(tmp, bufp, 2);
+ bufp += 2;
+
+ sscanf(tmp, "%02x", &byte);
+ *ptr = byte;
+ ptr++;
+ }
+
+ xen_add_resource(sd, domain, bus, &res);
+ sd->windows++;
+ }
+ kfree(buf);
+}
+#endif
+
+static int errno_to_pcibios_err(int errno)
+{
+ switch (errno) {
+ case XEN_PCI_ERR_success:
+ return PCIBIOS_SUCCESSFUL;
+
+ case XEN_PCI_ERR_dev_not_found:
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ case XEN_PCI_ERR_invalid_offset:
+ case XEN_PCI_ERR_op_failed:
+ return PCIBIOS_BAD_REGISTER_NUMBER;
+
+ case XEN_PCI_ERR_not_implemented:
+ return PCIBIOS_FUNC_NOT_SUPPORTED;
+
+ case XEN_PCI_ERR_access_denied:
+ return PCIBIOS_SET_FAILED;
+ }
+ return errno;
+}
+
+static inline void schedule_pcifront_aer_op(struct pcifront_device *pdev)
+{
+ if (test_bit(_XEN_PCIB_active, (unsigned long *)&pdev->sh_info->flags)
+ && !test_and_set_bit(_PDEVB_op_active, &pdev->flags)) {
+ dev_dbg(&pdev->xdev->dev, "schedule aer frontend job\n");
+ schedule_work(&pdev->op_work);
+ }
+}
+
+static int do_pci_op(struct pcifront_device *pdev, struct xen_pci_op *op)
+{
+ int err = 0;
+ struct xen_pci_op *active_op = &pdev->sh_info->op;
+ unsigned long irq_flags;
+ evtchn_port_t port = pdev->evtchn;
+ s64 ns, ns_timeout;
+ struct timeval tv;
+
+ spin_lock_irqsave(&pdev->sh_info_lock, irq_flags);
+
+ memcpy(active_op, op, sizeof(struct xen_pci_op));
+
+ /* Go */
+ wmb();
+ set_bit(_XEN_PCIF_active, (unsigned long *)&pdev->sh_info->flags);
+ notify_remote_via_evtchn(port);
+
+ /*
+ * We set a poll timeout of 3 seconds but give up on return after
+ * 2 seconds. It is better to time out too late rather than too early
+ * (in the latter case we end up continually re-executing poll() with a
+ * timeout in the past). 1s difference gives plenty of slack for error.
+ */
+ do_gettimeofday(&tv);
+ ns_timeout = timeval_to_ns(&tv) + 2 * (s64)NSEC_PER_SEC;
+
+ clear_evtchn(port);
+
+ while (test_bit(_XEN_PCIF_active,
+ (unsigned long *)&pdev->sh_info->flags)) {
+ if (HYPERVISOR_poll(&port, 1, jiffies + 3*HZ))
+ BUG();
+ clear_evtchn(port);
+ do_gettimeofday(&tv);
+ ns = timeval_to_ns(&tv);
+ if (ns > ns_timeout) {
+ dev_err(&pdev->xdev->dev,
+ "pciback not responding!!!\n");
+ clear_bit(_XEN_PCIF_active,
+ (unsigned long *)&pdev->sh_info->flags);
+ err = XEN_PCI_ERR_dev_not_found;
+ goto out;
+ }
+ }
+
+ /*
+ * We might lose backend service request since we
+ * reuse same evtchn with pci_conf backend response. So re-schedule
+ * aer pcifront service.
+ */
+ if (test_bit(_XEN_PCIB_active,
+ (unsigned long*)&pdev->sh_info->flags)) {
+ dev_err(&pdev->xdev->dev,
+ "schedule aer pcifront service\n");
+ schedule_pcifront_aer_op(pdev);
+ }
+
+ memcpy(op, active_op, sizeof(struct xen_pci_op));
+
+ err = op->err;
+ out:
+ spin_unlock_irqrestore(&pdev->sh_info_lock, irq_flags);
+ return err;
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_read(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, u32 * val)
+{
+ int err = 0;
+ struct xen_pci_op op = {
+ .cmd = XEN_PCI_OP_conf_read,
+ .domain = pci_domain_nr(bus),
+ .bus = bus->number,
+ .devfn = devfn,
+ .offset = where,
+ .size = size,
+ };
+ struct pcifront_sd *sd = bus->sysdata;
+ struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+ if (verbose_request)
+ dev_info(&pdev->xdev->dev,
+ "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+ pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+ PCI_FUNC(devfn), where, size);
+
+ err = do_pci_op(pdev, &op);
+
+ if (likely(!err)) {
+ if (verbose_request)
+ dev_info(&pdev->xdev->dev, "read got back value %x\n",
+ op.value);
+
+ *val = op.value;
+ } else if (err == -ENODEV) {
+ /* No device here, pretend that it just returned 0 */
+ err = 0;
+ *val = 0;
+ }
+
+ return errno_to_pcibios_err(err);
+}
+
+/* Access to this function is spinlocked in drivers/pci/access.c */
+static int pcifront_bus_write(struct pci_bus *bus, unsigned int devfn,
+ int where, int size, u32 val)
+{
+ struct xen_pci_op op = {
+ .cmd = XEN_PCI_OP_conf_write,
+ .domain = pci_domain_nr(bus),
+ .bus = bus->number,
+ .devfn = devfn,
+ .offset = where,
+ .size = size,
+ .value = val,
+ };
+ struct pcifront_sd *sd = bus->sysdata;
+ struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+ if (verbose_request)
+ dev_info(&pdev->xdev->dev,
+ "write dev=%04x:%02x:%02x.%01x - "
+ "offset %x size %d val %x\n",
+ pci_domain_nr(bus), bus->number,
+ PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
+
+ return errno_to_pcibios_err(do_pci_op(pdev, &op));
+}
+
+struct pci_ops pcifront_bus_ops = {
+ .read = pcifront_bus_read,
+ .write = pcifront_bus_write,
+};
+
+#ifdef CONFIG_PCI_MSI
+int pci_frontend_enable_msix(struct pci_dev *dev,
+ struct msix_entry *entries,
+ int nvec)
+{
+ int err;
+ int i;
+ struct xen_pci_op op = {
+ .cmd = XEN_PCI_OP_enable_msix,
+ .domain = pci_domain_nr(dev->bus),
+ .bus = dev->bus->number,
+ .devfn = dev->devfn,
+ .value = nvec,
+ };
+ struct pcifront_sd *sd = dev->bus->sysdata;
+ struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+ if (nvec > SH_INFO_MAX_VEC) {
+ printk("too much vector for pci frontend%x\n", nvec);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < nvec; i++) {
+ op.msix_entries[i].entry = entries[i].entry;
+ op.msix_entries[i].vector = entries[i].vector;
+ }
+
+ err = do_pci_op(pdev, &op);
+
+ if (!err) {
+ if (!op.value) {
+ /* we get the result */
+ for ( i = 0; i < nvec; i++)
+ entries[i].vector = op.msix_entries[i].vector;
+ return 0;
+ }
+ else {
+ printk("enable msix get value %x\n", op.value);
+ return op.value;
+ }
+ }
+ else {
+ printk("enable msix get err %x\n", err);
+ return err;
+ }
+}
+
+void pci_frontend_disable_msix(struct pci_dev* dev)
+{
+ int err;
+ struct xen_pci_op op = {
+ .cmd = XEN_PCI_OP_disable_msix,
+ .domain = pci_domain_nr(dev->bus),
+ .bus = dev->bus->number,
+ .devfn = dev->devfn,
+ };
+ struct pcifront_sd *sd = dev->bus->sysdata;
+ struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+ err = do_pci_op(pdev, &op);
+
+ /* What should do for error ? */
+ if (err)
+ printk("pci_disable_msix get err %x\n", err);
+}
+
+int pci_frontend_enable_msi(struct pci_dev *dev)
+{
+ int err;
+ struct xen_pci_op op = {
+ .cmd = XEN_PCI_OP_enable_msi,
+ .domain = pci_domain_nr(dev->bus),
+ .bus = dev->bus->number,
+ .devfn = dev->devfn,
+ };
+ struct pcifront_sd *sd = dev->bus->sysdata;
+ struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+ err = do_pci_op(pdev, &op);
+ if (likely(!err)) {
+ dev->irq = op.value;
+ }
+ else {
+ printk("pci frontend enable msi failed for dev %x:%x \n",
+ op.bus, op.devfn);
+ err = -EINVAL;
+ }
+ return err;
+}
+
+void pci_frontend_disable_msi(struct pci_dev* dev)
+{
+ int err;
+ struct xen_pci_op op = {
+ .cmd = XEN_PCI_OP_disable_msi,
+ .domain = pci_domain_nr(dev->bus),
+ .bus = dev->bus->number,
+ .devfn = dev->devfn,
+ };
+ struct pcifront_sd *sd = dev->bus->sysdata;
+ struct pcifront_device *pdev = pcifront_get_pdev(sd);
+
+ err = do_pci_op(pdev, &op);
+ if (err == XEN_PCI_ERR_dev_not_found) {
+ /* XXX No response from backend, what shall we do? */
+ printk("get no response from backend for disable MSI\n");
+ return;
+ }
+ if (likely(!err))
+ dev->irq = op.value;
+ else
+ /* how can pciback notify us fail? */
+ printk("get fake response frombackend \n");
+}
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static void pcifront_claim_resource(struct pci_dev *dev, void *data)
+{
+ struct pcifront_device *pdev = data;
+ int i;
+ struct resource *r;
+
+ for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+ r = &dev->resource[i];
+
+ if (!r->parent && r->start && r->flags) {
+ dev_dbg(&pdev->xdev->dev, "claiming resource %s/%d\n",
+ pci_name(dev), i);
+ pci_claim_resource(dev, i);
+ }
+ }
+}
+
+int __devinit pcifront_scan_root(struct pcifront_device *pdev,
+ unsigned int domain, unsigned int bus)
+{
+ struct pci_bus *b;
+ struct pcifront_sd *sd = NULL;
+ struct pci_bus_entry *bus_entry = NULL;
+ int err = 0;
+
+#ifndef CONFIG_PCI_DOMAINS
+ if (domain != 0) {
+ dev_err(&pdev->xdev->dev,
+ "PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+ dev_err(&pdev->xdev->dev,
+ "Please compile with CONFIG_PCI_DOMAINS\n");
+ err = -EINVAL;
+ goto err_out;
+ }
+#endif
+
+ dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n",
+ domain, bus);
+
+ bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL);
+ sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+ if (!bus_entry || !sd) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ pcifront_init_sd(sd, domain, bus, pdev);
+
+ b = pci_scan_bus_parented(&pdev->xdev->dev, bus,
+ &pcifront_bus_ops, sd);
+ if (!b) {
+ dev_err(&pdev->xdev->dev,
+ "Error creating PCI Frontend Bus!\n");
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ pcifront_setup_root_resources(b, sd);
+ bus_entry->bus = b;
+
+ list_add(&bus_entry->list, &pdev->root_buses);
+
+ /* Claim resources before going "live" with our devices */
+ pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+ pci_bus_add_devices(b);
+
+ return 0;
+
+ err_out:
+ kfree(bus_entry);
+ kfree(sd);
+
+ return err;
+}
+
+int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+ unsigned int domain, unsigned int bus)
+{
+ struct pci_bus *b;
+ struct pci_dev *d;
+ unsigned int devfn;
+
+#ifndef CONFIG_PCI_DOMAINS
+ if (domain != 0) {
+ dev_err(&pdev->xdev->dev,
+ "PCI Root in non-zero PCI Domain! domain=%d\n", domain);
+ dev_err(&pdev->xdev->dev,
+ "Please compile with CONFIG_PCI_DOMAINS\n");
+ return -EINVAL;
+ }
+#endif
+
+ dev_info(&pdev->xdev->dev, "Rescanning PCI Frontend Bus %04x:%02x\n",
+ domain, bus);
+
+ b = pci_find_bus(domain, bus);
+ if(!b)
+ /* If the bus is unknown, create it. */
+ return pcifront_scan_root(pdev, domain, bus);
+
+ /* Rescan the bus for newly attached functions and add.
+ * We omit handling of PCI bridge attachment because pciback prevents
+ * bridges from being exported.
+ */
+ for (devfn = 0; devfn < 0x100; devfn++) {
+ d = pci_get_slot(b, devfn);
+ if(d) {
+ /* Device is already known. */
+ pci_dev_put(d);
+ continue;
+ }
+
+ d = pci_scan_single_device(b, devfn);
+ if (d) {
+ dev_info(&pdev->xdev->dev, "New device on "
+ "%04x:%02x:%02x.%02x found.\n", domain, bus,
+ PCI_SLOT(devfn), PCI_FUNC(devfn));
+ pci_bus_add_device(d);
+ }
+ }
+
+ return 0;
+}
+
+static void free_root_bus_devs(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ while (!list_empty(&bus->devices)) {
+ dev = container_of(bus->devices.next, struct pci_dev,
+ bus_list);
+ dev_dbg(&dev->dev, "removing device\n");
+ pci_remove_bus_device(dev);
+ }
+}
+
+void pcifront_free_roots(struct pcifront_device *pdev)
+{
+ struct pci_bus_entry *bus_entry, *t;
+
+ dev_dbg(&pdev->xdev->dev, "cleaning up root buses\n");
+
+ list_for_each_entry_safe(bus_entry, t, &pdev->root_buses, list) {
+ list_del(&bus_entry->list);
+
+ free_root_bus_devs(bus_entry->bus);
+
+ kfree(bus_entry->bus->sysdata);
+
+ device_unregister(bus_entry->bus->bridge);
+ pci_remove_bus(bus_entry->bus);
+
+ kfree(bus_entry);
+ }
+}
+
+static pci_ers_result_t pcifront_common_process( int cmd, struct
pcifront_device *pdev,
+ pci_channel_state_t state)
+{
+ pci_ers_result_t result;
+ struct pci_driver *pdrv;
+ int bus = pdev->sh_info->aer_op.bus;
+ int devfn = pdev->sh_info->aer_op.devfn;
+ struct pci_dev *pcidev;
+ int flag = 0;
+
+ dev_dbg(&pdev->xdev->dev,
+ "pcifront AER process: cmd %x (bus:%x, devfn%x)",
+ cmd, bus, devfn);
+ result = PCI_ERS_RESULT_NONE;
+
+ pcidev = pci_get_bus_and_slot(bus, devfn);
+ if (!pcidev || !pcidev->driver){
+ dev_err(&pcidev->dev,
+ "device or driver is NULL\n");
+ return result;
+ }
+ pdrv = pcidev->driver;
+
+ if (get_driver(&pdrv->driver)) {
+ if (pdrv->err_handler && pdrv->err_handler->error_detected) {
+ dev_dbg(&pcidev->dev,
+ "trying to call AER service\n");
+ if (pcidev) {
+ flag = 1;
+ switch(cmd) {
+ case XEN_PCI_OP_aer_detected:
+ result =
pdrv->err_handler->error_detected(pcidev, state);
+ break;
+ case XEN_PCI_OP_aer_mmio:
+ result =
pdrv->err_handler->mmio_enabled(pcidev);
+ break;
+ case XEN_PCI_OP_aer_slotreset:
+ result =
pdrv->err_handler->slot_reset(pcidev);
+ break;
+ case XEN_PCI_OP_aer_resume:
+ pdrv->err_handler->resume(pcidev);
+ break;
+ default:
+ dev_err(&pdev->xdev->dev,
+ "bad request in aer recovery
operation!\n");
+
+ }
+ }
+ }
+ put_driver(&pdrv->driver);
+ }
+ if (!flag)
+ result = PCI_ERS_RESULT_NONE;
+
+ return result;
+}
+
+
+void pcifront_do_aer(void *data)
+{
+ struct pcifront_device *pdev = data;
+ int cmd = pdev->sh_info->aer_op.cmd;
+ pci_channel_state_t state =
+ (pci_channel_state_t)pdev->sh_info->aer_op.err;
+
+ /*If a pci_conf op is in progress,
+ we have to wait until it is done before service aer op*/
+ dev_dbg(&pdev->xdev->dev,
+ "pcifront service aer bus %x devfn %x\n",
pdev->sh_info->aer_op.bus,
+ pdev->sh_info->aer_op.devfn);
+
+ pdev->sh_info->aer_op.err = pcifront_common_process(cmd, pdev, state);
+
+ wmb();
+ clear_bit(_XEN_PCIB_active, (unsigned long*)&pdev->sh_info->flags);
+ notify_remote_via_evtchn(pdev->evtchn);
+
+ /*in case of we lost an aer request in four lines time_window*/
+ smp_mb__before_clear_bit();
+ clear_bit( _PDEVB_op_active, &pdev->flags);
+ smp_mb__after_clear_bit();
+
+ schedule_pcifront_aer_op(pdev);
+
+}
+
+irqreturn_t pcifront_handler_aer(int irq, void *dev, struct pt_regs *regs)
+{
+ struct pcifront_device *pdev = dev;
+ schedule_pcifront_aer_op(pdev);
+ return IRQ_HANDLED;
+}
diff --git a/drivers/xen/pcifront/pcifront.h b/drivers/xen/pcifront/pcifront.h
new file mode 100644
index 0000000..06cb3e1
--- /dev/null
+++ b/drivers/xen/pcifront/pcifront.h
@@ -0,0 +1,55 @@
+/*
+ * PCI Frontend - Common data structures & function declarations
+ *
+ * Author: Ryan Wilson <hap9@xxxxxxxxxxxxxx>
+ */
+#ifndef __XEN_PCIFRONT_H__
+#define __XEN_PCIFRONT_H__
+
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <linux/interrupt.h>
+#include <xen/pcifront.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+
+struct pci_bus_entry {
+ struct list_head list;
+ struct pci_bus *bus;
+};
+
+#define _PDEVB_op_active (0)
+#define PDEVB_op_active (1 << (_PDEVB_op_active))
+
+struct pcifront_device {
+ struct xenbus_device *xdev;
+ struct list_head root_buses;
+ spinlock_t dev_lock;
+
+ int evtchn;
+ int gnt_ref;
+
+ /* Lock this when doing any operations in sh_info */
+ spinlock_t sh_info_lock;
+ struct xen_pci_sharedinfo *sh_info;
+ struct work_struct op_work;
+ unsigned long flags;
+
+};
+
+int pcifront_connect(struct pcifront_device *pdev);
+void pcifront_disconnect(struct pcifront_device *pdev);
+
+int pcifront_scan_root(struct pcifront_device *pdev,
+ unsigned int domain, unsigned int bus);
+int pcifront_rescan_root(struct pcifront_device *pdev,
+ unsigned int domain, unsigned int bus);
+void pcifront_free_roots(struct pcifront_device *pdev);
+
+void pcifront_do_aer( void *data);
+
+irqreturn_t pcifront_handler_aer(int irq, void *dev, struct pt_regs *regs);
+
+#endif /* __XEN_PCIFRONT_H__ */
diff --git a/drivers/xen/pcifront/xenbus.c b/drivers/xen/pcifront/xenbus.c
new file mode 100644
index 0000000..ca40547
--- /dev/null
+++ b/drivers/xen/pcifront/xenbus.c
@@ -0,0 +1,468 @@
+/*
+ * PCI Frontend Xenbus Setup - handles setup with backend (imports page/evtchn)
+ *
+ * Author: Ryan Wilson <hap9@xxxxxxxxxxxxxx>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/evtchn.h>
+#include <xen/gnttab.h>
+#include "pcifront.h"
+
+#ifndef __init_refok
+#define __init_refok
+#endif
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN (-1)
+
+static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev)
+{
+ struct pcifront_device *pdev;
+
+ pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL);
+ if (pdev == NULL)
+ goto out;
+
+ pdev->sh_info =
+ (struct xen_pci_sharedinfo *)__get_free_page(GFP_KERNEL);
+ if (pdev->sh_info == NULL) {
+ kfree(pdev);
+ pdev = NULL;
+ goto out;
+ }
+ pdev->sh_info->flags = 0;
+
+ /*Flag for registering PV AER handler*/
+ set_bit(_XEN_PCIB_AERHANDLER, (void*)&pdev->sh_info->flags);
+
+ xdev->dev.driver_data = pdev;
+ pdev->xdev = xdev;
+
+ INIT_LIST_HEAD(&pdev->root_buses);
+
+ spin_lock_init(&pdev->dev_lock);
+ spin_lock_init(&pdev->sh_info_lock);
+
+ pdev->evtchn = INVALID_EVTCHN;
+ pdev->gnt_ref = INVALID_GRANT_REF;
+
+ INIT_WORK(&pdev->op_work, pcifront_do_aer, pdev);
+
+ dev_dbg(&xdev->dev, "Allocated pdev @ 0x%p pdev->sh_info @ 0x%p\n",
+ pdev, pdev->sh_info);
+ out:
+ return pdev;
+}
+
+static void free_pdev(struct pcifront_device *pdev)
+{
+ dev_dbg(&pdev->xdev->dev, "freeing pdev @ 0x%p\n", pdev);
+
+ pcifront_free_roots(pdev);
+
+ /*For PCIE_AER error handling job*/
+ flush_scheduled_work();
+ unbind_from_irqhandler(pdev->evtchn, pdev);
+
+ if (pdev->evtchn != INVALID_EVTCHN)
+ xenbus_free_evtchn(pdev->xdev, pdev->evtchn);
+
+ if (pdev->gnt_ref != INVALID_GRANT_REF)
+ gnttab_end_foreign_access(pdev->gnt_ref,
+ (unsigned long)pdev->sh_info);
+
+ pdev->xdev->dev.driver_data = NULL;
+
+ kfree(pdev);
+}
+
+static int pcifront_publish_info(struct pcifront_device *pdev)
+{
+ int err = 0;
+ struct xenbus_transaction trans;
+
+ err = xenbus_grant_ring(pdev->xdev, virt_to_mfn(pdev->sh_info));
+ if (err < 0)
+ goto out;
+
+ pdev->gnt_ref = err;
+
+ err = xenbus_alloc_evtchn(pdev->xdev, &pdev->evtchn);
+ if (err)
+ goto out;
+
+ bind_caller_port_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+ SA_SAMPLE_RANDOM, "pcifront", pdev);
+
+ do_publish:
+ err = xenbus_transaction_start(&trans);
+ if (err) {
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error writing configuration for backend "
+ "(start transaction)");
+ goto out;
+ }
+
+ err = xenbus_printf(trans, pdev->xdev->nodename,
+ "pci-op-ref", "%u", pdev->gnt_ref);
+ if (!err)
+ err = xenbus_printf(trans, pdev->xdev->nodename,
+ "event-channel", "%u", pdev->evtchn);
+ if (!err)
+ err = xenbus_printf(trans, pdev->xdev->nodename,
+ "magic", XEN_PCI_MAGIC);
+
+ if (err) {
+ xenbus_transaction_end(trans, 1);
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error writing configuration for backend");
+ goto out;
+ } else {
+ err = xenbus_transaction_end(trans, 0);
+ if (err == -EAGAIN)
+ goto do_publish;
+ else if (err) {
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error completing transaction "
+ "for backend");
+ goto out;
+ }
+ }
+
+ xenbus_switch_state(pdev->xdev, XenbusStateInitialised);
+
+ dev_dbg(&pdev->xdev->dev, "publishing successful!\n");
+
+ out:
+ return err;
+}
+
+static int __devinit pcifront_try_connect(struct pcifront_device *pdev)
+{
+ int err = -EFAULT;
+ int i, num_roots, len;
+ char str[64];
+ unsigned int domain, bus;
+
+ spin_lock(&pdev->dev_lock);
+
+ /* Only connect once */
+ if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+ XenbusStateInitialised)
+ goto out;
+
+ err = pcifront_connect(pdev);
+ if (err) {
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error connecting PCI Frontend");
+ goto out;
+ }
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+ "root_num", "%d", &num_roots);
+ if (err == -ENOENT) {
+ xenbus_dev_error(pdev->xdev, err,
+ "No PCI Roots found, trying 0000:00");
+ err = pcifront_scan_root(pdev, 0, 0);
+ num_roots = 0;
+ } else if (err != 1) {
+ if (err == 0)
+ err = -EINVAL;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error reading number of PCI roots");
+ goto out;
+ }
+
+ for (i = 0; i < num_roots; i++) {
+ len = snprintf(str, sizeof(str), "root-%d", i);
+ if (unlikely(len >= (sizeof(str) - 1))) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+ "%x:%x", &domain, &bus);
+ if (err != 2) {
+ if (err >= 0)
+ err = -EINVAL;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error reading PCI root %d", i);
+ goto out;
+ }
+
+ err = pcifront_scan_root(pdev, domain, bus);
+ if (err) {
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error scanning PCI root %04x:%02x",
+ domain, bus);
+ goto out;
+ }
+ }
+
+ err = xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+ if (err)
+ goto out;
+
+ out:
+ spin_unlock(&pdev->dev_lock);
+ return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+ int err = 0;
+ enum xenbus_state prev_state;
+
+ spin_lock(&pdev->dev_lock);
+
+ prev_state = xenbus_read_driver_state(pdev->xdev->nodename);
+
+ if (prev_state >= XenbusStateClosing)
+ goto out;
+
+ if(prev_state == XenbusStateConnected) {
+ pcifront_free_roots(pdev);
+ pcifront_disconnect(pdev);
+ }
+
+ err = xenbus_switch_state(pdev->xdev, XenbusStateClosed);
+
+ out:
+ spin_unlock(&pdev->dev_lock);
+
+ return err;
+}
+
+static int __devinit pcifront_attach_devices(struct pcifront_device *pdev)
+{
+ int err = -EFAULT;
+ int i, num_roots, len;
+ unsigned int domain, bus;
+ char str[64];
+
+ spin_lock(&pdev->dev_lock);
+
+ if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+ XenbusStateReconfiguring)
+ goto out;
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend,
+ "root_num", "%d", &num_roots);
+ if (err == -ENOENT) {
+ xenbus_dev_error(pdev->xdev, err,
+ "No PCI Roots found, trying 0000:00");
+ err = pcifront_rescan_root(pdev, 0, 0);
+ num_roots = 0;
+ } else if (err != 1) {
+ if (err == 0)
+ err = -EINVAL;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error reading number of PCI roots");
+ goto out;
+ }
+
+ for (i = 0; i < num_roots; i++) {
+ len = snprintf(str, sizeof(str), "root-%d", i);
+ if (unlikely(len >= (sizeof(str) - 1))) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+ "%x:%x", &domain, &bus);
+ if (err != 2) {
+ if (err >= 0)
+ err = -EINVAL;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error reading PCI root %d", i);
+ goto out;
+ }
+
+ err = pcifront_rescan_root(pdev, domain, bus);
+ if (err) {
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error scanning PCI root %04x:%02x",
+ domain, bus);
+ goto out;
+ }
+ }
+
+ xenbus_switch_state(pdev->xdev, XenbusStateConnected);
+
+ out:
+ spin_unlock(&pdev->dev_lock);
+ return err;
+}
+
+static int pcifront_detach_devices(struct pcifront_device *pdev)
+{
+ int err = 0;
+ int i, num_devs;
+ unsigned int domain, bus, slot, func;
+ struct pci_bus *pci_bus;
+ struct pci_dev *pci_dev;
+ char str[64];
+
+ spin_lock(&pdev->dev_lock);
+
+ if (xenbus_read_driver_state(pdev->xdev->nodename) !=
+ XenbusStateConnected)
+ goto out;
+
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, "num_devs", "%d",
+ &num_devs);
+ if (err != 1) {
+ if (err >= 0)
+ err = -EINVAL;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error reading number of PCI devices");
+ goto out;
+ }
+
+ /* Find devices being detached and remove them. */
+ for (i = 0; i < num_devs; i++) {
+ int l, state;
+ l = snprintf(str, sizeof(str), "state-%d", i);
+ if (unlikely(l >= (sizeof(str) - 1))) {
+ err = -ENOMEM;
+ goto out;
+ }
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d",
+ &state);
+ if (err != 1)
+ state = XenbusStateUnknown;
+
+ if (state != XenbusStateClosing)
+ continue;
+
+ /* Remove device. */
+ l = snprintf(str, sizeof(str), "vdev-%d", i);
+ if (unlikely(l >= (sizeof(str) - 1))) {
+ err = -ENOMEM;
+ goto out;
+ }
+ err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str,
+ "%x:%x:%x.%x", &domain, &bus, &slot, &func);
+ if (err != 4) {
+ if (err >= 0)
+ err = -EINVAL;
+ xenbus_dev_fatal(pdev->xdev, err,
+ "Error reading PCI device %d", i);
+ goto out;
+ }
+
+ pci_bus = pci_find_bus(domain, bus);
+ if(!pci_bus) {
+ dev_dbg(&pdev->xdev->dev, "Cannot get bus %04x:%02x\n",
+ domain, bus);
+ continue;
+ }
+ pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
+ if(!pci_dev) {
+ dev_dbg(&pdev->xdev->dev,
+ "Cannot get PCI device %04x:%02x:%02x.%02x\n",
+ domain, bus, slot, func);
+ continue;
+ }
+ pci_remove_bus_device(pci_dev);
+ pci_dev_put(pci_dev);
+
+ dev_dbg(&pdev->xdev->dev,
+ "PCI device %04x:%02x:%02x.%02x removed.\n",
+ domain, bus, slot, func);
+ }
+
+ err = xenbus_switch_state(pdev->xdev, XenbusStateReconfiguring);
+
+ out:
+ spin_unlock(&pdev->dev_lock);
+ return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+ enum xenbus_state be_state)
+{
+ struct pcifront_device *pdev = xdev->dev.driver_data;
+
+ switch (be_state) {
+ case XenbusStateUnknown:
+ case XenbusStateInitialising:
+ case XenbusStateInitWait:
+ case XenbusStateInitialised:
+ case XenbusStateClosed:
+ break;
+
+ case XenbusStateConnected:
+ pcifront_try_connect(pdev);
+ break;
+
+ case XenbusStateClosing:
+ dev_warn(&xdev->dev, "backend going away!\n");
+ pcifront_try_disconnect(pdev);
+ break;
+
+ case XenbusStateReconfiguring:
+ pcifront_detach_devices(pdev);
+ break;
+
+ case XenbusStateReconfigured:
+ pcifront_attach_devices(pdev);
+ break;
+ }
+}
+
+static int pcifront_xenbus_probe(struct xenbus_device *xdev,
+ const struct xenbus_device_id *id)
+{
+ int err = 0;
+ struct pcifront_device *pdev = alloc_pdev(xdev);
+
+ if (pdev == NULL) {
+ err = -ENOMEM;
+ xenbus_dev_fatal(xdev, err,
+ "Error allocating pcifront_device struct");
+ goto out;
+ }
+
+ err = pcifront_publish_info(pdev);
+
+ out:
+ return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+ if (xdev->dev.driver_data)
+ free_pdev(xdev->dev.driver_data);
+
+ return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+ {"pci"},
+ {{0}},
+};
+MODULE_ALIAS("xen:pci");
+
+static struct xenbus_driver xenbus_pcifront_driver = {
+ .name = "pcifront",
+ .owner = THIS_MODULE,
+ .ids = xenpci_ids,
+ .probe = pcifront_xenbus_probe,
+ .remove = pcifront_xenbus_remove,
+ .otherend_changed = pcifront_backend_changed,
+};
+
+static int __init pcifront_init(void)
+{
+ if (!is_running_on_xen())
+ return -ENODEV;
+
+ return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+/* Initialize after the Xen PCI Frontend Stub is initialized */
+subsys_initcall(pcifront_init);
diff --git a/include/xen/pcifront.h b/include/xen/pcifront.h
new file mode 100644
index 0000000..2557b13
--- /dev/null
+++ b/include/xen/pcifront.h
@@ -0,0 +1,83 @@
+/*
+ * PCI Frontend - arch-dependendent declarations
+ *
+ * Author: Ryan Wilson <hap9@xxxxxxxxxxxxxx>
+ */
+#ifndef __XEN_ASM_PCIFRONT_H__
+#define __XEN_ASM_PCIFRONT_H__
+
+#include <linux/spinlock.h>
+
+#ifdef __KERNEL__
+
+#ifndef __ia64__
+
+struct pcifront_device;
+struct pci_bus;
+
+struct pcifront_sd {
+ int domain;
+ struct pcifront_device *pdev;
+};
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+ return sd->pdev;
+}
+
+static inline void pcifront_init_sd(struct pcifront_sd *sd,
+ unsigned int domain, unsigned int bus,
+ struct pcifront_device *pdev)
+{
+ sd->domain = domain;
+ sd->pdev = pdev;
+}
+
+#if defined(CONFIG_PCI_DOMAINS)
+static inline int pci_domain_nr(struct pci_bus *bus)
+{
+ struct pcifront_sd *sd = bus->sysdata;
+ return sd->domain;
+}
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+ return pci_domain_nr(bus);
+}
+#endif /* CONFIG_PCI_DOMAINS */
+
+static inline void pcifront_setup_root_resources(struct pci_bus *bus,
+ struct pcifront_sd *sd)
+{
+}
+
+#else /* __ia64__ */
+
+#include <linux/acpi.h>
+#include <asm/pci.h>
+#define pcifront_sd pci_controller
+
+extern void xen_add_resource(struct pci_controller *, unsigned int,
+ unsigned int, struct acpi_resource *);
+extern void xen_pcibios_setup_root_windows(struct pci_bus *,
+ struct pci_controller *);
+
+static inline struct pcifront_device *
+pcifront_get_pdev(struct pcifront_sd *sd)
+{
+ return (struct pcifront_device *)sd->platform_data;
+}
+
+static inline void pcifront_setup_root_resources(struct pci_bus *bus,
+ struct pcifront_sd *sd)
+{
+ xen_pcibios_setup_root_windows(bus, sd);
+}
+
+#endif /* __ia64__ */
+
+extern struct rw_semaphore pci_bus_sem;
+
+#endif /* __KERNEL__ */
+
+#endif /* __XEN_ASM_PCIFRONT_H__ */
--
1.6.2.5
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home