2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 13:43:55 +08:00
linux-next/arch/arm/xen/enlighten.c

367 lines
9.1 KiB
C
Raw Normal View History

#include <xen/xen.h>
#include <xen/events.h>
#include <xen/grant_table.h>
#include <xen/hvm.h>
#include <xen/interface/vcpu.h>
#include <xen/interface/xen.h>
#include <xen/interface/memory.h>
#include <xen/interface/hvm/params.h>
#include <xen/features.h>
#include <xen/platform_pci.h>
#include <xen/xenbus.h>
#include <xen/page.h>
#include <xen/interface/sched.h>
#include <xen/xen-ops.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <asm/system_misc.h>
#include <linux/interrupt.h>
#include <linux/irqreturn.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/of_address.h>
#include <linux/cpuidle.h>
#include <linux/cpufreq.h>
#include <linux/cpu.h>
#include <linux/mm.h>
struct start_info _xen_start_info;
struct start_info *xen_start_info = &_xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);
enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL_GPL(xen_domain_type);
struct shared_info xen_dummy_shared_info;
struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
static struct vcpu_info __percpu *xen_vcpu_info;
/* These are unused until we support booting "pre-ballooned" */
unsigned long xen_released_pages;
struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
/* TODO: to be removed */
__read_mostly int xen_have_vector_callback;
EXPORT_SYMBOL_GPL(xen_have_vector_callback);
int xen_platform_pci_unplug = XEN_UNPLUG_ALL;
EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
static __read_mostly int xen_events_irq = -1;
/* map fgmfn of domid to lpfn in the current domain */
static int map_foreign_page(unsigned long lpfn, unsigned long fgmfn,
unsigned int domid)
{
int rc;
struct xen_add_to_physmap_range xatp = {
.domid = DOMID_SELF,
.foreign_domid = domid,
.size = 1,
.space = XENMAPSPACE_gmfn_foreign,
};
xen_ulong_t idx = fgmfn;
xen_pfn_t gpfn = lpfn;
int err = 0;
set_xen_guest_handle(xatp.idxs, &idx);
set_xen_guest_handle(xatp.gpfns, &gpfn);
set_xen_guest_handle(xatp.errs, &err);
rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
if (rc || err) {
pr_warn("Failed to map pfn to mfn rc:%d:%d pfn:%lx mfn:%lx\n",
rc, err, lpfn, fgmfn);
return 1;
}
return 0;
}
struct remap_data {
xen_pfn_t fgmfn; /* foreign domain's gmfn */
pgprot_t prot;
domid_t domid;
struct vm_area_struct *vma;
int index;
struct page **pages;
struct xen_remap_mfn_info *info;
};
static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
void *data)
{
struct remap_data *info = data;
struct page *page = info->pages[info->index++];
unsigned long pfn = page_to_pfn(page);
arm: xen: foreign mapping PTEs are special. These mappings are in fact special and require special handling in privcmd, which already exists. Failure to mark the PTE as special on arm64 causes all sorts of bad PTE fun. e.g. e.g.: BUG: Bad page map in process xl pte:e0004077b33f53 pmd:4079575003 page:ffffffbce1a2f328 count:1 mapcount:-1 mapping: (null) index:0x0 page flags: 0x4000000000000014(referenced|dirty) addr:0000007fb5259000 vm_flags:040644fa anon_vma: (null) mapping:ffffffc03a6fda58 index:0 vma->vm_ops->fault: privcmd_fault+0x0/0x38 vma->vm_file->f_op->mmap: privcmd_mmap+0x0/0x2c CPU: 0 PID: 2657 Comm: xl Not tainted 3.12.0+ #102 Call trace: [<ffffffc0000880f8>] dump_backtrace+0x0/0x12c [<ffffffc000088238>] show_stack+0x14/0x1c [<ffffffc0004b67e0>] dump_stack+0x70/0x90 [<ffffffc000125690>] print_bad_pte+0x12c/0x1bc [<ffffffc0001268f4>] unmap_single_vma+0x4cc/0x700 [<ffffffc0001273b4>] unmap_vmas+0x68/0xb4 [<ffffffc00012c050>] unmap_region+0xcc/0x1d4 [<ffffffc00012df20>] do_munmap+0x218/0x314 [<ffffffc00012e060>] vm_munmap+0x44/0x64 [<ffffffc00012ed78>] SyS_munmap+0x24/0x34 Where unmap_single_vma contains inlined -> unmap_page_range -> zap_pud_range -> zap_pmd_range -> zap_pte_range -> print_bad_pte. Or: BUG: Bad page state in process xl pfn:4077b4d page:ffffffbce1a2f8d8 count:0 mapcount:-1 mapping: (null) index:0x0 page flags: 0x4000000000000014(referenced|dirty) Modules linked in: CPU: 0 PID: 2657 Comm: xl Tainted: G B 3.12.0+ #102 Call trace: [<ffffffc0000880f8>] dump_backtrace+0x0/0x12c [<ffffffc000088238>] show_stack+0x14/0x1c [<ffffffc0004b67e0>] dump_stack+0x70/0x90 [<ffffffc00010f798>] bad_page+0xc4/0x110 [<ffffffc00010f8b4>] free_pages_prepare+0xd0/0xd8 [<ffffffc000110e94>] free_hot_cold_page+0x28/0x178 [<ffffffc000111460>] free_hot_cold_page_list+0x38/0x60 [<ffffffc000114cf0>] release_pages+0x190/0x1dc [<ffffffc00012c0e0>] unmap_region+0x15c/0x1d4 [<ffffffc00012df20>] do_munmap+0x218/0x314 [<ffffffc00012e060>] vm_munmap+0x44/0x64 [<ffffffc00012ed78>] SyS_munmap+0x24/0x34 x86 already gets this correct. 32-bit arm gets away with this because there is not PTE_SPECIAL bit in the PTE there and the vm_normal_page fallback path does the right thing. Signed-off-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
2013-12-12 01:02:27 +08:00
pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
if (map_foreign_page(pfn, info->fgmfn, info->domid))
return -EFAULT;
set_pte_at(info->vma->vm_mm, addr, ptep, pte);
return 0;
}
int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
unsigned long addr,
xen_pfn_t mfn, int nr,
pgprot_t prot, unsigned domid,
struct page **pages)
{
int err;
struct remap_data data;
/* TBD: Batching, current sole caller only does page at a time */
if (nr > 1)
return -EINVAL;
data.fgmfn = mfn;
data.prot = prot;
data.domid = domid;
data.vma = vma;
data.index = 0;
data.pages = pages;
err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT,
remap_pte_fn, &data);
return err;
}
EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
int nr, struct page **pages)
{
int i;
for (i = 0; i < nr; i++) {
struct xen_remove_from_physmap xrp;
unsigned long rc, pfn;
pfn = page_to_pfn(pages[i]);
xrp.domid = DOMID_SELF;
xrp.gpfn = pfn;
rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
if (rc) {
pr_warn("Failed to unmap pfn:%lx rc:%ld\n",
pfn, rc);
return rc;
}
}
return 0;
}
EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
static void xen_percpu_init(void)
{
struct vcpu_register_vcpu_info info;
struct vcpu_info *vcpup;
int err;
int cpu = get_cpu();
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
info.mfn = __pa(vcpup) >> PAGE_SHIFT;
info.offset = offset_in_page(vcpup);
err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
BUG_ON(err);
per_cpu(xen_vcpu, cpu) = vcpup;
enable_percpu_irq(xen_events_irq, 0);
put_cpu();
}
static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
{
struct sched_shutdown r = { .reason = SHUTDOWN_reboot };
int rc;
rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
BUG_ON(rc);
}
static void xen_power_off(void)
{
struct sched_shutdown r = { .reason = SHUTDOWN_poweroff };
int rc;
rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
BUG_ON(rc);
}
static int xen_cpu_notification(struct notifier_block *self,
unsigned long action,
void *hcpu)
{
switch (action) {
case CPU_STARTING:
xen_percpu_init();
break;
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block xen_cpu_notifier = {
.notifier_call = xen_cpu_notification,
};
static irqreturn_t xen_arm_callback(int irq, void *arg)
{
xen_hvm_evtchn_do_upcall();
return IRQ_HANDLED;
}
/*
* see Documentation/devicetree/bindings/arm/xen.txt for the
* documentation of the Xen Device Tree format.
*/
#define GRANT_TABLE_PHYSADDR 0
static int __init xen_guest_init(void)
{
struct xen_add_to_physmap xatp;
static struct shared_info *shared_info_page = 0;
struct device_node *node;
int len;
const char *s = NULL;
const char *version = NULL;
const char *xen_prefix = "xen,xen-";
struct resource res;
phys_addr_t grant_frames;
node = of_find_compatible_node(NULL, NULL, "xen,xen");
if (!node) {
pr_debug("No Xen support\n");
return 0;
}
s = of_get_property(node, "compatible", &len);
if (strlen(xen_prefix) + 3 < len &&
!strncmp(xen_prefix, s, strlen(xen_prefix)))
version = s + strlen(xen_prefix);
if (version == NULL) {
pr_debug("Xen version not found\n");
return 0;
}
if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
return 0;
grant_frames = res.start;
xen_events_irq = irq_of_parse_and_map(node, 0);
pr_info("Xen %s support found, events_irq=%d gnttab_frame=%pa\n",
version, xen_events_irq, &grant_frames);
if (xen_events_irq < 0)
return -ENODEV;
xen_domain_type = XEN_HVM_DOMAIN;
xen_setup_features();
if (!xen_feature(XENFEAT_grant_map_identity)) {
pr_warn("Please upgrade your Xen.\n"
"If your platform has any non-coherent DMA devices, they won't work properly.\n");
}
if (xen_feature(XENFEAT_dom0))
xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
else
xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
if (!shared_info_page)
shared_info_page = (struct shared_info *)
get_zeroed_page(GFP_KERNEL);
if (!shared_info_page) {
pr_err("not enough memory\n");
return -ENOMEM;
}
xatp.domid = DOMID_SELF;
xatp.idx = 0;
xatp.space = XENMAPSPACE_shared_info;
xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
BUG();
HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
/* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
* page, we use it in the event channel upcall and in some pvclock
* related functions.
* The shared info contains exactly 1 CPU (the boot CPU). The guest
* is required to use VCPUOP_register_vcpu_info to place vcpu info
* for secondary CPUs as they are brought up.
* For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
*/
xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
sizeof(struct vcpu_info));
if (xen_vcpu_info == NULL)
return -ENOMEM;
if (gnttab_setup_auto_xlat_frames(grant_frames)) {
free_percpu(xen_vcpu_info);
return -ENOMEM;
}
gnttab_init();
if (!xen_initial_domain())
xenbus_probe(NULL);
/*
* Making sure board specific code will not set up ops for
* cpu idle and cpu freq.
*/
disable_cpuidle();
disable_cpufreq();
xen_init_IRQ();
if (request_percpu_irq(xen_events_irq, xen_arm_callback,
"events", &xen_vcpu)) {
pr_err("Error request IRQ %d\n", xen_events_irq);
return -EINVAL;
}
xen_percpu_init();
register_cpu_notifier(&xen_cpu_notifier);
return 0;
}
early_initcall(xen_guest_init);
static int __init xen_pm_init(void)
{
if (!xen_domain())
return -ENODEV;
pm_power_off = xen_power_off;
arm_pm_restart = xen_restart;
return 0;
}
late_initcall(xen_pm_init);
/* empty stubs */
void xen_arch_pre_suspend(void) { }
void xen_arch_post_suspend(int suspend_cancelled) { }
void xen_timer_resume(void) { }
void xen_arch_resume(void) { }
/* In the hypervisor.S file. */
EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version);
EXPORT_SYMBOL_GPL(HYPERVISOR_console_io);
EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
EXPORT_SYMBOL_GPL(privcmd_call);