out:
return ret;
}
+
+ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev, int irq)
+ {
+ int ret = 0;
+
+ if (pci_seg_supported) {
+ struct physdev_pci_device restore_ext;
+
+ restore_ext.seg = pci_domain_nr(dev->bus);
+ restore_ext.bus = dev->bus->number;
+ restore_ext.devfn = dev->devfn;
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi_ext,
+ &restore_ext);
+ if (ret == -ENOSYS)
+ pci_seg_supported = false;
+ WARN(ret && ret != -ENOSYS, "restore_msi_ext -> %d\n", ret);
+ }
+ if (!pci_seg_supported) {
+ struct physdev_restore_msi restore;
+
+ restore.bus = dev->bus->number;
+ restore.devfn = dev->devfn;
+ ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore);
+ WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
+ }
+ }
#endif
static void xen_teardown_msi_irqs(struct pci_dev *dev)
int __init pci_xen_hvm_init(void)
{
- if (!xen_feature(XENFEAT_hvm_pirqs))
+ if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
return 0;
#ifdef CONFIG_ACPI
#ifdef CONFIG_PCI_MSI
x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+ x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
#endif
xen_setup_acpi_sci();
__acpi_register_gsi = acpi_register_gsi_xen;
#include <asm/reboot.h>
#include <asm/stackprotector.h>
#include <asm/hypervisor.h>
+ #include <asm/mwait.h>
+
+ #ifdef CONFIG_ACPI
+ #include <linux/acpi.h>
+ #include <asm/acpi.h>
+ #include <acpi/pdc_intel.h>
+ #include <acpi/processor.h>
+ #include <xen/interface/platform.h>
+ #endif
#include "xen-ops.h"
#include "mmu.h"
static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
+ static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask;
+ static __read_mostly unsigned int cpuid_leaf5_ecx_val;
+ static __read_mostly unsigned int cpuid_leaf5_edx_val;
+
static void xen_cpuid(unsigned int *ax, unsigned int *bx,
unsigned int *cx, unsigned int *dx)
{
unsigned maskebx = ~0;
unsigned maskecx = ~0;
unsigned maskedx = ~0;
-
+ unsigned setecx = 0;
/*
* Mask out inconvenient features, to try and disable as many
* unsupported kernel subsystems as possible.
switch (*ax) {
case 1:
maskecx = cpuid_leaf1_ecx_mask;
+ setecx = cpuid_leaf1_ecx_set_mask;
maskedx = cpuid_leaf1_edx_mask;
break;
+ case CPUID_MWAIT_LEAF:
+ /* Synthesize the values.. */
+ *ax = 0;
+ *bx = 0;
+ *cx = cpuid_leaf5_ecx_val;
+ *dx = cpuid_leaf5_edx_val;
+ return;
+
case 0xb:
/* Suppress extended topology stuff */
maskebx = 0;
*bx &= maskebx;
*cx &= maskecx;
+ *cx |= setecx;
*dx &= maskedx;
+
}
+ static bool __init xen_check_mwait(void)
+ {
+ #ifdef CONFIG_ACPI
+ struct xen_platform_op op = {
+ .cmd = XENPF_set_processor_pminfo,
+ .u.set_pminfo.id = -1,
+ .u.set_pminfo.type = XEN_PM_PDC,
+ };
+ uint32_t buf[3];
+ unsigned int ax, bx, cx, dx;
+ unsigned int mwait_mask;
+
+ /* We need to determine whether it is OK to expose the MWAIT
+ * capability to the kernel to harvest deeper than C3 states from ACPI
+ * _CST using the processor_harvest_xen.c module. For this to work, we
+ * need to gather the MWAIT_LEAF values (which the cstate.c code
+ * checks against). The hypervisor won't expose the MWAIT flag because
+ * it would break backwards compatibility; so we will find out directly
+ * from the hardware and hypercall.
+ */
+ if (!xen_initial_domain())
+ return false;
+
+ ax = 1;
+ cx = 0;
+
+ native_cpuid(&ax, &bx, &cx, &dx);
+
+ mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
+ (1 << (X86_FEATURE_MWAIT % 32));
+
+ if ((cx & mwait_mask) != mwait_mask)
+ return false;
+
+ /* We need to emulate the MWAIT_LEAF and for that we need both
+ * ecx and edx. The hypercall provides only partial information.
+ */
+
+ ax = CPUID_MWAIT_LEAF;
+ bx = 0;
+ cx = 0;
+ dx = 0;
+
+ native_cpuid(&ax, &bx, &cx, &dx);
+
+ /* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
+ * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
+ */
+ buf[0] = ACPI_PDC_REVISION_ID;
+ buf[1] = 1;
+ buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
+
+ set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+
+ if ((HYPERVISOR_dom0_op(&op) == 0) &&
+ (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
+ cpuid_leaf5_ecx_val = cx;
+ cpuid_leaf5_edx_val = dx;
+ }
+ return true;
+ #else
+ return false;
+ #endif
+ }
static void __init xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
if ((cx & xsave_mask) != xsave_mask)
cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
+
+ if (xen_check_mwait())
+ cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
}
static void xen_set_debugreg(int reg, unsigned long val)
static unsigned long xen_read_cr0(void)
{
- unsigned long cr0 = percpu_read(xen_cr0_value);
+ unsigned long cr0 = this_cpu_read(xen_cr0_value);
if (unlikely(cr0 == 0)) {
cr0 = native_read_cr0();
- percpu_write(xen_cr0_value, cr0);
+ this_cpu_write(xen_cr0_value, cr0);
}
return cr0;
{
struct multicall_space mcs;
- percpu_write(xen_cr0_value, cr0);
+ this_cpu_write(xen_cr0_value, cr0);
/* Only pay attention to cr0.TS; everything else is
ignored. */
/* Prevent unwanted bits from being set in PTEs. */
__supported_pte_mask &= ~_PAGE_GLOBAL;
+#if 0
if (!xen_initial_domain())
+#endif
__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
__supported_pte_mask |= _PAGE_IOMAP;
pgd = (pgd_t *)xen_start_info->pt_base;
- if (!xen_initial_domain())
- __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
- __supported_pte_mask |= _PAGE_IOMAP;
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
static pteval_t xen_pte_val(pte_t pte)
{
pteval_t pteval = pte.pte;
-
+#if 0
/* If this is a WC pte, convert back from Xen WC to Linux WC */
if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
WARN_ON(!pat_enabled);
pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
}
-
+#endif
if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
return pteval;
static pte_t xen_make_pte(pteval_t pte)
{
phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
/* If Linux is trying to set a WC pte, then map to the Xen WC.
* If _PAGE_PAT is set, then it probably means it is really
* _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
}
-
+#endif
/*
* Unprivileged domains are allowed to do IOMAPpings for
* PCI passthrough, but not map ISA space. The ISA
struct mm_struct *mm = info;
struct mm_struct *active_mm;
- active_mm = percpu_read(cpu_tlbstate.active_mm);
+ active_mm = this_cpu_read(cpu_tlbstate.active_mm);
- if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
+ if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
leave_mm(smp_processor_id());
/* If this cpu still has a stale cr3 reference, then make sure
it has been flushed. */
- if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
+ if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd))
load_cr3(swapper_pg_dir);
}
static void xen_write_cr2(unsigned long cr2)
{
- percpu_read(xen_vcpu)->arch.cr2 = cr2;
+ this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
}
static unsigned long xen_read_cr2(void)
{
- return percpu_read(xen_vcpu)->arch.cr2;
+ return this_cpu_read(xen_vcpu)->arch.cr2;
}
unsigned long xen_read_cr2_direct(void)
{
- return percpu_read(xen_vcpu_info.arch.cr2);
+ return this_cpu_read(xen_vcpu_info.arch.cr2);
}
static void xen_flush_tlb(void)
static unsigned long xen_read_cr3(void)
{
- return percpu_read(xen_cr3);
+ return this_cpu_read(xen_cr3);
}
static void set_current_cr3(void *v)
{
- percpu_write(xen_current_cr3, (unsigned long)v);
+ this_cpu_write(xen_current_cr3, (unsigned long)v);
}
static void __xen_write_cr3(bool kernel, unsigned long cr3)
xen_extend_mmuext_op(&op);
if (kernel) {
- percpu_write(xen_cr3, cr3);
+ this_cpu_write(xen_cr3, cr3);
/* Update xen_current_cr3 once the batch has actually
been submitted. */
/* Update while interrupts are disabled, so its atomic with
respect to ipis */
- percpu_write(xen_cr3, cr3);
+ this_cpu_write(xen_cr3, cr3);
__xen_write_cr3(true, cr3);
xen_setup_cpu_clockevents();
set_cpu_online(cpu, true);
- percpu_write(cpu_state, CPU_ONLINE);
+ this_cpu_write(cpu_state, CPU_ONLINE);
wmb();
/* We can take interrupts now: we're officially "up". */
play_dead_common();
HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
cpu_bringup();
+ /*
+ * Balance out the preempt calls - as we are running in cpu_idle
+ * loop which has been called at bootup from cpu_bringup_and_idle.
+ * The cpucpu_bringup_and_idle called cpu_bringup which made a
+ * preempt_disable() So this preempt_enable will balance it out.
+ */
+ preempt_enable();
}
#else /* !CONFIG_HOTPLUG_CPU */
/**
* pci_intx_mask_supported - probe for INTx masking support
- * @pdev: the PCI device to operate on
+ * @dev: the PCI device to operate on
*
* Check if the device dev support INTx masking via the config space
* command word.
/**
* pci_check_and_mask_intx - mask INTx on pending interrupt
- * @pdev: the PCI device to operate on
+ * @dev: the PCI device to operate on
*
* Check if the device dev has its INTx line asserted, mask it and
* return true in that case. False is returned if not interrupt was
/**
* pci_check_and_mask_intx - unmask INTx of no interrupt is pending
- * @pdev: the PCI device to operate on
+ * @dev: the PCI device to operate on
*
* Check if the device dev has its INTx line asserted, unmask it if not
* and return true. False is returned and the mask remains active if
}
EXPORT_SYMBOL_GPL(__pci_reset_function);
+ /**
+ * __pci_reset_function_locked - reset a PCI device function while holding
+ * the @dev mutex lock.
+ * @dev: PCI device to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device. The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * The device function is presumed to be unused and the caller is holding
+ * the device mutex lock when this function is called.
+ * Resetting the device will make the contents of PCI configuration space
+ * random, so any caller of this must be prepared to reinitialise the
+ * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
+ * etc.
+ *
+ * Returns 0 if the device function was successfully reset or negative if the
+ * device doesn't support resetting a single function.
+ */
+ int __pci_reset_function_locked(struct pci_dev *dev)
+ {
+ return pci_dev_reset(dev, 1);
+ }
+ EXPORT_SYMBOL_GPL(__pci_reset_function_locked);
+
/**
* pci_probe_reset_function - check whether the device can be safely reset
* @dev: PCI device to reset
depends on HVC_CONSOLE
default n
-config HVC_ISERIES
- bool "iSeries Hypervisor Virtual Console support"
- depends on PPC_ISERIES
- default y
- select HVC_DRIVER
- select HVC_IRQ
- select VIOPATH
- help
- iSeries machines support a hypervisor virtual console.
-
config HVC_OPAL
bool "OPAL Console support"
depends on PPC_POWERNV
help
Xen virtual console device driver
+ config HVC_XEN_FRONTEND
+ bool "Xen Hypervisor Multiple Consoles support"
+ depends on HVC_XEN
+ select XEN_XENBUS_FRONTEND
+ default y
+ help
+ Xen driver for secondary virtual consoles
+
config HVC_UDBG
bool "udbg based fake hypervisor console"
depends on PPC && EXPERIMENTAL
select HVC_DRIVER
default n
+ help
+ This is meant to be used during HW bring up or debugging when
+ no other console mechanism exist but udbg, to get you a quick
+ console for userspace. Do NOT enable in production kernels.
config HVC_DCC
bool "ARM JTAG DCC console"
au1100fb:panel=<name>.
config FB_AU1200
- bool "Au1200 LCD Driver"
+ bool "Au1200/Au1300 LCD Driver"
depends on (FB = y) && MIPS_ALCHEMY
select FB_SYS_FILLRECT
select FB_SYS_COPYAREA
select FB_SYS_IMAGEBLIT
select FB_SYS_FOPS
help
- This is the framebuffer driver for the AMD Au1200 SOC. It can drive
- various panels and CRTs by passing in kernel cmd line option
- au1200fb:panel=<name>.
+ This is the framebuffer driver for the Au1200/Au1300 SOCs.
+ It can drive various panels and CRTs by passing in kernel cmd line
+ option au1200fb:panel=<name>.
config FB_VT8500
bool "VT8500 LCD Driver"
select FB_SYS_IMAGEBLIT
select FB_SYS_FOPS
select FB_DEFERRED_IO
+ select INPUT_XEN_KBDDEV_FRONTEND
select XEN_XENBUS_FRONTEND
default y
help
source "drivers/video/omap2/Kconfig"
source "drivers/video/backlight/Kconfig"
-source "drivers/video/display/Kconfig"
if VT
source "drivers/video/console/Kconfig"
NULL
};
- static struct attribute_group balloon_info_group = {
+ static const struct attribute_group balloon_info_group = {
.name = "info",
.attrs = balloon_info_attrs
};
{
int i, error;
- error = bus_register(&balloon_subsys);
+ error = subsys_system_register(&balloon_subsys, NULL);
if (error)
return error;
static void pcistub_device_release(struct kref *kref)
{
struct pcistub_device *psdev;
+ struct xen_pcibk_dev_data *dev_data;
psdev = container_of(kref, struct pcistub_device, kref);
+ dev_data = pci_get_drvdata(psdev->dev);
dev_dbg(&psdev->dev->dev, "pcistub_device_release\n");
xen_unregister_device_domain_owner(psdev->dev);
- /* Clean-up the device */
+ /* Call the reset function which does not take lock as this
+ * is called from "unbind" which takes a device_lock mutex.
+ */
+ __pci_reset_function_locked(psdev->dev);
+ if (pci_load_and_free_saved_state(psdev->dev,
+ &dev_data->pci_saved_state)) {
+ dev_dbg(&psdev->dev->dev, "Could not reload PCI state\n");
+ } else
+ pci_restore_state(psdev->dev);
+
+ /* Disable the device */
xen_pcibk_reset_device(psdev->dev);
+
+ kfree(dev_data);
+ pci_set_drvdata(psdev->dev, NULL);
+
+ /* Clean-up the device */
xen_pcibk_config_free_dyn_fields(psdev->dev);
xen_pcibk_config_free_dev(psdev->dev);
- kfree(pci_get_drvdata(psdev->dev));
- pci_set_drvdata(psdev->dev, NULL);
psdev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
pci_dev_put(psdev->dev);
/* Cleanup our device
* (so it's ready for the next domain)
*/
+
+ /* This is OK - we are running from workqueue context
+ * and want to inhibit the user from fiddling with 'reset'
+ */
+ pci_reset_function(dev);
+ pci_restore_state(psdev->dev);
+
+ /* This disables the device. */
xen_pcibk_reset_device(found_psdev->dev);
+
+ /* And cleanup up our emulated fields. */
xen_pcibk_config_free_dyn_fields(found_psdev->dev);
xen_pcibk_config_reset_dev(found_psdev->dev);
if (err)
goto config_release;
+ dev_dbg(&dev->dev, "reseting (FLR, D3, etc) the device\n");
+ __pci_reset_function_locked(dev);
+
+ /* We need the device active to save the state. */
+ dev_dbg(&dev->dev, "save state of device\n");
+ pci_save_state(dev);
+ dev_data->pci_saved_state = pci_store_saved_state(dev);
+ if (!dev_data->pci_saved_state)
+ dev_err(&dev->dev, "Could not store PCI conf saved state!\n");
+
/* Now disable the device (this also ensures some private device
* data is setup before we export)
*/
int err;
err =
- sscanf(buf, " %04x:%02x:%02x.%1x-%08x:%1x:%08x", domain, bus, slot,
+ sscanf(buf, " %04x:%02x:%02x.%d-%08x:%1x:%08x", domain, bus, slot,
func, reg, size, mask);
if (err == 7)
return 0;
pci_dev_id->bus = bus;
pci_dev_id->devfn = PCI_DEVFN(slot, func);
- pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%01x\n",
+ pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%d\n",
domain, bus, slot, func);
spin_lock_irqsave(&device_ids_lock, flags);
err = 0;
- pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%01x from "
+ pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%d from "
"seize list\n", domain, bus, slot, func);
}
}
break;
count += scnprintf(buf + count, PAGE_SIZE - count,
- "%04x:%02x:%02x.%01x\n",
+ "%04x:%02x:%02x.%d\n",
pci_dev_id->domain, pci_dev_id->bus,
PCI_SLOT(pci_dev_id->devfn),
PCI_FUNC(pci_dev_id->devfn));
int where, u32 val);
struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops);
-static inline int pci_read_config_byte(struct pci_dev *dev, int where, u8 *val)
+static inline int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val)
{
return pci_bus_read_config_byte(dev->bus, dev->devfn, where, val);
}
-static inline int pci_read_config_word(struct pci_dev *dev, int where, u16 *val)
+static inline int pci_read_config_word(const struct pci_dev *dev, int where, u16 *val)
{
return pci_bus_read_config_word(dev->bus, dev->devfn, where, val);
}
-static inline int pci_read_config_dword(struct pci_dev *dev, int where,
+static inline int pci_read_config_dword(const struct pci_dev *dev, int where,
u32 *val)
{
return pci_bus_read_config_dword(dev->bus, dev->devfn, where, val);
}
-static inline int pci_write_config_byte(struct pci_dev *dev, int where, u8 val)
+static inline int pci_write_config_byte(const struct pci_dev *dev, int where, u8 val)
{
return pci_bus_write_config_byte(dev->bus, dev->devfn, where, val);
}
-static inline int pci_write_config_word(struct pci_dev *dev, int where, u16 val)
+static inline int pci_write_config_word(const struct pci_dev *dev, int where, u16 val)
{
return pci_bus_write_config_word(dev->bus, dev->devfn, where, val);
}
-static inline int pci_write_config_dword(struct pci_dev *dev, int where,
+static inline int pci_write_config_dword(const struct pci_dev *dev, int where,
u32 val)
{
return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
int pcie_get_mps(struct pci_dev *dev);
int pcie_set_mps(struct pci_dev *dev, int mps);
int __pci_reset_function(struct pci_dev *dev);
+ int __pci_reset_function_locked(struct pci_dev *dev);
int pci_reset_function(struct pci_dev *dev);
void pci_update_resource(struct pci_dev *dev, int resno);
int __must_check pci_assign_resource(struct pci_dev *dev, int i);
__pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
void pci_unregister_driver(struct pci_driver *dev);
+
+/**
+ * module_pci_driver() - Helper macro for registering a PCI driver
+ * @__pci_driver: pci_driver struct
+ *
+ * Helper macro for PCI drivers which do not do anything special in module
+ * init/exit. This eliminates a lot of boilerplate. Each module may only
+ * use this macro once, and calling it replaces module_init() and module_exit()
+ */
+#define module_pci_driver(__pci_driver) \
+ module_driver(__pci_driver, pci_register_driver, \
+ pci_unregister_driver)
+
void pci_remove_behind_bridge(struct pci_dev *dev);
struct pci_driver *pci_dev_driver(const struct pci_dev *dev);
int pci_add_dynid(struct pci_driver *drv,
static inline void pci_release_bus_of_node(struct pci_bus *bus) { }
#endif /* CONFIG_OF */
+#ifdef CONFIG_EEH
+static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
+{
+ return pdev->dev.archdata.edev;
+}
+#endif
+
/**
* pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device
* @pdev: the PCI device