1 // SPDX-License-Identifier: GPL-2.0-only
2 #include <xen/xen.h>
3 #include <xen/events.h>
4 #include <xen/grant_table.h>
5 #include <xen/hvm.h>
6 #include <xen/interface/vcpu.h>
7 #include <xen/interface/xen.h>
8 #include <xen/interface/memory.h>
9 #include <xen/interface/hvm/params.h>
10 #include <xen/features.h>
11 #include <xen/platform_pci.h>
12 #include <xen/xenbus.h>
13 #include <xen/page.h>
14 #include <xen/interface/sched.h>
15 #include <xen/xen-ops.h>
16 #include <asm/xen/hypervisor.h>
17 #include <asm/xen/hypercall.h>
18 #include <asm/system_misc.h>
19 #include <asm/efi.h>
20 #include <linux/interrupt.h>
21 #include <linux/irqreturn.h>
22 #include <linux/module.h>
23 #include <linux/of.h>
24 #include <linux/of_fdt.h>
25 #include <linux/of_irq.h>
26 #include <linux/of_address.h>
27 #include <linux/cpuidle.h>
28 #include <linux/cpufreq.h>
29 #include <linux/cpu.h>
30 #include <linux/console.h>
31 #include <linux/pvclock_gtod.h>
32 #include <linux/time64.h>
33 #include <linux/timekeeping.h>
34 #include <linux/timekeeper_internal.h>
35 #include <linux/acpi.h>
36
37 #include <linux/mm.h>
38
39 static struct start_info _xen_start_info;
40 struct start_info *xen_start_info = &_xen_start_info;
41 EXPORT_SYMBOL(xen_start_info);
42
43 enum xen_domain_type xen_domain_type = XEN_NATIVE;
44 EXPORT_SYMBOL(xen_domain_type);
45
46 struct shared_info xen_dummy_shared_info;
47 struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
48
49 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
50 static struct vcpu_info __percpu *xen_vcpu_info;
51
52 /* Linux <-> Xen vCPU id mapping */
53 DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
54 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
55
56 /* These are unused until we support booting "pre-ballooned" */
57 unsigned long xen_released_pages;
58 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
59
60 static __read_mostly unsigned int xen_events_irq;
61
62 uint32_t xen_start_flags;
63 EXPORT_SYMBOL(xen_start_flags);
64
xen_unmap_domain_gfn_range(struct vm_area_struct *vma, int nr, struct page **pages)65 int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
66 int nr, struct page **pages)
67 {
68 return xen_xlate_unmap_gfn_range(vma, nr, pages);
69 }
70 EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
71
xen_read_wallclock(struct timespec64 *ts)72 static void xen_read_wallclock(struct timespec64 *ts)
73 {
74 u32 version;
75 struct timespec64 now, ts_monotonic;
76 struct shared_info *s = HYPERVISOR_shared_info;
77 struct pvclock_wall_clock *wall_clock = &(s->wc);
78
79 /* get wallclock at system boot */
80 do {
81 version = wall_clock->version;
82 rmb(); /* fetch version before time */
83 now.tv_sec = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec;
84 now.tv_nsec = wall_clock->nsec;
85 rmb(); /* fetch time before checking version */
86 } while ((wall_clock->version & 1) || (version != wall_clock->version));
87
88 /* time since system boot */
89 ktime_get_ts64(&ts_monotonic);
90 *ts = timespec64_add(now, ts_monotonic);
91 }
92
xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set, void *priv)93 static int xen_pvclock_gtod_notify(struct notifier_block *nb,
94 unsigned long was_set, void *priv)
95 {
96 /* Protected by the calling core code serialization */
97 static struct timespec64 next_sync;
98
99 struct xen_platform_op op;
100 struct timespec64 now, system_time;
101 struct timekeeper *tk = priv;
102
103 now.tv_sec = tk->xtime_sec;
104 now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift);
105 system_time = timespec64_add(now, tk->wall_to_monotonic);
106
107 /*
108 * We only take the expensive HV call when the clock was set
109 * or when the 11 minutes RTC synchronization time elapsed.
110 */
111 if (!was_set && timespec64_compare(&now, &next_sync) < 0)
112 return NOTIFY_OK;
113
114 op.cmd = XENPF_settime64;
115 op.u.settime64.mbz = 0;
116 op.u.settime64.secs = now.tv_sec;
117 op.u.settime64.nsecs = now.tv_nsec;
118 op.u.settime64.system_time = timespec64_to_ns(&system_time);
119 (void)HYPERVISOR_platform_op(&op);
120
121 /*
122 * Move the next drift compensation time 11 minutes
123 * ahead. That's emulating the sync_cmos_clock() update for
124 * the hardware RTC.
125 */
126 next_sync = now;
127 next_sync.tv_sec += 11 * 60;
128
129 return NOTIFY_OK;
130 }
131
132 static struct notifier_block xen_pvclock_gtod_notifier = {
133 .notifier_call = xen_pvclock_gtod_notify,
134 };
135
xen_starting_cpu(unsigned int cpu)136 static int xen_starting_cpu(unsigned int cpu)
137 {
138 struct vcpu_register_vcpu_info info;
139 struct vcpu_info *vcpup;
140 int err;
141
142 /*
143 * VCPUOP_register_vcpu_info cannot be called twice for the same
144 * vcpu, so if vcpu_info is already registered, just get out. This
145 * can happen with cpu-hotplug.
146 */
147 if (per_cpu(xen_vcpu, cpu) != NULL)
148 goto after_register_vcpu_info;
149
150 pr_info("Xen: initializing cpu%d\n", cpu);
151 vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
152
153 info.mfn = percpu_to_gfn(vcpup);
154 info.offset = xen_offset_in_page(vcpup);
155
156 err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),
157 &info);
158 BUG_ON(err);
159 per_cpu(xen_vcpu, cpu) = vcpup;
160
161 after_register_vcpu_info:
162 enable_percpu_irq(xen_events_irq, 0);
163 return 0;
164 }
165
xen_dying_cpu(unsigned int cpu)166 static int xen_dying_cpu(unsigned int cpu)
167 {
168 disable_percpu_irq(xen_events_irq);
169 return 0;
170 }
171
xen_reboot(int reason)172 void xen_reboot(int reason)
173 {
174 struct sched_shutdown r = { .reason = reason };
175 int rc;
176
177 rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r);
178 BUG_ON(rc);
179 }
180
xen_restart(enum reboot_mode reboot_mode, const char *cmd)181 static void xen_restart(enum reboot_mode reboot_mode, const char *cmd)
182 {
183 xen_reboot(SHUTDOWN_reboot);
184 }
185
186
xen_power_off(void)187 static void xen_power_off(void)
188 {
189 xen_reboot(SHUTDOWN_poweroff);
190 }
191
xen_arm_callback(int irq, void *arg)192 static irqreturn_t xen_arm_callback(int irq, void *arg)
193 {
194 xen_hvm_evtchn_do_upcall();
195 return IRQ_HANDLED;
196 }
197
198 static __initdata struct {
199 const char *compat;
200 const char *prefix;
201 const char *version;
202 bool found;
203 } hyper_node = {"xen,xen", "xen,xen-", NULL, false};
204
fdt_find_hyper_node(unsigned long node, const char *uname, int depth, void *data)205 static int __init fdt_find_hyper_node(unsigned long node, const char *uname,
206 int depth, void *data)
207 {
208 const void *s = NULL;
209 int len;
210
211 if (depth != 1 || strcmp(uname, "hypervisor") != 0)
212 return 0;
213
214 if (of_flat_dt_is_compatible(node, hyper_node.compat))
215 hyper_node.found = true;
216
217 s = of_get_flat_dt_prop(node, "compatible", &len);
218 if (strlen(hyper_node.prefix) + 3 < len &&
219 !strncmp(hyper_node.prefix, s, strlen(hyper_node.prefix)))
220 hyper_node.version = s + strlen(hyper_node.prefix);
221
222 /*
223 * Check if Xen supports EFI by checking whether there is the
224 * "/hypervisor/uefi" node in DT. If so, runtime services are available
225 * through proxy functions (e.g. in case of Xen dom0 EFI implementation
226 * they call special hypercall which executes relevant EFI functions)
227 * and that is why they are always enabled.
228 */
229 if (IS_ENABLED(CONFIG_XEN_EFI)) {
230 if ((of_get_flat_dt_subnode_by_name(node, "uefi") > 0) &&
231 !efi_runtime_disabled())
232 set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
233 }
234
235 return 0;
236 }
237
238 /*
239 * see Documentation/devicetree/bindings/arm/xen.txt for the
240 * documentation of the Xen Device Tree format.
241 */
xen_early_init(void)242 void __init xen_early_init(void)
243 {
244 of_scan_flat_dt(fdt_find_hyper_node, NULL);
245 if (!hyper_node.found) {
246 pr_debug("No Xen support\n");
247 return;
248 }
249
250 if (hyper_node.version == NULL) {
251 pr_debug("Xen version not found\n");
252 return;
253 }
254
255 pr_info("Xen %s support found\n", hyper_node.version);
256
257 xen_domain_type = XEN_HVM_DOMAIN;
258
259 xen_setup_features();
260
261 if (xen_feature(XENFEAT_dom0))
262 xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED;
263
264 if (!console_set_on_cmdline && !xen_initial_domain())
265 add_preferred_console("hvc", 0, NULL);
266 }
267
xen_acpi_guest_init(void)268 static void __init xen_acpi_guest_init(void)
269 {
270 #ifdef CONFIG_ACPI
271 struct xen_hvm_param a;
272 int interrupt, trigger, polarity;
273
274 a.domid = DOMID_SELF;
275 a.index = HVM_PARAM_CALLBACK_IRQ;
276
277 if (HYPERVISOR_hvm_op(HVMOP_get_param, &a)
278 || (a.value >> 56) != HVM_PARAM_CALLBACK_TYPE_PPI) {
279 xen_events_irq = 0;
280 return;
281 }
282
283 interrupt = a.value & 0xff;
284 trigger = ((a.value >> 8) & 0x1) ? ACPI_EDGE_SENSITIVE
285 : ACPI_LEVEL_SENSITIVE;
286 polarity = ((a.value >> 8) & 0x2) ? ACPI_ACTIVE_LOW
287 : ACPI_ACTIVE_HIGH;
288 xen_events_irq = acpi_register_gsi(NULL, interrupt, trigger, polarity);
289 #endif
290 }
291
xen_dt_guest_init(void)292 static void __init xen_dt_guest_init(void)
293 {
294 struct device_node *xen_node;
295
296 xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
297 if (!xen_node) {
298 pr_err("Xen support was detected before, but it has disappeared\n");
299 return;
300 }
301
302 xen_events_irq = irq_of_parse_and_map(xen_node, 0);
303 }
304
xen_guest_init(void)305 static int __init xen_guest_init(void)
306 {
307 struct xen_add_to_physmap xatp;
308 struct shared_info *shared_info_page = NULL;
309 int cpu;
310
311 if (!xen_domain())
312 return 0;
313
314 if (!acpi_disabled)
315 xen_acpi_guest_init();
316 else
317 xen_dt_guest_init();
318
319 if (!xen_events_irq) {
320 pr_err("Xen event channel interrupt not found\n");
321 return -ENODEV;
322 }
323
324 /*
325 * The fdt parsing codes have set EFI_RUNTIME_SERVICES if Xen EFI
326 * parameters are found. Force enable runtime services.
327 */
328 if (efi_enabled(EFI_RUNTIME_SERVICES))
329 xen_efi_runtime_setup();
330
331 shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
332
333 if (!shared_info_page) {
334 pr_err("not enough memory\n");
335 return -ENOMEM;
336 }
337 xatp.domid = DOMID_SELF;
338 xatp.idx = 0;
339 xatp.space = XENMAPSPACE_shared_info;
340 xatp.gpfn = virt_to_gfn(shared_info_page);
341 if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
342 BUG();
343
344 HYPERVISOR_shared_info = (struct shared_info *)shared_info_page;
345
346 /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info
347 * page, we use it in the event channel upcall and in some pvclock
348 * related functions.
349 * The shared info contains exactly 1 CPU (the boot CPU). The guest
350 * is required to use VCPUOP_register_vcpu_info to place vcpu info
351 * for secondary CPUs as they are brought up.
352 * For uniformity we use VCPUOP_register_vcpu_info even on cpu0.
353 */
354 xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info),
355 1 << fls(sizeof(struct vcpu_info) - 1));
356 if (xen_vcpu_info == NULL)
357 return -ENOMEM;
358
359 /* Direct vCPU id mapping for ARM guests. */
360 for_each_possible_cpu(cpu)
361 per_cpu(xen_vcpu_id, cpu) = cpu;
362
363 xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
364 if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
365 &xen_auto_xlat_grant_frames.vaddr,
366 xen_auto_xlat_grant_frames.count)) {
367 free_percpu(xen_vcpu_info);
368 return -ENOMEM;
369 }
370 gnttab_init();
371
372 /*
373 * Making sure board specific code will not set up ops for
374 * cpu idle and cpu freq.
375 */
376 disable_cpuidle();
377 disable_cpufreq();
378
379 xen_init_IRQ();
380
381 if (request_percpu_irq(xen_events_irq, xen_arm_callback,
382 "events", &xen_vcpu)) {
383 pr_err("Error request IRQ %d\n", xen_events_irq);
384 return -EINVAL;
385 }
386
387 if (xen_initial_domain())
388 pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
389
390 return cpuhp_setup_state(CPUHP_AP_ARM_XEN_STARTING,
391 "arm/xen:starting", xen_starting_cpu,
392 xen_dying_cpu);
393 }
394 early_initcall(xen_guest_init);
395
xen_starting_runstate_cpu(unsigned int cpu)396 static int xen_starting_runstate_cpu(unsigned int cpu)
397 {
398 xen_setup_runstate_info(cpu);
399 return 0;
400 }
401
xen_late_init(void)402 static int __init xen_late_init(void)
403 {
404 if (!xen_domain())
405 return -ENODEV;
406
407 pm_power_off = xen_power_off;
408 arm_pm_restart = xen_restart;
409 if (!xen_initial_domain()) {
410 struct timespec64 ts;
411 xen_read_wallclock(&ts);
412 do_settimeofday64(&ts);
413 }
414
415 if (xen_kernel_unmapped_at_usr())
416 return 0;
417
418 xen_time_setup_guest();
419
420 return cpuhp_setup_state(CPUHP_AP_ARM_XEN_RUNSTATE_STARTING,
421 "arm/xen_runstate:starting",
422 xen_starting_runstate_cpu, NULL);
423 }
424 late_initcall(xen_late_init);
425
426
427 /* empty stubs */
xen_arch_pre_suspend(void)428 void xen_arch_pre_suspend(void) { }
xen_arch_post_suspend(int suspend_cancelled)429 void xen_arch_post_suspend(int suspend_cancelled) { }
xen_timer_resume(void)430 void xen_timer_resume(void) { }
xen_arch_resume(void)431 void xen_arch_resume(void) { }
xen_arch_suspend(void)432 void xen_arch_suspend(void) { }
433
434
435 /* In the hypercall.S file. */
436 EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
437 EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
438 EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version);
439 EXPORT_SYMBOL_GPL(HYPERVISOR_console_io);
440 EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op);
441 EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op);
442 EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
443 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
444 EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
445 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
446 EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw);
447 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
448 EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
449 EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
450 EXPORT_SYMBOL_GPL(privcmd_call);
451