aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/pci
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--drivers/pci/Kconfig21
-rw-r--r--drivers/pci/Makefile6
-rw-r--r--drivers/pci/bus.c54
-rw-r--r--drivers/pci/hotplug/ibmphp_hpc.c4
-rw-r--r--drivers/pci/msi.c14
-rw-r--r--drivers/pci/msi.h4
-rw-r--r--drivers/pci/pci.c79
-rw-r--r--drivers/pci/pci.h3
-rw-r--r--drivers/pci/pcie/aer/aerdrv.c2
-rw-r--r--drivers/pci/pcie/aer/aerdrv.h3
-rw-r--r--drivers/pci/pcie/aer/aerdrv_acpi.c34
-rw-r--r--drivers/pci/pcie/aer/aerdrv_core.c2
-rw-r--r--drivers/pci/pcie/portdrv_acpi.c2
-rw-r--r--drivers/pci/probe.c4
-rw-r--r--drivers/pci/proc.c4
-rw-r--r--drivers/pci/quirks.c31
-rw-r--r--drivers/pci/setup-res.c2
-rw-r--r--drivers/pci/xen-pcifront.c1148
18 files changed, 1390 insertions, 27 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 34ef70d562b2..5b1630e4e9e3 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -40,6 +40,27 @@ config PCI_STUB
When in doubt, say N.
+config XEN_PCIDEV_FRONTEND
+ tristate "Xen PCI Frontend"
+ depends on PCI && X86 && XEN
+ select HOTPLUG
+ select PCI_XEN
+ 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 && PCI_DEBUG
+ help
+ Say Y here if you want the Xen PCI frontend to produce a bunch of debug
+ messages to the system log. Select this if you are having a
+ problem with Xen PCI frontend support and want to see more of what is
+ going on.
+
+ When in doubt, say N.
+
config HT_IRQ
bool "Interrupts on hypertransport devices"
default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index dc1aa0922868..f01e344cf4bd 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -65,6 +65,6 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o
obj-$(CONFIG_PCI_STUB) += pci-stub.o
-ifeq ($(CONFIG_PCI_DEBUG),y)
-EXTRA_CFLAGS += -DDEBUG
-endif
+obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+
+ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 7f0af0e9b826..5624db8c9ad0 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -64,6 +64,49 @@ void pci_bus_remove_resources(struct pci_bus *bus)
}
}
+/*
+ * Find the highest-address bus resource below the cursor "res". If the
+ * cursor is NULL, return the highest resource.
+ */
+static struct resource *pci_bus_find_resource_prev(struct pci_bus *bus,
+ unsigned int type,
+ struct resource *res)
+{
+ struct resource *r, *prev = NULL;
+ int i;
+
+ pci_bus_for_each_resource(bus, r, i) {
+ if (!r)
+ continue;
+
+ if ((r->flags & IORESOURCE_TYPE_BITS) != type)
+ continue;
+
+ /* If this resource is at or past the cursor, skip it */
+ if (res) {
+ if (r == res)
+ continue;
+ if (r->end > res->end)
+ continue;
+ if (r->end == res->end && r->start > res->start)
+ continue;
+ }
+
+ if (!prev)
+ prev = r;
+
+ /*
+ * A small resource is higher than a large one that ends at
+ * the same address.
+ */
+ if (r->end > prev->end ||
+ (r->end == prev->end && r->start > prev->start))
+ prev = r;
+ }
+
+ return prev;
+}
+
/**
* pci_bus_alloc_resource - allocate a resource from a parent bus
* @bus: PCI bus
@@ -89,9 +132,10 @@ pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
resource_size_t),
void *alignf_data)
{
- int i, ret = -ENOMEM;
+ int ret = -ENOMEM;
struct resource *r;
resource_size_t max = -1;
+ unsigned int type = res->flags & IORESOURCE_TYPE_BITS;
type_mask |= IORESOURCE_IO | IORESOURCE_MEM;
@@ -99,10 +143,9 @@ pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
if (!(res->flags & IORESOURCE_MEM_64))
max = PCIBIOS_MAX_MEM_32;
- pci_bus_for_each_resource(bus, r, i) {
- if (!r)
- continue;
-
+ /* Look for space at highest addresses first */
+ r = pci_bus_find_resource_prev(bus, type, NULL);
+ for ( ; r; r = pci_bus_find_resource_prev(bus, type, r)) {
/* type_mask must match */
if ((res->flags ^ r->flags) & type_mask)
continue;
@@ -299,6 +342,7 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *),
}
up_read(&pci_bus_sem);
}
+EXPORT_SYMBOL_GPL(pci_walk_bus);
EXPORT_SYMBOL(pci_bus_alloc_resource);
EXPORT_SYMBOL_GPL(pci_bus_add_device);
diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c
index 1aaf3f32d3cd..f59ed30512b5 100644
--- a/drivers/pci/hotplug/ibmphp_hpc.c
+++ b/drivers/pci/hotplug/ibmphp_hpc.c
@@ -133,8 +133,8 @@ void __init ibmphp_hpc_initvars (void)
debug ("%s - Entry\n", __func__);
mutex_init(&sem_hpcaccess);
- init_MUTEX (&semOperations);
- init_MUTEX_LOCKED (&sem_exit);
+ sema_init(&semOperations, 1);
+ sema_init(&sem_exit, 0);
to_debug = 0;
debug ("%s - Exit\n", __func__);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 5fcf5aec680f..7c24dcef2989 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -35,7 +35,12 @@ int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
#endif
#ifndef arch_setup_msi_irqs
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+# define arch_setup_msi_irqs default_setup_msi_irqs
+# define HAVE_DEFAULT_MSI_SETUP_IRQS
+#endif
+
+#ifdef HAVE_DEFAULT_MSI_SETUP_IRQS
+int default_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
struct msi_desc *entry;
int ret;
@@ -60,7 +65,12 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
#endif
#ifndef arch_teardown_msi_irqs
-void arch_teardown_msi_irqs(struct pci_dev *dev)
+# define arch_teardown_msi_irqs default_teardown_msi_irqs
+# define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+#endif
+
+#ifdef HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+void default_teardown_msi_irqs(struct pci_dev *dev)
{
struct msi_desc *entry;
diff --git a/drivers/pci/msi.h b/drivers/pci/msi.h
index de27c1cb5a2b..feff3bee6fe5 100644
--- a/drivers/pci/msi.h
+++ b/drivers/pci/msi.h
@@ -22,8 +22,8 @@
#define is_64bit_address(control) (!!(control & PCI_MSI_FLAGS_64BIT))
#define is_mask_bit_support(control) (!!(control & PCI_MSI_FLAGS_MASKBIT))
-#define msix_table_offset_reg(base) (base + 0x04)
-#define msix_pba_offset_reg(base) (base + 0x08)
+#define msix_table_offset_reg(base) (base + PCI_MSIX_TABLE)
+#define msix_pba_offset_reg(base) (base + PCI_MSIX_PBA)
#define msix_table_size(control) ((control & PCI_MSIX_FLAGS_QSIZE)+1)
#define multi_msix_capable(control) msix_table_size((control))
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7fa3cbd742c5..e98c8104297b 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -38,6 +38,19 @@ EXPORT_SYMBOL(pci_pci_problems);
unsigned int pci_pm_d3_delay;
+static void pci_pme_list_scan(struct work_struct *work);
+
+static LIST_HEAD(pci_pme_list);
+static DEFINE_MUTEX(pci_pme_list_mutex);
+static DECLARE_DELAYED_WORK(pci_pme_work, pci_pme_list_scan);
+
+struct pci_pme_device {
+ struct list_head list;
+ struct pci_dev *dev;
+};
+
+#define PME_TIMEOUT 1000 /* How long between PME checks */
+
static void pci_dev_d3_sleep(struct pci_dev *dev)
{
unsigned int delay = dev->d3_delay;
@@ -1331,6 +1344,32 @@ bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
return !!(dev->pme_support & (1 << state));
}
+static void pci_pme_list_scan(struct work_struct *work)
+{
+ struct pci_pme_device *pme_dev;
+
+ mutex_lock(&pci_pme_list_mutex);
+ if (!list_empty(&pci_pme_list)) {
+ list_for_each_entry(pme_dev, &pci_pme_list, list)
+ pci_pme_wakeup(pme_dev->dev, NULL);
+ schedule_delayed_work(&pci_pme_work, msecs_to_jiffies(PME_TIMEOUT));
+ }
+ mutex_unlock(&pci_pme_list_mutex);
+}
+
+/**
+ * pci_external_pme - is a device an external PCI PME source?
+ * @dev: PCI device to check
+ *
+ */
+
+static bool pci_external_pme(struct pci_dev *dev)
+{
+ if (pci_is_pcie(dev) || dev->bus->number == 0)
+ return false;
+ return true;
+}
+
/**
* pci_pme_active - enable or disable PCI device's PME# function
* @dev: PCI device to handle.
@@ -1354,6 +1393,44 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
+ /* PCI (as opposed to PCIe) PME requires that the device have
+ its PME# line hooked up correctly. Not all hardware vendors
+ do this, so the PME never gets delivered and the device
+ remains asleep. The easiest way around this is to
+ periodically walk the list of suspended devices and check
+ whether any have their PME flag set. The assumption is that
+ we'll wake up often enough anyway that this won't be a huge
+ hit, and the power savings from the devices will still be a
+ win. */
+
+ if (pci_external_pme(dev)) {
+ struct pci_pme_device *pme_dev;
+ if (enable) {
+ pme_dev = kmalloc(sizeof(struct pci_pme_device),
+ GFP_KERNEL);
+ if (!pme_dev)
+ goto out;
+ pme_dev->dev = dev;
+ mutex_lock(&pci_pme_list_mutex);
+ list_add(&pme_dev->list, &pci_pme_list);
+ if (list_is_singular(&pci_pme_list))
+ schedule_delayed_work(&pci_pme_work,
+ msecs_to_jiffies(PME_TIMEOUT));
+ mutex_unlock(&pci_pme_list_mutex);
+ } else {
+ mutex_lock(&pci_pme_list_mutex);
+ list_for_each_entry(pme_dev, &pci_pme_list, list) {
+ if (pme_dev->dev == dev) {
+ list_del(&pme_dev->list);
+ kfree(pme_dev);
+ break;
+ }
+ }
+ mutex_unlock(&pci_pme_list_mutex);
+ }
+ }
+
+out:
dev_printk(KERN_DEBUG, &dev->dev, "PME# %s\n",
enable ? "enabled" : "disabled");
}
@@ -2689,7 +2766,7 @@ int pcie_get_readrq(struct pci_dev *dev)
ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl);
if (!ret)
- ret = 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12);
+ ret = 128 << ((ctl & PCI_EXP_DEVCTL_READRQ) >> 12);
return ret;
}
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 6beb11b617a9..f5c7c382765f 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -63,11 +63,8 @@ struct pci_platform_pm_ops {
extern int pci_set_platform_pm(struct pci_platform_pm_ops *ops);
extern void pci_update_current_state(struct pci_dev *dev, pci_power_t state);
extern void pci_disable_enabled_device(struct pci_dev *dev);
-extern bool pci_check_pme_status(struct pci_dev *dev);
extern int pci_finish_runtime_suspend(struct pci_dev *dev);
-extern void pci_wakeup_event(struct pci_dev *dev);
extern int __pci_pme_wakeup(struct pci_dev *dev, void *ign);
-extern void pci_pme_wakeup_bus(struct pci_bus *bus);
extern void pci_pm_init(struct pci_dev *dev);
extern void platform_pci_wakeup_init(struct pci_dev *dev);
extern void pci_allocate_cap_save_buffers(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index f409948e1a9b..2b2b6508efde 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -416,7 +416,7 @@ static void aer_error_resume(struct pci_dev *dev)
*/
static int __init aer_service_init(void)
{
- if (!pci_aer_available())
+ if (!pci_aer_available() || aer_acpi_firmware_first())
return -ENXIO;
return pcie_port_service_register(&aerdriver);
}
diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h
index 80c11d131499..9656e3060412 100644
--- a/drivers/pci/pcie/aer/aerdrv.h
+++ b/drivers/pci/pcie/aer/aerdrv.h
@@ -132,6 +132,7 @@ static inline int aer_osc_setup(struct pcie_device *pciedev)
#ifdef CONFIG_ACPI_APEI
extern int pcie_aer_get_firmware_first(struct pci_dev *pci_dev);
+extern bool aer_acpi_firmware_first(void);
#else
static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
{
@@ -139,6 +140,8 @@ static inline int pcie_aer_get_firmware_first(struct pci_dev *pci_dev)
return pci_dev->__aer_firmware_first;
return 0;
}
+
+static inline bool aer_acpi_firmware_first(void) { return false; }
#endif
static inline void pcie_aer_force_firmware_first(struct pci_dev *pci_dev,
diff --git a/drivers/pci/pcie/aer/aerdrv_acpi.c b/drivers/pci/pcie/aer/aerdrv_acpi.c
index 2bb9b8972211..275bf158ffa7 100644
--- a/drivers/pci/pcie/aer/aerdrv_acpi.c
+++ b/drivers/pci/pcie/aer/aerdrv_acpi.c
@@ -93,4 +93,38 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev)
aer_set_firmware_first(dev);
return dev->__aer_firmware_first;
}
+
+static bool aer_firmware_first;
+
+static int aer_hest_parse_aff(struct acpi_hest_header *hest_hdr, void *data)
+{
+ struct acpi_hest_aer_common *p;
+
+ if (aer_firmware_first)
+ return 0;
+
+ switch (hest_hdr->type) {
+ case ACPI_HEST_TYPE_AER_ROOT_PORT:
+ case ACPI_HEST_TYPE_AER_ENDPOINT:
+ case ACPI_HEST_TYPE_AER_BRIDGE:
+ p = (struct acpi_hest_aer_common *)(hest_hdr + 1);
+ aer_firmware_first = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+ default:
+ return 0;
+ }
+}
+
+/**
+ * aer_acpi_firmware_first - Check if APEI should control AER.
+ */
+bool aer_acpi_firmware_first(void)
+{
+ static bool parsed = false;
+
+ if (!parsed) {
+ apei_hest_parse(aer_hest_parse_aff, NULL);
+ parsed = true;
+ }
+ return aer_firmware_first;
+}
#endif
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 29e268fadf14..43421fbe080a 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -754,7 +754,7 @@ void aer_isr(struct work_struct *work)
{
struct aer_rpc *rpc = container_of(work, struct aer_rpc, dpc_handler);
struct pcie_device *p_device = rpc->rpd;
- struct aer_err_source e_src;
+ struct aer_err_source uninitialized_var(e_src);
mutex_lock(&rpc->rpc_mutex);
while (get_e_source(rpc, &e_src))
diff --git a/drivers/pci/pcie/portdrv_acpi.c b/drivers/pci/pcie/portdrv_acpi.c
index b7c4cb1ccb23..5982b6a63b89 100644
--- a/drivers/pci/pcie/portdrv_acpi.c
+++ b/drivers/pci/pcie/portdrv_acpi.c
@@ -49,7 +49,7 @@ int pcie_port_acpi_setup(struct pci_dev *port, int *srv_mask)
| OSC_PCI_EXPRESS_PME_CONTROL;
if (pci_aer_available()) {
- if (pcie_aer_get_firmware_first(port))
+ if (aer_acpi_firmware_first())
dev_dbg(&port->dev, "PCIe errors handled by BIOS.\n");
else
flags |= OSC_PCI_EXPRESS_AER_CONTROL;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 12625d90f8b5..c84900da3c59 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -961,8 +961,8 @@ int pci_setup_device(struct pci_dev *dev)
dev->class = class;
class >>= 8;
- dev_dbg(&dev->dev, "found [%04x:%04x] class %06x header type %02x\n",
- dev->vendor, dev->device, class, dev->hdr_type);
+ dev_printk(KERN_DEBUG, &dev->dev, "[%04x:%04x] type %d class %#08x\n",
+ dev->vendor, dev->device, dev->hdr_type, class);
/* need to have dev->class ready */
dev->cfg_size = pci_cfg_space_size(dev);
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 01f0306525a5..297b72c880a1 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -212,8 +212,6 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
#endif /* HAVE_PCI_MMAP */
int ret = 0;
- lock_kernel();
-
switch (cmd) {
case PCIIOC_CONTROLLER:
ret = pci_domain_nr(dev->bus);
@@ -242,7 +240,6 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
break;
};
- unlock_kernel();
return ret;
}
@@ -306,6 +303,7 @@ static const struct file_operations proc_bus_pci_operations = {
.read = proc_bus_pci_read,
.write = proc_bus_pci_write,
.unlocked_ioctl = proc_bus_pci_ioctl,
+ .compat_ioctl = proc_bus_pci_ioctl,
#ifdef HAVE_PCI_MMAP
.open = proc_bus_pci_open,
.release = proc_bus_pci_release,
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index cc96c7142dac..f5c63fe9db5c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2297,6 +2297,37 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
PCI_DEVICE_ID_NVIDIA_NVENET_15,
nvenet_msi_disable);
+/*
+ * Some versions of the MCP55 bridge from nvidia have a legacy irq routing
+ * config register. This register controls the routing of legacy interrupts
+ * from devices that route through the MCP55. If this register is misprogramed
+ * interrupts are only sent to the bsp, unlike conventional systems where the
+ * irq is broadxast to all online cpus. Not having this register set
+ * properly prevents kdump from booting up properly, so lets make sure that
+ * we have it set correctly.
+ * Note this is an undocumented register.
+ */
+static void __devinit nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
+{
+ u32 cfg;
+
+ pci_read_config_dword(dev, 0x74, &cfg);
+
+ if (cfg & ((1 << 2) | (1 << 15))) {
+ printk(KERN_INFO "Rewriting irq routing register on MCP55\n");
+ cfg &= ~((1 << 2) | (1 << 15));
+ pci_write_config_dword(dev, 0x74, cfg);
+ }
+}
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+ PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V0,
+ nvbridge_check_legacy_irq_routing);
+
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA,
+ PCI_DEVICE_ID_NVIDIA_MCP55_BRIDGE_V4,
+ nvbridge_check_legacy_irq_routing);
+
static int __devinit ht_check_msi_mapping(struct pci_dev *dev)
{
int pos, ttl = 48;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 2aaa13150de3..bc0e6eea0fff 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -85,7 +85,7 @@ void pci_update_resource(struct pci_dev *dev, int resno)
}
}
res->flags &= ~IORESOURCE_UNSET;
- dev_info(&dev->dev, "BAR %d: set to %pR (PCI address [%#llx-%#llx]\n",
+ dev_info(&dev->dev, "BAR %d: set to %pR (PCI address [%#llx-%#llx])\n",
resno, res, (unsigned long long)region.start,
(unsigned long long)region.end);
}
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
new file mode 100644
index 000000000000..a87c4985326e
--- /dev/null
+++ b/drivers/pci/xen-pcifront.c
@@ -0,0 +1,1148 @@
+/*
+ * Xen PCI Frontend.
+ *
+ * Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <xen/xenbus.h>
+#include <xen/events.h>
+#include <xen/grant_table.h>
+#include <xen/page.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <xen/xenbus.h>
+#include <xen/interface/io/pciif.h>
+#include <asm/xen/pci.h>
+#include <linux/interrupt.h>
+#include <asm/atomic.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <linux/time.h>
+
+#define INVALID_GRANT_REF (0)
+#define INVALID_EVTCHN (-1)
+
+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;
+
+ int evtchn;
+ int gnt_ref;
+
+ int irq;
+
+ /* 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;
+
+};
+
+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;
+}
+
+static DEFINE_SPINLOCK(pcifront_dev_lock);
+static struct pcifront_device *pcifront_dev;
+
+static int verbose_request;
+module_param(verbose_request, int, 0644);
+
+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;
+ unsigned irq = pdev->irq;
+ 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;
+
+ xen_clear_irq_pending(irq);
+
+ while (test_bit(_XEN_PCIF_active,
+ (unsigned long *)&pdev->sh_info->flags)) {
+ xen_poll_irq_timeout(irq, jiffies + 3*HZ);
+ xen_clear_irq_pending(irq);
+ 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
+static int pci_frontend_enable_msix(struct pci_dev *dev,
+ int **vector, 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);
+ struct msi_desc *entry;
+
+ if (nvec > SH_INFO_MAX_VEC) {
+ dev_err(&dev->dev, "too much vector for pci frontend: %x."
+ " Increase SH_INFO_MAX_VEC.\n", nvec);
+ return -EINVAL;
+ }
+
+ i = 0;
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+ /* Vector is useless at this point. */
+ op.msix_entries[i].vector = -1;
+ i++;
+ }
+
+ err = do_pci_op(pdev, &op);
+
+ if (likely(!err)) {
+ if (likely(!op.value)) {
+ /* we get the result */
+ for (i = 0; i < nvec; i++)
+ *(*vector+i) = op.msix_entries[i].vector;
+ return 0;
+ } else {
+ printk(KERN_DEBUG "enable msix get value %x\n",
+ op.value);
+ return op.value;
+ }
+ } else {
+ dev_err(&dev->dev, "enable msix get err %x\n", err);
+ return err;
+ }
+}
+
+static 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)
+ dev_err(&dev->dev, "pci_disable_msix get err %x\n", err);
+}
+
+static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector)
+{
+ 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)) {
+ *(*vector) = op.value;
+ } else {
+ dev_err(&dev->dev, "pci frontend enable msi failed for dev "
+ "%x:%x\n", op.bus, op.devfn);
+ err = -EINVAL;
+ }
+ return err;
+}
+
+static 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(KERN_DEBUG "get no response from backend for disable MSI\n");
+ return;
+ }
+ if (err)
+ /* how can pciback notify us fail? */
+ printk(KERN_DEBUG "get fake response frombackend\n");
+}
+
+static struct xen_pci_frontend_ops pci_frontend_ops = {
+ .enable_msi = pci_frontend_enable_msi,
+ .disable_msi = pci_frontend_disable_msi,
+ .enable_msix = pci_frontend_enable_msix,
+ .disable_msix = pci_frontend_disable_msix,
+};
+
+static void pci_frontend_registrar(int enable)
+{
+ if (enable)
+ xen_pci_frontend = &pci_frontend_ops;
+ else
+ xen_pci_frontend = NULL;
+};
+#else
+static inline void pci_frontend_registrar(int enable) { };
+#endif /* CONFIG_PCI_MSI */
+
+/* Claim resources for the PCI frontend as-is, backend won't allow changes */
+static int 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_info(&pdev->xdev->dev, "claiming resource %s/%d\n",
+ pci_name(dev), i);
+ if (pci_claim_resource(dev, i)) {
+ dev_err(&pdev->xdev->dev, "Could not claim "
+ "resource %s/%d! Device offline. Try "
+ "giving less than 4GB to domain.\n",
+ pci_name(dev), i);
+ }
+ }
+ }
+
+ return 0;
+}
+
+static int __devinit pcifront_scan_bus(struct pcifront_device *pdev,
+ unsigned int domain, unsigned int bus,
+ struct pci_bus *b)
+{
+ struct pci_dev *d;
+ unsigned int devfn;
+
+ /* Scan the bus for 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));
+ }
+
+ return 0;
+}
+
+static 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;
+ }
+
+ bus_entry->bus = b;
+
+ list_add(&bus_entry->list, &pdev->root_buses);
+
+ /* pci_scan_bus_parented skips devices which do not have a have
+ * devfn==0. The pcifront_scan_bus enumerates all devfn. */
+ err = pcifront_scan_bus(pdev, domain, bus, b);
+
+ /* Claim resources before going "live" with our devices */
+ pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+ /* Create SysFS and notify udev of the devices. Aka: "going live" */
+ pci_bus_add_devices(b);
+
+ return err;
+
+err_out:
+ kfree(bus_entry);
+ kfree(sd);
+
+ return err;
+}
+
+static int __devinit pcifront_rescan_root(struct pcifront_device *pdev,
+ unsigned int domain, unsigned int bus)
+{
+ int err;
+ struct pci_bus *b;
+
+#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);
+
+ err = pcifront_scan_bus(pdev, domain, bus, b);
+
+ /* Claim resources before going "live" with our devices */
+ pci_walk_bus(b, pcifront_claim_resource, pdev);
+
+ /* Create SysFS and notify udev of the devices. Aka: "going live" */
+ pci_bus_add_devices(b);
+
+ return err;
+}
+
+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);
+ }
+}
+
+static 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;
+}
+
+
+static void pcifront_do_aer(struct work_struct *data)
+{
+ struct pcifront_device *pdev =
+ container_of(data, struct pcifront_device, op_work);
+ 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);
+
+ /* Post the operation to the guest. */
+ 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);
+
+}
+
+static irqreturn_t pcifront_handler_aer(int irq, void *dev)
+{
+ struct pcifront_device *pdev = dev;
+ schedule_pcifront_aer_op(pdev);
+ return IRQ_HANDLED;
+}
+static 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;
+}
+
+static 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);
+}
+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);
+
+ dev_set_drvdata(&xdev->dev, pdev);
+ pdev->xdev = xdev;
+
+ INIT_LIST_HEAD(&pdev->root_buses);
+
+ spin_lock_init(&pdev->sh_info_lock);
+
+ pdev->evtchn = INVALID_EVTCHN;
+ pdev->gnt_ref = INVALID_GRANT_REF;
+ pdev->irq = -1;
+
+ INIT_WORK(&pdev->op_work, pcifront_do_aer);
+
+ 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();
+
+ if (pdev->irq >= 0)
+ unbind_from_irqhandler(pdev->irq, 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, 0 /* r/w page */,
+ (unsigned long)pdev->sh_info);
+ else
+ free_page((unsigned long)pdev->sh_info);
+
+ dev_set_drvdata(&pdev->xdev->dev, 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;
+
+ err = bind_evtchn_to_irqhandler(pdev->evtchn, pcifront_handler_aer,
+ 0, "pcifront", pdev);
+
+ if (err < 0)
+ return err;
+
+ pdev->irq = err;
+
+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;
+
+
+ /* 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);
+
+out:
+ return err;
+}
+
+static int pcifront_try_disconnect(struct pcifront_device *pdev)
+{
+ int err = 0;
+ enum xenbus_state prev_state;
+
+
+ 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:
+
+ 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];
+
+ 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:
+ 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];
+
+ 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:
+ return err;
+}
+
+static void __init_refok pcifront_backend_changed(struct xenbus_device *xdev,
+ enum xenbus_state be_state)
+{
+ struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+
+ 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);
+ if (err)
+ free_pdev(pdev);
+
+out:
+ return err;
+}
+
+static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+{
+ struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
+ if (pdev)
+ free_pdev(pdev);
+
+ return 0;
+}
+
+static const struct xenbus_device_id xenpci_ids[] = {
+ {"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 (!xen_pv_domain() || xen_initial_domain())
+ return -ENODEV;
+
+ pci_frontend_registrar(1 /* enable */);
+
+ return xenbus_register_frontend(&xenbus_pcifront_driver);
+}
+
+static void __exit pcifront_cleanup(void)
+{
+ xenbus_unregister_driver(&xenbus_pcifront_driver);
+ pci_frontend_registrar(0 /* disable */);
+}
+module_init(pcifront_init);
+module_exit(pcifront_cleanup);
+
+MODULE_DESCRIPTION("Xen PCI passthrough frontend.");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("xen:pci");
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.