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 39static struct start_info _xen_start_info; 40struct start_info *xen_start_info = &_xen_start_info; 41EXPORT_SYMBOL(xen_start_info); 42 43enum xen_domain_type xen_domain_type = XEN_NATIVE; 44EXPORT_SYMBOL(xen_domain_type); 45 46struct shared_info xen_dummy_shared_info; 47struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info; 48 49DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); 50static struct vcpu_info __percpu *xen_vcpu_info; 51 52/* Linux <-> Xen vCPU id mapping */ 53DEFINE_PER_CPU(uint32_t, xen_vcpu_id); 54EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); 55 56/* These are unused until we support booting "pre-ballooned" */ 57unsigned long xen_released_pages; 58struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; 59 60static __read_mostly unsigned int xen_events_irq; 61 62uint32_t xen_start_flags; 63EXPORT_SYMBOL(xen_start_flags); 64 65int 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} 70EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); 71 72static 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 93static 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 132static struct notifier_block xen_pvclock_gtod_notifier = { 133 .notifier_call = xen_pvclock_gtod_notify, 134}; 135 136static 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 161after_register_vcpu_info: 162 enable_percpu_irq(xen_events_irq, 0); 163 return 0; 164} 165 166static int xen_dying_cpu(unsigned int cpu) 167{ 168 disable_percpu_irq(xen_events_irq); 169 return 0; 170} 171 172void 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 181static void xen_restart(enum reboot_mode reboot_mode, const char *cmd) 182{ 183 xen_reboot(SHUTDOWN_reboot); 184} 185 186 187static void xen_power_off(void) 188{ 189 xen_reboot(SHUTDOWN_poweroff); 190} 191 192static irqreturn_t xen_arm_callback(int irq, void *arg) 193{ 194 xen_hvm_evtchn_do_upcall(); 195 return IRQ_HANDLED; 196} 197 198static __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 205static 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 */ 242void __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 268static 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 292static 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 305static 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} 394early_initcall(xen_guest_init); 395 396static int xen_starting_runstate_cpu(unsigned int cpu) 397{ 398 xen_setup_runstate_info(cpu); 399 return 0; 400} 401 402static 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} 424late_initcall(xen_late_init); 425 426 427/* empty stubs */ 428void xen_arch_pre_suspend(void) { } 429void xen_arch_post_suspend(int suspend_cancelled) { } 430void xen_timer_resume(void) { } 431void xen_arch_resume(void) { } 432void xen_arch_suspend(void) { } 433 434 435/* In the hypercall.S file. */ 436EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op); 437EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op); 438EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version); 439EXPORT_SYMBOL_GPL(HYPERVISOR_console_io); 440EXPORT_SYMBOL_GPL(HYPERVISOR_sched_op); 441EXPORT_SYMBOL_GPL(HYPERVISOR_hvm_op); 442EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); 443EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); 444EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); 445EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); 446EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw); 447EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); 448EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist); 449EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op); 450EXPORT_SYMBOL_GPL(privcmd_call); 451