/*H:470
* Finally, a routine which throws away everything: all PGD entries in all
* the shadow page tables, including the Guest's kernel mappings. This is used
* when we destroy the Guest.
*/
static void release_all_pagetables(struct lguest *lg)
{
unsigned int i, j;
/* Every shadow pagetable this Guest has */
for (i = 0; i < ARRAY_SIZE(lg->pgdirs); i++)
if (lg->pgdirs[i].pgdir) {
#ifdef CONFIG_X86_PAE
pgd_t *spgd;
pmd_t *pmdpage;
unsigned int k;
/* Get the last pmd page. */
spgd = lg->pgdirs[i].pgdir + SWITCHER_PGD_INDEX;
pmdpage = __va(pgd_pfn(*spgd) << PAGE_SHIFT);
/*
* And release the pmd entries of that pmd page,
* except for the switcher pmd.
*/
for (k = 0; k < SWITCHER_PMD_INDEX; k++)
release_pmd(&pmdpage[k]);
#endif
/* Every PGD entry except the Switcher at the top */
for (j = 0; j < SWITCHER_PGD_INDEX; j++)
release_pgd(lg->pgdirs[i].pgdir + j);
}
}
/* Follow the PGD to the PTE (no mid-level for !PAE). */
static unsigned long gpte_addr(struct lg_cpu *cpu,
pgd_t gpgd, unsigned long vaddr)
{
unsigned long gpage = pgd_pfn(gpgd) << PAGE_SHIFT;
BUG_ON(!(pgd_flags(gpgd) & _PAGE_PRESENT));
return gpage + pte_index(vaddr) * sizeof(pte_t);
}
static bool check_gpgd(struct lg_cpu *cpu, pgd_t gpgd)
{
if ((pgd_flags(gpgd) & ~CHECK_GPGD_MASK) ||
(pgd_pfn(gpgd) >= cpu->lg->pfn_limit)) {
kill_guest(cpu, "bad page directory entry");
return false;
}
return true;
}
/*
* This routine then takes the PGD entry given above, which contains the
* address of the PMD page. It then returns a pointer to the PMD entry for the
* given address.
*/
static pmd_t *spmd_addr(struct lg_cpu *cpu, pgd_t spgd, unsigned long vaddr)
{
unsigned int index = pmd_index(vaddr);
pmd_t *page;
/* You should never call this if the PGD entry wasn't valid */
BUG_ON(!(pgd_flags(spgd) & _PAGE_PRESENT));
page = __va(pgd_pfn(spgd) << PAGE_SHIFT);
return &page[index];
}
static void release_pgd(pgd_t *spgd)
{
/* If the entry's not present, there's nothing to release. */
if (pgd_flags(*spgd) & _PAGE_PRESENT) {
unsigned int i;
pmd_t *pmdpage = __va(pgd_pfn(*spgd) << PAGE_SHIFT);
for (i = 0; i < PTRS_PER_PMD; i++)
release_pmd(&pmdpage[i]);
/* Now we can free the page of PMDs */
free_page((long)pmdpage);
/* And zero out the PGD entry so we never release it twice. */
set_pgd(spgd, __pgd(0));
}
}
/*
* This routine then takes the page directory entry returned above, which
* contains the address of the page table entry (PTE) page. It then returns a
* pointer to the PTE entry for the given address.
*/
static pte_t *spte_addr(struct lg_cpu *cpu, pgd_t spgd, unsigned long vaddr)
{
#ifdef CONFIG_X86_PAE
pmd_t *pmd = spmd_addr(cpu, spgd, vaddr);
pte_t *page = __va(pmd_pfn(*pmd) << PAGE_SHIFT);
/* You should never call this if the PMD entry wasn't valid */
BUG_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT));
#else
pte_t *page = __va(pgd_pfn(spgd) << PAGE_SHIFT);
/* You should never call this if the PGD entry wasn't valid */
BUG_ON(!(pgd_flags(spgd) & _PAGE_PRESENT));
#endif
return &page[pte_index(vaddr)];
}
/*
* This routine then takes the PGD entry given above, which contains the
* address of the PMD page. It then returns a pointer to the PMD entry for the
* given address.
*/
static pmd_t *spmd_addr(struct lg_cpu *cpu, pgd_t spgd, unsigned long vaddr)
{
unsigned int index = pmd_index(vaddr);
pmd_t *page;
/* We kill any Guest trying to touch the Switcher addresses. */
if (pgd_index(vaddr) == SWITCHER_PGD_INDEX &&
index >= SWITCHER_PMD_INDEX) {
kill_guest(cpu, "attempt to access switcher pages");
index = 0;
}
/* You should never call this if the PGD entry wasn't valid */
BUG_ON(!(pgd_flags(spgd) & _PAGE_PRESENT));
page = __va(pgd_pfn(spgd) << PAGE_SHIFT);
return &page[index];
}
/*H:480
* (vi) Mapping the Switcher when the Guest is about to run.
*
* The Switcher and the two pages for this CPU need to be visible in the
* Guest (and not the pages for other CPUs). We have the appropriate PTE pages
* for each CPU already set up, we just need to hook them in now we know which
* Guest is about to run on this CPU.
*/
void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages)
{
pte_t *switcher_pte_page = __this_cpu_read(switcher_pte_pages);
pte_t regs_pte;
#ifdef CONFIG_X86_PAE
pmd_t switcher_pmd;
pmd_t *pmd_table;
switcher_pmd = pfn_pmd(__pa(switcher_pte_page) >> PAGE_SHIFT,
PAGE_KERNEL_EXEC);
/* Figure out where the pmd page is, by reading the PGD, and converting
* it to a virtual address. */
pmd_table = __va(pgd_pfn(cpu->lg->
pgdirs[cpu->cpu_pgd].pgdir[SWITCHER_PGD_INDEX])
<< PAGE_SHIFT);
/* Now write it into the shadow page table. */
set_pmd(&pmd_table[SWITCHER_PMD_INDEX], switcher_pmd);
#else
pgd_t switcher_pgd;
/*
* Make the last PGD entry for this Guest point to the Switcher's PTE
* page for this CPU (with appropriate flags).
*/
switcher_pgd = __pgd(__pa(switcher_pte_page) | __PAGE_KERNEL_EXEC);
cpu->lg->pgdirs[cpu->cpu_pgd].pgdir[SWITCHER_PGD_INDEX] = switcher_pgd;
#endif
/*
* We also change the Switcher PTE page. When we're running the Guest,
* we want the Guest's "regs" page to appear where the first Switcher
* page for this CPU is. This is an optimization: when the Switcher
* saves the Guest registers, it saves them into the first page of this
* CPU's "struct lguest_pages": if we make sure the Guest's register
* page is already mapped there, we don't have to copy them out
* again.
*/
regs_pte = pfn_pte(__pa(cpu->regs_page) >> PAGE_SHIFT, PAGE_KERNEL);
set_pte(&switcher_pte_page[pte_index((unsigned long)pages)], regs_pte);
}
/*H:450
* If we chase down the release_pgd() code, the non-PAE version looks like
* this. The PAE version is almost identical, but instead of calling
* release_pte it calls release_pmd(), which looks much like this.
*/
static void release_pgd(pgd_t *spgd)
{
/* If the entry's not present, there's nothing to release. */
if (pgd_flags(*spgd) & _PAGE_PRESENT) {
unsigned int i;
/*
* Converting the pfn to find the actual PTE page is easy: turn
* the page number into a physical address, then convert to a
* virtual address (easy for kernel pages like this one).
*/
pte_t *ptepage = __va(pgd_pfn(*spgd) << PAGE_SHIFT);
/* For each entry in the page, we might need to release it. */
for (i = 0; i < PTRS_PER_PTE; i++)
release_pte(ptepage[i]);
/* Now we can free the page of PTEs */
free_page((long)ptepage);
/* And zero out the PGD entry so we never release it twice. */
*spgd = __pgd(0);
}
}
static void check_gpgd(struct lg_cpu *cpu, pgd_t gpgd)
{
if ((pgd_flags(gpgd) & ~CHECK_GPGD_MASK) ||
(pgd_pfn(gpgd) >= cpu->lg->pfn_limit))
kill_guest(cpu, "bad page directory entry");
}
/* Follow the PGD to the PMD. */
static unsigned long gpmd_addr(pgd_t gpgd, unsigned long vaddr)
{
unsigned long gpage = pgd_pfn(gpgd) << PAGE_SHIFT;
BUG_ON(!(pgd_flags(gpgd) & _PAGE_PRESENT));
return gpage + pmd_index(vaddr) * sizeof(pmd_t);
}
