e500_mmu_host.c 17.3 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 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195
/*
 * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
 *
 * Author: Yu Liu, yu.liu@freescale.com
 *         Scott Wood, scottwood@freescale.com
 *         Ashish Kalra, ashish.kalra@freescale.com
 *         Varun Sethi, varun.sethi@freescale.com
 *         Alexander Graf, agraf@suse.de
 *
 * Description:
 * This file is based on arch/powerpc/kvm/44x_tlb.c,
 * by Hollis Blanchard <hollisb@us.ibm.com>.
 *
 * 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.
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/log2.h>
#include <linux/uaccess.h>
#include <linux/sched.h>
#include <linux/rwsem.h>
#include <linux/vmalloc.h>
#include <linux/hugetlb.h>
#include <asm/kvm_ppc.h>

#include "e500.h"
#include "trace.h"
#include "timing.h"
#include "e500_mmu_host.h"

#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)

static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];

static inline unsigned int tlb1_max_shadow_size(void)
{
	/* reserve one entry for magic page */
	return host_tlb_params[1].entries - tlbcam_index - 1;
}

static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
{
	/* Mask off reserved bits. */
	mas3 &= MAS3_ATTRIB_MASK;

#ifndef CONFIG_KVM_BOOKE_HV
	if (!usermode) {
		/* Guest is in supervisor mode,
		 * so we need to translate guest
		 * supervisor permissions into user permissions. */
		mas3 &= ~E500_TLB_USER_PERM_MASK;
		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
	}
	mas3 |= E500_TLB_SUPER_PERM_MASK;
#endif
	return mas3;
}

static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
{
#ifdef CONFIG_SMP
	return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M;
#else
	return mas2 & MAS2_ATTRIB_MASK;
#endif
}

/*
 * writing shadow tlb entry to host TLB
 */
static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
				     uint32_t mas0)
{
	unsigned long flags;

	local_irq_save(flags);
	mtspr(SPRN_MAS0, mas0);
	mtspr(SPRN_MAS1, stlbe->mas1);
	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
#ifdef CONFIG_KVM_BOOKE_HV
	mtspr(SPRN_MAS8, stlbe->mas8);
#endif
	asm volatile("isync; tlbwe" : : : "memory");

#ifdef CONFIG_KVM_BOOKE_HV
	/* Must clear mas8 for other host tlbwe's */
	mtspr(SPRN_MAS8, 0);
	isync();
#endif
	local_irq_restore(flags);

	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
	                              stlbe->mas2, stlbe->mas7_3);
}

/*
 * Acquire a mas0 with victim hint, as if we just took a TLB miss.
 *
 * We don't care about the address we're searching for, other than that it's
 * in the right set and is not present in the TLB.  Using a zero PID and a
 * userspace address means we don't have to set and then restore MAS5, or
 * calculate a proper MAS6 value.
 */
static u32 get_host_mas0(unsigned long eaddr)
{
	unsigned long flags;
	u32 mas0;

	local_irq_save(flags);
	mtspr(SPRN_MAS6, 0);
	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
	mas0 = mfspr(SPRN_MAS0);
	local_irq_restore(flags);

	return mas0;
}

/* sesel is for tlb1 only */
static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
{
	u32 mas0;

	if (tlbsel == 0) {
		mas0 = get_host_mas0(stlbe->mas2);
		__write_host_tlbe(stlbe, mas0);
	} else {
		__write_host_tlbe(stlbe,
				  MAS0_TLBSEL(1) |
				  MAS0_ESEL(to_htlb1_esel(sesel)));
	}
}

/* sesel is for tlb1 only */
static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
			struct kvm_book3e_206_tlb_entry *gtlbe,
			struct kvm_book3e_206_tlb_entry *stlbe,
			int stlbsel, int sesel)
{
	int stid;

	preempt_disable();
	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);

	stlbe->mas1 |= MAS1_TID(stid);
	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
	preempt_enable();
}

#ifdef CONFIG_KVM_E500V2
/* XXX should be a hook in the gva2hpa translation */
void kvmppc_map_magic(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct kvm_book3e_206_tlb_entry magic;
	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
	unsigned int stid;
	pfn_t pfn;

	pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT;
	get_page(pfn_to_page(pfn));

	preempt_disable();
	stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0);

	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
	magic.mas8 = 0;

	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
	preempt_enable();
}
#endif

void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
			 int esel)
{
	struct kvm_book3e_206_tlb_entry *gtlbe =
		get_entry(vcpu_e500, tlbsel, esel);
	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;

	/* Don't bother with unmapped entries */
S
Scott Wood 已提交
196 197 198 199 200
	if (!(ref->flags & E500_TLB_VALID)) {
		WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
		     "%s: flags %x\n", __func__, ref->flags);
		WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
	}
201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221

	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
		int hw_tlb_indx;
		unsigned long flags;

		local_irq_save(flags);
		while (tmp) {
			hw_tlb_indx = __ilog2_u64(tmp & -tmp);
			mtspr(SPRN_MAS0,
			      MAS0_TLBSEL(1) |
			      MAS0_ESEL(to_htlb1_esel(hw_tlb_indx)));
			mtspr(SPRN_MAS1, 0);
			asm volatile("tlbwe");
			vcpu_e500->h2g_tlb1_rmap[hw_tlb_indx] = 0;
			tmp &= tmp - 1;
		}
		mb();
		vcpu_e500->g2h_tlb1_map[esel] = 0;
		ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
		local_irq_restore(flags);
222
	}
223

224 225 226 227 228 229 230
	if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) {
		/*
		 * TLB1 entry is backed by 4k pages. This should happen
		 * rarely and is not worth optimizing. Invalidate everything.
		 */
		kvmppc_e500_tlbil_all(vcpu_e500);
		ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
231 232
	}

233 234 235 236
	/* Already invalidated in between */
	if (!(ref->flags & E500_TLB_VALID))
		return;

237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253
	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);

	/* Mark the TLB as not backed by the host anymore */
	ref->flags &= ~E500_TLB_VALID;
}

static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
{
	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
}

static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
					 struct kvm_book3e_206_tlb_entry *gtlbe,
					 pfn_t pfn)
{
	ref->pfn = pfn;
S
Scott Wood 已提交
254
	ref->flags |= E500_TLB_VALID;
255 256 257 258 259 260 261 262

	if (tlbe_is_writable(gtlbe))
		kvm_set_pfn_dirty(pfn);
}

static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
{
	if (ref->flags & E500_TLB_VALID) {
S
Scott Wood 已提交
263
		/* FIXME: don't log bogus pfn for TLB1 */
264 265 266 267 268
		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
		ref->flags = 0;
	}
}

269
static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
270 271 272 273 274 275 276 277 278 279 280
{
	if (vcpu_e500->g2h_tlb1_map)
		memset(vcpu_e500->g2h_tlb1_map, 0,
		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
	if (vcpu_e500->h2g_tlb1_rmap)
		memset(vcpu_e500->h2g_tlb1_rmap, 0,
		       sizeof(unsigned int) * host_tlb_params[1].entries);
}

static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
{
S
Scott Wood 已提交
281
	int tlbsel;
282 283
	int i;

S
Scott Wood 已提交
284 285 286 287 288 289
	for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
			struct tlbe_ref *ref =
				&vcpu_e500->gtlb_priv[tlbsel][i].ref;
			kvmppc_e500_ref_release(ref);
		}
290 291 292 293 294 295
	}
}

void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
S
Scott Wood 已提交
296 297
	kvmppc_e500_tlbil_all(vcpu_e500);
	clear_tlb_privs(vcpu_e500);
298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489
	clear_tlb1_bitmap(vcpu_e500);
}

/* TID must be supplied by the caller */
static void kvmppc_e500_setup_stlbe(
	struct kvm_vcpu *vcpu,
	struct kvm_book3e_206_tlb_entry *gtlbe,
	int tsize, struct tlbe_ref *ref, u64 gvaddr,
	struct kvm_book3e_206_tlb_entry *stlbe)
{
	pfn_t pfn = ref->pfn;
	u32 pr = vcpu->arch.shared->msr & MSR_PR;

	BUG_ON(!(ref->flags & E500_TLB_VALID));

	/* Force IPROT=0 for all guest mappings. */
	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
	stlbe->mas2 = (gvaddr & MAS2_EPN) |
		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);

#ifdef CONFIG_KVM_BOOKE_HV
	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
#endif
}

static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
	struct tlbe_ref *ref)
{
	struct kvm_memory_slot *slot;
	unsigned long pfn = 0; /* silence GCC warning */
	unsigned long hva;
	int pfnmap = 0;
	int tsize = BOOK3E_PAGESZ_4K;

	/*
	 * Translate guest physical to true physical, acquiring
	 * a page reference if it is normal, non-reserved memory.
	 *
	 * gfn_to_memslot() must succeed because otherwise we wouldn't
	 * have gotten this far.  Eventually we should just pass the slot
	 * pointer through from the first lookup.
	 */
	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
	hva = gfn_to_hva_memslot(slot, gfn);

	if (tlbsel == 1) {
		struct vm_area_struct *vma;
		down_read(&current->mm->mmap_sem);

		vma = find_vma(current->mm, hva);
		if (vma && hva >= vma->vm_start &&
		    (vma->vm_flags & VM_PFNMAP)) {
			/*
			 * This VMA is a physically contiguous region (e.g.
			 * /dev/mem) that bypasses normal Linux page
			 * management.  Find the overlap between the
			 * vma and the memslot.
			 */

			unsigned long start, end;
			unsigned long slot_start, slot_end;

			pfnmap = 1;

			start = vma->vm_pgoff;
			end = start +
			      ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT);

			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);

			slot_start = pfn - (gfn - slot->base_gfn);
			slot_end = slot_start + slot->npages;

			if (start < slot_start)
				start = slot_start;
			if (end > slot_end)
				end = slot_end;

			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
				MAS1_TSIZE_SHIFT;

			/*
			 * e500 doesn't implement the lowest tsize bit,
			 * or 1K pages.
			 */
			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);

			/*
			 * Now find the largest tsize (up to what the guest
			 * requested) that will cover gfn, stay within the
			 * range, and for which gfn and pfn are mutually
			 * aligned.
			 */

			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
				unsigned long gfn_start, gfn_end, tsize_pages;
				tsize_pages = 1 << (tsize - 2);

				gfn_start = gfn & ~(tsize_pages - 1);
				gfn_end = gfn_start + tsize_pages;

				if (gfn_start + pfn - gfn < start)
					continue;
				if (gfn_end + pfn - gfn > end)
					continue;
				if ((gfn & (tsize_pages - 1)) !=
				    (pfn & (tsize_pages - 1)))
					continue;

				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
				pfn &= ~(tsize_pages - 1);
				break;
			}
		} else if (vma && hva >= vma->vm_start &&
			   (vma->vm_flags & VM_HUGETLB)) {
			unsigned long psize = vma_kernel_pagesize(vma);

			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
				MAS1_TSIZE_SHIFT;

			/*
			 * Take the largest page size that satisfies both host
			 * and guest mapping
			 */
			tsize = min(__ilog2(psize) - 10, tsize);

			/*
			 * e500 doesn't implement the lowest tsize bit,
			 * or 1K pages.
			 */
			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
		}

		up_read(&current->mm->mmap_sem);
	}

	if (likely(!pfnmap)) {
		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
		pfn = gfn_to_pfn_memslot(slot, gfn);
		if (is_error_noslot_pfn(pfn)) {
			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
					(long)gfn);
			return -EINVAL;
		}

		/* Align guest and physical address to page map boundaries */
		pfn &= ~(tsize_pages - 1);
		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
	}

	kvmppc_e500_ref_setup(ref, gtlbe, pfn);

	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
				ref, gvaddr, stlbe);

	/* Clear i-cache for new pages */
	kvmppc_mmu_flush_icache(pfn);

	/* Drop refcount on page, so that mmu notifiers can clear it */
	kvm_release_pfn_clean(pfn);

	return 0;
}

/* XXX only map the one-one case, for now use TLB0 */
static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
				struct kvm_book3e_206_tlb_entry *stlbe)
{
	struct kvm_book3e_206_tlb_entry *gtlbe;
	struct tlbe_ref *ref;
	int stlbsel = 0;
	int sesel = 0;
	int r;

	gtlbe = get_entry(vcpu_e500, 0, esel);
	ref = &vcpu_e500->gtlb_priv[0][esel].ref;

	r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
			gtlbe, 0, stlbe, ref);
	if (r)
		return r;

	write_stlbe(vcpu_e500, gtlbe, stlbe, stlbsel, sesel);

	return 0;
}

490 491 492 493 494 495 496 497 498 499
static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
				     struct tlbe_ref *ref,
				     int esel)
{
	unsigned int sesel = vcpu_e500->host_tlb1_nv++;

	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
		vcpu_e500->host_tlb1_nv = 0;

	if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
500
		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1;
501 502
		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
	}
503 504 505

	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
506
	vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
S
Scott Wood 已提交
507
	WARN_ON(!(ref->flags & E500_TLB_VALID));
508 509 510 511

	return sesel;
}

512 513
/* Caller must ensure that the specified guest TLB entry is safe to insert into
 * the shadow TLB. */
514
/* For both one-one and one-to-many */
515 516 517 518
static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
{
S
Scott Wood 已提交
519
	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
520
	int sesel;
521 522 523
	int r;

	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
S
Scott Wood 已提交
524
				   ref);
525 526 527
	if (r)
		return r;

528 529 530 531 532
	/* Use TLB0 when we can only map a page with 4k */
	if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) {
		vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0;
		write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0);
		return 0;
533 534
	}

535
	/* Otherwise map into TLB1 */
S
Scott Wood 已提交
536
	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
537
	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556

	return 0;
}

void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
		    unsigned int index)
{
	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
	struct tlbe_priv *priv;
	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
	int tlbsel = tlbsel_of(index);
	int esel = esel_of(index);

	gtlbe = get_entry(vcpu_e500, tlbsel, esel);

	switch (tlbsel) {
	case 0:
		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];

S
Scott Wood 已提交
557
		/* Triggers after clear_tlb_privs or on initial mapping */
558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660
		if (!(priv->ref.flags & E500_TLB_VALID)) {
			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
		} else {
			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
						&priv->ref, eaddr, &stlbe);
			write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0);
		}
		break;

	case 1: {
		gfn_t gfn = gpaddr >> PAGE_SHIFT;
		kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe, &stlbe,
				     esel);
		break;
	}

	default:
		BUG();
		break;
	}
}

/************* MMU Notifiers *************/

int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
{
	trace_kvm_unmap_hva(hva);

	/*
	 * Flush all shadow tlb entries everywhere. This is slow, but
	 * we are 100% sure that we catch the to be unmapped page
	 */
	kvm_flush_remote_tlbs(kvm);

	return 0;
}

int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
{
	/* kvm_unmap_hva flushes everything anyways */
	kvm_unmap_hva(kvm, start);

	return 0;
}

int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
	/* XXX could be more clever ;) */
	return 0;
}

int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
{
	/* XXX could be more clever ;) */
	return 0;
}

void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
	/* The page will get remapped properly on its next fault */
	kvm_unmap_hva(kvm, hva);
}

/*****************************************/

int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;

	/*
	 * This should never happen on real e500 hardware, but is
	 * architecturally possible -- e.g. in some weird nested
	 * virtualization case.
	 */
	if (host_tlb_params[0].entries == 0 ||
	    host_tlb_params[1].entries == 0) {
		pr_err("%s: need to know host tlb size\n", __func__);
		return -ENODEV;
	}

	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
				  TLBnCFG_ASSOC_SHIFT;
	host_tlb_params[1].ways = host_tlb_params[1].entries;

	if (!is_power_of_2(host_tlb_params[0].entries) ||
	    !is_power_of_2(host_tlb_params[0].ways) ||
	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
	    host_tlb_params[0].ways == 0) {
		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
		       __func__, host_tlb_params[0].entries,
		       host_tlb_params[0].ways);
		return -ENODEV;
	}

	host_tlb_params[0].sets =
		host_tlb_params[0].entries / host_tlb_params[0].ways;
	host_tlb_params[1].sets = 1;

	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
					   host_tlb_params[1].entries,
					   GFP_KERNEL);
	if (!vcpu_e500->h2g_tlb1_rmap)
S
Scott Wood 已提交
661
		return -EINVAL;
662 663 664 665 666 667 668 669

	return 0;
}

void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
{
	kfree(vcpu_e500->h2g_tlb1_rmap);
}