path: root/arch/x86/xen/mmu.c

/*
 * 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
 */
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/debugfs.h>
#include <linux/bug.h>

#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
#include <asm/mmu_context.h>
#include <asm/paravirt.h>
#include <asm/linkage.h>

#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>

#include <xen/page.h>
#include <xen/interface/xen.h>

#include "multicalls.h"
#include "mmu.h"
#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 */

/*
 * 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)


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

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

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

/* Arrays of p2m arrays expressed in mfns used for save/restore */
static unsigned long p2m_top_mfn[TOP_ENTRIES] __page_aligned_bss;

static unsigned long p2m_top_mfn_list[TOP_ENTRIES / P2M_ENTRIES_PER_PAGE]
	__page_aligned_bss;

static inline unsigned p2m_top_index(unsigned long pfn)
{
	BUG_ON(pfn >= MAX_DOMAIN_PAGES);
	return pfn / P2M_ENTRIES_PER_PAGE;
}

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

/* Build the parallel p2m_top_mfn structures */
void xen_setup_mfn_list_list(void)
{
	unsigned pfn, idx;

	for(pfn