#include "multicalls.h"
#include "mmu.h"
+#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]
+ __attribute__((section(".data.page_aligned"))) =
+ { [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL };
+
+ /* Array of pointers to pages containing p2m entries */
+static unsigned long *p2m_top[TOP_ENTRIES]
+ __attribute__((section(".data.page_aligned"))) =
+ { [ 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]
+ __attribute__((section(".bss.page_aligned")));
+
+static unsigned long p2m_top_mfn_list[
+ PAGE_ALIGN(TOP_ENTRIES / P2M_ENTRIES_PER_PAGE)]
+ __attribute__((section(".bss.page_aligned")));
+
+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 = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+
+ p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
+ }
+
+ for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
+ unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
+ p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
+ }
+
+ 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 */
+void __init xen_build_dynamic_phys_to_machine(void)
+{
+ unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
+ unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
+ unsigned pfn;
+
+ for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+
+ p2m_top[topidx] = &mfn_list[pfn];
+ }
+}
+
+unsigned long get_phys_to_machine(unsigned long pfn)
+{
+ unsigned topidx, idx;
+
+ if (unlikely(pfn >= MAX_DOMAIN_PAGES))
+ return INVALID_P2M_ENTRY;
+
+ topidx = p2m_top_index(pfn);
+ idx = p2m_index(pfn);
+ return p2m_top[topidx][idx];
+}
+EXPORT_SYMBOL_GPL(get_phys_to_machine);
+
+static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
+{
+ unsigned long *p;
+ unsigned i;
+
+ p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
+ BUG_ON(p == NULL);
+
+ for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
+ p[i] = INVALID_P2M_ENTRY;
+
+ if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
+ free_page((unsigned long)p);
+ else
+ *mfnp = virt_to_mfn(p);
+}
+
+void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+ unsigned topidx, idx;
+
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+ BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+ return;
+ }
+
+ if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
+ BUG_ON(mfn != INVALID_P2M_ENTRY);
+ return;
+ }
+
+ topidx = p2m_top_index(pfn);
+ if (p2m_top[topidx] == p2m_missing) {
+ /* no need to allocate a page to store an invalid entry */
+ if (mfn == INVALID_P2M_ENTRY)
+ return;
+ alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]);
+ }
+
+ idx = p2m_index(pfn);
+ p2m_top[topidx][idx] = mfn;
+}
+
xmaddr_t arbitrary_virt_to_machine(unsigned long address)
{
unsigned int level;
}
-void xen_set_pmd(pmd_t *ptr, pmd_t val)
+static bool page_pinned(void *ptr)
+{
+ struct page *page = virt_to_page(ptr);
+
+ return PagePinned(page);
+}
+
+void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
{
struct multicall_space mcs;
struct mmu_update *u;
preempt_enable();
}
+void xen_set_pmd(pmd_t *ptr, pmd_t val)
+{
+ /* If page is not pinned, we can just update the entry
+ directly */
+ if (!page_pinned(ptr)) {
+ *ptr = val;
+ return;
+ }
+
+ xen_set_pmd_hyper(ptr, val);
+}
+
/*
* Associate a virtual page frame with a given physical page frame
* and protection flags for that frame.
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
+ /* updates to init_mm may be done without lock */
+ if (mm == &init_mm)
+ preempt_disable();
+
if (mm == current->mm || mm == &init_mm) {
if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
struct multicall_space mcs;
MULTI_update_va_mapping(mcs.mc, addr, pteval, 0);
xen_mc_issue(PARAVIRT_LAZY_MMU);
- return;
+ goto out;
} else
if (HYPERVISOR_update_va_mapping(addr, pteval, 0) == 0)
- return;
+ goto out;
}
xen_set_pte(ptep, pteval);
-}
-
-#ifdef CONFIG_X86_PAE
-void xen_set_pud(pud_t *ptr, pud_t val)
-{
- struct multicall_space mcs;
- struct mmu_update *u;
- preempt_disable();
-
- mcs = xen_mc_entry(sizeof(*u));
- u = mcs.args;
- u->ptr = virt_to_machine(ptr).maddr;
- u->val = pud_val_ma(val);
- MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
-
- xen_mc_issue(PARAVIRT_LAZY_MMU);
-
- preempt_enable();
+out:
+ if (mm == &init_mm)
+ preempt_enable();
}
-void xen_set_pte(pte_t *ptep, pte_t pte)
+pteval_t xen_pte_val(pte_t pte)
{
- ptep->pte_high = pte.pte_high;
- smp_wmb();
- ptep->pte_low = pte.pte_low;
-}
+ pteval_t ret = pte.pte;
-void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
- set_64bit((u64 *)ptep, pte_val_ma(pte));
-}
+ if (ret & _PAGE_PRESENT)
+ ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-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;
+ return ret;
}
-void xen_pmd_clear(pmd_t *pmdp)
+pgdval_t xen_pgd_val(pgd_t pgd)
{
- xen_set_pmd(pmdp, __pmd(0));
+ pgdval_t ret = pgd.pgd;
+ if (ret & _PAGE_PRESENT)
+ ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
+ return ret;
}
-unsigned long long xen_pte_val(pte_t pte)
+pte_t xen_make_pte(pteval_t pte)
{
- unsigned long long ret = 0;
-
- if (pte.pte_low) {
- ret = ((unsigned long long)pte.pte_high << 32) | pte.pte_low;
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
+ if (pte & _PAGE_PRESENT) {
+ pte = phys_to_machine(XPADDR(pte)).maddr;
+ pte &= ~(_PAGE_PCD | _PAGE_PWT);
}
- return ret;
+ return (pte_t){ .pte = pte };
}
-unsigned long long xen_pmd_val(pmd_t pmd)
+pgd_t xen_make_pgd(pgdval_t pgd)
{
- unsigned long long ret = pmd.pmd;
- if (ret)
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
- return ret;
+ if (pgd & _PAGE_PRESENT)
+ pgd = phys_to_machine(XPADDR(pgd)).maddr;
+
+ return (pgd_t){ pgd };
}
-unsigned long long xen_pgd_val(pgd_t pgd)
+pmdval_t xen_pmd_val(pmd_t pmd)
{
- unsigned long long ret = pgd.pgd;
- if (ret)
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
+ pmdval_t ret = native_pmd_val(pmd);
+ if (ret & _PAGE_PRESENT)
+ ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
return ret;
}
-pte_t xen_make_pte(unsigned long long pte)
+void xen_set_pud_hyper(pud_t *ptr, pud_t val)
{
- if (pte & _PAGE_PRESENT) {
- pte = phys_to_machine(XPADDR(pte)).maddr;
- pte &= ~(_PAGE_PCD | _PAGE_PWT);
- }
+ struct multicall_space mcs;
+ struct mmu_update *u;
- return (pte_t){ .pte = pte };
-}
+ preempt_disable();
-pmd_t xen_make_pmd(unsigned long long pmd)
-{
- if (pmd & 1)
- pmd = phys_to_machine(XPADDR(pmd)).maddr;
+ mcs = xen_mc_entry(sizeof(*u));
+ u = mcs.args;
+ u->ptr = virt_to_machine(ptr).maddr;
+ u->val = pud_val_ma(val);
+ MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
- return (pmd_t){ pmd };
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+ preempt_enable();
}
-pgd_t xen_make_pgd(unsigned long long pgd)
+void xen_set_pud(pud_t *ptr, pud_t val)
{
- if (pgd & _PAGE_PRESENT)
- pgd = phys_to_machine(XPADDR(pgd)).maddr;
+ /* If page is not pinned, we can just update the entry
+ directly */
+ if (!page_pinned(ptr)) {
+ *ptr = val;
+ return;
+ }
- return (pgd_t){ pgd };
+ xen_set_pud_hyper(ptr, val);
}
-#else /* !PAE */
+
void xen_set_pte(pte_t *ptep, pte_t pte)
{
- *ptep = pte;
+ ptep->pte_high = pte.pte_high;
+ smp_wmb();
+ ptep->pte_low = pte.pte_low;
}
-unsigned long xen_pte_val(pte_t pte)
+void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
{
- unsigned long ret = pte.pte_low;
-
- if (ret & _PAGE_PRESENT)
- ret = machine_to_phys(XMADDR(ret)).paddr;
-
- return ret;
+ set_64bit((u64 *)ptep, pte_val_ma(pte));
}
-unsigned long xen_pgd_val(pgd_t pgd)
+void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
- unsigned long ret = pgd.pgd;
- if (ret)
- ret = machine_to_phys(XMADDR(ret)).paddr | 1;
- return ret;
+ ptep->pte_low = 0;
+ smp_wmb(); /* make sure low gets written first */
+ ptep->pte_high = 0;
}
-pte_t xen_make_pte(unsigned long pte)
+void xen_pmd_clear(pmd_t *pmdp)
{
- if (pte & _PAGE_PRESENT) {
- pte = phys_to_machine(XPADDR(pte)).maddr;
- pte &= ~(_PAGE_PCD | _PAGE_PWT);
- }
-
- return (pte_t){ pte };
+ set_pmd(pmdp, __pmd(0));
}
-pgd_t xen_make_pgd(unsigned long pgd)
+pmd_t xen_make_pmd(pmdval_t pmd)
{
- if (pgd & _PAGE_PRESENT)
- pgd = phys_to_machine(XPADDR(pgd)).maddr;
+ if (pmd & _PAGE_PRESENT)
+ pmd = phys_to_machine(XPADDR(pmd)).maddr;
- return (pgd_t){ pgd };
+ return native_make_pmd(pmd);
}
-#endif /* CONFIG_X86_PAE */
-
-enum pt_level {
- PT_PGD,
- PT_PUD,
- PT_PMD,
- PT_PTE
-};
/*
(Yet another) pagetable walker. This one is intended for pinning a
static int pin_page(struct page *page, enum pt_level level)
{
- unsigned pgfl = test_and_set_bit(PG_pinned, &page->flags);
+ unsigned pgfl = TestSetPagePinned(page);
int flush;
if (pgfl)
read-only, and can be pinned. */
void xen_pgd_pin(pgd_t *pgd)
{
- unsigned level;
-
xen_mc_batch();
if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
xen_mc_batch();
}
-#ifdef CONFIG_X86_PAE
- level = MMUEXT_PIN_L3_TABLE;
-#else
- level = MMUEXT_PIN_L2_TABLE;
-#endif
+ xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
+ xen_mc_issue(0);
+}
+
+/*
+ * 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).
+ */
+void xen_mm_pin_all(void)
+{
+ unsigned long flags;
+ struct page *page;
- xen_do_pin(level, PFN_DOWN(__pa(pgd)));
+ spin_lock_irqsave(&pgd_lock, flags);
- xen_mc_issue(0);
+ list_for_each_entry(page, &pgd_list, lru) {
+ if (!PagePinned(page)) {
+ xen_pgd_pin((pgd_t *)page_address(page));
+ SetPageSavePinned(page);
+ }
+ }
+
+ spin_unlock_irqrestore(&pgd_lock, flags);
}
/* The init_mm pagetable is really pinned as soon as its created, but
static int unpin_page(struct page *page, enum pt_level level)
{
- unsigned pgfl = test_and_clear_bit(PG_pinned, &page->flags);
+ unsigned pgfl = TestClearPagePinned(page);
if (pgfl && !PageHighMem(page)) {
void *pt = lowmem_page_address(page);
xen_mc_issue(0);
}
+/*
+ * 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));
+ printk("unpinning pinned %p\n", page_address(page));
+ xen_pgd_unpin((pgd_t *)page_address(page));
+ ClearPageSavePinned(page);
+ }
+ }
+
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
{
spin_lock(&next->page_table_lock);
spin_lock(&mm->page_table_lock);
/* pgd may not be pinned in the error exit path of execve */
- if (PagePinned(virt_to_page(mm->pgd)))
+ if (page_pinned(mm->pgd))
xen_pgd_unpin(mm->pgd);
spin_unlock(&mm->page_table_lock);