book3s_64_mmu_hv.c 40.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 *
 * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
 */

#include <linux/types.h>
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/hugetlb.h>
26
#include <linux/vmalloc.h>
27
#include <linux/srcu.h>
28 29
#include <linux/anon_inodes.h>
#include <linux/file.h>
30 31 32 33 34 35 36 37 38 39

#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
#include <asm/mmu-hash64.h>
#include <asm/hvcall.h>
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
#include <asm/cputable.h>

40 41
/* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
#define MAX_LPID_970	63
42

43 44 45
/* Power architecture requires HPT is at least 256kB */
#define PPC_MIN_HPT_ORDER	18

46 47 48
static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
				long pte_index, unsigned long pteh,
				unsigned long ptel, unsigned long *pte_idx_ret);
49
static void kvmppc_rmap_reset(struct kvm *kvm);
50

51
long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
52 53
{
	unsigned long hpt;
54
	struct revmap_entry *rev;
A
Alexander Graf 已提交
55
	struct kvmppc_linear_info *li;
56
	long order = kvm_hpt_order;
57

58 59 60 61 62 63 64 65 66 67 68 69
	if (htab_orderp) {
		order = *htab_orderp;
		if (order < PPC_MIN_HPT_ORDER)
			order = PPC_MIN_HPT_ORDER;
	}

	/*
	 * If the user wants a different size from default,
	 * try first to allocate it from the kernel page allocator.
	 */
	hpt = 0;
	if (order != kvm_hpt_order) {
A
Alexander Graf 已提交
70
		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
71 72 73
				       __GFP_NOWARN, order - PAGE_SHIFT);
		if (!hpt)
			--order;
A
Alexander Graf 已提交
74 75
	}

76
	/* Next try to allocate from the preallocated pool */
77
	if (!hpt) {
78 79 80 81 82 83
		li = kvm_alloc_hpt();
		if (li) {
			hpt = (ulong)li->base_virt;
			kvm->arch.hpt_li = li;
			order = kvm_hpt_order;
		}
84
	}
85 86 87 88 89 90 91 92 93 94 95 96

	/* Lastly try successively smaller sizes from the page allocator */
	while (!hpt && order > PPC_MIN_HPT_ORDER) {
		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
				       __GFP_NOWARN, order - PAGE_SHIFT);
		if (!hpt)
			--order;
	}

	if (!hpt)
		return -ENOMEM;

97
	kvm->arch.hpt_virt = hpt;
98 99 100 101 102
	kvm->arch.hpt_order = order;
	/* HPTEs are 2**4 bytes long */
	kvm->arch.hpt_npte = 1ul << (order - 4);
	/* 128 (2**7) bytes in each HPTEG */
	kvm->arch.hpt_mask = (1ul << (order - 7)) - 1;
103

104
	/* Allocate reverse map array */
105
	rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte);
106 107 108 109 110
	if (!rev) {
		pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
		goto out_freehpt;
	}
	kvm->arch.revmap = rev;
111
	kvm->arch.sdr1 = __pa(hpt) | (order - 18);
112

113 114
	pr_info("KVM guest htab at %lx (order %ld), LPID %x\n",
		hpt, order, kvm->arch.lpid);
115

116 117
	if (htab_orderp)
		*htab_orderp = order;
118
	return 0;
119 120

 out_freehpt:
121 122 123 124
	if (kvm->arch.hpt_li)
		kvm_release_hpt(kvm->arch.hpt_li);
	else
		free_pages(hpt, order - PAGE_SHIFT);
125
	return -ENOMEM;
126 127
}

128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146
long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
{
	long err = -EBUSY;
	long order;

	mutex_lock(&kvm->lock);
	if (kvm->arch.rma_setup_done) {
		kvm->arch.rma_setup_done = 0;
		/* order rma_setup_done vs. vcpus_running */
		smp_mb();
		if (atomic_read(&kvm->arch.vcpus_running)) {
			kvm->arch.rma_setup_done = 1;
			goto out;
		}
	}
	if (kvm->arch.hpt_virt) {
		order = kvm->arch.hpt_order;
		/* Set the entire HPT to 0, i.e. invalid HPTEs */
		memset((void *)kvm->arch.hpt_virt, 0, 1ul << order);
147 148 149 150
		/*
		 * Reset all the reverse-mapping chains for all memslots
		 */
		kvmppc_rmap_reset(kvm);
151 152
		/* Ensure that each vcpu will flush its TLB on next entry. */
		cpumask_setall(&kvm->arch.need_tlb_flush);
153 154 155 156 157 158 159 160 161 162 163
		*htab_orderp = order;
		err = 0;
	} else {
		err = kvmppc_alloc_hpt(kvm, htab_orderp);
		order = *htab_orderp;
	}
 out:
	mutex_unlock(&kvm->lock);
	return err;
}

164 165
void kvmppc_free_hpt(struct kvm *kvm)
{
166
	kvmppc_free_lpid(kvm->arch.lpid);
167
	vfree(kvm->arch.revmap);
A
Alexander Graf 已提交
168 169 170
	if (kvm->arch.hpt_li)
		kvm_release_hpt(kvm->arch.hpt_li);
	else
171 172
		free_pages(kvm->arch.hpt_virt,
			   kvm->arch.hpt_order - PAGE_SHIFT);
173 174
}

175 176 177 178 179 180 181 182 183 184 185 186 187 188
/* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
static inline unsigned long hpte0_pgsize_encoding(unsigned long pgsize)
{
	return (pgsize > 0x1000) ? HPTE_V_LARGE : 0;
}

/* Bits in second HPTE dword for pagesize 4k, 64k or 16M */
static inline unsigned long hpte1_pgsize_encoding(unsigned long pgsize)
{
	return (pgsize == 0x10000) ? 0x1000 : 0;
}

void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
		     unsigned long porder)
189 190
{
	unsigned long i;
191
	unsigned long npages;
192 193
	unsigned long hp_v, hp_r;
	unsigned long addr, hash;
194 195
	unsigned long psize;
	unsigned long hp0, hp1;
196
	unsigned long idx_ret;
197
	long ret;
198
	struct kvm *kvm = vcpu->kvm;
199

200 201
	psize = 1ul << porder;
	npages = memslot->npages >> (porder - PAGE_SHIFT);
202 203

	/* VRMA can't be > 1TB */
204 205
	if (npages > 1ul << (40 - porder))
		npages = 1ul << (40 - porder);
206
	/* Can't use more than 1 HPTE per HPTEG */
207 208
	if (npages > kvm->arch.hpt_mask + 1)
		npages = kvm->arch.hpt_mask + 1;
209

210 211 212 213 214
	hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
		HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
	hp1 = hpte1_pgsize_encoding(psize) |
		HPTE_R_R | HPTE_R_C | HPTE_R_M | PP_RWXX;

215
	for (i = 0; i < npages; ++i) {
216
		addr = i << porder;
217
		/* can't use hpt_hash since va > 64 bits */
218
		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask;
219 220 221 222 223 224
		/*
		 * We assume that the hash table is empty and no
		 * vcpus are using it at this stage.  Since we create
		 * at most one HPTE per HPTEG, we just assume entry 7
		 * is available and use it.
		 */
225
		hash = (hash << 3) + 7;
226 227
		hp_v = hp0 | ((addr >> 16) & ~0x7fUL);
		hp_r = hp1 | addr;
228 229
		ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, hash, hp_v, hp_r,
						 &idx_ret);
230 231 232 233 234
		if (ret != H_SUCCESS) {
			pr_err("KVM: map_vrma at %lx failed, ret=%ld\n",
			       addr, ret);
			break;
		}
235 236 237 238 239
	}
}

int kvmppc_mmu_hv_init(void)
{
240 241 242
	unsigned long host_lpid, rsvd_lpid;

	if (!cpu_has_feature(CPU_FTR_HVMODE))
243
		return -EINVAL;
244

245
	/* POWER7 has 10-bit LPIDs, PPC970 and e500mc have 6-bit LPIDs */
246 247 248 249 250 251 252 253
	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
		host_lpid = mfspr(SPRN_LPID);	/* POWER7 */
		rsvd_lpid = LPID_RSVD;
	} else {
		host_lpid = 0;			/* PPC970 */
		rsvd_lpid = MAX_LPID_970;
	}

254 255 256
	kvmppc_init_lpid(rsvd_lpid + 1);

	kvmppc_claim_lpid(host_lpid);
257
	/* rsvd_lpid is reserved for use in partition switching */
258
	kvmppc_claim_lpid(rsvd_lpid);
259 260 261 262 263 264 265 266 267 268 269 270 271

	return 0;
}

void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
}

static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
{
	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
}

272 273
/*
 * This is called to get a reference to a guest page if there isn't
274
 * one already in the memslot->arch.slot_phys[] array.
275 276
 */
static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
277 278
				  struct kvm_memory_slot *memslot,
				  unsigned long psize)
279 280
{
	unsigned long start;
281 282 283
	long np, err;
	struct page *page, *hpage, *pages[1];
	unsigned long s, pgsize;
284
	unsigned long *physp;
285 286
	unsigned int is_io, got, pgorder;
	struct vm_area_struct *vma;
287
	unsigned long pfn, i, npages;
288

289
	physp = memslot->arch.slot_phys;
290 291
	if (!physp)
		return -EINVAL;
292
	if (physp[gfn - memslot->base_gfn])
293 294
		return 0;

295 296
	is_io = 0;
	got = 0;
297
	page = NULL;
298
	pgsize = psize;
299
	err = -EINVAL;
300 301 302 303
	start = gfn_to_hva_memslot(memslot, gfn);

	/* Instantiate and get the page we want access to */
	np = get_user_pages_fast(start, 1, 1, pages);
304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332
	if (np != 1) {
		/* Look up the vma for the page */
		down_read(&current->mm->mmap_sem);
		vma = find_vma(current->mm, start);
		if (!vma || vma->vm_start > start ||
		    start + psize > vma->vm_end ||
		    !(vma->vm_flags & VM_PFNMAP))
			goto up_err;
		is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
		pfn = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
		/* check alignment of pfn vs. requested page size */
		if (psize > PAGE_SIZE && (pfn & ((psize >> PAGE_SHIFT) - 1)))
			goto up_err;
		up_read(&current->mm->mmap_sem);

	} else {
		page = pages[0];
		got = KVMPPC_GOT_PAGE;

		/* See if this is a large page */
		s = PAGE_SIZE;
		if (PageHuge(page)) {
			hpage = compound_head(page);
			s <<= compound_order(hpage);
			/* Get the whole large page if slot alignment is ok */
			if (s > psize && slot_is_aligned(memslot, s) &&
			    !(memslot->userspace_addr & (s - 1))) {
				start &= ~(s - 1);
				pgsize = s;
333 334
				get_page(hpage);
				put_page(page);
335 336
				page = hpage;
			}
337
		}
338 339 340
		if (s < psize)
			goto out;
		pfn = page_to_pfn(page);
341 342
	}

343 344 345
	npages = pgsize >> PAGE_SHIFT;
	pgorder = __ilog2(npages);
	physp += (gfn - memslot->base_gfn) & ~(npages - 1);
346
	spin_lock(&kvm->arch.slot_phys_lock);
347 348
	for (i = 0; i < npages; ++i) {
		if (!physp[i]) {
349 350
			physp[i] = ((pfn + i) << PAGE_SHIFT) +
				got + is_io + pgorder;
351 352 353
			got = 0;
		}
	}
354
	spin_unlock(&kvm->arch.slot_phys_lock);
355
	err = 0;
356

357
 out:
358
	if (got)
359 360
		put_page(page);
	return err;
361 362 363 364

 up_err:
	up_read(&current->mm->mmap_sem);
	return err;
365 366
}

367 368 369
long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
				long pte_index, unsigned long pteh,
				unsigned long ptel, unsigned long *pte_idx_ret)
370 371 372 373 374
{
	unsigned long psize, gpa, gfn;
	struct kvm_memory_slot *memslot;
	long ret;

375 376 377
	if (kvm->arch.using_mmu_notifiers)
		goto do_insert;

378 379 380 381
	psize = hpte_page_size(pteh, ptel);
	if (!psize)
		return H_PARAMETER;

382 383
	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);

384 385 386 387
	/* Find the memslot (if any) for this address */
	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
	gfn = gpa >> PAGE_SHIFT;
	memslot = gfn_to_memslot(kvm, gfn);
388 389 390 391 392 393
	if (memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)) {
		if (!slot_is_aligned(memslot, psize))
			return H_PARAMETER;
		if (kvmppc_get_guest_page(kvm, gfn, memslot, psize) < 0)
			return H_PARAMETER;
	}
394

395 396 397
 do_insert:
	/* Protect linux PTE lookup from page table destruction */
	rcu_read_lock_sched();	/* this disables preemption too */
398 399
	ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel,
				current->mm->pgd, false, pte_idx_ret);
400
	rcu_read_unlock_sched();
401 402 403 404 405 406 407 408 409
	if (ret == H_TOO_HARD) {
		/* this can't happen */
		pr_err("KVM: Oops, kvmppc_h_enter returned too hard!\n");
		ret = H_RESOURCE;	/* or something */
	}
	return ret;

}

410 411 412 413 414 415 416 417 418 419 420 421 422
/*
 * We come here on a H_ENTER call from the guest when we are not
 * using mmu notifiers and we don't have the requested page pinned
 * already.
 */
long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
			     long pte_index, unsigned long pteh,
			     unsigned long ptel)
{
	return kvmppc_virtmode_do_h_enter(vcpu->kvm, flags, pte_index,
					  pteh, ptel, &vcpu->arch.gpr[4]);
}

423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu,
							 gva_t eaddr)
{
	u64 mask;
	int i;

	for (i = 0; i < vcpu->arch.slb_nr; i++) {
		if (!(vcpu->arch.slb[i].orige & SLB_ESID_V))
			continue;

		if (vcpu->arch.slb[i].origv & SLB_VSID_B_1T)
			mask = ESID_MASK_1T;
		else
			mask = ESID_MASK;

		if (((vcpu->arch.slb[i].orige ^ eaddr) & mask) == 0)
			return &vcpu->arch.slb[i];
	}
	return NULL;
}

static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r,
			unsigned long ea)
{
	unsigned long ra_mask;

	ra_mask = hpte_page_size(v, r) - 1;
	return (r & HPTE_R_RPN & ~ra_mask) | (ea & ra_mask);
}

453
static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
454
			struct kvmppc_pte *gpte, bool data)
455
{
456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
	struct kvm *kvm = vcpu->kvm;
	struct kvmppc_slb *slbe;
	unsigned long slb_v;
	unsigned long pp, key;
	unsigned long v, gr;
	unsigned long *hptep;
	int index;
	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);

	/* Get SLB entry */
	if (virtmode) {
		slbe = kvmppc_mmu_book3s_hv_find_slbe(vcpu, eaddr);
		if (!slbe)
			return -EINVAL;
		slb_v = slbe->origv;
	} else {
		/* real mode access */
		slb_v = vcpu->kvm->arch.vrma_slb_v;
	}

	/* Find the HPTE in the hash table */
	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
					 HPTE_V_VALID | HPTE_V_ABSENT);
	if (index < 0)
		return -ENOENT;
	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
	v = hptep[0] & ~HPTE_V_HVLOCK;
	gr = kvm->arch.revmap[index].guest_rpte;

	/* Unlock the HPTE */
	asm volatile("lwsync" : : : "memory");
	hptep[0] = v;

	gpte->eaddr = eaddr;
	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);

	/* Get PP bits and key for permission check */
	pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
	key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
	key &= slb_v;

	/* Calculate permissions */
	gpte->may_read = hpte_read_permission(pp, key);
	gpte->may_write = hpte_write_permission(pp, key);
	gpte->may_execute = gpte->may_read && !(gr & (HPTE_R_N | HPTE_R_G));

	/* Storage key permission check for POWER7 */
	if (data && virtmode && cpu_has_feature(CPU_FTR_ARCH_206)) {
		int amrfield = hpte_get_skey_perm(gr, vcpu->arch.amr);
		if (amrfield & 1)
			gpte->may_read = 0;
		if (amrfield & 2)
			gpte->may_write = 0;
	}

	/* Get the guest physical address */
	gpte->raddr = kvmppc_mmu_get_real_addr(v, gr, eaddr);
	return 0;
}

/*
 * Quick test for whether an instruction is a load or a store.
 * If the instruction is a load or a store, then this will indicate
 * which it is, at least on server processors.  (Embedded processors
 * have some external PID instructions that don't follow the rule
 * embodied here.)  If the instruction isn't a load or store, then
 * this doesn't return anything useful.
 */
static int instruction_is_store(unsigned int instr)
{
	unsigned int mask;

	mask = 0x10000000;
	if ((instr & 0xfc000000) == 0x7c000000)
		mask = 0x100;		/* major opcode 31 */
	return (instr & mask) != 0;
}

static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
535
				  unsigned long gpa, gva_t ea, int is_store)
536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581
{
	int ret;
	u32 last_inst;
	unsigned long srr0 = kvmppc_get_pc(vcpu);

	/* We try to load the last instruction.  We don't let
	 * emulate_instruction do it as it doesn't check what
	 * kvmppc_ld returns.
	 * If we fail, we just return to the guest and try executing it again.
	 */
	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
		ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
		if (ret != EMULATE_DONE || last_inst == KVM_INST_FETCH_FAILED)
			return RESUME_GUEST;
		vcpu->arch.last_inst = last_inst;
	}

	/*
	 * WARNING: We do not know for sure whether the instruction we just
	 * read from memory is the same that caused the fault in the first
	 * place.  If the instruction we read is neither an load or a store,
	 * then it can't access memory, so we don't need to worry about
	 * enforcing access permissions.  So, assuming it is a load or
	 * store, we just check that its direction (load or store) is
	 * consistent with the original fault, since that's what we
	 * checked the access permissions against.  If there is a mismatch
	 * we just return and retry the instruction.
	 */

	if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
		return RESUME_GUEST;

	/*
	 * Emulated accesses are emulated by looking at the hash for
	 * translation once, then performing the access later. The
	 * translation could be invalidated in the meantime in which
	 * point performing the subsequent memory access on the old
	 * physical address could possibly be a security hole for the
	 * guest (but not the host).
	 *
	 * This is less of an issue for MMIO stores since they aren't
	 * globally visible. It could be an issue for MMIO loads to
	 * a certain extent but we'll ignore it for now.
	 */

	vcpu->arch.paddr_accessed = gpa;
582
	vcpu->arch.vaddr_accessed = ea;
583 584 585 586 587 588 589
	return kvmppc_emulate_mmio(run, vcpu);
}

int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
				unsigned long ea, unsigned long dsisr)
{
	struct kvm *kvm = vcpu->kvm;
590 591
	unsigned long *hptep, hpte[3], r;
	unsigned long mmu_seq, psize, pte_size;
592
	unsigned long gpa, gfn, hva, pfn;
593
	struct kvm_memory_slot *memslot;
594
	unsigned long *rmap;
595
	struct revmap_entry *rev;
596 597 598
	struct page *page, *pages[1];
	long index, ret, npages;
	unsigned long is_io;
599
	unsigned int writing, write_ok;
600
	struct vm_area_struct *vma;
601
	unsigned long rcbits;
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618

	/*
	 * Real-mode code has already searched the HPT and found the
	 * entry we're interested in.  Lock the entry and check that
	 * it hasn't changed.  If it has, just return and re-execute the
	 * instruction.
	 */
	if (ea != vcpu->arch.pgfault_addr)
		return RESUME_GUEST;
	index = vcpu->arch.pgfault_index;
	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
	rev = &kvm->arch.revmap[index];
	preempt_disable();
	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
		cpu_relax();
	hpte[0] = hptep[0] & ~HPTE_V_HVLOCK;
	hpte[1] = hptep[1];
619
	hpte[2] = r = rev->guest_rpte;
620 621 622 623 624 625 626 627 628
	asm volatile("lwsync" : : : "memory");
	hptep[0] = hpte[0];
	preempt_enable();

	if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
	    hpte[1] != vcpu->arch.pgfault_hpte[1])
		return RESUME_GUEST;

	/* Translate the logical address and get the page */
629
	psize = hpte_page_size(hpte[0], r);
630 631
	gpa = (r & HPTE_R_RPN & ~(psize - 1)) | (ea & (psize - 1));
	gfn = gpa >> PAGE_SHIFT;
632 633 634
	memslot = gfn_to_memslot(kvm, gfn);

	/* No memslot means it's an emulated MMIO region */
635
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
636
		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea,
637 638
					      dsisr & DSISR_ISSTORE);

639 640 641 642 643 644 645 646 647 648 649
	if (!kvm->arch.using_mmu_notifiers)
		return -EFAULT;		/* should never get here */

	/* used to check for invalidations in progress */
	mmu_seq = kvm->mmu_notifier_seq;
	smp_rmb();

	is_io = 0;
	pfn = 0;
	page = NULL;
	pte_size = PAGE_SIZE;
650 651 652
	writing = (dsisr & DSISR_ISSTORE) != 0;
	/* If writing != 0, then the HPTE must allow writing, if we get here */
	write_ok = writing;
653
	hva = gfn_to_hva_memslot(memslot, gfn);
654
	npages = get_user_pages_fast(hva, 1, writing, pages);
655 656 657 658 659 660 661 662 663 664
	if (npages < 1) {
		/* Check if it's an I/O mapping */
		down_read(&current->mm->mmap_sem);
		vma = find_vma(current->mm, hva);
		if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
		    (vma->vm_flags & VM_PFNMAP)) {
			pfn = vma->vm_pgoff +
				((hva - vma->vm_start) >> PAGE_SHIFT);
			pte_size = psize;
			is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
665
			write_ok = vma->vm_flags & VM_WRITE;
666 667 668 669 670 671 672 673 674 675
		}
		up_read(&current->mm->mmap_sem);
		if (!pfn)
			return -EFAULT;
	} else {
		page = pages[0];
		if (PageHuge(page)) {
			page = compound_head(page);
			pte_size <<= compound_order(page);
		}
676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693
		/* if the guest wants write access, see if that is OK */
		if (!writing && hpte_is_writable(r)) {
			pte_t *ptep, pte;

			/*
			 * We need to protect against page table destruction
			 * while looking up and updating the pte.
			 */
			rcu_read_lock_sched();
			ptep = find_linux_pte_or_hugepte(current->mm->pgd,
							 hva, NULL);
			if (ptep && pte_present(*ptep)) {
				pte = kvmppc_read_update_linux_pte(ptep, 1);
				if (pte_write(pte))
					write_ok = 1;
			}
			rcu_read_unlock_sched();
		}
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713
		pfn = page_to_pfn(page);
	}

	ret = -EFAULT;
	if (psize > pte_size)
		goto out_put;

	/* Check WIMG vs. the actual page we're accessing */
	if (!hpte_cache_flags_ok(r, is_io)) {
		if (is_io)
			return -EFAULT;
		/*
		 * Allow guest to map emulated device memory as
		 * uncacheable, but actually make it cacheable.
		 */
		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
	}

	/* Set the HPTE to point to pfn */
	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
714 715
	if (hpte_is_writable(r) && !write_ok)
		r = hpte_make_readonly(r);
716 717 718 719 720 721 722 723 724 725
	ret = RESUME_GUEST;
	preempt_disable();
	while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
		cpu_relax();
	if ((hptep[0] & ~HPTE_V_HVLOCK) != hpte[0] || hptep[1] != hpte[1] ||
	    rev->guest_rpte != hpte[2])
		/* HPTE has been changed under us; let the guest retry */
		goto out_unlock;
	hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;

726
	rmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
727 728 729 730
	lock_rmap(rmap);

	/* Check if we might have been invalidated; let the guest retry if so */
	ret = RESUME_GUEST;
731
	if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
732 733 734
		unlock_rmap(rmap);
		goto out_unlock;
	}
735

736 737 738 739
	/* Only set R/C in real HPTE if set in both *rmap and guest_rpte */
	rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
	r &= rcbits | ~(HPTE_R_R | HPTE_R_C);

740 741 742 743 744
	if (hptep[0] & HPTE_V_VALID) {
		/* HPTE was previously valid, so we need to invalidate it */
		unlock_rmap(rmap);
		hptep[0] |= HPTE_V_ABSENT;
		kvmppc_invalidate_hpte(kvm, hptep, index);
745 746
		/* don't lose previous R and C bits */
		r |= hptep[1] & (HPTE_R_R | HPTE_R_C);
747 748 749
	} else {
		kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
	}
750 751 752 753 754 755

	hptep[1] = r;
	eieio();
	hptep[0] = hpte[0];
	asm volatile("ptesync" : : : "memory");
	preempt_enable();
756
	if (page && hpte_is_writable(r))
757 758 759
		SetPageDirty(page);

 out_put:
760 761 762 763 764 765 766 767 768
	if (page) {
		/*
		 * We drop pages[0] here, not page because page might
		 * have been set to the head page of a compound, but
		 * we have to drop the reference on the correct tail
		 * page to match the get inside gup()
		 */
		put_page(pages[0]);
	}
769 770 771 772 773 774 775 776
	return ret;

 out_unlock:
	hptep[0] &= ~HPTE_V_HVLOCK;
	preempt_enable();
	goto out_put;
}

777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795
static void kvmppc_rmap_reset(struct kvm *kvm)
{
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;
	int srcu_idx;

	srcu_idx = srcu_read_lock(&kvm->srcu);
	slots = kvm->memslots;
	kvm_for_each_memslot(memslot, slots) {
		/*
		 * This assumes it is acceptable to lose reference and
		 * change bits across a reset.
		 */
		memset(memslot->arch.rmap, 0,
		       memslot->npages * sizeof(*memslot->arch.rmap));
	}
	srcu_read_unlock(&kvm->srcu, srcu_idx);
}

796 797 798 799 800 801
static int kvm_handle_hva_range(struct kvm *kvm,
				unsigned long start,
				unsigned long end,
				int (*handler)(struct kvm *kvm,
					       unsigned long *rmapp,
					       unsigned long gfn))
802 803 804 805 806 807 808 809
{
	int ret;
	int retval = 0;
	struct kvm_memslots *slots;
	struct kvm_memory_slot *memslot;

	slots = kvm_memslots(kvm);
	kvm_for_each_memslot(memslot, slots) {
810 811 812 813 814 815 816 817 818 819 820 821 822 823
		unsigned long hva_start, hva_end;
		gfn_t gfn, gfn_end;

		hva_start = max(start, memslot->userspace_addr);
		hva_end = min(end, memslot->userspace_addr +
					(memslot->npages << PAGE_SHIFT));
		if (hva_start >= hva_end)
			continue;
		/*
		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
		 * {gfn, gfn+1, ..., gfn_end-1}.
		 */
		gfn = hva_to_gfn_memslot(hva_start, memslot);
		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
824

825
		for (; gfn < gfn_end; ++gfn) {
826
			gfn_t gfn_offset = gfn - memslot->base_gfn;
827

828
			ret = handler(kvm, &memslot->arch.rmap[gfn_offset], gfn);
829 830 831 832 833 834 835
			retval |= ret;
		}
	}

	return retval;
}

836 837 838 839 840 841 842
static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
					 unsigned long gfn))
{
	return kvm_handle_hva_range(kvm, hva, hva + 1, handler);
}

843 844 845 846 847 848
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
			   unsigned long gfn)
{
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long h, i, j;
	unsigned long *hptep;
849
	unsigned long ptel, psize, rcbits;
850 851

	for (;;) {
852
		lock_rmap(rmapp);
853
		if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
854
			unlock_rmap(rmapp);
855 856 857 858 859
			break;
		}

		/*
		 * To avoid an ABBA deadlock with the HPTE lock bit,
860 861
		 * we can't spin on the HPTE lock while holding the
		 * rmap chain lock.
862 863
		 */
		i = *rmapp & KVMPPC_RMAP_INDEX;
864 865 866 867 868 869 870 871
		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
			/* unlock rmap before spinning on the HPTE lock */
			unlock_rmap(rmapp);
			while (hptep[0] & HPTE_V_HVLOCK)
				cpu_relax();
			continue;
		}
872 873 874
		j = rev[i].forw;
		if (j == i) {
			/* chain is now empty */
875
			*rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
876 877 878 879 880 881
		} else {
			/* remove i from chain */
			h = rev[i].back;
			rev[h].forw = j;
			rev[j].back = h;
			rev[i].forw = rev[i].back = i;
882
			*rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j;
883 884
		}

885
		/* Now check and modify the HPTE */
886 887 888 889
		ptel = rev[i].guest_rpte;
		psize = hpte_page_size(hptep[0], ptel);
		if ((hptep[0] & HPTE_V_VALID) &&
		    hpte_rpn(ptel, psize) == gfn) {
890 891
			if (kvm->arch.using_mmu_notifiers)
				hptep[0] |= HPTE_V_ABSENT;
892 893 894 895
			kvmppc_invalidate_hpte(kvm, hptep, i);
			/* Harvest R and C */
			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
			*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
896 897 898 899
			if (rcbits & ~rev[i].guest_rpte) {
				rev[i].guest_rpte = ptel | rcbits;
				note_hpte_modification(kvm, &rev[i]);
			}
900
		}
901
		unlock_rmap(rmapp);
902 903 904 905 906 907 908 909 910 911 912 913
		hptep[0] &= ~HPTE_V_HVLOCK;
	}
	return 0;
}

int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
	if (kvm->arch.using_mmu_notifiers)
		kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
	return 0;
}

914 915 916 917 918 919 920
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
{
	if (kvm->arch.using_mmu_notifiers)
		kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
	return 0;
}

921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942
void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
	unsigned long *rmapp;
	unsigned long gfn;
	unsigned long n;

	rmapp = memslot->arch.rmap;
	gfn = memslot->base_gfn;
	for (n = memslot->npages; n; --n) {
		/*
		 * Testing the present bit without locking is OK because
		 * the memslot has been marked invalid already, and hence
		 * no new HPTEs referencing this page can be created,
		 * thus the present bit can't go from 0 to 1.
		 */
		if (*rmapp & KVMPPC_RMAP_PRESENT)
			kvm_unmap_rmapp(kvm, rmapp, gfn);
		++rmapp;
		++gfn;
	}
}

943 944 945
static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
			 unsigned long gfn)
{
946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long head, i, j;
	unsigned long *hptep;
	int ret = 0;

 retry:
	lock_rmap(rmapp);
	if (*rmapp & KVMPPC_RMAP_REFERENCED) {
		*rmapp &= ~KVMPPC_RMAP_REFERENCED;
		ret = 1;
	}
	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
		unlock_rmap(rmapp);
		return ret;
	}

	i = head = *rmapp & KVMPPC_RMAP_INDEX;
	do {
		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
		j = rev[i].forw;

		/* If this HPTE isn't referenced, ignore it */
		if (!(hptep[1] & HPTE_R_R))
			continue;

		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
			/* unlock rmap before spinning on the HPTE lock */
			unlock_rmap(rmapp);
			while (hptep[0] & HPTE_V_HVLOCK)
				cpu_relax();
			goto retry;
		}

		/* Now check and modify the HPTE */
		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) {
			kvmppc_clear_ref_hpte(kvm, hptep, i);
982 983 984 985
			if (!(rev[i].guest_rpte & HPTE_R_R)) {
				rev[i].guest_rpte |= HPTE_R_R;
				note_hpte_modification(kvm, &rev[i]);
			}
986 987 988 989 990 991 992
			ret = 1;
		}
		hptep[0] &= ~HPTE_V_HVLOCK;
	} while ((i = j) != head);

	unlock_rmap(rmapp);
	return ret;
993 994 995 996 997 998 999 1000 1001 1002 1003 1004
}

int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
	if (!kvm->arch.using_mmu_notifiers)
		return 0;
	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
}

static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
			      unsigned long gfn)
{
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long head, i, j;
	unsigned long *hp;
	int ret = 1;

	if (*rmapp & KVMPPC_RMAP_REFERENCED)
		return 1;

	lock_rmap(rmapp);
	if (*rmapp & KVMPPC_RMAP_REFERENCED)
		goto out;

	if (*rmapp & KVMPPC_RMAP_PRESENT) {
		i = head = *rmapp & KVMPPC_RMAP_INDEX;
		do {
			hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4));
			j = rev[i].forw;
			if (hp[1] & HPTE_R_R)
				goto out;
		} while ((i = j) != head);
	}
	ret = 0;

 out:
	unlock_rmap(rmapp);
	return ret;
1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044
}

int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
	if (!kvm->arch.using_mmu_notifiers)
		return 0;
	return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
}

void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
	if (!kvm->arch.using_mmu_notifiers)
		return;
	kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
1045 1046
}

1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088
static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
{
	struct revmap_entry *rev = kvm->arch.revmap;
	unsigned long head, i, j;
	unsigned long *hptep;
	int ret = 0;

 retry:
	lock_rmap(rmapp);
	if (*rmapp & KVMPPC_RMAP_CHANGED) {
		*rmapp &= ~KVMPPC_RMAP_CHANGED;
		ret = 1;
	}
	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
		unlock_rmap(rmapp);
		return ret;
	}

	i = head = *rmapp & KVMPPC_RMAP_INDEX;
	do {
		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
		j = rev[i].forw;

		if (!(hptep[1] & HPTE_R_C))
			continue;

		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
			/* unlock rmap before spinning on the HPTE lock */
			unlock_rmap(rmapp);
			while (hptep[0] & HPTE_V_HVLOCK)
				cpu_relax();
			goto retry;
		}

		/* Now check and modify the HPTE */
		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_C)) {
			/* need to make it temporarily absent to clear C */
			hptep[0] |= HPTE_V_ABSENT;
			kvmppc_invalidate_hpte(kvm, hptep, i);
			hptep[1] &= ~HPTE_R_C;
			eieio();
			hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
1089 1090 1091 1092
			if (!(rev[i].guest_rpte & HPTE_R_C)) {
				rev[i].guest_rpte |= HPTE_R_C;
				note_hpte_modification(kvm, &rev[i]);
			}
1093 1094 1095 1096 1097 1098 1099 1100 1101
			ret = 1;
		}
		hptep[0] &= ~HPTE_V_HVLOCK;
	} while ((i = j) != head);

	unlock_rmap(rmapp);
	return ret;
}

1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119
static void harvest_vpa_dirty(struct kvmppc_vpa *vpa,
			      struct kvm_memory_slot *memslot,
			      unsigned long *map)
{
	unsigned long gfn;

	if (!vpa->dirty || !vpa->pinned_addr)
		return;
	gfn = vpa->gpa >> PAGE_SHIFT;
	if (gfn < memslot->base_gfn ||
	    gfn >= memslot->base_gfn + memslot->npages)
		return;

	vpa->dirty = false;
	if (map)
		__set_bit_le(gfn - memslot->base_gfn, map);
}

1120 1121
long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot,
			     unsigned long *map)
1122 1123
{
	unsigned long i;
1124
	unsigned long *rmapp;
1125
	struct kvm_vcpu *vcpu;
1126 1127

	preempt_disable();
1128
	rmapp = memslot->arch.rmap;
1129
	for (i = 0; i < memslot->npages; ++i) {
1130
		if (kvm_test_clear_dirty(kvm, rmapp) && map)
1131 1132 1133
			__set_bit_le(i, map);
		++rmapp;
	}
1134 1135 1136 1137 1138 1139 1140 1141 1142

	/* Harvest dirty bits from VPA and DTL updates */
	/* Note: we never modify the SLB shadow buffer areas */
	kvm_for_each_vcpu(i, vcpu, kvm) {
		spin_lock(&vcpu->arch.vpa_update_lock);
		harvest_vpa_dirty(&vcpu->arch.vpa, memslot, map);
		harvest_vpa_dirty(&vcpu->arch.dtl, memslot, map);
		spin_unlock(&vcpu->arch.vpa_update_lock);
	}
1143 1144 1145 1146
	preempt_enable();
	return 0;
}

1147 1148 1149 1150 1151
void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
			    unsigned long *nb_ret)
{
	struct kvm_memory_slot *memslot;
	unsigned long gfn = gpa >> PAGE_SHIFT;
1152 1153
	struct page *page, *pages[1];
	int npages;
1154
	unsigned long hva, offset;
1155
	unsigned long pa;
1156
	unsigned long *physp;
1157
	int srcu_idx;
1158

1159
	srcu_idx = srcu_read_lock(&kvm->srcu);
1160 1161
	memslot = gfn_to_memslot(kvm, gfn);
	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
1162
		goto err;
1163
	if (!kvm->arch.using_mmu_notifiers) {
1164
		physp = memslot->arch.slot_phys;
1165
		if (!physp)
1166
			goto err;
1167
		physp += gfn - memslot->base_gfn;
1168
		pa = *physp;
1169 1170 1171
		if (!pa) {
			if (kvmppc_get_guest_page(kvm, gfn, memslot,
						  PAGE_SIZE) < 0)
1172
				goto err;
1173 1174 1175
			pa = *physp;
		}
		page = pfn_to_page(pa >> PAGE_SHIFT);
1176
		get_page(page);
1177 1178 1179 1180
	} else {
		hva = gfn_to_hva_memslot(memslot, gfn);
		npages = get_user_pages_fast(hva, 1, 1, pages);
		if (npages < 1)
1181
			goto err;
1182
		page = pages[0];
1183
	}
1184 1185
	srcu_read_unlock(&kvm->srcu, srcu_idx);

1186
	offset = gpa & (PAGE_SIZE - 1);
1187
	if (nb_ret)
1188
		*nb_ret = PAGE_SIZE - offset;
1189
	return page_address(page) + offset;
1190 1191 1192 1193

 err:
	srcu_read_unlock(&kvm->srcu, srcu_idx);
	return NULL;
1194 1195
}

1196 1197
void kvmppc_unpin_guest_page(struct kvm *kvm, void *va, unsigned long gpa,
			     bool dirty)
1198 1199
{
	struct page *page = virt_to_page(va);
1200 1201 1202 1203
	struct kvm_memory_slot *memslot;
	unsigned long gfn;
	unsigned long *rmap;
	int srcu_idx;
1204 1205

	put_page(page);
1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220

	if (!dirty || !kvm->arch.using_mmu_notifiers)
		return;

	/* We need to mark this page dirty in the rmap chain */
	gfn = gpa >> PAGE_SHIFT;
	srcu_idx = srcu_read_lock(&kvm->srcu);
	memslot = gfn_to_memslot(kvm, gfn);
	if (memslot) {
		rmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
		lock_rmap(rmap);
		*rmap |= KVMPPC_RMAP_CHANGED;
		unlock_rmap(rmap);
	}
	srcu_read_unlock(&kvm->srcu, srcu_idx);
1221 1222
}

1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247
/*
 * Functions for reading and writing the hash table via reads and
 * writes on a file descriptor.
 *
 * Reads return the guest view of the hash table, which has to be
 * pieced together from the real hash table and the guest_rpte
 * values in the revmap array.
 *
 * On writes, each HPTE written is considered in turn, and if it
 * is valid, it is written to the HPT as if an H_ENTER with the
 * exact flag set was done.  When the invalid count is non-zero
 * in the header written to the stream, the kernel will make
 * sure that that many HPTEs are invalid, and invalidate them
 * if not.
 */

struct kvm_htab_ctx {
	unsigned long	index;
	unsigned long	flags;
	struct kvm	*kvm;
	int		first_pass;
};

#define HPTE_SIZE	(2 * sizeof(unsigned long))

1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266
/*
 * Returns 1 if this HPT entry has been modified or has pending
 * R/C bit changes.
 */
static int hpte_dirty(struct revmap_entry *revp, unsigned long *hptp)
{
	unsigned long rcbits_unset;

	if (revp->guest_rpte & HPTE_GR_MODIFIED)
		return 1;

	/* Also need to consider changes in reference and changed bits */
	rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
	if ((hptp[0] & HPTE_V_VALID) && (hptp[1] & rcbits_unset))
		return 1;

	return 0;
}

1267 1268 1269 1270 1271
static long record_hpte(unsigned long flags, unsigned long *hptp,
			unsigned long *hpte, struct revmap_entry *revp,
			int want_valid, int first_pass)
{
	unsigned long v, r;
1272
	unsigned long rcbits_unset;
1273 1274 1275 1276
	int ok = 1;
	int valid, dirty;

	/* Unmodified entries are uninteresting except on the first pass */
1277
	dirty = hpte_dirty(revp, hptp);
1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
	if (!first_pass && !dirty)
		return 0;

	valid = 0;
	if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT)) {
		valid = 1;
		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) &&
		    !(hptp[0] & HPTE_V_BOLTED))
			valid = 0;
	}
	if (valid != want_valid)
		return 0;

	v = r = 0;
	if (valid || dirty) {
		/* lock the HPTE so it's stable and read it */
		preempt_disable();
		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
			cpu_relax();
		v = hptp[0];
1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310

		/* re-evaluate valid and dirty from synchronized HPTE value */
		valid = !!(v & HPTE_V_VALID);
		dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);

		/* Harvest R and C into guest view if necessary */
		rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
		if (valid && (rcbits_unset & hptp[1])) {
			revp->guest_rpte |= (hptp[1] & (HPTE_R_R | HPTE_R_C)) |
				HPTE_GR_MODIFIED;
			dirty = 1;
		}

1311 1312 1313
		if (v & HPTE_V_ABSENT) {
			v &= ~HPTE_V_ABSENT;
			v |= HPTE_V_VALID;
1314
			valid = 1;
1315 1316 1317
		}
		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && !(v & HPTE_V_BOLTED))
			valid = 0;
1318 1319

		r = revp->guest_rpte;
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374
		/* only clear modified if this is the right sort of entry */
		if (valid == want_valid && dirty) {
			r &= ~HPTE_GR_MODIFIED;
			revp->guest_rpte = r;
		}
		asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
		hptp[0] &= ~HPTE_V_HVLOCK;
		preempt_enable();
		if (!(valid == want_valid && (first_pass || dirty)))
			ok = 0;
	}
	hpte[0] = v;
	hpte[1] = r;
	return ok;
}

static ssize_t kvm_htab_read(struct file *file, char __user *buf,
			     size_t count, loff_t *ppos)
{
	struct kvm_htab_ctx *ctx = file->private_data;
	struct kvm *kvm = ctx->kvm;
	struct kvm_get_htab_header hdr;
	unsigned long *hptp;
	struct revmap_entry *revp;
	unsigned long i, nb, nw;
	unsigned long __user *lbuf;
	struct kvm_get_htab_header __user *hptr;
	unsigned long flags;
	int first_pass;
	unsigned long hpte[2];

	if (!access_ok(VERIFY_WRITE, buf, count))
		return -EFAULT;

	first_pass = ctx->first_pass;
	flags = ctx->flags;

	i = ctx->index;
	hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
	revp = kvm->arch.revmap + i;
	lbuf = (unsigned long __user *)buf;

	nb = 0;
	while (nb + sizeof(hdr) + HPTE_SIZE < count) {
		/* Initialize header */
		hptr = (struct kvm_get_htab_header __user *)buf;
		hdr.n_valid = 0;
		hdr.n_invalid = 0;
		nw = nb;
		nb += sizeof(hdr);
		lbuf = (unsigned long __user *)(buf + sizeof(hdr));

		/* Skip uninteresting entries, i.e. clean on not-first pass */
		if (!first_pass) {
			while (i < kvm->arch.hpt_npte &&
1375
			       !hpte_dirty(revp, hptp)) {
1376 1377 1378 1379 1380
				++i;
				hptp += 2;
				++revp;
			}
		}
1381
		hdr.index = i;
1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553

		/* Grab a series of valid entries */
		while (i < kvm->arch.hpt_npte &&
		       hdr.n_valid < 0xffff &&
		       nb + HPTE_SIZE < count &&
		       record_hpte(flags, hptp, hpte, revp, 1, first_pass)) {
			/* valid entry, write it out */
			++hdr.n_valid;
			if (__put_user(hpte[0], lbuf) ||
			    __put_user(hpte[1], lbuf + 1))
				return -EFAULT;
			nb += HPTE_SIZE;
			lbuf += 2;
			++i;
			hptp += 2;
			++revp;
		}
		/* Now skip invalid entries while we can */
		while (i < kvm->arch.hpt_npte &&
		       hdr.n_invalid < 0xffff &&
		       record_hpte(flags, hptp, hpte, revp, 0, first_pass)) {
			/* found an invalid entry */
			++hdr.n_invalid;
			++i;
			hptp += 2;
			++revp;
		}

		if (hdr.n_valid || hdr.n_invalid) {
			/* write back the header */
			if (__copy_to_user(hptr, &hdr, sizeof(hdr)))
				return -EFAULT;
			nw = nb;
			buf = (char __user *)lbuf;
		} else {
			nb = nw;
		}

		/* Check if we've wrapped around the hash table */
		if (i >= kvm->arch.hpt_npte) {
			i = 0;
			ctx->first_pass = 0;
			break;
		}
	}

	ctx->index = i;

	return nb;
}

static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
			      size_t count, loff_t *ppos)
{
	struct kvm_htab_ctx *ctx = file->private_data;
	struct kvm *kvm = ctx->kvm;
	struct kvm_get_htab_header hdr;
	unsigned long i, j;
	unsigned long v, r;
	unsigned long __user *lbuf;
	unsigned long *hptp;
	unsigned long tmp[2];
	ssize_t nb;
	long int err, ret;
	int rma_setup;

	if (!access_ok(VERIFY_READ, buf, count))
		return -EFAULT;

	/* lock out vcpus from running while we're doing this */
	mutex_lock(&kvm->lock);
	rma_setup = kvm->arch.rma_setup_done;
	if (rma_setup) {
		kvm->arch.rma_setup_done = 0;	/* temporarily */
		/* order rma_setup_done vs. vcpus_running */
		smp_mb();
		if (atomic_read(&kvm->arch.vcpus_running)) {
			kvm->arch.rma_setup_done = 1;
			mutex_unlock(&kvm->lock);
			return -EBUSY;
		}
	}

	err = 0;
	for (nb = 0; nb + sizeof(hdr) <= count; ) {
		err = -EFAULT;
		if (__copy_from_user(&hdr, buf, sizeof(hdr)))
			break;

		err = 0;
		if (nb + hdr.n_valid * HPTE_SIZE > count)
			break;

		nb += sizeof(hdr);
		buf += sizeof(hdr);

		err = -EINVAL;
		i = hdr.index;
		if (i >= kvm->arch.hpt_npte ||
		    i + hdr.n_valid + hdr.n_invalid > kvm->arch.hpt_npte)
			break;

		hptp = (unsigned long *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
		lbuf = (unsigned long __user *)buf;
		for (j = 0; j < hdr.n_valid; ++j) {
			err = -EFAULT;
			if (__get_user(v, lbuf) || __get_user(r, lbuf + 1))
				goto out;
			err = -EINVAL;
			if (!(v & HPTE_V_VALID))
				goto out;
			lbuf += 2;
			nb += HPTE_SIZE;

			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
			err = -EIO;
			ret = kvmppc_virtmode_do_h_enter(kvm, H_EXACT, i, v, r,
							 tmp);
			if (ret != H_SUCCESS) {
				pr_err("kvm_htab_write ret %ld i=%ld v=%lx "
				       "r=%lx\n", ret, i, v, r);
				goto out;
			}
			if (!rma_setup && is_vrma_hpte(v)) {
				unsigned long psize = hpte_page_size(v, r);
				unsigned long senc = slb_pgsize_encoding(psize);
				unsigned long lpcr;

				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
					(VRMA_VSID << SLB_VSID_SHIFT_1T);
				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
				lpcr |= senc << (LPCR_VRMASD_SH - 4);
				kvm->arch.lpcr = lpcr;
				rma_setup = 1;
			}
			++i;
			hptp += 2;
		}

		for (j = 0; j < hdr.n_invalid; ++j) {
			if (hptp[0] & (HPTE_V_VALID | HPTE_V_ABSENT))
				kvmppc_do_h_remove(kvm, 0, i, 0, tmp);
			++i;
			hptp += 2;
		}
		err = 0;
	}

 out:
	/* Order HPTE updates vs. rma_setup_done */
	smp_wmb();
	kvm->arch.rma_setup_done = rma_setup;
	mutex_unlock(&kvm->lock);

	if (err)
		return err;
	return nb;
}

static int kvm_htab_release(struct inode *inode, struct file *filp)
{
	struct kvm_htab_ctx *ctx = filp->private_data;

	filp->private_data = NULL;
	if (!(ctx->flags & KVM_GET_HTAB_WRITE))
		atomic_dec(&ctx->kvm->arch.hpte_mod_interest);
	kvm_put_kvm(ctx->kvm);
	kfree(ctx);
	return 0;
}

1554
static const struct file_operations kvm_htab_fops = {
1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596
	.read		= kvm_htab_read,
	.write		= kvm_htab_write,
	.llseek		= default_llseek,
	.release	= kvm_htab_release,
};

int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
{
	int ret;
	struct kvm_htab_ctx *ctx;
	int rwflag;

	/* reject flags we don't recognize */
	if (ghf->flags & ~(KVM_GET_HTAB_BOLTED_ONLY | KVM_GET_HTAB_WRITE))
		return -EINVAL;
	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;
	kvm_get_kvm(kvm);
	ctx->kvm = kvm;
	ctx->index = ghf->start_index;
	ctx->flags = ghf->flags;
	ctx->first_pass = 1;

	rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY;
	ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag);
	if (ret < 0) {
		kvm_put_kvm(kvm);
		return ret;
	}

	if (rwflag == O_RDONLY) {
		mutex_lock(&kvm->slots_lock);
		atomic_inc(&kvm->arch.hpte_mod_interest);
		/* make sure kvmppc_do_h_enter etc. see the increment */
		synchronize_srcu_expedited(&kvm->srcu);
		mutex_unlock(&kvm->slots_lock);
	}

	return ret;
}

1597 1598 1599 1600
void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
{
	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;

1601 1602 1603 1604
	if (cpu_has_feature(CPU_FTR_ARCH_206))
		vcpu->arch.slb_nr = 32;		/* POWER7 */
	else
		vcpu->arch.slb_nr = 64;
1605 1606 1607 1608 1609 1610

	mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate;
	mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr;

	vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
}