mmu.c 49.1 KB
Newer Older
J
Jeremy Fitzhardinge 已提交
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
/*
 * Xen mmu operations
 *
 * This file contains the various mmu fetch and update operations.
 * The most important job they must perform is the mapping between the
 * domain's pfn and the overall machine mfns.
 *
 * Xen allows guests to directly update the pagetable, in a controlled
 * fashion.  In other words, the guest modifies the same pagetable
 * that the CPU actually uses, which eliminates the overhead of having
 * a separate shadow pagetable.
 *
 * In order to allow this, it falls on the guest domain to map its
 * notion of a "physical" pfn - which is just a domain-local linear
 * address - into a real "machine address" which the CPU's MMU can
 * use.
 *
 * A pgd_t/pmd_t/pte_t will typically contain an mfn, and so can be
 * inserted directly into the pagetable.  When creating a new
 * pte/pmd/pgd, it converts the passed pfn into an mfn.  Conversely,
 * when reading the content back with __(pgd|pmd|pte)_val, it converts
 * the mfn back into a pfn.
 *
 * The other constraint is that all pages which make up a pagetable
 * must be mapped read-only in the guest.  This prevents uncontrolled
 * guest updates to the pagetable.  Xen strictly enforces this, and
 * will disallow any pagetable update which will end up mapping a
 * pagetable page RW, and will disallow using any writable page as a
 * pagetable.
 *
 * Naively, when loading %cr3 with the base of a new pagetable, Xen
 * would need to validate the whole pagetable before going on.
 * Naturally, this is quite slow.  The solution is to "pin" a
 * pagetable, which enforces all the constraints on the pagetable even
 * when it is not actively in use.  This menas that Xen can be assured
 * that it is still valid when you do load it into %cr3, and doesn't
 * need to revalidate it.
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */
41
#include <linux/sched.h>
42
#include <linux/highmem.h>
J
Jeremy Fitzhardinge 已提交
43
#include <linux/debugfs.h>
J
Jeremy Fitzhardinge 已提交
44
#include <linux/bug.h>
45
#include <linux/module.h>
J
Jeremy Fitzhardinge 已提交
46 47 48

#include <asm/pgtable.h>
#include <asm/tlbflush.h>
49
#include <asm/fixmap.h>
J
Jeremy Fitzhardinge 已提交
50
#include <asm/mmu_context.h>
51
#include <asm/setup.h>
52
#include <asm/paravirt.h>
53
#include <asm/linkage.h>
J
Jeremy Fitzhardinge 已提交
54 55

#include <asm/xen/hypercall.h>
56
#include <asm/xen/hypervisor.h>
J
Jeremy Fitzhardinge 已提交
57 58 59

#include <xen/page.h>
#include <xen/interface/xen.h>
60 61
#include <xen/interface/version.h>
#include <xen/hvc-console.h>
J
Jeremy Fitzhardinge 已提交
62

63
#include "multicalls.h"
J
Jeremy Fitzhardinge 已提交
64
#include "mmu.h"
J
Jeremy Fitzhardinge 已提交
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
#include "debugfs.h"

#define MMU_UPDATE_HISTO	30

#ifdef CONFIG_XEN_DEBUG_FS

static struct {
	u32 pgd_update;
	u32 pgd_update_pinned;
	u32 pgd_update_batched;

	u32 pud_update;
	u32 pud_update_pinned;
	u32 pud_update_batched;

	u32 pmd_update;
	u32 pmd_update_pinned;
	u32 pmd_update_batched;

	u32 pte_update;
	u32 pte_update_pinned;
	u32 pte_update_batched;

	u32 mmu_update;
	u32 mmu_update_extended;
	u32 mmu_update_histo[MMU_UPDATE_HISTO];

	u32 prot_commit;
	u32 prot_commit_batched;

	u32 set_pte_at;
	u32 set_pte_at_batched;
	u32 set_pte_at_pinned;
	u32 set_pte_at_current;
	u32 set_pte_at_kernel;
} mmu_stats;

static u8 zero_stats;

static inline void check_zero(void)
{
	if (unlikely(zero_stats)) {
		memset(&mmu_stats, 0, sizeof(mmu_stats));
		zero_stats = 0;
	}
}

#define ADD_STATS(elem, val)			\
	do { check_zero(); mmu_stats.elem += (val); } while(0)

#else  /* !CONFIG_XEN_DEBUG_FS */

#define ADD_STATS(elem, val)	do { (void)(val); } while(0)

#endif /* CONFIG_XEN_DEBUG_FS */
J
Jeremy Fitzhardinge 已提交
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

/*
 * Identity map, in addition to plain kernel map.  This needs to be
 * large enough to allocate page table pages to allocate the rest.
 * Each page can map 2MB.
 */
static pte_t level1_ident_pgt[PTRS_PER_PTE * 4] __page_aligned_bss;

#ifdef CONFIG_X86_64
/* l3 pud for userspace vsyscall mapping */
static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
#endif /* CONFIG_X86_64 */

/*
 * Note about cr3 (pagetable base) values:
 *
 * xen_cr3 contains the current logical cr3 value; it contains the
 * last set cr3.  This may not be the current effective cr3, because
 * its update may be being lazily deferred.  However, a vcpu looking
 * at its own cr3 can use this value knowing that it everything will
 * be self-consistent.
 *
 * xen_current_cr3 contains the actual vcpu cr3; it is set once the
 * hypercall to set the vcpu cr3 is complete (so it may be a little
 * out of date, but it will never be set early).  If one vcpu is
 * looking at another vcpu's cr3 value, it should use this variable.
 */
DEFINE_PER_CPU(unsigned long, xen_cr3);	 /* cr3 stored as physaddr */
DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */


152 153 154 155 156 157 158
/*
 * Just beyond the highest usermode address.  STACK_TOP_MAX has a
 * redzone above it, so round it up to a PGD boundary.
 */
#define USER_LIMIT	((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)


159
#define P2M_ENTRIES_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long))
160
#define TOP_ENTRIES		(MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE)
161

162
/* Placeholder for holes in the address space */
163
static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE] __page_aligned_data =
164 165 166
		{ [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL };

 /* Array of pointers to pages containing p2m entries */
167
static unsigned long *p2m_top[TOP_ENTRIES] __page_aligned_data =
168
		{ [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
169

J
Jeremy Fitzhardinge 已提交
170
/* Arrays of p2m arrays expressed in mfns used for save/restore */
171
static unsigned long p2m_top_mfn[TOP_ENTRIES] __page_aligned_bss;
J
Jeremy Fitzhardinge 已提交
172

173 174
static unsigned long p2m_top_mfn_list[TOP_ENTRIES / P2M_ENTRIES_PER_PAGE]
	__page_aligned_bss;
J
Jeremy Fitzhardinge 已提交
175

176 177
static inline unsigned p2m_top_index(unsigned long pfn)
{
178
	BUG_ON(pfn >= MAX_DOMAIN_PAGES);
179 180 181 182 183 184 185 186
	return pfn / P2M_ENTRIES_PER_PAGE;
}

static inline unsigned p2m_index(unsigned long pfn)
{
	return pfn % P2M_ENTRIES_PER_PAGE;
}

J
Jeremy Fitzhardinge 已提交
187
/* Build the parallel p2m_top_mfn structures */
188
static void __init xen_build_mfn_list_list(void)
J
Jeremy Fitzhardinge 已提交
189 190 191
{
	unsigned pfn, idx;

T
Tej 已提交
192
	for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
J
Jeremy Fitzhardinge 已提交
193 194 195 196 197
		unsigned topidx = p2m_top_index(pfn);

		p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
	}

T
Tej 已提交
198
	for (idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
J
Jeremy Fitzhardinge 已提交
199 200 201
		unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
		p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
	}
202
}
J
Jeremy Fitzhardinge 已提交
203

204 205
void xen_setup_mfn_list_list(void)
{
J
Jeremy Fitzhardinge 已提交
206 207 208 209 210 211 212 213
	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);

	HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
		virt_to_mfn(p2m_top_mfn_list);
	HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages;
}

/* Set up p2m_top to point to the domain-builder provided p2m pages */
214 215 216
void __init xen_build_dynamic_phys_to_machine(void)
{
	unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
217
	unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
J
Jeremy Fitzhardinge 已提交
218
	unsigned pfn;
219

T
Tej 已提交
220
	for (pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
221 222 223 224
		unsigned topidx = p2m_top_index(pfn);

		p2m_top[topidx] = &mfn_list[pfn];
	}
225 226

	xen_build_mfn_list_list();
227 228 229 230 231 232
}

unsigned long get_phys_to_machine(unsigned long pfn)
{
	unsigned topidx, idx;

233 234 235
	if (unlikely(pfn >= MAX_DOMAIN_PAGES))
		return INVALID_P2M_ENTRY;

236 237 238 239
	topidx = p2m_top_index(pfn);
	idx = p2m_index(pfn);
	return p2m_top[topidx][idx];
}
I
Ingo Molnar 已提交
240
EXPORT_SYMBOL_GPL(get_phys_to_machine);
241

242 243
/* install a  new p2m_top page */
bool install_p2mtop_page(unsigned long pfn, unsigned long *p)
244
{
245 246
	unsigned topidx = p2m_top_index(pfn);
	unsigned long **pfnp, *mfnp;
247 248
	unsigned i;

249 250
	pfnp = &p2m_top[topidx];
	mfnp = &p2m_top_mfn[topidx];
251

T
Tej 已提交
252
	for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
253 254
		p[i] = INVALID_P2M_ENTRY;

255
	if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) {
J
Jeremy Fitzhardinge 已提交
256
		*mfnp = virt_to_mfn(p);
257 258 259 260
		return true;
	}

	return false;
261 262
}

263
static void alloc_p2m(unsigned long pfn)
264
{
265
	unsigned long *p;
266

267 268 269 270 271 272 273 274 275 276 277
	p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
	BUG_ON(p == NULL);

	if (!install_p2mtop_page(pfn, p))
		free_page((unsigned long)p);
}

/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	unsigned topidx, idx;
278 279 280

	if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
		BUG_ON(mfn != INVALID_P2M_ENTRY);
281
		return true;
282 283 284
	}

	topidx = p2m_top_index(pfn);
285
	if (p2m_top[topidx] == p2m_missing) {
286
		if (mfn == INVALID_P2M_ENTRY)
287 288
			return true;
		return false;
289 290 291 292
	}

	idx = p2m_index(pfn);
	p2m_top[topidx][idx] = mfn;
293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309

	return true;
}

void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
		return;
	}

	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
		alloc_p2m(pfn);

		if (!__set_phys_to_machine(pfn, mfn))
			BUG();
	}
310 311
}

312 313 314 315 316 317 318
unsigned long arbitrary_virt_to_mfn(void *vaddr)
{
	xmaddr_t maddr = arbitrary_virt_to_machine(vaddr);

	return PFN_DOWN(maddr.maddr);
}

319
xmaddr_t arbitrary_virt_to_machine(void *vaddr)
J
Jeremy Fitzhardinge 已提交
320
{
321
	unsigned long address = (unsigned long)vaddr;
322
	unsigned int level;
323 324
	pte_t *pte;
	unsigned offset;
J
Jeremy Fitzhardinge 已提交
325

326 327 328 329 330 331 332 333
	/*
	 * if the PFN is in the linear mapped vaddr range, we can just use
	 * the (quick) virt_to_machine() p2m lookup
	 */
	if (virt_addr_valid(vaddr))
		return virt_to_machine(vaddr);

	/* otherwise we have to do a (slower) full page-table walk */
J
Jeremy Fitzhardinge 已提交
334

335 336 337
	pte = lookup_address(address, &level);
	BUG_ON(pte == NULL);
	offset = address & ~PAGE_MASK;
338
	return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset);
J
Jeremy Fitzhardinge 已提交
339 340 341 342 343 344
}

void make_lowmem_page_readonly(void *vaddr)
{
	pte_t *pte, ptev;
	unsigned long address = (unsigned long)vaddr;
345
	unsigned int level;
J
Jeremy Fitzhardinge 已提交
346

347
	pte = lookup_address(address, &level);
J
Jeremy Fitzhardinge 已提交
348 349 350 351 352 353 354 355 356 357 358 359
	BUG_ON(pte == NULL);

	ptev = pte_wrprotect(*pte);

	if (HYPERVISOR_update_va_mapping(address, ptev, 0))
		BUG();
}

void make_lowmem_page_readwrite(void *vaddr)
{
	pte_t *pte, ptev;
	unsigned long address = (unsigned long)vaddr;
360
	unsigned int level;
J
Jeremy Fitzhardinge 已提交
361

362
	pte = lookup_address(address, &level);
J
Jeremy Fitzhardinge 已提交
363 364 365 366 367 368 369 370 371
	BUG_ON(pte == NULL);

	ptev = pte_mkwrite(*pte);

	if (HYPERVISOR_update_va_mapping(address, ptev, 0))
		BUG();
}


372
static bool xen_page_pinned(void *ptr)
373 374 375 376 377 378
{
	struct page *page = virt_to_page(ptr);

	return PagePinned(page);
}

379
static void xen_extend_mmu_update(const struct mmu_update *update)
J
Jeremy Fitzhardinge 已提交
380
{
J
Jeremy Fitzhardinge 已提交
381 382
	struct multicall_space mcs;
	struct mmu_update *u;
J
Jeremy Fitzhardinge 已提交
383

384 385
	mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));

J
Jeremy Fitzhardinge 已提交
386 387 388 389
	if (mcs.mc != NULL) {
		ADD_STATS(mmu_update_extended, 1);
		ADD_STATS(mmu_update_histo[mcs.mc->args[1]], -1);

390
		mcs.mc->args[1]++;
J
Jeremy Fitzhardinge 已提交
391 392 393 394 395 396 397

		if (mcs.mc->args[1] < MMU_UPDATE_HISTO)
			ADD_STATS(mmu_update_histo[mcs.mc->args[1]], 1);
		else
			ADD_STATS(mmu_update_histo[0], 1);
	} else {
		ADD_STATS(mmu_update, 1);
398 399
		mcs = __xen_mc_entry(sizeof(*u));
		MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
J
Jeremy Fitzhardinge 已提交
400
		ADD_STATS(mmu_update_histo[1], 1);
401
	}
J
Jeremy Fitzhardinge 已提交
402 403

	u = mcs.args;
404 405 406 407 408 409 410 411 412 413 414
	*u = *update;
}

void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
{
	struct mmu_update u;

	preempt_disable();

	xen_mc_batch();

415 416
	/* ptr may be ioremapped for 64-bit pagetable setup */
	u.ptr = arbitrary_virt_to_machine(ptr).maddr;
417
	u.val = pmd_val_ma(val);
418
	xen_extend_mmu_update(&u);
J
Jeremy Fitzhardinge 已提交
419

J
Jeremy Fitzhardinge 已提交
420 421
	ADD_STATS(pmd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);

J
Jeremy Fitzhardinge 已提交
422 423 424
	xen_mc_issue(PARAVIRT_LAZY_MMU);

	preempt_enable();
J
Jeremy Fitzhardinge 已提交
425 426
}

427 428
void xen_set_pmd(pmd_t *ptr, pmd_t val)
{
J
Jeremy Fitzhardinge 已提交
429 430
	ADD_STATS(pmd_update, 1);

431 432
	/* If page is not pinned, we can just update the entry
	   directly */
433
	if (!xen_page_pinned(ptr)) {
434 435 436 437
		*ptr = val;
		return;
	}

J
Jeremy Fitzhardinge 已提交
438 439
	ADD_STATS(pmd_update_pinned, 1);

440 441 442
	xen_set_pmd_hyper(ptr, val);
}

J
Jeremy Fitzhardinge 已提交
443 444 445 446 447 448
/*
 * Associate a virtual page frame with a given physical page frame
 * and protection flags for that frame.
 */
void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
{
J
Jeremy Fitzhardinge 已提交
449
	set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
J
Jeremy Fitzhardinge 已提交
450 451 452 453 454
}

void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
		    pte_t *ptep, pte_t pteval)
{
J
Jeremy Fitzhardinge 已提交
455 456 457 458 459
	ADD_STATS(set_pte_at, 1);
//	ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
	ADD_STATS(set_pte_at_current, mm == current->mm);
	ADD_STATS(set_pte_at_kernel, mm == &init_mm);

J
Jeremy Fitzhardinge 已提交
460
	if (mm == current->mm || mm == &init_mm) {
461
		if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
J
Jeremy Fitzhardinge 已提交
462 463 464 465
			struct multicall_space mcs;
			mcs = xen_mc_entry(0);

			MULTI_update_va_mapping(mcs.mc, addr, pteval, 0);
J
Jeremy Fitzhardinge 已提交
466
			ADD_STATS(set_pte_at_batched, 1);
J
Jeremy Fitzhardinge 已提交
467
			xen_mc_issue(PARAVIRT_LAZY_MMU);
468
			goto out;
J
Jeremy Fitzhardinge 已提交
469 470
		} else
			if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0)
471
				goto out;
J
Jeremy Fitzhardinge 已提交
472 473
	}
	xen_set_pte(ptep, pteval);
474

475
out:	return;
J
Jeremy Fitzhardinge 已提交
476 477
}

T
Tej 已提交
478 479
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
				 unsigned long addr, pte_t *ptep)
J
Jeremy Fitzhardinge 已提交
480
{
481 482 483 484 485 486 487
	/* Just return the pte as-is.  We preserve the bits on commit */
	return *ptep;
}

void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
				 pte_t *ptep, pte_t pte)
{
488
	struct mmu_update u;
489

490
	xen_mc_batch();
J
Jeremy Fitzhardinge 已提交
491

492
	u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
493
	u.val = pte_val_ma(pte);
494
	xen_extend_mmu_update(&u);
J
Jeremy Fitzhardinge 已提交
495

J
Jeremy Fitzhardinge 已提交
496 497 498
	ADD_STATS(prot_commit, 1);
	ADD_STATS(prot_commit_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);

499
	xen_mc_issue(PARAVIRT_LAZY_MMU);
J
Jeremy Fitzhardinge 已提交
500 501
}

J
Jeremy Fitzhardinge 已提交
502 503
/* Assume pteval_t is equivalent to all the other *val_t types. */
static pteval_t pte_mfn_to_pfn(pteval_t val)
J
Jeremy Fitzhardinge 已提交
504
{
J
Jeremy Fitzhardinge 已提交
505
	if (val & _PAGE_PRESENT) {
506
		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
J
Jeremy Fitzhardinge 已提交
507
		pteval_t flags = val & PTE_FLAGS_MASK;
508
		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
J
Jeremy Fitzhardinge 已提交
509
	}
J
Jeremy Fitzhardinge 已提交
510

J
Jeremy Fitzhardinge 已提交
511
	return val;
J
Jeremy Fitzhardinge 已提交
512 513
}

J
Jeremy Fitzhardinge 已提交
514
static pteval_t pte_pfn_to_mfn(pteval_t val)
J
Jeremy Fitzhardinge 已提交
515
{
J
Jeremy Fitzhardinge 已提交
516
	if (val & _PAGE_PRESENT) {
517
		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
J
Jeremy Fitzhardinge 已提交
518
		pteval_t flags = val & PTE_FLAGS_MASK;
519
		val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
J
Jeremy Fitzhardinge 已提交
520 521
	}

J
Jeremy Fitzhardinge 已提交
522
	return val;
J
Jeremy Fitzhardinge 已提交
523 524
}

J
Jeremy Fitzhardinge 已提交
525
pteval_t xen_pte_val(pte_t pte)
J
Jeremy Fitzhardinge 已提交
526
{
J
Jeremy Fitzhardinge 已提交
527
	return pte_mfn_to_pfn(pte.pte);
J
Jeremy Fitzhardinge 已提交
528
}
529
PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val);
J
Jeremy Fitzhardinge 已提交
530 531 532

pgdval_t xen_pgd_val(pgd_t pgd)
{
J
Jeremy Fitzhardinge 已提交
533
	return pte_mfn_to_pfn(pgd.pgd);
J
Jeremy Fitzhardinge 已提交
534
}
535
PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
J
Jeremy Fitzhardinge 已提交
536 537 538

pte_t xen_make_pte(pteval_t pte)
{
J
Jeremy Fitzhardinge 已提交
539 540
	pte = pte_pfn_to_mfn(pte);
	return native_make_pte(pte);
J
Jeremy Fitzhardinge 已提交
541
}
542
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
J
Jeremy Fitzhardinge 已提交
543 544 545

pgd_t xen_make_pgd(pgdval_t pgd)
{
J
Jeremy Fitzhardinge 已提交
546 547
	pgd = pte_pfn_to_mfn(pgd);
	return native_make_pgd(pgd);
J
Jeremy Fitzhardinge 已提交
548
}
549
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pgd);
J
Jeremy Fitzhardinge 已提交
550 551 552

pmdval_t xen_pmd_val(pmd_t pmd)
{
J
Jeremy Fitzhardinge 已提交
553
	return pte_mfn_to_pfn(pmd.pmd);
J
Jeremy Fitzhardinge 已提交
554
}
555
PV_CALLEE_SAVE_REGS_THUNK(xen_pmd_val);
556

557
void xen_set_pud_hyper(pud_t *ptr, pud_t val)
558
{
559
	struct mmu_update u;
560

J
Jeremy Fitzhardinge 已提交
561 562
	preempt_disable();

563 564
	xen_mc_batch();

565 566
	/* ptr may be ioremapped for 64-bit pagetable setup */
	u.ptr = arbitrary_virt_to_machine(ptr).maddr;
567
	u.val = pud_val_ma(val);
568
	xen_extend_mmu_update(&u);
J
Jeremy Fitzhardinge 已提交
569

J
Jeremy Fitzhardinge 已提交
570 571
	ADD_STATS(pud_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);

J
Jeremy Fitzhardinge 已提交
572 573 574
	xen_mc_issue(PARAVIRT_LAZY_MMU);

	preempt_enable();
575 576
}

577 578
void xen_set_pud(pud_t *ptr, pud_t val)
{
J
Jeremy Fitzhardinge 已提交
579 580
	ADD_STATS(pud_update, 1);

581 582
	/* If page is not pinned, we can just update the entry
	   directly */
583
	if (!xen_page_pinned(ptr)) {
584 585 586 587
		*ptr = val;
		return;
	}

J
Jeremy Fitzhardinge 已提交
588 589
	ADD_STATS(pud_update_pinned, 1);

590 591 592
	xen_set_pud_hyper(ptr, val);
}

593 594
void xen_set_pte(pte_t *ptep, pte_t pte)
{
J
Jeremy Fitzhardinge 已提交
595 596 597 598
	ADD_STATS(pte_update, 1);
//	ADD_STATS(pte_update_pinned, xen_page_pinned(ptep));
	ADD_STATS(pte_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);

599
#ifdef CONFIG_X86_PAE
600 601 602
	ptep->pte_high = pte.pte_high;
	smp_wmb();
	ptep->pte_low = pte.pte_low;
603 604 605
#else
	*ptep = pte;
#endif
606 607
}

608
#ifdef CONFIG_X86_PAE
J
Jeremy Fitzhardinge 已提交
609 610
void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
{
611
	set_64bit((u64 *)ptep, native_pte_val(pte));
J
Jeremy Fitzhardinge 已提交
612 613 614 615 616 617 618 619 620 621 622
}

void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
	ptep->pte_low = 0;
	smp_wmb();		/* make sure low gets written first */
	ptep->pte_high = 0;
}

void xen_pmd_clear(pmd_t *pmdp)
{
623
	set_pmd(pmdp, __pmd(0));
J
Jeremy Fitzhardinge 已提交
624
}
625
#endif	/* CONFIG_X86_PAE */
J
Jeremy Fitzhardinge 已提交
626

627
pmd_t xen_make_pmd(pmdval_t pmd)
J
Jeremy Fitzhardinge 已提交
628
{
J
Jeremy Fitzhardinge 已提交
629
	pmd = pte_pfn_to_mfn(pmd);
J
Jeremy Fitzhardinge 已提交
630
	return native_make_pmd(pmd);
J
Jeremy Fitzhardinge 已提交
631
}
632
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd);
J
Jeremy Fitzhardinge 已提交
633

634 635 636 637 638
#if PAGETABLE_LEVELS == 4
pudval_t xen_pud_val(pud_t pud)
{
	return pte_mfn_to_pfn(pud.pud);
}
639
PV_CALLEE_SAVE_REGS_THUNK(xen_pud_val);
640 641 642 643 644 645 646

pud_t xen_make_pud(pudval_t pud)
{
	pud = pte_pfn_to_mfn(pud);

	return native_make_pud(pud);
}
647
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pud);
648

649
pgd_t *xen_get_user_pgd(pgd_t *pgd)
650
{
651 652 653
	pgd_t *pgd_page = (pgd_t *)(((unsigned long)pgd) & PAGE_MASK);
	unsigned offset = pgd - pgd_page;
	pgd_t *user_ptr = NULL;
654

655 656 657 658 659 660
	if (offset < pgd_index(USER_LIMIT)) {
		struct page *page = virt_to_page(pgd_page);
		user_ptr = (pgd_t *)page->private;
		if (user_ptr)
			user_ptr += offset;
	}
661

662 663 664 665 666 667
	return user_ptr;
}

static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
{
	struct mmu_update u;
668 669 670

	u.ptr = virt_to_machine(ptr).maddr;
	u.val = pgd_val_ma(val);
671
	xen_extend_mmu_update(&u);
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
}

/*
 * Raw hypercall-based set_pgd, intended for in early boot before
 * there's a page structure.  This implies:
 *  1. The only existing pagetable is the kernel's
 *  2. It is always pinned
 *  3. It has no user pagetable attached to it
 */
void __init xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
{
	preempt_disable();

	xen_mc_batch();

	__xen_set_pgd_hyper(ptr, val);
688 689 690 691 692 693 694 695

	xen_mc_issue(PARAVIRT_LAZY_MMU);

	preempt_enable();
}

void xen_set_pgd(pgd_t *ptr, pgd_t val)
{
696 697
	pgd_t *user_ptr = xen_get_user_pgd(ptr);

J
Jeremy Fitzhardinge 已提交
698 699
	ADD_STATS(pgd_update, 1);

700 701
	/* If page is not pinned, we can just update the entry
	   directly */
702
	if (!xen_page_pinned(ptr)) {
703
		*ptr = val;
704
		if (user_ptr) {
705
			WARN_ON(xen_page_pinned(user_ptr));
706 707
			*user_ptr = val;
		}
708 709 710
		return;
	}

J
Jeremy Fitzhardinge 已提交
711 712 713
	ADD_STATS(pgd_update_pinned, 1);
	ADD_STATS(pgd_update_batched, paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU);

714 715 716 717 718 719 720 721 722
	/* If it's pinned, then we can at least batch the kernel and
	   user updates together. */
	xen_mc_batch();

	__xen_set_pgd_hyper(ptr, val);
	if (user_ptr)
		__xen_set_pgd_hyper(user_ptr, val);

	xen_mc_issue(PARAVIRT_LAZY_MMU);
723 724 725
}
#endif	/* PAGETABLE_LEVELS == 4 */

726
/*
727 728 729 730 731 732 733 734 735 736 737 738 739 740
 * (Yet another) pagetable walker.  This one is intended for pinning a
 * pagetable.  This means that it walks a pagetable and calls the
 * callback function on each page it finds making up the page table,
 * at every level.  It walks the entire pagetable, but it only bothers
 * pinning pte pages which are below limit.  In the normal case this
 * will be STACK_TOP_MAX, but at boot we need to pin up to
 * FIXADDR_TOP.
 *
 * For 32-bit the important bit is that we don't pin beyond there,
 * because then we start getting into Xen's ptes.
 *
 * For 64-bit, we must skip the Xen hole in the middle of the address
 * space, just after the big x86-64 virtual hole.
 */
I
Ian Campbell 已提交
741 742 743 744
static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
			  int (*func)(struct mm_struct *mm, struct page *,
				      enum pt_level),
			  unsigned long limit)
J
Jeremy Fitzhardinge 已提交
745
{
746
	int flush = 0;
747 748 749
	unsigned hole_low, hole_high;
	unsigned pgdidx_limit, pudidx_limit, pmdidx_limit;
	unsigned pgdidx, pudidx, pmdidx;
750

751 752 753
	/* The limit is the last byte to be touched */
	limit--;
	BUG_ON(limit >= FIXADDR_TOP);
J
Jeremy Fitzhardinge 已提交
754 755

	if (xen_feature(XENFEAT_auto_translated_physmap))
756 757
		return 0;

758 759 760 761 762
	/*
	 * 64-bit has a great big hole in the middle of the address
	 * space, which contains the Xen mappings.  On 32-bit these
	 * will end up making a zero-sized hole and so is a no-op.
	 */
763
	hole_low = pgd_index(USER_LIMIT);
764 765 766 767 768 769 770 771 772 773 774 775 776 777 778
	hole_high = pgd_index(PAGE_OFFSET);

	pgdidx_limit = pgd_index(limit);
#if PTRS_PER_PUD > 1
	pudidx_limit = pud_index(limit);
#else
	pudidx_limit = 0;
#endif
#if PTRS_PER_PMD > 1
	pmdidx_limit = pmd_index(limit);
#else
	pmdidx_limit = 0;
#endif

	for (pgdidx = 0; pgdidx <= pgdidx_limit; pgdidx++) {
779
		pud_t *pud;
J
Jeremy Fitzhardinge 已提交
780

781 782
		if (pgdidx >= hole_low && pgdidx < hole_high)
			continue;
783

784
		if (!pgd_val(pgd[pgdidx]))
J
Jeremy Fitzhardinge 已提交
785
			continue;
786

787
		pud = pud_offset(&pgd[pgdidx], 0);
J
Jeremy Fitzhardinge 已提交
788 789

		if (PTRS_PER_PUD > 1) /* not folded */
790
			flush |= (*func)(mm, virt_to_page(pud), PT_PUD);
791

792
		for (pudidx = 0; pudidx < PTRS_PER_PUD; pudidx++) {
793 794
			pmd_t *pmd;

795 796 797
			if (pgdidx == pgdidx_limit &&
			    pudidx > pudidx_limit)
				goto out;
J
Jeremy Fitzhardinge 已提交
798

799
			if (pud_none(pud[pudidx]))
J
Jeremy Fitzhardinge 已提交
800
				continue;
801

802
			pmd = pmd_offset(&pud[pudidx], 0);
J
Jeremy Fitzhardinge 已提交
803 804

			if (PTRS_PER_PMD > 1) /* not folded */
805
				flush |= (*func)(mm, virt_to_page(pmd), PT_PMD);
806

807 808 809 810 811 812 813
			for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) {
				struct page *pte;

				if (pgdidx == pgdidx_limit &&
				    pudidx == pudidx_limit &&
				    pmdidx > pmdidx_limit)
					goto out;
J
Jeremy Fitzhardinge 已提交
814

815
				if (pmd_none(pmd[pmdidx]))
J
Jeremy Fitzhardinge 已提交
816 817
					continue;

818
				pte = pmd_page(pmd[pmdidx]);
819
				flush |= (*func)(mm, pte, PT_PTE);
J
Jeremy Fitzhardinge 已提交
820 821 822
			}
		}
	}
823

824
out:
825 826
	/* Do the top level last, so that the callbacks can use it as
	   a cue to do final things like tlb flushes. */
827
	flush |= (*func)(mm, virt_to_page(pgd), PT_PGD);
828 829

	return flush;
J
Jeremy Fitzhardinge 已提交
830 831
}

I
Ian Campbell 已提交
832 833 834 835 836 837 838 839
static int xen_pgd_walk(struct mm_struct *mm,
			int (*func)(struct mm_struct *mm, struct page *,
				    enum pt_level),
			unsigned long limit)
{
	return __xen_pgd_walk(mm, mm->pgd, func, limit);
}

840 841
/* If we're using split pte locks, then take the page's lock and
   return a pointer to it.  Otherwise return NULL. */
842
static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm)
843 844 845
{
	spinlock_t *ptl = NULL;

846
#if USE_SPLIT_PTLOCKS
847
	ptl = __pte_lockptr(page);
848
	spin_lock_nest_lock(ptl, &mm->page_table_lock);
849 850 851 852 853
#endif

	return ptl;
}

854
static void xen_pte_unlock(void *v)
855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871
{
	spinlock_t *ptl = v;
	spin_unlock(ptl);
}

static void xen_do_pin(unsigned level, unsigned long pfn)
{
	struct mmuext_op *op;
	struct multicall_space mcs;

	mcs = __xen_mc_entry(sizeof(*op));
	op = mcs.args;
	op->cmd = level;
	op->arg1.mfn = pfn_to_mfn(pfn);
	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
}

872 873
static int xen_pin_page(struct mm_struct *mm, struct page *page,
			enum pt_level level)
874
{
875
	unsigned pgfl = TestSetPagePinned(page);
876 877 878 879 880 881 882 883 884 885 886 887
	int flush;

	if (pgfl)
		flush = 0;		/* already pinned */
	else if (PageHighMem(page))
		/* kmaps need flushing if we found an unpinned
		   highpage */
		flush = 1;
	else {
		void *pt = lowmem_page_address(page);
		unsigned long pfn = page_to_pfn(page);
		struct multicall_space mcs = __xen_mc_entry(0);
888
		spinlock_t *ptl;
889 890 891

		flush = 0;

892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911
		/*
		 * We need to hold the pagetable lock between the time
		 * we make the pagetable RO and when we actually pin
		 * it.  If we don't, then other users may come in and
		 * attempt to update the pagetable by writing it,
		 * which will fail because the memory is RO but not
		 * pinned, so Xen won't do the trap'n'emulate.
		 *
		 * If we're using split pte locks, we can't hold the
		 * entire pagetable's worth of locks during the
		 * traverse, because we may wrap the preempt count (8
		 * bits).  The solution is to mark RO and pin each PTE
		 * page while holding the lock.  This means the number
		 * of locks we end up holding is never more than a
		 * batch size (~32 entries, at present).
		 *
		 * If we're not using split pte locks, we needn't pin
		 * the PTE pages independently, because we're
		 * protected by the overall pagetable lock.
		 */
912 913
		ptl = NULL;
		if (level == PT_PTE)
914
			ptl = xen_pte_lock(page, mm);
915

916 917
		MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
					pfn_pte(pfn, PAGE_KERNEL_RO),
918 919
					level == PT_PGD ? UVMF_TLB_FLUSH : 0);

920
		if (ptl) {
921 922 923 924
			xen_do_pin(MMUEXT_PIN_L1_TABLE, pfn);

			/* Queue a deferred unlock for when this batch
			   is completed. */
925
			xen_mc_callback(xen_pte_unlock, ptl);
926
		}
927 928 929 930
	}

	return flush;
}
J
Jeremy Fitzhardinge 已提交
931

932 933 934
/* This is called just after a mm has been created, but it has not
   been used yet.  We need to make sure that its pagetable is all
   read-only, and can be pinned. */
935
static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
J
Jeremy Fitzhardinge 已提交
936
{
937 938
	vm_unmap_aliases();

939
	xen_mc_batch();
J
Jeremy Fitzhardinge 已提交
940

I
Ian Campbell 已提交
941
	if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) {
942
		/* re-enable interrupts for flushing */
J
Jeremy Fitzhardinge 已提交
943
		xen_mc_issue(0);
944

945
		kmap_flush_unused();
946

J
Jeremy Fitzhardinge 已提交
947 948
		xen_mc_batch();
	}
949

950 951 952 953 954 955 956
#ifdef CONFIG_X86_64
	{
		pgd_t *user_pgd = xen_get_user_pgd(pgd);

		xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd)));

		if (user_pgd) {
957
			xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD);
T
Tej 已提交
958 959
			xen_do_pin(MMUEXT_PIN_L4_TABLE,
				   PFN_DOWN(__pa(user_pgd)));
960 961 962
		}
	}
#else /* CONFIG_X86_32 */
963 964
#ifdef CONFIG_X86_PAE
	/* Need to make sure unshared kernel PMD is pinnable */
965
	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
966
		     PT_PMD);
967
#endif
968
	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
969
#endif /* CONFIG_X86_64 */
970
	xen_mc_issue(0);
J
Jeremy Fitzhardinge 已提交
971 972
}

973 974 975 976 977
static void xen_pgd_pin(struct mm_struct *mm)
{
	__xen_pgd_pin(mm, mm->pgd);
}

978 979 980 981 982
/*
 * On save, we need to pin all pagetables to make sure they get their
 * mfns turned into pfns.  Search the list for any unpinned pgds and pin
 * them (unpinned pgds are not currently in use, probably because the
 * process is under construction or destruction).
983 984 985 986
 *
 * Expected to be called in stop_machine() ("equivalent to taking
 * every spinlock in the system"), so the locking doesn't really
 * matter all that much.
987 988 989 990 991
 */
void xen_mm_pin_all(void)
{
	unsigned long flags;
	struct page *page;
992

993
	spin_lock_irqsave(&pgd_lock, flags);
994

995 996
	list_for_each_entry(page, &pgd_list, lru) {
		if (!PagePinned(page)) {
997
			__xen_pgd_pin(&init_mm, (pgd_t *)page_address(page));
998 999 1000 1001 1002
			SetPageSavePinned(page);
		}
	}

	spin_unlock_irqrestore(&pgd_lock, flags);
J
Jeremy Fitzhardinge 已提交
1003 1004
}

1005 1006 1007 1008 1009
/*
 * The init_mm pagetable is really pinned as soon as its created, but
 * that's before we have page structures to store the bits.  So do all
 * the book-keeping now.
 */
1010 1011
static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page,
				  enum pt_level level)
J
Jeremy Fitzhardinge 已提交
1012
{
1013 1014 1015
	SetPagePinned(page);
	return 0;
}
J
Jeremy Fitzhardinge 已提交
1016

1017
static void __init xen_mark_init_mm_pinned(void)
1018
{
1019
	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
1020
}
J
Jeremy Fitzhardinge 已提交
1021

1022 1023
static int xen_unpin_page(struct mm_struct *mm, struct page *page,
			  enum pt_level level)
1024
{
1025
	unsigned pgfl = TestClearPagePinned(page);
J
Jeremy Fitzhardinge 已提交
1026

1027 1028 1029
	if (pgfl && !PageHighMem(page)) {
		void *pt = lowmem_page_address(page);
		unsigned long pfn = page_to_pfn(page);
1030 1031 1032
		spinlock_t *ptl = NULL;
		struct multicall_space mcs;

1033 1034 1035 1036 1037 1038 1039
		/*
		 * Do the converse to pin_page.  If we're using split
		 * pte locks, we must be holding the lock for while
		 * the pte page is unpinned but still RO to prevent
		 * concurrent updates from seeing it in this
		 * partially-pinned state.
		 */
1040
		if (level == PT_PTE) {
1041
			ptl = xen_pte_lock(page, mm);
1042

1043 1044
			if (ptl)
				xen_do_pin(MMUEXT_UNPIN_TABLE, pfn);
1045 1046 1047
		}

		mcs = __xen_mc_entry(0);
1048 1049 1050

		MULTI_update_va_mapping(mcs.mc, (unsigned long)pt,
					pfn_pte(pfn, PAGE_KERNEL),
1051 1052 1053 1054
					level == PT_PGD ? UVMF_TLB_FLUSH : 0);

		if (ptl) {
			/* unlock when batch completed */
1055
			xen_mc_callback(xen_pte_unlock, ptl);
1056
		}
1057 1058 1059
	}

	return 0;		/* never need to flush on unpin */
J
Jeremy Fitzhardinge 已提交
1060 1061
}

1062
/* Release a pagetables pages back as normal RW */
1063
static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
1064 1065 1066
{
	xen_mc_batch();

1067
	xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
1068

1069 1070 1071 1072 1073
#ifdef CONFIG_X86_64
	{
		pgd_t *user_pgd = xen_get_user_pgd(pgd);

		if (user_pgd) {
T
Tej 已提交
1074 1075
			xen_do_pin(MMUEXT_UNPIN_TABLE,
				   PFN_DOWN(__pa(user_pgd)));
1076
			xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD);
1077 1078 1079 1080
		}
	}
#endif

1081 1082
#ifdef CONFIG_X86_PAE
	/* Need to make sure unshared kernel PMD is unpinned */
1083
	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
1084
		       PT_PMD);
1085
#endif
1086

I
Ian Campbell 已提交
1087
	__xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT);
1088 1089 1090

	xen_mc_issue(0);
}
J
Jeremy Fitzhardinge 已提交
1091

1092 1093 1094 1095 1096
static void xen_pgd_unpin(struct mm_struct *mm)
{
	__xen_pgd_unpin(mm, mm->pgd);
}

1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110
/*
 * On resume, undo any pinning done at save, so that the rest of the
 * kernel doesn't see any unexpected pinned pagetables.
 */
void xen_mm_unpin_all(void)
{
	unsigned long flags;
	struct page *page;

	spin_lock_irqsave(&pgd_lock, flags);

	list_for_each_entry(page, &pgd_list, lru) {
		if (PageSavePinned(page)) {
			BUG_ON(!PagePinned(page));
1111
			__xen_pgd_unpin(&init_mm, (pgd_t *)page_address(page));
1112 1113 1114 1115 1116 1117 1118
			ClearPageSavePinned(page);
		}
	}

	spin_unlock_irqrestore(&pgd_lock, flags);
}

J
Jeremy Fitzhardinge 已提交
1119 1120
void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
{
1121
	spin_lock(&next->page_table_lock);
1122
	xen_pgd_pin(next);
1123
	spin_unlock(&next->page_table_lock);
J
Jeremy Fitzhardinge 已提交
1124 1125 1126 1127
}

void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
{
1128
	spin_lock(&mm->page_table_lock);
1129
	xen_pgd_pin(mm);
1130
	spin_unlock(&mm->page_table_lock);
J
Jeremy Fitzhardinge 已提交
1131 1132 1133
}


J
Jeremy Fitzhardinge 已提交
1134 1135 1136 1137 1138 1139
#ifdef CONFIG_SMP
/* Another cpu may still have their %cr3 pointing at the pagetable, so
   we need to repoint it somewhere else before we can unpin it. */
static void drop_other_mm_ref(void *info)
{
	struct mm_struct *mm = info;
1140
	struct mm_struct *active_mm;
J
Jeremy Fitzhardinge 已提交
1141

1142
	active_mm = percpu_read(cpu_tlbstate.active_mm);
1143 1144

	if (active_mm == mm)
J
Jeremy Fitzhardinge 已提交
1145
		leave_mm(smp_processor_id());
1146 1147 1148

	/* If this cpu still has a stale cr3 reference, then make sure
	   it has been flushed. */
1149
	if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
1150
		load_cr3(swapper_pg_dir);
J
Jeremy Fitzhardinge 已提交
1151
}
J
Jeremy Fitzhardinge 已提交
1152

1153
static void xen_drop_mm_ref(struct mm_struct *mm)
J
Jeremy Fitzhardinge 已提交
1154
{
1155
	cpumask_var_t mask;
1156 1157
	unsigned cpu;

J
Jeremy Fitzhardinge 已提交
1158 1159 1160 1161 1162
	if (current->active_mm == mm) {
		if (current->mm == mm)
			load_cr3(swapper_pg_dir);
		else
			leave_mm(smp_processor_id());
1163 1164 1165
	}

	/* Get the "official" set of cpus referring to our pagetable. */
1166 1167
	if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) {
		for_each_online_cpu(cpu) {
1168
			if (!cpumask_test_cpu(cpu, mm_cpumask(mm))
1169 1170 1171 1172 1173 1174
			    && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd))
				continue;
			smp_call_function_single(cpu, drop_other_mm_ref, mm, 1);
		}
		return;
	}
1175
	cpumask_copy(mask, mm_cpumask(mm));
1176 1177 1178 1179 1180 1181 1182 1183

	/* It's possible that a vcpu may have a stale reference to our
	   cr3, because its in lazy mode, and it hasn't yet flushed
	   its set of pending hypercalls yet.  In this case, we can
	   look at its actual current cr3 value, and force it to flush
	   if needed. */
	for_each_online_cpu(cpu) {
		if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
1184
			cpumask_set_cpu(cpu, mask);
J
Jeremy Fitzhardinge 已提交
1185 1186
	}

1187 1188 1189
	if (!cpumask_empty(mask))
		smp_call_function_many(mask, drop_other_mm_ref, mm, 1);
	free_cpumask_var(mask);
J
Jeremy Fitzhardinge 已提交
1190 1191
}
#else
1192
static void xen_drop_mm_ref(struct mm_struct *mm)
J
Jeremy Fitzhardinge 已提交
1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215
{
	if (current->active_mm == mm)
		load_cr3(swapper_pg_dir);
}
#endif

/*
 * While a process runs, Xen pins its pagetables, which means that the
 * hypervisor forces it to be read-only, and it controls all updates
 * to it.  This means that all pagetable updates have to go via the
 * hypervisor, which is moderately expensive.
 *
 * Since we're pulling the pagetable down, we switch to use init_mm,
 * unpin old process pagetable and mark it all read-write, which
 * allows further operations on it to be simple memory accesses.
 *
 * The only subtle point is that another CPU may be still using the
 * pagetable because of lazy tlb flushing.  This means we need need to
 * switch all CPUs off this pagetable before we can unpin it.
 */
void xen_exit_mmap(struct mm_struct *mm)
{
	get_cpu();		/* make sure we don't move around */
1216
	xen_drop_mm_ref(mm);
J
Jeremy Fitzhardinge 已提交
1217
	put_cpu();
J
Jeremy Fitzhardinge 已提交
1218

1219
	spin_lock(&mm->page_table_lock);
1220 1221

	/* pgd may not be pinned in the error exit path of execve */
1222
	if (xen_page_pinned(mm->pgd))
1223
		xen_pgd_unpin(mm);
1224

1225
	spin_unlock(&mm->page_table_lock);
J
Jeremy Fitzhardinge 已提交
1226
}
J
Jeremy Fitzhardinge 已提交
1227

1228 1229 1230 1231
static __init void xen_pagetable_setup_start(pgd_t *base)
{
}

1232 1233
static void xen_post_allocator_init(void);

1234 1235 1236
static __init void xen_pagetable_setup_done(pgd_t *base)
{
	xen_setup_shared_info();
1237
	xen_post_allocator_init();
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299
}

static void xen_write_cr2(unsigned long cr2)
{
	percpu_read(xen_vcpu)->arch.cr2 = cr2;
}

static unsigned long xen_read_cr2(void)
{
	return percpu_read(xen_vcpu)->arch.cr2;
}

unsigned long xen_read_cr2_direct(void)
{
	return percpu_read(xen_vcpu_info.arch.cr2);
}

static void xen_flush_tlb(void)
{
	struct mmuext_op *op;
	struct multicall_space mcs;

	preempt_disable();

	mcs = xen_mc_entry(sizeof(*op));

	op = mcs.args;
	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_MMU);

	preempt_enable();
}

static void xen_flush_tlb_single(unsigned long addr)
{
	struct mmuext_op *op;
	struct multicall_space mcs;

	preempt_disable();

	mcs = xen_mc_entry(sizeof(*op));
	op = mcs.args;
	op->cmd = MMUEXT_INVLPG_LOCAL;
	op->arg1.linear_addr = addr & PAGE_MASK;
	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_MMU);

	preempt_enable();
}

static void xen_flush_tlb_others(const struct cpumask *cpus,
				 struct mm_struct *mm, unsigned long va)
{
	struct {
		struct mmuext_op op;
		DECLARE_BITMAP(mask, NR_CPUS);
	} *args;
	struct multicall_space mcs;

1300 1301
	if (cpumask_empty(cpus))
		return;		/* nothing to do */
1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 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 1375 1376 1377 1378 1379 1380 1381 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

	mcs = xen_mc_entry(sizeof(*args));
	args = mcs.args;
	args->op.arg2.vcpumask = to_cpumask(args->mask);

	/* Remove us, and any offline CPUS. */
	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));

	if (va == TLB_FLUSH_ALL) {
		args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
	} else {
		args->op.cmd = MMUEXT_INVLPG_MULTI;
		args->op.arg1.linear_addr = va;
	}

	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);

	xen_mc_issue(PARAVIRT_LAZY_MMU);
}

static unsigned long xen_read_cr3(void)
{
	return percpu_read(xen_cr3);
}

static void set_current_cr3(void *v)
{
	percpu_write(xen_current_cr3, (unsigned long)v);
}

static void __xen_write_cr3(bool kernel, unsigned long cr3)
{
	struct mmuext_op *op;
	struct multicall_space mcs;
	unsigned long mfn;

	if (cr3)
		mfn = pfn_to_mfn(PFN_DOWN(cr3));
	else
		mfn = 0;

	WARN_ON(mfn == 0 && kernel);

	mcs = __xen_mc_entry(sizeof(*op));

	op = mcs.args;
	op->cmd = kernel ? MMUEXT_NEW_BASEPTR : MMUEXT_NEW_USER_BASEPTR;
	op->arg1.mfn = mfn;

	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);

	if (kernel) {
		percpu_write(xen_cr3, cr3);

		/* Update xen_current_cr3 once the batch has actually
		   been submitted. */
		xen_mc_callback(set_current_cr3, (void *)cr3);
	}
}

static void xen_write_cr3(unsigned long cr3)
{
	BUG_ON(preemptible());

	xen_mc_batch();  /* disables interrupts */

	/* Update while interrupts are disabled, so its atomic with
	   respect to ipis */
	percpu_write(xen_cr3, cr3);

	__xen_write_cr3(true, cr3);

#ifdef CONFIG_X86_64
	{
		pgd_t *user_pgd = xen_get_user_pgd(__va(cr3));
		if (user_pgd)
			__xen_write_cr3(false, __pa(user_pgd));
		else
			__xen_write_cr3(false, 0);
	}
#endif

	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
}

static int xen_pgd_alloc(struct mm_struct *mm)
{
	pgd_t *pgd = mm->pgd;
	int ret = 0;

	BUG_ON(PagePinned(virt_to_page(pgd)));

#ifdef CONFIG_X86_64
	{
		struct page *page = virt_to_page(pgd);
		pgd_t *user_pgd;

		BUG_ON(page->private != 0);

		ret = -ENOMEM;

		user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
		page->private = (unsigned long)user_pgd;

		if (user_pgd != NULL) {
			user_pgd[pgd_index(VSYSCALL_START)] =
				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
			ret = 0;
		}

		BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd))));
	}
#endif

	return ret;
}

static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
#ifdef CONFIG_X86_64
	pgd_t *user_pgd = xen_get_user_pgd(pgd);

	if (user_pgd)
		free_page((unsigned long)user_pgd);
#endif
}

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
#ifdef CONFIG_HIGHPTE
static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
{
	pgprot_t prot = PAGE_KERNEL;

	if (PagePinned(page))
		prot = PAGE_KERNEL_RO;

	if (0 && PageHighMem(page))
		printk("mapping highpte %lx type %d prot %s\n",
		       page_to_pfn(page), type,
		       (unsigned long)pgprot_val(prot) & _PAGE_RW ? "WRITE" : "READ");

	return kmap_atomic_prot(page, type, prot);
}
#endif

#ifdef CONFIG_X86_32
static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
{
	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
			       pte_val_ma(pte));

	return pte;
}

/* Init-time set_pte while constructing initial pagetables, which
   doesn't allow RO pagetable pages to be remapped RW */
static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
{
	pte = mask_rw_pte(ptep, pte);

	xen_set_pte(ptep, pte);
}
#endif
1467

1468 1469 1470 1471 1472 1473 1474 1475 1476
static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
{
	struct mmuext_op op;
	op.cmd = cmd;
	op.arg1.mfn = pfn_to_mfn(pfn);
	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
		BUG();
}

1477 1478 1479 1480
/* Early in boot, while setting up the initial pagetable, assume
   everything is pinned. */
static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
{
1481 1482 1483 1484 1485 1486 1487 1488 1489 1490
#ifdef CONFIG_FLATMEM
	BUG_ON(mem_map);	/* should only be used early */
#endif
	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
	pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
}

/* Used for pmd and pud */
static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
{
1491 1492 1493 1494 1495 1496 1497 1498
#ifdef CONFIG_FLATMEM
	BUG_ON(mem_map);	/* should only be used early */
#endif
	make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
}

/* Early release_pte assumes that all pts are pinned, since there's
   only init_mm and anything attached to that is pinned. */
1499
static __init void xen_release_pte_init(unsigned long pfn)
1500
{
1501
	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
1502 1503 1504
	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
}

1505
static __init void xen_release_pmd_init(unsigned long pfn)
1506
{
1507
	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
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 1554 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 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768
}

/* This needs to make sure the new pte page is pinned iff its being
   attached to a pinned pagetable. */
static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level)
{
	struct page *page = pfn_to_page(pfn);

	if (PagePinned(virt_to_page(mm->pgd))) {
		SetPagePinned(page);

		vm_unmap_aliases();
		if (!PageHighMem(page)) {
			make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
		} else {
			/* make sure there are no stray mappings of
			   this page */
			kmap_flush_unused();
		}
	}
}

static void xen_alloc_pte(struct mm_struct *mm, unsigned long pfn)
{
	xen_alloc_ptpage(mm, pfn, PT_PTE);
}

static void xen_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
{
	xen_alloc_ptpage(mm, pfn, PT_PMD);
}

/* This should never happen until we're OK to use struct page */
static void xen_release_ptpage(unsigned long pfn, unsigned level)
{
	struct page *page = pfn_to_page(pfn);

	if (PagePinned(page)) {
		if (!PageHighMem(page)) {
			if (level == PT_PTE && USE_SPLIT_PTLOCKS)
				pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
			make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
		}
		ClearPagePinned(page);
	}
}

static void xen_release_pte(unsigned long pfn)
{
	xen_release_ptpage(pfn, PT_PTE);
}

static void xen_release_pmd(unsigned long pfn)
{
	xen_release_ptpage(pfn, PT_PMD);
}

#if PAGETABLE_LEVELS == 4
static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn)
{
	xen_alloc_ptpage(mm, pfn, PT_PUD);
}

static void xen_release_pud(unsigned long pfn)
{
	xen_release_ptpage(pfn, PT_PUD);
}
#endif

void __init xen_reserve_top(void)
{
#ifdef CONFIG_X86_32
	unsigned long top = HYPERVISOR_VIRT_START;
	struct xen_platform_parameters pp;

	if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0)
		top = pp.virt_start;

	reserve_top_address(-top);
#endif	/* CONFIG_X86_32 */
}

/*
 * Like __va(), but returns address in the kernel mapping (which is
 * all we have until the physical memory mapping has been set up.
 */
static void *__ka(phys_addr_t paddr)
{
#ifdef CONFIG_X86_64
	return (void *)(paddr + __START_KERNEL_map);
#else
	return __va(paddr);
#endif
}

/* Convert a machine address to physical address */
static unsigned long m2p(phys_addr_t maddr)
{
	phys_addr_t paddr;

	maddr &= PTE_PFN_MASK;
	paddr = mfn_to_pfn(maddr >> PAGE_SHIFT) << PAGE_SHIFT;

	return paddr;
}

/* Convert a machine address to kernel virtual */
static void *m2v(phys_addr_t maddr)
{
	return __ka(m2p(maddr));
}

static void set_page_prot(void *addr, pgprot_t prot)
{
	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
	pte_t pte = pfn_pte(pfn, prot);

	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
		BUG();
}

static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
	unsigned pmdidx, pteidx;
	unsigned ident_pte;
	unsigned long pfn;

	ident_pte = 0;
	pfn = 0;
	for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) {
		pte_t *pte_page;

		/* Reuse or allocate a page of ptes */
		if (pmd_present(pmd[pmdidx]))
			pte_page = m2v(pmd[pmdidx].pmd);
		else {
			/* Check for free pte pages */
			if (ident_pte == ARRAY_SIZE(level1_ident_pgt))
				break;

			pte_page = &level1_ident_pgt[ident_pte];
			ident_pte += PTRS_PER_PTE;

			pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE);
		}

		/* Install mappings */
		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
			pte_t pte;

			if (pfn > max_pfn_mapped)
				max_pfn_mapped = pfn;

			if (!pte_none(pte_page[pteidx]))
				continue;

			pte = pfn_pte(pfn, PAGE_KERNEL_EXEC);
			pte_page[pteidx] = pte;
		}
	}

	for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE)
		set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO);

	set_page_prot(pmd, PAGE_KERNEL_RO);
}

#ifdef CONFIG_X86_64
static void convert_pfn_mfn(void *v)
{
	pte_t *pte = v;
	int i;

	/* All levels are converted the same way, so just treat them
	   as ptes. */
	for (i = 0; i < PTRS_PER_PTE; i++)
		pte[i] = xen_make_pte(pte[i].pte);
}

/*
 * Set up the inital kernel pagetable.
 *
 * We can construct this by grafting the Xen provided pagetable into
 * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
 * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt.  This
 * means that only the kernel has a physical mapping to start with -
 * but that's enough to get __va working.  We need to fill in the rest
 * of the physical mapping once some sort of allocator has been set
 * up.
 */
__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
					 unsigned long max_pfn)
{
	pud_t *l3;
	pmd_t *l2;

	/* Zap identity mapping */
	init_level4_pgt[0] = __pgd(0);

	/* Pre-constructed entries are in pfn, so convert to mfn */
	convert_pfn_mfn(init_level4_pgt);
	convert_pfn_mfn(level3_ident_pgt);
	convert_pfn_mfn(level3_kernel_pgt);

	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
	l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);

	memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
	memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);

	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
	memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);

	/* Set up identity map */
	xen_map_identity_early(level2_ident_pgt, max_pfn);

	/* Make pagetable pieces RO */
	set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
	set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
	set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
	set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
	set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);

	/* Pin down new L4 */
	pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
			  PFN_DOWN(__pa_symbol(init_level4_pgt)));

	/* Unpin Xen-provided one */
	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));

	/* Switch over */
	pgd = init_level4_pgt;

	/*
	 * At this stage there can be no user pgd, and no page
	 * structure to attach it to, so make sure we just set kernel
	 * pgd.
	 */
	xen_mc_batch();
	__xen_write_cr3(true, __pa(pgd));
	xen_mc_issue(PARAVIRT_LAZY_CPU);

	reserve_early(__pa(xen_start_info->pt_base),
		      __pa(xen_start_info->pt_base +
			   xen_start_info->nr_pt_frames * PAGE_SIZE),
		      "XEN PAGETABLES");

	return pgd;
}
#else	/* !CONFIG_X86_64 */
static pmd_t level2_kernel_pgt[PTRS_PER_PMD] __page_aligned_bss;

__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
					 unsigned long max_pfn)
{
	pmd_t *kernel_pmd;

1769 1770 1771
	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
				  xen_start_info->nr_pt_frames * PAGE_SIZE +
				  512*1024);
1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791

	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
	memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);

	xen_map_identity_early(level2_kernel_pgt, max_pfn);

	memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
	set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
			__pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));

	set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
	set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
	set_page_prot(empty_zero_page, PAGE_KERNEL_RO);

	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));

	xen_write_cr3(__pa(swapper_pg_dir));

	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));

1792 1793 1794 1795 1796
	reserve_early(__pa(xen_start_info->pt_base),
		      __pa(xen_start_info->pt_base +
			   xen_start_info->nr_pt_frames * PAGE_SIZE),
		      "XEN PAGETABLES");

1797 1798 1799 1800
	return swapper_pg_dir;
}
#endif	/* CONFIG_X86_64 */

1801
static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823
{
	pte_t pte;

	phys >>= PAGE_SHIFT;

	switch (idx) {
	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
#ifdef CONFIG_X86_F00F_BUG
	case FIX_F00F_IDT:
#endif
#ifdef CONFIG_X86_32
	case FIX_WP_TEST:
	case FIX_VDSO:
# ifdef CONFIG_HIGHMEM
	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
# endif
#else
	case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE:
#endif
#ifdef CONFIG_X86_LOCAL_APIC
	case FIX_APIC_BASE:	/* maps dummy local APIC */
#endif
1824 1825 1826
	case FIX_TEXT_POKE0:
	case FIX_TEXT_POKE1:
		/* All local page mappings */
1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846
		pte = pfn_pte(phys, prot);
		break;

	default:
		pte = mfn_pte(phys, prot);
		break;
	}

	__native_set_fixmap(idx, pte);

#ifdef CONFIG_X86_64
	/* Replicate changes to map the vsyscall page into the user
	   pagetable vsyscall mapping. */
	if (idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) {
		unsigned long vaddr = __fix_to_virt(idx);
		set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte);
	}
#endif
}

1847
static __init void xen_post_allocator_init(void)
1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
{
	pv_mmu_ops.set_pte = xen_set_pte;
	pv_mmu_ops.set_pmd = xen_set_pmd;
	pv_mmu_ops.set_pud = xen_set_pud;
#if PAGETABLE_LEVELS == 4
	pv_mmu_ops.set_pgd = xen_set_pgd;
#endif

	/* This will work as long as patching hasn't happened yet
	   (which it hasn't) */
	pv_mmu_ops.alloc_pte = xen_alloc_pte;
	pv_mmu_ops.alloc_pmd = xen_alloc_pmd;
	pv_mmu_ops.release_pte = xen_release_pte;
	pv_mmu_ops.release_pmd = xen_release_pmd;
#if PAGETABLE_LEVELS == 4
	pv_mmu_ops.alloc_pud = xen_alloc_pud;
	pv_mmu_ops.release_pud = xen_release_pud;
#endif

#ifdef CONFIG_X86_64
	SetPagePinned(virt_to_page(level3_user_vsyscall));
#endif
	xen_mark_init_mm_pinned();
}

1873 1874
static void xen_leave_lazy_mmu(void)
{
1875
	preempt_disable();
1876 1877
	xen_mc_flush();
	paravirt_leave_lazy_mmu();
1878
	preempt_enable();
1879
}
1880

1881
static const struct pv_mmu_ops xen_mmu_ops __initdata = {
1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900
	.read_cr2 = xen_read_cr2,
	.write_cr2 = xen_write_cr2,

	.read_cr3 = xen_read_cr3,
	.write_cr3 = xen_write_cr3,

	.flush_tlb_user = xen_flush_tlb,
	.flush_tlb_kernel = xen_flush_tlb,
	.flush_tlb_single = xen_flush_tlb_single,
	.flush_tlb_others = xen_flush_tlb_others,

	.pte_update = paravirt_nop,
	.pte_update_defer = paravirt_nop,

	.pgd_alloc = xen_pgd_alloc,
	.pgd_free = xen_pgd_free,

	.alloc_pte = xen_alloc_pte_init,
	.release_pte = xen_release_pte_init,
1901
	.alloc_pmd = xen_alloc_pmd_init,
1902
	.alloc_pmd_clone = paravirt_nop,
1903
	.release_pmd = xen_release_pmd_init,
1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919

#ifdef CONFIG_HIGHPTE
	.kmap_atomic_pte = xen_kmap_atomic_pte,
#endif

#ifdef CONFIG_X86_64
	.set_pte = xen_set_pte,
#else
	.set_pte = xen_set_pte_init,
#endif
	.set_pte_at = xen_set_pte_at,
	.set_pmd = xen_set_pmd_hyper,

	.ptep_modify_prot_start = __ptep_modify_prot_start,
	.ptep_modify_prot_commit = __ptep_modify_prot_commit,

1920 1921
	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
1922

1923 1924
	.make_pte = PV_CALLEE_SAVE(xen_make_pte),
	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
1925 1926 1927 1928 1929 1930 1931 1932

#ifdef CONFIG_X86_PAE
	.set_pte_atomic = xen_set_pte_atomic,
	.pte_clear = xen_pte_clear,
	.pmd_clear = xen_pmd_clear,
#endif	/* CONFIG_X86_PAE */
	.set_pud = xen_set_pud_hyper,

1933 1934
	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
1935 1936

#if PAGETABLE_LEVELS == 4
1937 1938
	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
1939 1940
	.set_pgd = xen_set_pgd_hyper,

1941 1942
	.alloc_pud = xen_alloc_pmd_init,
	.release_pud = xen_release_pmd_init,
1943 1944 1945 1946 1947 1948 1949 1950
#endif	/* PAGETABLE_LEVELS == 4 */

	.activate_mm = xen_activate_mm,
	.dup_mmap = xen_dup_mmap,
	.exit_mmap = xen_exit_mmap,

	.lazy_mode = {
		.enter = paravirt_enter_lazy_mmu,
1951
		.leave = xen_leave_lazy_mmu,
1952 1953 1954 1955 1956
	},

	.set_fixmap = xen_set_fixmap,
};

1957 1958 1959 1960 1961 1962
void __init xen_init_mmu_ops(void)
{
	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
	pv_mmu_ops = xen_mmu_ops;
}
1963

J
Jeremy Fitzhardinge 已提交
1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025
#ifdef CONFIG_XEN_DEBUG_FS

static struct dentry *d_mmu_debug;

static int __init xen_mmu_debugfs(void)
{
	struct dentry *d_xen = xen_init_debugfs();

	if (d_xen == NULL)
		return -ENOMEM;

	d_mmu_debug = debugfs_create_dir("mmu", d_xen);

	debugfs_create_u8("zero_stats", 0644, d_mmu_debug, &zero_stats);

	debugfs_create_u32("pgd_update", 0444, d_mmu_debug, &mmu_stats.pgd_update);
	debugfs_create_u32("pgd_update_pinned", 0444, d_mmu_debug,
			   &mmu_stats.pgd_update_pinned);
	debugfs_create_u32("pgd_update_batched", 0444, d_mmu_debug,
			   &mmu_stats.pgd_update_pinned);

	debugfs_create_u32("pud_update", 0444, d_mmu_debug, &mmu_stats.pud_update);
	debugfs_create_u32("pud_update_pinned", 0444, d_mmu_debug,
			   &mmu_stats.pud_update_pinned);
	debugfs_create_u32("pud_update_batched", 0444, d_mmu_debug,
			   &mmu_stats.pud_update_pinned);

	debugfs_create_u32("pmd_update", 0444, d_mmu_debug, &mmu_stats.pmd_update);
	debugfs_create_u32("pmd_update_pinned", 0444, d_mmu_debug,
			   &mmu_stats.pmd_update_pinned);
	debugfs_create_u32("pmd_update_batched", 0444, d_mmu_debug,
			   &mmu_stats.pmd_update_pinned);

	debugfs_create_u32("pte_update", 0444, d_mmu_debug, &mmu_stats.pte_update);
//	debugfs_create_u32("pte_update_pinned", 0444, d_mmu_debug,
//			   &mmu_stats.pte_update_pinned);
	debugfs_create_u32("pte_update_batched", 0444, d_mmu_debug,
			   &mmu_stats.pte_update_pinned);

	debugfs_create_u32("mmu_update", 0444, d_mmu_debug, &mmu_stats.mmu_update);
	debugfs_create_u32("mmu_update_extended", 0444, d_mmu_debug,
			   &mmu_stats.mmu_update_extended);
	xen_debugfs_create_u32_array("mmu_update_histo", 0444, d_mmu_debug,
				     mmu_stats.mmu_update_histo, 20);

	debugfs_create_u32("set_pte_at", 0444, d_mmu_debug, &mmu_stats.set_pte_at);
	debugfs_create_u32("set_pte_at_batched", 0444, d_mmu_debug,
			   &mmu_stats.set_pte_at_batched);
	debugfs_create_u32("set_pte_at_current", 0444, d_mmu_debug,
			   &mmu_stats.set_pte_at_current);
	debugfs_create_u32("set_pte_at_kernel", 0444, d_mmu_debug,
			   &mmu_stats.set_pte_at_kernel);

	debugfs_create_u32("prot_commit", 0444, d_mmu_debug, &mmu_stats.prot_commit);
	debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
			   &mmu_stats.prot_commit_batched);

	return 0;
}
fs_initcall(xen_mmu_debugfs);

#endif	/* CONFIG_XEN_DEBUG_FS */