linux/arch/arm/xen/enlighten.c
Stefano Stabellini 7bf9a6b465 arm/xen: fix xen_vcpu_info allocation alignment
xen_vcpu_info is a percpu area than needs to be mapped by Xen.
Currently, it could cross a page boundary resulting in Xen being unable
to map it:

[    0.567318] kernel BUG at arch/arm64/xen/../../arm/xen/enlighten.c:164!
[    0.574002] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP

Fix the issue by using __alloc_percpu and requesting alignment for the
memory allocation.

Signed-off-by: Stefano Stabellini <stefano.stabellini@amd.com>

Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2311221501340.2053963@ubuntu-linux-20-04-desktop
Fixes: 24d5373dda ("arm/xen: Use alloc_percpu rather than __alloc_percpu")
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
2023-11-23 09:32:41 +01:00

587 lines
15 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
#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 <asm/efi.h>
#include <linux/interrupt.h>
#include <linux/irqreturn.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_fdt.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/console.h>
#include <linux/pvclock_gtod.h>
#include <linux/reboot.h>
#include <linux/time64.h>
#include <linux/timekeeping.h>
#include <linux/timekeeper_internal.h>
#include <linux/acpi.h>
#include <linux/virtio_anchor.h>
#include <linux/mm.h>
static struct start_info _xen_start_info;
struct start_info *xen_start_info = &_xen_start_info;
EXPORT_SYMBOL(xen_start_info);
enum xen_domain_type xen_domain_type = XEN_NATIVE;
EXPORT_SYMBOL(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;
/* Linux <-> Xen vCPU id mapping */
DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
/* 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;
static __read_mostly unsigned int xen_events_irq;
static __read_mostly phys_addr_t xen_grant_frames;
#define GRANT_TABLE_INDEX 0
#define EXT_REGION_INDEX 1
uint32_t xen_start_flags;
EXPORT_SYMBOL(xen_start_flags);
int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
int nr, struct page **pages)
{
return xen_xlate_unmap_gfn_range(vma, nr, pages);
}
EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
static void xen_read_wallclock(struct timespec64 *ts)
{
u32 version;
struct timespec64 now, ts_monotonic;
struct shared_info *s = HYPERVISOR_shared_info;
struct pvclock_wall_clock *wall_clock = &(s->wc);
/* get wallclock at system boot */
do {
version = wall_clock->version;
rmb(); /* fetch version before time */
now.tv_sec = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec;
now.tv_nsec = wall_clock->nsec;
rmb(); /* fetch time before checking version */
} while ((wall_clock->version & 1) || (version != wall_clock->version));
/* time since system boot */
ktime_get_ts64(&ts_monotonic);
*ts = timespec64_add(now, ts_monotonic);
}
static int xen_pvclock_gtod_notify(struct notifier_block *nb,
unsigned long was_set, void *priv)
{
/* Protected by the calling core code serialization */
static struct timespec64 next_sync;
struct xen_platform_op op;
struct timespec64 now, system_time;
struct timekeeper *tk = priv;
now.tv_sec = tk->xtime_sec;
now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
system_time = timespec64_add(now, tk->wall_to_monotonic);
/*
* We only take the expensive HV call when the clock was set
* or when the 11 minutes RTC synchronization time elapsed.
*/
if (!was_set && timespec64_compare(&now, &next_sync) < 0)
return NOTIFY_OK;
op.cmd = XENPF_settime64;
op.u.settime64.mbz = 0;
op.u.settime64.secs = now.tv_sec;
op.u.settime64.nsecs = now.tv_nsec;
op.u.settime64.system_time = timespec64_to_ns(&system_time);
(void)HYPERVISOR_platform_op(&op);
/*
* Move the next drift compensation time 11 minutes
* ahead. That's emulating the sync_cmos_clock() update for
* the hardware RTC.
*/
next_sync = now;
next_sync.tv_sec += 11 * 60;
return NOTIFY_OK;
}
static struct notifier_block xen_pvclock_gtod_notifier = {
.notifier_call = xen_pvclock_gtod_notify,
};
static int xen_starting_cpu(unsigned int cpu)
{
struct vcpu_register_vcpu_info info;
struct vcpu_info *vcpup;
int err;
/*
* VCPUOP_register_vcpu_info cannot be called twice for the same
* vcpu, so if vcpu_info is already registered, just get out. This
* can happen with cpu-hotplug.
*/
if (per_cpu(xen_vcpu, cpu) != NULL)
goto after_register_vcpu_info;
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
info.mfn = percpu_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
&info);
BUG_ON(err);
per_cpu(xen_vcpu, cpu) = vcpup;
after_register_vcpu_info:
enable_percpu_irq(xen_events_irq, 0);
return 0;
}
static int xen_dying_cpu(unsigned int cpu)
{
disable_percpu_irq(xen_events_irq);
return 0;
}
void xen_reboot(int reason)
{
struct sched_shutdown r = { .reason = reason };
int rc;
rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
BUG_ON(rc);
}
static int xen_restart(struct notifier_block *nb, unsigned long action,
void *data)
{
xen_reboot(SHUTDOWN_reboot);
return NOTIFY_DONE;
}
static struct notifier_block xen_restart_nb = {
.notifier_call = xen_restart,
.priority = 192,
};
static void xen_power_off(void)
{
xen_reboot(SHUTDOWN_poweroff);
}
static irqreturn_t xen_arm_callback(int irq, void *arg)
{
xen_evtchn_do_upcall();
return IRQ_HANDLED;
}
static __initdata struct {
const char *compat;
const char *prefix;
const char *version;
bool found;
} hyper_node = {"xen,xen", "xen,xen-", NULL, false};
static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
int depth, void *data)
{
const void *s = NULL;
int len;
if (depth != 1 || strcmp(uname, "hypervisor") != 0)
return 0;
if (of_flat_dt_is_compatible(node, hyper_node.compat))
hyper_node.found = true;
s = of_get_flat_dt_prop(node, "compatible", &len);
if (strlen(hyper_node.prefix) + 3 < len &&
!strncmp(hyper_node.prefix, s, strlen(hyper_node.prefix)))
hyper_node.version = s + strlen(hyper_node.prefix);
/*
* Check if Xen supports EFI by checking whether there is the
* "/hypervisor/uefi" node in DT. If so, runtime services are available
* through proxy functions (e.g. in case of Xen dom0 EFI implementation
* they call special hypercall which executes relevant EFI functions)
* and that is why they are always enabled.
*/
if (IS_ENABLED(CONFIG_XEN_EFI)) {
if ((of_get_flat_dt_subnode_by_name(node, "uefi") > 0) &&
!efi_runtime_disabled())
set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
}
return 0;
}
/*
* see Documentation/devicetree/bindings/arm/xen.txt for the
* documentation of the Xen Device Tree format.
*/
void __init xen_early_init(void)
{
of_scan_flat_dt(fdt_find_hyper_node, NULL);
if (!hyper_node.found) {
pr_debug("No Xen support\n");
return;
}
if (hyper_node.version == NULL) {
pr_debug("Xen version not found\n");
return;
}
pr_info("Xen %s support found\n", hyper_node.version);
xen_domain_type = XEN_HVM_DOMAIN;
xen_setup_features();
if (xen_feature(XENFEAT_dom0))
xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
if (!console_set_on_cmdline && !xen_initial_domain())
add_preferred_console("hvc", 0, NULL);
}
static void __init xen_acpi_guest_init(void)
{
#ifdef CONFIG_ACPI
struct xen_hvm_param a;
int interrupt, trigger, polarity;
a.domid = DOMID_SELF;
a.index = HVM_PARAM_CALLBACK_IRQ;
if (HYPERVISOR_hvm_op(HVMOP_get_param, &a)
|| (a.value >> 56) != HVM_PARAM_CALLBACK_TYPE_PPI) {
xen_events_irq = 0;
return;
}
interrupt = a.value & 0xff;
trigger = ((a.value >> 8) & 0x1) ? ACPI_EDGE_SENSITIVE
: ACPI_LEVEL_SENSITIVE;
polarity = ((a.value >> 8) & 0x2) ? ACPI_ACTIVE_LOW
: ACPI_ACTIVE_HIGH;
xen_events_irq = acpi_register_gsi(NULL, interrupt, trigger, polarity);
#endif
}
#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
/*
* A type-less specific Xen resource which contains extended regions
* (unused regions of guest physical address space provided by the hypervisor).
*/
static struct resource xen_resource = {
.name = "Xen unused space",
};
int __init arch_xen_unpopulated_init(struct resource **res)
{
struct device_node *np;
struct resource *regs, *tmp_res;
uint64_t min_gpaddr = -1, max_gpaddr = 0;
unsigned int i, nr_reg = 0;
int rc;
if (!xen_domain())
return -ENODEV;
if (!acpi_disabled)
return -ENODEV;
np = of_find_compatible_node(NULL, NULL, "xen,xen");
if (WARN_ON(!np))
return -ENODEV;
/* Skip region 0 which is reserved for grant table space */
while (of_get_address(np, nr_reg + EXT_REGION_INDEX, NULL, NULL))
nr_reg++;
if (!nr_reg) {
pr_err("No extended regions are found\n");
of_node_put(np);
return -EINVAL;
}
regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL);
if (!regs) {
of_node_put(np);
return -ENOMEM;
}
/*
* Create resource from extended regions provided by the hypervisor to be
* used as unused address space for Xen scratch pages.
*/
for (i = 0; i < nr_reg; i++) {
rc = of_address_to_resource(np, i + EXT_REGION_INDEX, &regs[i]);
if (rc)
goto err;
if (max_gpaddr < regs[i].end)
max_gpaddr = regs[i].end;
if (min_gpaddr > regs[i].start)
min_gpaddr = regs[i].start;
}
xen_resource.start = min_gpaddr;
xen_resource.end = max_gpaddr;
/*
* Mark holes between extended regions as unavailable. The rest of that
* address space will be available for the allocation.
*/
for (i = 1; i < nr_reg; i++) {
resource_size_t start, end;
/* There is an overlap between regions */
if (regs[i - 1].end + 1 > regs[i].start) {
rc = -EINVAL;
goto err;
}
/* There is no hole between regions */
if (regs[i - 1].end + 1 == regs[i].start)
continue;
start = regs[i - 1].end + 1;
end = regs[i].start - 1;
tmp_res = kzalloc(sizeof(*tmp_res), GFP_KERNEL);
if (!tmp_res) {
rc = -ENOMEM;
goto err;
}
tmp_res->name = "Unavailable space";
tmp_res->start = start;
tmp_res->end = end;
rc = insert_resource(&xen_resource, tmp_res);
if (rc) {
pr_err("Cannot insert resource %pR (%d)\n", tmp_res, rc);
kfree(tmp_res);
goto err;
}
}
*res = &xen_resource;
err:
of_node_put(np);
kfree(regs);
return rc;
}
#endif
static void __init xen_dt_guest_init(void)
{
struct device_node *xen_node;
struct resource res;
xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
if (!xen_node) {
pr_err("Xen support was detected before, but it has disappeared\n");
return;
}
xen_events_irq = irq_of_parse_and_map(xen_node, 0);
if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) {
pr_err("Xen grant table region is not found\n");
of_node_put(xen_node);
return;
}
of_node_put(xen_node);
xen_grant_frames = res.start;
}
static int __init xen_guest_init(void)
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
int rc, cpu;
if (!xen_domain())
return 0;
if (IS_ENABLED(CONFIG_XEN_VIRTIO))
virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc);
if (!acpi_disabled)
xen_acpi_guest_init();
else
xen_dt_guest_init();
if (!xen_events_irq) {
pr_err("Xen event channel interrupt not found\n");
return -ENODEV;
}
/*
* The fdt parsing codes have set EFI_RUNTIME_SERVICES if Xen EFI
* parameters are found. Force enable runtime services.
*/
if (efi_enabled(EFI_RUNTIME_SERVICES))
xen_efi_runtime_setup();
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 = virt_to_gfn(shared_info_page);
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),
1 << fls(sizeof(struct vcpu_info) - 1));
if (xen_vcpu_info == NULL)
return -ENOMEM;
/* Direct vCPU id mapping for ARM guests. */
for_each_possible_cpu(cpu)
per_cpu(xen_vcpu_id, cpu) = cpu;
if (!xen_grant_frames) {
xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
rc = xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
&xen_auto_xlat_grant_frames.vaddr,
xen_auto_xlat_grant_frames.count);
} else
rc = gnttab_setup_auto_xlat_frames(xen_grant_frames);
if (rc) {
free_percpu(xen_vcpu_info);
return rc;
}
gnttab_init();
/*
* 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;
}
if (xen_initial_domain())
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
"arm/xen:starting", xen_starting_cpu,
xen_dying_cpu);
}
early_initcall(xen_guest_init);
static int xen_starting_runstate_cpu(unsigned int cpu)
{
xen_setup_runstate_info(cpu);
return 0;
}
static int __init xen_late_init(void)
{
if (!xen_domain())
return -ENODEV;
pm_power_off = xen_power_off;
register_restart_handler(&xen_restart_nb);
if (!xen_initial_domain()) {
struct timespec64 ts;
xen_read_wallclock(&ts);
do_settimeofday64(&ts);
}
if (xen_kernel_unmapped_at_usr())
return 0;
xen_time_setup_guest();
return cpuhp_setup_state(CPUHP_AP_ARM_XEN_RUNSTATE_STARTING,
"arm/xen_runstate:starting",
xen_starting_runstate_cpu, NULL);
}
late_initcall(xen_late_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) { }
void xen_arch_suspend(void) { }
/* In the hypercall.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_platform_op_raw);
EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
EXPORT_SYMBOL_GPL(privcmd_call);