1// SPDX-License-Identifier: GPL-2.0 2/* 3 * Core of Xen paravirt_ops implementation. 4 * 5 * This file contains the xen_paravirt_ops structure itself, and the 6 * implementations for: 7 * - privileged instructions 8 * - interrupt flags 9 * - segment operations 10 * - booting and setup 11 * 12 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 13 */ 14 15#include <linux/cpu.h> 16#include <linux/kernel.h> 17#include <linux/init.h> 18#include <linux/smp.h> 19#include <linux/preempt.h> 20#include <linux/hardirq.h> 21#include <linux/percpu.h> 22#include <linux/delay.h> 23#include <linux/start_kernel.h> 24#include <linux/sched.h> 25#include <linux/kprobes.h> 26#include <linux/kstrtox.h> 27#include <linux/memblock.h> 28#include <linux/export.h> 29#include <linux/mm.h> 30#include <linux/page-flags.h> 31#include <linux/pci.h> 32#include <linux/gfp.h> 33#include <linux/edd.h> 34#include <linux/reboot.h> 35#include <linux/virtio_anchor.h> 36#include <linux/stackprotector.h> 37 38#include <xen/xen.h> 39#include <xen/events.h> 40#include <xen/interface/xen.h> 41#include <xen/interface/version.h> 42#include <xen/interface/physdev.h> 43#include <xen/interface/vcpu.h> 44#include <xen/interface/memory.h> 45#include <xen/interface/nmi.h> 46#include <xen/interface/xen-mca.h> 47#include <xen/features.h> 48#include <xen/page.h> 49#include <xen/hvc-console.h> 50#include <xen/acpi.h> 51 52#include <asm/paravirt.h> 53#include <asm/apic.h> 54#include <asm/page.h> 55#include <asm/xen/pci.h> 56#include <asm/xen/hypercall.h> 57#include <asm/xen/hypervisor.h> 58#include <asm/xen/cpuid.h> 59#include <asm/fixmap.h> 60#include <asm/processor.h> 61#include <asm/proto.h> 62#include <asm/msr-index.h> 63#include <asm/traps.h> 64#include <asm/setup.h> 65#include <asm/desc.h> 66#include <asm/pgalloc.h> 67#include <asm/tlbflush.h> 68#include <asm/reboot.h> 69#include <asm/hypervisor.h> 70#include <asm/mach_traps.h> 71#include <asm/mtrr.h> 72#include <asm/mwait.h> 73#include <asm/pci_x86.h> 74#include <asm/cpu.h> 75#ifdef CONFIG_X86_IOPL_IOPERM 76#include <asm/io_bitmap.h> 77#endif 78 79#ifdef CONFIG_ACPI 80#include <linux/acpi.h> 81#include <asm/acpi.h> 82#include <acpi/proc_cap_intel.h> 83#include <acpi/processor.h> 84#include <xen/interface/platform.h> 85#endif 86 87#include "xen-ops.h" 88#include "mmu.h" 89#include "smp.h" 90#include "multicalls.h" 91#include "pmu.h" 92 93#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */ 94 95void *xen_initial_gdt; 96 97static int xen_cpu_up_prepare_pv(unsigned int cpu); 98static int xen_cpu_dead_pv(unsigned int cpu); 99 100struct tls_descs { 101 struct desc_struct desc[3]; 102}; 103 104DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE; 105DEFINE_PER_CPU(unsigned int, xen_lazy_nesting); 106 107enum xen_lazy_mode xen_get_lazy_mode(void) 108{ 109 if (in_interrupt()) 110 return XEN_LAZY_NONE; 111 112 return this_cpu_read(xen_lazy_mode); 113} 114 115/* 116 * Updating the 3 TLS descriptors in the GDT on every task switch is 117 * surprisingly expensive so we avoid updating them if they haven't 118 * changed. Since Xen writes different descriptors than the one 119 * passed in the update_descriptor hypercall we keep shadow copies to 120 * compare against. 121 */ 122static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); 123 124static __read_mostly bool xen_msr_safe = IS_ENABLED(CONFIG_XEN_PV_MSR_SAFE); 125 126static int __init parse_xen_msr_safe(char *str) 127{ 128 if (str) 129 return kstrtobool(str, &xen_msr_safe); 130 return -EINVAL; 131} 132early_param("xen_msr_safe", parse_xen_msr_safe); 133 134/* Get MTRR settings from Xen and put them into mtrr_state. */ 135static void __init xen_set_mtrr_data(void) 136{ 137#ifdef CONFIG_MTRR 138 struct xen_platform_op op = { 139 .cmd = XENPF_read_memtype, 140 .interface_version = XENPF_INTERFACE_VERSION, 141 }; 142 unsigned int reg; 143 unsigned long mask; 144 uint32_t eax, width; 145 static struct mtrr_var_range var[MTRR_MAX_VAR_RANGES] __initdata; 146 147 /* Get physical address width (only 64-bit cpus supported). */ 148 width = 36; 149 eax = cpuid_eax(0x80000000); 150 if ((eax >> 16) == 0x8000 && eax >= 0x80000008) { 151 eax = cpuid_eax(0x80000008); 152 width = eax & 0xff; 153 } 154 155 for (reg = 0; reg < MTRR_MAX_VAR_RANGES; reg++) { 156 op.u.read_memtype.reg = reg; 157 if (HYPERVISOR_platform_op(&op)) 158 break; 159 160 /* 161 * Only called in dom0, which has all RAM PFNs mapped at 162 * RAM MFNs, and all PCI space etc. is identity mapped. 163 * This means we can treat MFN == PFN regarding MTRR settings. 164 */ 165 var[reg].base_lo = op.u.read_memtype.type; 166 var[reg].base_lo |= op.u.read_memtype.mfn << PAGE_SHIFT; 167 var[reg].base_hi = op.u.read_memtype.mfn >> (32 - PAGE_SHIFT); 168 mask = ~((op.u.read_memtype.nr_mfns << PAGE_SHIFT) - 1); 169 mask &= (1UL << width) - 1; 170 if (mask) 171 mask |= MTRR_PHYSMASK_V; 172 var[reg].mask_lo = mask; 173 var[reg].mask_hi = mask >> 32; 174 } 175 176 /* Only overwrite MTRR state if any MTRR could be got from Xen. */ 177 if (reg) 178 mtrr_overwrite_state(var, reg, MTRR_TYPE_UNCACHABLE); 179#endif 180} 181 182static void __init xen_pv_init_platform(void) 183{ 184 /* PV guests can't operate virtio devices without grants. */ 185 if (IS_ENABLED(CONFIG_XEN_VIRTIO)) 186 virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc); 187 188 populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); 189 190 set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); 191 HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); 192 193 /* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */ 194 xen_vcpu_info_reset(0); 195 196 /* pvclock is in shared info area */ 197 xen_init_time_ops(); 198 199 if (xen_initial_domain()) 200 xen_set_mtrr_data(); 201 else 202 mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); 203} 204 205static void __init xen_pv_guest_late_init(void) 206{ 207#ifndef CONFIG_SMP 208 /* Setup shared vcpu info for non-smp configurations */ 209 xen_setup_vcpu_info_placement(); 210#endif 211} 212 213static __read_mostly unsigned int cpuid_leaf5_ecx_val; 214static __read_mostly unsigned int cpuid_leaf5_edx_val; 215 216static void xen_cpuid(unsigned int *ax, unsigned int *bx, 217 unsigned int *cx, unsigned int *dx) 218{ 219 unsigned maskebx = ~0; 220 221 /* 222 * Mask out inconvenient features, to try and disable as many 223 * unsupported kernel subsystems as possible. 224 */ 225 switch (*ax) { 226 case CPUID_MWAIT_LEAF: 227 /* Synthesize the values.. */ 228 *ax = 0; 229 *bx = 0; 230 *cx = cpuid_leaf5_ecx_val; 231 *dx = cpuid_leaf5_edx_val; 232 return; 233 234 case 0xb: 235 /* Suppress extended topology stuff */ 236 maskebx = 0; 237 break; 238 } 239 240 asm(XEN_EMULATE_PREFIX "cpuid" 241 : "=a" (*ax), 242 "=b" (*bx), 243 "=c" (*cx), 244 "=d" (*dx) 245 : "0" (*ax), "2" (*cx)); 246 247 *bx &= maskebx; 248} 249 250static bool __init xen_check_mwait(void) 251{ 252#ifdef CONFIG_ACPI 253 struct xen_platform_op op = { 254 .cmd = XENPF_set_processor_pminfo, 255 .u.set_pminfo.id = -1, 256 .u.set_pminfo.type = XEN_PM_PDC, 257 }; 258 uint32_t buf[3]; 259 unsigned int ax, bx, cx, dx; 260 unsigned int mwait_mask; 261 262 /* We need to determine whether it is OK to expose the MWAIT 263 * capability to the kernel to harvest deeper than C3 states from ACPI 264 * _CST using the processor_harvest_xen.c module. For this to work, we 265 * need to gather the MWAIT_LEAF values (which the cstate.c code 266 * checks against). The hypervisor won't expose the MWAIT flag because 267 * it would break backwards compatibility; so we will find out directly 268 * from the hardware and hypercall. 269 */ 270 if (!xen_initial_domain()) 271 return false; 272 273 /* 274 * When running under platform earlier than Xen4.2, do not expose 275 * mwait, to avoid the risk of loading native acpi pad driver 276 */ 277 if (!xen_running_on_version_or_later(4, 2)) 278 return false; 279 280 ax = 1; 281 cx = 0; 282 283 native_cpuid(&ax, &bx, &cx, &dx); 284 285 mwait_mask = (1 << (X86_FEATURE_EST % 32)) | 286 (1 << (X86_FEATURE_MWAIT % 32)); 287 288 if ((cx & mwait_mask) != mwait_mask) 289 return false; 290 291 /* We need to emulate the MWAIT_LEAF and for that we need both 292 * ecx and edx. The hypercall provides only partial information. 293 */ 294 295 ax = CPUID_MWAIT_LEAF; 296 bx = 0; 297 cx = 0; 298 dx = 0; 299 300 native_cpuid(&ax, &bx, &cx, &dx); 301 302 /* Ask the Hypervisor whether to clear ACPI_PROC_CAP_C_C2C3_FFH. If so, 303 * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3. 304 */ 305 buf[0] = ACPI_PDC_REVISION_ID; 306 buf[1] = 1; 307 buf[2] = (ACPI_PROC_CAP_C_CAPABILITY_SMP | ACPI_PROC_CAP_EST_CAPABILITY_SWSMP); 308 309 set_xen_guest_handle(op.u.set_pminfo.pdc, buf); 310 311 if ((HYPERVISOR_platform_op(&op) == 0) && 312 (buf[2] & (ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH))) { 313 cpuid_leaf5_ecx_val = cx; 314 cpuid_leaf5_edx_val = dx; 315 } 316 return true; 317#else 318 return false; 319#endif 320} 321 322static bool __init xen_check_xsave(void) 323{ 324 unsigned int cx, xsave_mask; 325 326 cx = cpuid_ecx(1); 327 328 xsave_mask = (1 << (X86_FEATURE_XSAVE % 32)) | 329 (1 << (X86_FEATURE_OSXSAVE % 32)); 330 331 /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ 332 return (cx & xsave_mask) == xsave_mask; 333} 334 335static void __init xen_init_capabilities(void) 336{ 337 setup_force_cpu_cap(X86_FEATURE_XENPV); 338 setup_clear_cpu_cap(X86_FEATURE_DCA); 339 setup_clear_cpu_cap(X86_FEATURE_APERFMPERF); 340 setup_clear_cpu_cap(X86_FEATURE_MTRR); 341 setup_clear_cpu_cap(X86_FEATURE_ACC); 342 setup_clear_cpu_cap(X86_FEATURE_X2APIC); 343 setup_clear_cpu_cap(X86_FEATURE_SME); 344 setup_clear_cpu_cap(X86_FEATURE_LKGS); 345 346 /* 347 * Xen PV would need some work to support PCID: CR3 handling as well 348 * as xen_flush_tlb_others() would need updating. 349 */ 350 setup_clear_cpu_cap(X86_FEATURE_PCID); 351 352 if (!xen_initial_domain()) 353 setup_clear_cpu_cap(X86_FEATURE_ACPI); 354 355 if (xen_check_mwait()) 356 setup_force_cpu_cap(X86_FEATURE_MWAIT); 357 else 358 setup_clear_cpu_cap(X86_FEATURE_MWAIT); 359 360 if (!xen_check_xsave()) { 361 setup_clear_cpu_cap(X86_FEATURE_XSAVE); 362 setup_clear_cpu_cap(X86_FEATURE_OSXSAVE); 363 } 364} 365 366static noinstr void xen_set_debugreg(int reg, unsigned long val) 367{ 368 HYPERVISOR_set_debugreg(reg, val); 369} 370 371static noinstr unsigned long xen_get_debugreg(int reg) 372{ 373 return HYPERVISOR_get_debugreg(reg); 374} 375 376static void xen_start_context_switch(struct task_struct *prev) 377{ 378 BUG_ON(preemptible()); 379 380 if (this_cpu_read(xen_lazy_mode) == XEN_LAZY_MMU) { 381 arch_leave_lazy_mmu_mode(); 382 set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES); 383 } 384 enter_lazy(XEN_LAZY_CPU); 385} 386 387static void xen_end_context_switch(struct task_struct *next) 388{ 389 BUG_ON(preemptible()); 390 391 xen_mc_flush(); 392 leave_lazy(XEN_LAZY_CPU); 393 if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES)) 394 arch_enter_lazy_mmu_mode(); 395} 396 397static unsigned long xen_store_tr(void) 398{ 399 return 0; 400} 401 402/* 403 * Set the page permissions for a particular virtual address. If the 404 * address is a vmalloc mapping (or other non-linear mapping), then 405 * find the linear mapping of the page and also set its protections to 406 * match. 407 */ 408static void set_aliased_prot(void *v, pgprot_t prot) 409{ 410 int level; 411 pte_t *ptep; 412 pte_t pte; 413 unsigned long pfn; 414 unsigned char dummy; 415 void *va; 416 417 ptep = lookup_address((unsigned long)v, &level); 418 BUG_ON(ptep == NULL); 419 420 pfn = pte_pfn(*ptep); 421 pte = pfn_pte(pfn, prot); 422 423 /* 424 * Careful: update_va_mapping() will fail if the virtual address 425 * we're poking isn't populated in the page tables. We don't 426 * need to worry about the direct map (that's always in the page 427 * tables), but we need to be careful about vmap space. In 428 * particular, the top level page table can lazily propagate 429 * entries between processes, so if we've switched mms since we 430 * vmapped the target in the first place, we might not have the 431 * top-level page table entry populated. 432 * 433 * We disable preemption because we want the same mm active when 434 * we probe the target and when we issue the hypercall. We'll 435 * have the same nominal mm, but if we're a kernel thread, lazy 436 * mm dropping could change our pgd. 437 * 438 * Out of an abundance of caution, this uses __get_user() to fault 439 * in the target address just in case there's some obscure case 440 * in which the target address isn't readable. 441 */ 442 443 preempt_disable(); 444 445 copy_from_kernel_nofault(&dummy, v, 1); 446 447 if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) 448 BUG(); 449 450 va = __va(PFN_PHYS(pfn)); 451 452 if (va != v && HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0)) 453 BUG(); 454 455 preempt_enable(); 456} 457 458static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries) 459{ 460 const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; 461 int i; 462 463 /* 464 * We need to mark the all aliases of the LDT pages RO. We 465 * don't need to call vm_flush_aliases(), though, since that's 466 * only responsible for flushing aliases out the TLBs, not the 467 * page tables, and Xen will flush the TLB for us if needed. 468 * 469 * To avoid confusing future readers: none of this is necessary 470 * to load the LDT. The hypervisor only checks this when the 471 * LDT is faulted in due to subsequent descriptor access. 472 */ 473 474 for (i = 0; i < entries; i += entries_per_page) 475 set_aliased_prot(ldt + i, PAGE_KERNEL_RO); 476} 477 478static void xen_free_ldt(struct desc_struct *ldt, unsigned entries) 479{ 480 const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE; 481 int i; 482 483 for (i = 0; i < entries; i += entries_per_page) 484 set_aliased_prot(ldt + i, PAGE_KERNEL); 485} 486 487static void xen_set_ldt(const void *addr, unsigned entries) 488{ 489 struct mmuext_op *op; 490 struct multicall_space mcs = xen_mc_entry(sizeof(*op)); 491 492 trace_xen_cpu_set_ldt(addr, entries); 493 494 op = mcs.args; 495 op->cmd = MMUEXT_SET_LDT; 496 op->arg1.linear_addr = (unsigned long)addr; 497 op->arg2.nr_ents = entries; 498 499 MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); 500 501 xen_mc_issue(XEN_LAZY_CPU); 502} 503 504static void xen_load_gdt(const struct desc_ptr *dtr) 505{ 506 unsigned long va = dtr->address; 507 unsigned int size = dtr->size + 1; 508 unsigned long pfn, mfn; 509 int level; 510 pte_t *ptep; 511 void *virt; 512 513 /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */ 514 BUG_ON(size > PAGE_SIZE); 515 BUG_ON(va & ~PAGE_MASK); 516 517 /* 518 * The GDT is per-cpu and is in the percpu data area. 519 * That can be virtually mapped, so we need to do a 520 * page-walk to get the underlying MFN for the 521 * hypercall. The page can also be in the kernel's 522 * linear range, so we need to RO that mapping too. 523 */ 524 ptep = lookup_address(va, &level); 525 BUG_ON(ptep == NULL); 526 527 pfn = pte_pfn(*ptep); 528 mfn = pfn_to_mfn(pfn); 529 virt = __va(PFN_PHYS(pfn)); 530 531 make_lowmem_page_readonly((void *)va); 532 make_lowmem_page_readonly(virt); 533 534 if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct))) 535 BUG(); 536} 537 538/* 539 * load_gdt for early boot, when the gdt is only mapped once 540 */ 541static void __init xen_load_gdt_boot(const struct desc_ptr *dtr) 542{ 543 unsigned long va = dtr->address; 544 unsigned int size = dtr->size + 1; 545 unsigned long pfn, mfn; 546 pte_t pte; 547 548 /* @size should be at most GDT_SIZE which is smaller than PAGE_SIZE. */ 549 BUG_ON(size > PAGE_SIZE); 550 BUG_ON(va & ~PAGE_MASK); 551 552 pfn = virt_to_pfn((void *)va); 553 mfn = pfn_to_mfn(pfn); 554 555 pte = pfn_pte(pfn, PAGE_KERNEL_RO); 556 557 if (HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0)) 558 BUG(); 559 560 if (HYPERVISOR_set_gdt(&mfn, size / sizeof(struct desc_struct))) 561 BUG(); 562} 563 564static inline bool desc_equal(const struct desc_struct *d1, 565 const struct desc_struct *d2) 566{ 567 return !memcmp(d1, d2, sizeof(*d1)); 568} 569 570static void load_TLS_descriptor(struct thread_struct *t, 571 unsigned int cpu, unsigned int i) 572{ 573 struct desc_struct *shadow = &per_cpu(shadow_tls_desc, cpu).desc[i]; 574 struct desc_struct *gdt; 575 xmaddr_t maddr; 576 struct multicall_space mc; 577 578 if (desc_equal(shadow, &t->tls_array[i])) 579 return; 580 581 *shadow = t->tls_array[i]; 582 583 gdt = get_cpu_gdt_rw(cpu); 584 maddr = arbitrary_virt_to_machine(&gdt[GDT_ENTRY_TLS_MIN+i]); 585 mc = __xen_mc_entry(0); 586 587 MULTI_update_descriptor(mc.mc, maddr.maddr, t->tls_array[i]); 588} 589 590static void xen_load_tls(struct thread_struct *t, unsigned int cpu) 591{ 592 /* 593 * In lazy mode we need to zero %fs, otherwise we may get an 594 * exception between the new %fs descriptor being loaded and 595 * %fs being effectively cleared at __switch_to(). 596 */ 597 if (xen_get_lazy_mode() == XEN_LAZY_CPU) 598 loadsegment(fs, 0); 599 600 xen_mc_batch(); 601 602 load_TLS_descriptor(t, cpu, 0); 603 load_TLS_descriptor(t, cpu, 1); 604 load_TLS_descriptor(t, cpu, 2); 605 606 xen_mc_issue(XEN_LAZY_CPU); 607} 608 609static void xen_load_gs_index(unsigned int idx) 610{ 611 if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx)) 612 BUG(); 613} 614 615static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, 616 const void *ptr) 617{ 618 xmaddr_t mach_lp = arbitrary_virt_to_machine(&dt[entrynum]); 619 u64 entry = *(u64 *)ptr; 620 621 trace_xen_cpu_write_ldt_entry(dt, entrynum, entry); 622 623 preempt_disable(); 624 625 xen_mc_flush(); 626 if (HYPERVISOR_update_descriptor(mach_lp.maddr, entry)) 627 BUG(); 628 629 preempt_enable(); 630} 631 632void noist_exc_debug(struct pt_regs *regs); 633 634DEFINE_IDTENTRY_RAW(xenpv_exc_nmi) 635{ 636 /* On Xen PV, NMI doesn't use IST. The C part is the same as native. */ 637 exc_nmi(regs); 638} 639 640DEFINE_IDTENTRY_RAW_ERRORCODE(xenpv_exc_double_fault) 641{ 642 /* On Xen PV, DF doesn't use IST. The C part is the same as native. */ 643 exc_double_fault(regs, error_code); 644} 645 646DEFINE_IDTENTRY_RAW(xenpv_exc_debug) 647{ 648 /* 649 * There's no IST on Xen PV, but we still need to dispatch 650 * to the correct handler. 651 */ 652 if (user_mode(regs)) 653 noist_exc_debug(regs); 654 else 655 exc_debug(regs); 656} 657 658DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap) 659{ 660 /* This should never happen and there is no way to handle it. */ 661 instrumentation_begin(); 662 pr_err("Unknown trap in Xen PV mode."); 663 BUG(); 664 instrumentation_end(); 665} 666 667#ifdef CONFIG_X86_MCE 668DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check) 669{ 670 /* 671 * There's no IST on Xen PV, but we still need to dispatch 672 * to the correct handler. 673 */ 674 if (user_mode(regs)) 675 noist_exc_machine_check(regs); 676 else 677 exc_machine_check(regs); 678} 679#endif 680 681struct trap_array_entry { 682 void (*orig)(void); 683 void (*xen)(void); 684 bool ist_okay; 685}; 686 687#define TRAP_ENTRY(func, ist_ok) { \ 688 .orig = asm_##func, \ 689 .xen = xen_asm_##func, \ 690 .ist_okay = ist_ok } 691 692#define TRAP_ENTRY_REDIR(func, ist_ok) { \ 693 .orig = asm_##func, \ 694 .xen = xen_asm_xenpv_##func, \ 695 .ist_okay = ist_ok } 696 697static struct trap_array_entry trap_array[] = { 698 TRAP_ENTRY_REDIR(exc_debug, true ), 699 TRAP_ENTRY_REDIR(exc_double_fault, true ), 700#ifdef CONFIG_X86_MCE 701 TRAP_ENTRY_REDIR(exc_machine_check, true ), 702#endif 703 TRAP_ENTRY_REDIR(exc_nmi, true ), 704 TRAP_ENTRY(exc_int3, false ), 705 TRAP_ENTRY(exc_overflow, false ), 706#ifdef CONFIG_IA32_EMULATION 707 TRAP_ENTRY(int80_emulation, false ), 708#endif 709 TRAP_ENTRY(exc_page_fault, false ), 710 TRAP_ENTRY(exc_divide_error, false ), 711 TRAP_ENTRY(exc_bounds, false ), 712 TRAP_ENTRY(exc_invalid_op, false ), 713 TRAP_ENTRY(exc_device_not_available, false ), 714 TRAP_ENTRY(exc_coproc_segment_overrun, false ), 715 TRAP_ENTRY(exc_invalid_tss, false ), 716 TRAP_ENTRY(exc_segment_not_present, false ), 717 TRAP_ENTRY(exc_stack_segment, false ), 718 TRAP_ENTRY(exc_general_protection, false ), 719 TRAP_ENTRY(exc_spurious_interrupt_bug, false ), 720 TRAP_ENTRY(exc_coprocessor_error, false ), 721 TRAP_ENTRY(exc_alignment_check, false ), 722 TRAP_ENTRY(exc_simd_coprocessor_error, false ), 723#ifdef CONFIG_X86_CET 724 TRAP_ENTRY(exc_control_protection, false ), 725#endif 726}; 727 728static bool __ref get_trap_addr(void **addr, unsigned int ist) 729{ 730 unsigned int nr; 731 bool ist_okay = false; 732 bool found = false; 733 734 /* 735 * Replace trap handler addresses by Xen specific ones. 736 * Check for known traps using IST and whitelist them. 737 * The debugger ones are the only ones we care about. 738 * Xen will handle faults like double_fault, so we should never see 739 * them. Warn if there's an unexpected IST-using fault handler. 740 */ 741 for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) { 742 struct trap_array_entry *entry = trap_array + nr; 743 744 if (*addr == entry->orig) { 745 *addr = entry->xen; 746 ist_okay = entry->ist_okay; 747 found = true; 748 break; 749 } 750 } 751 752 if (nr == ARRAY_SIZE(trap_array) && 753 *addr >= (void *)early_idt_handler_array[0] && 754 *addr < (void *)early_idt_handler_array[NUM_EXCEPTION_VECTORS]) { 755 nr = (*addr - (void *)early_idt_handler_array[0]) / 756 EARLY_IDT_HANDLER_SIZE; 757 *addr = (void *)xen_early_idt_handler_array[nr]; 758 found = true; 759 } 760 761 if (!found) 762 *addr = (void *)xen_asm_exc_xen_unknown_trap; 763 764 if (WARN_ON(found && ist != 0 && !ist_okay)) 765 return false; 766 767 return true; 768} 769 770static int cvt_gate_to_trap(int vector, const gate_desc *val, 771 struct trap_info *info) 772{ 773 unsigned long addr; 774 775 if (val->bits.type != GATE_TRAP && val->bits.type != GATE_INTERRUPT) 776 return 0; 777 778 info->vector = vector; 779 780 addr = gate_offset(val); 781 if (!get_trap_addr((void **)&addr, val->bits.ist)) 782 return 0; 783 info->address = addr; 784 785 info->cs = gate_segment(val); 786 info->flags = val->bits.dpl; 787 /* interrupt gates clear IF */ 788 if (val->bits.type == GATE_INTERRUPT) 789 info->flags |= 1 << 2; 790 791 return 1; 792} 793 794/* Locations of each CPU's IDT */ 795static DEFINE_PER_CPU(struct desc_ptr, idt_desc); 796 797/* Set an IDT entry. If the entry is part of the current IDT, then 798 also update Xen. */ 799static void xen_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) 800{ 801 unsigned long p = (unsigned long)&dt[entrynum]; 802 unsigned long start, end; 803 804 trace_xen_cpu_write_idt_entry(dt, entrynum, g); 805 806 preempt_disable(); 807 808 start = __this_cpu_read(idt_desc.address); 809 end = start + __this_cpu_read(idt_desc.size) + 1; 810 811 xen_mc_flush(); 812 813 native_write_idt_entry(dt, entrynum, g); 814 815 if (p >= start && (p + 8) <= end) { 816 struct trap_info info[2]; 817 818 info[1].address = 0; 819 820 if (cvt_gate_to_trap(entrynum, g, &info[0])) 821 if (HYPERVISOR_set_trap_table(info)) 822 BUG(); 823 } 824 825 preempt_enable(); 826} 827 828static unsigned xen_convert_trap_info(const struct desc_ptr *desc, 829 struct trap_info *traps, bool full) 830{ 831 unsigned in, out, count; 832 833 count = (desc->size+1) / sizeof(gate_desc); 834 BUG_ON(count > 256); 835 836 for (in = out = 0; in < count; in++) { 837 gate_desc *entry = (gate_desc *)(desc->address) + in; 838 839 if (cvt_gate_to_trap(in, entry, &traps[out]) || full) 840 out++; 841 } 842 843 return out; 844} 845 846void xen_copy_trap_info(struct trap_info *traps) 847{ 848 const struct desc_ptr *desc = this_cpu_ptr(&idt_desc); 849 850 xen_convert_trap_info(desc, traps, true); 851} 852 853/* Load a new IDT into Xen. In principle this can be per-CPU, so we 854 hold a spinlock to protect the static traps[] array (static because 855 it avoids allocation, and saves stack space). */ 856static void xen_load_idt(const struct desc_ptr *desc) 857{ 858 static DEFINE_SPINLOCK(lock); 859 static struct trap_info traps[257]; 860 static const struct trap_info zero = { }; 861 unsigned out; 862 863 trace_xen_cpu_load_idt(desc); 864 865 spin_lock(&lock); 866 867 memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); 868 869 out = xen_convert_trap_info(desc, traps, false); 870 traps[out] = zero; 871 872 xen_mc_flush(); 873 if (HYPERVISOR_set_trap_table(traps)) 874 BUG(); 875 876 spin_unlock(&lock); 877} 878 879/* Write a GDT descriptor entry. Ignore LDT descriptors, since 880 they're handled differently. */ 881static void xen_write_gdt_entry(struct desc_struct *dt, int entry, 882 const void *desc, int type) 883{ 884 trace_xen_cpu_write_gdt_entry(dt, entry, desc, type); 885 886 preempt_disable(); 887 888 switch (type) { 889 case DESC_LDT: 890 case DESC_TSS: 891 /* ignore */ 892 break; 893 894 default: { 895 xmaddr_t maddr = arbitrary_virt_to_machine(&dt[entry]); 896 897 xen_mc_flush(); 898 if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc)) 899 BUG(); 900 } 901 902 } 903 904 preempt_enable(); 905} 906 907/* 908 * Version of write_gdt_entry for use at early boot-time needed to 909 * update an entry as simply as possible. 910 */ 911static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry, 912 const void *desc, int type) 913{ 914 trace_xen_cpu_write_gdt_entry(dt, entry, desc, type); 915 916 switch (type) { 917 case DESC_LDT: 918 case DESC_TSS: 919 /* ignore */ 920 break; 921 922 default: { 923 xmaddr_t maddr = virt_to_machine(&dt[entry]); 924 925 if (HYPERVISOR_update_descriptor(maddr.maddr, *(u64 *)desc)) 926 dt[entry] = *(struct desc_struct *)desc; 927 } 928 929 } 930} 931 932static void xen_load_sp0(unsigned long sp0) 933{ 934 struct multicall_space mcs; 935 936 mcs = xen_mc_entry(0); 937 MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); 938 xen_mc_issue(XEN_LAZY_CPU); 939 this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); 940} 941 942#ifdef CONFIG_X86_IOPL_IOPERM 943static void xen_invalidate_io_bitmap(void) 944{ 945 struct physdev_set_iobitmap iobitmap = { 946 .bitmap = NULL, 947 .nr_ports = 0, 948 }; 949 950 native_tss_invalidate_io_bitmap(); 951 HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); 952} 953 954static void xen_update_io_bitmap(void) 955{ 956 struct physdev_set_iobitmap iobitmap; 957 struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); 958 959 native_tss_update_io_bitmap(); 960 961 iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) + 962 tss->x86_tss.io_bitmap_base; 963 if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID) 964 iobitmap.nr_ports = 0; 965 else 966 iobitmap.nr_ports = IO_BITMAP_BITS; 967 968 HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); 969} 970#endif 971 972static void xen_io_delay(void) 973{ 974} 975 976static DEFINE_PER_CPU(unsigned long, xen_cr0_value); 977 978static unsigned long xen_read_cr0(void) 979{ 980 unsigned long cr0 = this_cpu_read(xen_cr0_value); 981 982 if (unlikely(cr0 == 0)) { 983 cr0 = native_read_cr0(); 984 this_cpu_write(xen_cr0_value, cr0); 985 } 986 987 return cr0; 988} 989 990static void xen_write_cr0(unsigned long cr0) 991{ 992 struct multicall_space mcs; 993 994 this_cpu_write(xen_cr0_value, cr0); 995 996 /* Only pay attention to cr0.TS; everything else is 997 ignored. */ 998 mcs = xen_mc_entry(0); 999 1000 MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0); 1001 1002 xen_mc_issue(XEN_LAZY_CPU); 1003} 1004 1005static void xen_write_cr4(unsigned long cr4) 1006{ 1007 cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE); 1008 1009 native_write_cr4(cr4); 1010} 1011 1012static u64 xen_do_read_msr(unsigned int msr, int *err) 1013{ 1014 u64 val = 0; /* Avoid uninitialized value for safe variant. */ 1015 1016 if (pmu_msr_read(msr, &val, err)) 1017 return val; 1018 1019 if (err) 1020 val = native_read_msr_safe(msr, err); 1021 else 1022 val = native_read_msr(msr); 1023 1024 switch (msr) { 1025 case MSR_IA32_APICBASE: 1026 val &= ~X2APIC_ENABLE; 1027 break; 1028 } 1029 return val; 1030} 1031 1032static void set_seg(unsigned int which, unsigned int low, unsigned int high, 1033 int *err) 1034{ 1035 u64 base = ((u64)high << 32) | low; 1036 1037 if (HYPERVISOR_set_segment_base(which, base) == 0) 1038 return; 1039 1040 if (err) 1041 *err = -EIO; 1042 else 1043 WARN(1, "Xen set_segment_base(%u, %llx) failed\n", which, base); 1044} 1045 1046/* 1047 * Support write_msr_safe() and write_msr() semantics. 1048 * With err == NULL write_msr() semantics are selected. 1049 * Supplying an err pointer requires err to be pre-initialized with 0. 1050 */ 1051static void xen_do_write_msr(unsigned int msr, unsigned int low, 1052 unsigned int high, int *err) 1053{ 1054 switch (msr) { 1055 case MSR_FS_BASE: 1056 set_seg(SEGBASE_FS, low, high, err); 1057 break; 1058 1059 case MSR_KERNEL_GS_BASE: 1060 set_seg(SEGBASE_GS_USER, low, high, err); 1061 break; 1062 1063 case MSR_GS_BASE: 1064 set_seg(SEGBASE_GS_KERNEL, low, high, err); 1065 break; 1066 1067 case MSR_STAR: 1068 case MSR_CSTAR: 1069 case MSR_LSTAR: 1070 case MSR_SYSCALL_MASK: 1071 case MSR_IA32_SYSENTER_CS: 1072 case MSR_IA32_SYSENTER_ESP: 1073 case MSR_IA32_SYSENTER_EIP: 1074 /* Fast syscall setup is all done in hypercalls, so 1075 these are all ignored. Stub them out here to stop 1076 Xen console noise. */ 1077 break; 1078 1079 default: 1080 if (!pmu_msr_write(msr, low, high, err)) { 1081 if (err) 1082 *err = native_write_msr_safe(msr, low, high); 1083 else 1084 native_write_msr(msr, low, high); 1085 } 1086 } 1087} 1088 1089static u64 xen_read_msr_safe(unsigned int msr, int *err) 1090{ 1091 return xen_do_read_msr(msr, err); 1092} 1093 1094static int xen_write_msr_safe(unsigned int msr, unsigned int low, 1095 unsigned int high) 1096{ 1097 int err = 0; 1098 1099 xen_do_write_msr(msr, low, high, &err); 1100 1101 return err; 1102} 1103 1104static u64 xen_read_msr(unsigned int msr) 1105{ 1106 int err; 1107 1108 return xen_do_read_msr(msr, xen_msr_safe ? &err : NULL); 1109} 1110 1111static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) 1112{ 1113 int err; 1114 1115 xen_do_write_msr(msr, low, high, xen_msr_safe ? &err : NULL); 1116} 1117 1118/* This is called once we have the cpu_possible_mask */ 1119void __init xen_setup_vcpu_info_placement(void) 1120{ 1121 int cpu; 1122 1123 for_each_possible_cpu(cpu) { 1124 /* Set up direct vCPU id mapping for PV guests. */ 1125 per_cpu(xen_vcpu_id, cpu) = cpu; 1126 xen_vcpu_setup(cpu); 1127 } 1128 1129 pv_ops.irq.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); 1130 pv_ops.irq.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); 1131 pv_ops.irq.irq_enable = __PV_IS_CALLEE_SAVE(xen_irq_enable_direct); 1132 pv_ops.mmu.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2_direct); 1133} 1134 1135static const struct pv_info xen_info __initconst = { 1136 .extra_user_64bit_cs = FLAT_USER_CS64, 1137 .name = "Xen", 1138}; 1139 1140static const typeof(pv_ops) xen_cpu_ops __initconst = { 1141 .cpu = { 1142 .cpuid = xen_cpuid, 1143 1144 .set_debugreg = xen_set_debugreg, 1145 .get_debugreg = xen_get_debugreg, 1146 1147 .read_cr0 = xen_read_cr0, 1148 .write_cr0 = xen_write_cr0, 1149 1150 .write_cr4 = xen_write_cr4, 1151 1152 .wbinvd = pv_native_wbinvd, 1153 1154 .read_msr = xen_read_msr, 1155 .write_msr = xen_write_msr, 1156 1157 .read_msr_safe = xen_read_msr_safe, 1158 .write_msr_safe = xen_write_msr_safe, 1159 1160 .read_pmc = xen_read_pmc, 1161 1162 .load_tr_desc = paravirt_nop, 1163 .set_ldt = xen_set_ldt, 1164 .load_gdt = xen_load_gdt, 1165 .load_idt = xen_load_idt, 1166 .load_tls = xen_load_tls, 1167 .load_gs_index = xen_load_gs_index, 1168 1169 .alloc_ldt = xen_alloc_ldt, 1170 .free_ldt = xen_free_ldt, 1171 1172 .store_tr = xen_store_tr, 1173 1174 .write_ldt_entry = xen_write_ldt_entry, 1175 .write_gdt_entry = xen_write_gdt_entry, 1176 .write_idt_entry = xen_write_idt_entry, 1177 .load_sp0 = xen_load_sp0, 1178 1179#ifdef CONFIG_X86_IOPL_IOPERM 1180 .invalidate_io_bitmap = xen_invalidate_io_bitmap, 1181 .update_io_bitmap = xen_update_io_bitmap, 1182#endif 1183 .io_delay = xen_io_delay, 1184 1185 .start_context_switch = xen_start_context_switch, 1186 .end_context_switch = xen_end_context_switch, 1187 }, 1188}; 1189 1190static void xen_restart(char *msg) 1191{ 1192 xen_reboot(SHUTDOWN_reboot); 1193} 1194 1195static void xen_machine_halt(void) 1196{ 1197 xen_reboot(SHUTDOWN_poweroff); 1198} 1199 1200static void xen_machine_power_off(void) 1201{ 1202 do_kernel_power_off(); 1203 xen_reboot(SHUTDOWN_poweroff); 1204} 1205 1206static void xen_crash_shutdown(struct pt_regs *regs) 1207{ 1208 xen_reboot(SHUTDOWN_crash); 1209} 1210 1211static const struct machine_ops xen_machine_ops __initconst = { 1212 .restart = xen_restart, 1213 .halt = xen_machine_halt, 1214 .power_off = xen_machine_power_off, 1215 .shutdown = xen_machine_halt, 1216 .crash_shutdown = xen_crash_shutdown, 1217 .emergency_restart = xen_emergency_restart, 1218}; 1219 1220static unsigned char xen_get_nmi_reason(void) 1221{ 1222 unsigned char reason = 0; 1223 1224 /* Construct a value which looks like it came from port 0x61. */ 1225 if (test_bit(_XEN_NMIREASON_io_error, 1226 &HYPERVISOR_shared_info->arch.nmi_reason)) 1227 reason |= NMI_REASON_IOCHK; 1228 if (test_bit(_XEN_NMIREASON_pci_serr, 1229 &HYPERVISOR_shared_info->arch.nmi_reason)) 1230 reason |= NMI_REASON_SERR; 1231 1232 return reason; 1233} 1234 1235static void __init xen_boot_params_init_edd(void) 1236{ 1237#if IS_ENABLED(CONFIG_EDD) 1238 struct xen_platform_op op; 1239 struct edd_info *edd_info; 1240 u32 *mbr_signature; 1241 unsigned nr; 1242 int ret; 1243 1244 edd_info = boot_params.eddbuf; 1245 mbr_signature = boot_params.edd_mbr_sig_buffer; 1246 1247 op.cmd = XENPF_firmware_info; 1248 1249 op.u.firmware_info.type = XEN_FW_DISK_INFO; 1250 for (nr = 0; nr < EDDMAXNR; nr++) { 1251 struct edd_info *info = edd_info + nr; 1252 1253 op.u.firmware_info.index = nr; 1254 info->params.length = sizeof(info->params); 1255 set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, 1256 &info->params); 1257 ret = HYPERVISOR_platform_op(&op); 1258 if (ret) 1259 break; 1260 1261#define C(x) info->x = op.u.firmware_info.u.disk_info.x 1262 C(device); 1263 C(version); 1264 C(interface_support); 1265 C(legacy_max_cylinder); 1266 C(legacy_max_head); 1267 C(legacy_sectors_per_track); 1268#undef C 1269 } 1270 boot_params.eddbuf_entries = nr; 1271 1272 op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; 1273 for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { 1274 op.u.firmware_info.index = nr; 1275 ret = HYPERVISOR_platform_op(&op); 1276 if (ret) 1277 break; 1278 mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; 1279 } 1280 boot_params.edd_mbr_sig_buf_entries = nr; 1281#endif 1282} 1283 1284/* 1285 * Set up the GDT and segment registers for -fstack-protector. Until 1286 * we do this, we have to be careful not to call any stack-protected 1287 * function, which is most of the kernel. 1288 */ 1289static void __init xen_setup_gdt(int cpu) 1290{ 1291 pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot; 1292 pv_ops.cpu.load_gdt = xen_load_gdt_boot; 1293 1294 switch_gdt_and_percpu_base(cpu); 1295 1296 pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry; 1297 pv_ops.cpu.load_gdt = xen_load_gdt; 1298} 1299 1300static void __init xen_dom0_set_legacy_features(void) 1301{ 1302 x86_platform.legacy.rtc = 1; 1303} 1304 1305static void __init xen_domu_set_legacy_features(void) 1306{ 1307 x86_platform.legacy.rtc = 0; 1308} 1309 1310extern void early_xen_iret_patch(void); 1311 1312/* First C function to be called on Xen boot */ 1313asmlinkage __visible void __init xen_start_kernel(struct start_info *si) 1314{ 1315 struct physdev_set_iopl set_iopl; 1316 unsigned long initrd_start = 0; 1317 int rc; 1318 1319 if (!si) 1320 return; 1321 1322 clear_bss(); 1323 1324 xen_start_info = si; 1325 1326 __text_gen_insn(&early_xen_iret_patch, 1327 JMP32_INSN_OPCODE, &early_xen_iret_patch, &xen_iret, 1328 JMP32_INSN_SIZE); 1329 1330 xen_domain_type = XEN_PV_DOMAIN; 1331 xen_start_flags = xen_start_info->flags; 1332 1333 xen_setup_features(); 1334 1335 /* Install Xen paravirt ops */ 1336 pv_info = xen_info; 1337 pv_ops.cpu = xen_cpu_ops.cpu; 1338 xen_init_irq_ops(); 1339 1340 /* 1341 * Setup xen_vcpu early because it is needed for 1342 * local_irq_disable(), irqs_disabled(), e.g. in printk(). 1343 * 1344 * Don't do the full vcpu_info placement stuff until we have 1345 * the cpu_possible_mask and a non-dummy shared_info. 1346 */ 1347 xen_vcpu_info_reset(0); 1348 1349 x86_platform.get_nmi_reason = xen_get_nmi_reason; 1350 x86_platform.realmode_reserve = x86_init_noop; 1351 x86_platform.realmode_init = x86_init_noop; 1352 1353 x86_init.resources.memory_setup = xen_memory_setup; 1354 x86_init.irqs.intr_mode_select = x86_init_noop; 1355 x86_init.irqs.intr_mode_init = x86_64_probe_apic; 1356 x86_init.oem.arch_setup = xen_arch_setup; 1357 x86_init.oem.banner = xen_banner; 1358 x86_init.hyper.init_platform = xen_pv_init_platform; 1359 x86_init.hyper.guest_late_init = xen_pv_guest_late_init; 1360 1361 /* 1362 * Set up some pagetable state before starting to set any ptes. 1363 */ 1364 1365 xen_setup_machphys_mapping(); 1366 xen_init_mmu_ops(); 1367 1368 /* Prevent unwanted bits from being set in PTEs. */ 1369 __supported_pte_mask &= ~_PAGE_GLOBAL; 1370 __default_kernel_pte_mask &= ~_PAGE_GLOBAL; 1371 1372 /* Get mfn list */ 1373 xen_build_dynamic_phys_to_machine(); 1374 1375 /* Work out if we support NX */ 1376 get_cpu_cap(&boot_cpu_data); 1377 x86_configure_nx(); 1378 1379 /* 1380 * Set up kernel GDT and segment registers, mainly so that 1381 * -fstack-protector code can be executed. 1382 */ 1383 xen_setup_gdt(0); 1384 1385 /* Determine virtual and physical address sizes */ 1386 get_cpu_address_sizes(&boot_cpu_data); 1387 1388 /* Let's presume PV guests always boot on vCPU with id 0. */ 1389 per_cpu(xen_vcpu_id, 0) = 0; 1390 1391 idt_setup_early_handler(); 1392 1393 xen_init_capabilities(); 1394 1395 /* 1396 * set up the basic apic ops. 1397 */ 1398 xen_init_apic(); 1399 1400 machine_ops = xen_machine_ops; 1401 1402 /* 1403 * The only reliable way to retain the initial address of the 1404 * percpu gdt_page is to remember it here, so we can go and 1405 * mark it RW later, when the initial percpu area is freed. 1406 */ 1407 xen_initial_gdt = &per_cpu(gdt_page, 0); 1408 1409 xen_smp_init(); 1410 1411#ifdef CONFIG_ACPI_NUMA 1412 /* 1413 * The pages we from Xen are not related to machine pages, so 1414 * any NUMA information the kernel tries to get from ACPI will 1415 * be meaningless. Prevent it from trying. 1416 */ 1417 disable_srat(); 1418#endif 1419 WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); 1420 1421 local_irq_disable(); 1422 early_boot_irqs_disabled = true; 1423 1424 xen_raw_console_write("mapping kernel into physical memory\n"); 1425 xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, 1426 xen_start_info->nr_pages); 1427 xen_reserve_special_pages(); 1428 1429 /* 1430 * We used to do this in xen_arch_setup, but that is too late 1431 * on AMD were early_cpu_init (run before ->arch_setup()) calls 1432 * early_amd_init which pokes 0xcf8 port. 1433 */ 1434 set_iopl.iopl = 1; 1435 rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); 1436 if (rc != 0) 1437 xen_raw_printk("physdev_op failed %d\n", rc); 1438 1439 1440 if (xen_start_info->mod_start) { 1441 if (xen_start_info->flags & SIF_MOD_START_PFN) 1442 initrd_start = PFN_PHYS(xen_start_info->mod_start); 1443 else 1444 initrd_start = __pa(xen_start_info->mod_start); 1445 } 1446 1447 /* Poke various useful things into boot_params */ 1448 boot_params.hdr.type_of_loader = (9 << 4) | 0; 1449 boot_params.hdr.ramdisk_image = initrd_start; 1450 boot_params.hdr.ramdisk_size = xen_start_info->mod_len; 1451 boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line); 1452 boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN; 1453 1454 if (!xen_initial_domain()) { 1455 if (pci_xen) 1456 x86_init.pci.arch_init = pci_xen_init; 1457 x86_platform.set_legacy_features = 1458 xen_domu_set_legacy_features; 1459 } else { 1460 const struct dom0_vga_console_info *info = 1461 (void *)((char *)xen_start_info + 1462 xen_start_info->console.dom0.info_off); 1463 struct xen_platform_op op = { 1464 .cmd = XENPF_firmware_info, 1465 .interface_version = XENPF_INTERFACE_VERSION, 1466 .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS, 1467 }; 1468 1469 x86_platform.set_legacy_features = 1470 xen_dom0_set_legacy_features; 1471 xen_init_vga(info, xen_start_info->console.dom0.info_size, 1472 &boot_params.screen_info); 1473 xen_start_info->console.domU.mfn = 0; 1474 xen_start_info->console.domU.evtchn = 0; 1475 1476 if (HYPERVISOR_platform_op(&op) == 0) 1477 boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; 1478 1479 /* Make sure ACS will be enabled */ 1480 pci_request_acs(); 1481 1482 xen_acpi_sleep_register(); 1483 1484 xen_boot_params_init_edd(); 1485 1486#ifdef CONFIG_ACPI 1487 /* 1488 * Disable selecting "Firmware First mode" for correctable 1489 * memory errors, as this is the duty of the hypervisor to 1490 * decide. 1491 */ 1492 acpi_disable_cmcff = 1; 1493#endif 1494 } 1495 1496 xen_add_preferred_consoles(); 1497 1498#ifdef CONFIG_PCI 1499 /* PCI BIOS service won't work from a PV guest. */ 1500 pci_probe &= ~PCI_PROBE_BIOS; 1501#endif 1502 xen_raw_console_write("about to get started...\n"); 1503 1504 /* We need this for printk timestamps */ 1505 xen_setup_runstate_info(0); 1506 1507 xen_efi_init(&boot_params); 1508 1509 /* Start the world */ 1510 cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */ 1511 x86_64_start_reservations((char *)__pa_symbol(&boot_params)); 1512} 1513 1514static int xen_cpu_up_prepare_pv(unsigned int cpu) 1515{ 1516 int rc; 1517 1518 if (per_cpu(xen_vcpu, cpu) == NULL) 1519 return -ENODEV; 1520 1521 xen_setup_timer(cpu); 1522 1523 rc = xen_smp_intr_init(cpu); 1524 if (rc) { 1525 WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n", 1526 cpu, rc); 1527 return rc; 1528 } 1529 1530 rc = xen_smp_intr_init_pv(cpu); 1531 if (rc) { 1532 WARN(1, "xen_smp_intr_init_pv() for CPU %d failed: %d\n", 1533 cpu, rc); 1534 return rc; 1535 } 1536 1537 return 0; 1538} 1539 1540static int xen_cpu_dead_pv(unsigned int cpu) 1541{ 1542 xen_smp_intr_free(cpu); 1543 xen_smp_intr_free_pv(cpu); 1544 1545 xen_teardown_timer(cpu); 1546 1547 return 0; 1548} 1549 1550static uint32_t __init xen_platform_pv(void) 1551{ 1552 if (xen_pv_domain()) 1553 return xen_cpuid_base(); 1554 1555 return 0; 1556} 1557 1558const __initconst struct hypervisor_x86 x86_hyper_xen_pv = { 1559 .name = "Xen PV", 1560 .detect = xen_platform_pv, 1561 .type = X86_HYPER_XEN_PV, 1562 .runtime.pin_vcpu = xen_pin_vcpu, 1563 .ignore_nopv = true, 1564}; 1565