#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 "multicalls.h"
#include "mmu.h"
+/*
+ * 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)
p2m_top[topidx][idx] = mfn;
}
-xmaddr_t arbitrary_virt_to_machine(unsigned long address)
+xmaddr_t arbitrary_virt_to_machine(void *vaddr)
{
+ unsigned long address = (unsigned long)vaddr;
unsigned int level;
pte_t *pte = lookup_address(address, &level);
unsigned offset = address & ~PAGE_MASK;
BUG_ON(pte == NULL);
- return XMADDR((pte_mfn(*pte) << PAGE_SHIFT) + offset);
+ return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset);
}
void make_lowmem_page_readonly(void *vaddr)
xen_mc_batch();
- u.ptr = virt_to_machine(ptr).maddr;
+ /* ptr may be ioremapped for 64-bit pagetable setup */
+ u.ptr = arbitrary_virt_to_machine(ptr).maddr;
u.val = pmd_val_ma(val);
extend_mmu_update(&u);
*/
void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
-
- pgd = swapper_pg_dir + pgd_index(vaddr);
- if (pgd_none(*pgd)) {
- BUG();
- return;
- }
- pud = pud_offset(pgd, vaddr);
- if (pud_none(*pud)) {
- BUG();
- return;
- }
- pmd = pmd_offset(pud, vaddr);
- if (pmd_none(*pmd)) {
- BUG();
- return;
- }
- pte = pte_offset_kernel(pmd, vaddr);
- /* <mfn,flags> stored as-is, to permit clearing entries */
- xen_set_pte(pte, mfn_pte(mfn, flags));
-
- /*
- * It's enough to flush this one mapping.
- * (PGE mappings get flushed as well)
- */
- __flush_tlb_one(vaddr);
+ set_pte_vaddr(vaddr, mfn_pte(mfn, flags));
}
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
static pteval_t pte_mfn_to_pfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
- unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
- pteval_t flags = val & ~PTE_MASK;
+ unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & PTE_FLAGS_MASK;
val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
}
static pteval_t pte_pfn_to_mfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
- unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
- pteval_t flags = val & ~PTE_MASK;
+ unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+ pteval_t flags = val & PTE_FLAGS_MASK;
val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
}
xen_mc_batch();
- u.ptr = virt_to_machine(ptr).maddr;
+ /* ptr may be ioremapped for 64-bit pagetable setup */
+ u.ptr = arbitrary_virt_to_machine(ptr).maddr;
u.val = pud_val_ma(val);
extend_mmu_update(&u);
return native_make_pud(pud);
}
-void xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+pgd_t *xen_get_user_pgd(pgd_t *pgd)
{
- struct mmu_update u;
+ pgd_t *pgd_page = (pgd_t *)(((unsigned long)pgd) & PAGE_MASK);
+ unsigned offset = pgd - pgd_page;
+ pgd_t *user_ptr = NULL;
- preempt_disable();
+ 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;
+ }
- xen_mc_batch();
+ return user_ptr;
+}
+
+static void __xen_set_pgd_hyper(pgd_t *ptr, pgd_t val)
+{
+ struct mmu_update u;
u.ptr = virt_to_machine(ptr).maddr;
u.val = pgd_val_ma(val);
extend_mmu_update(&u);
+}
+
+/*
+ * 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);
xen_mc_issue(PARAVIRT_LAZY_MMU);
void xen_set_pgd(pgd_t *ptr, pgd_t val)
{
+ pgd_t *user_ptr = xen_get_user_pgd(ptr);
+
/* If page is not pinned, we can just update the entry
directly */
if (!page_pinned(ptr)) {
*ptr = val;
+ if (user_ptr) {
+ WARN_ON(page_pinned(user_ptr));
+ *user_ptr = val;
+ }
return;
}
- xen_set_pgd_hyper(ptr, val);
+ /* 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);
}
#endif /* PAGETABLE_LEVELS == 4 */
/*
- (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 pte_limit. In the normal case
- this will be TASK_SIZE, but at boot we need to pin up to
- FIXADDR_TOP. But the important bit is that we don't pin beyond
- there, because then we start getting into Xen's ptes.
-*/
-static int pgd_walk(pgd_t *pgd_base, int (*func)(struct page *, enum pt_level),
+ * (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.
+ */
+static int pgd_walk(pgd_t *pgd, int (*func)(struct page *, enum pt_level),
unsigned long limit)
{
- pgd_t *pgd = pgd_base;
int flush = 0;
- unsigned long addr = 0;
- unsigned long pgd_next;
+ unsigned hole_low, hole_high;
+ unsigned pgdidx_limit, pudidx_limit, pmdidx_limit;
+ unsigned pgdidx, pudidx, pmdidx;
- BUG_ON(limit > FIXADDR_TOP);
+ /* The limit is the last byte to be touched */
+ limit--;
+ BUG_ON(limit >= FIXADDR_TOP);
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
- for (; addr != FIXADDR_TOP; pgd++, addr = pgd_next) {
+ /*
+ * 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.
+ */
+ hole_low = pgd_index(USER_LIMIT);
+ 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
+
+ flush |= (*func)(virt_to_page(pgd), PT_PGD);
+
+ for (pgdidx = 0; pgdidx <= pgdidx_limit; pgdidx++) {
pud_t *pud;
- unsigned long pud_limit, pud_next;
- pgd_next = pud_limit = pgd_addr_end(addr, FIXADDR_TOP);
+ if (pgdidx >= hole_low && pgdidx < hole_high)
+ continue;
- if (!pgd_val(*pgd))
+ if (!pgd_val(pgd[pgdidx]))
continue;
- pud = pud_offset(pgd, 0);
+ pud = pud_offset(&pgd[pgdidx], 0);
if (PTRS_PER_PUD > 1) /* not folded */
flush |= (*func)(virt_to_page(pud), PT_PUD);
- for (; addr != pud_limit; pud++, addr = pud_next) {
+ for (pudidx = 0; pudidx < PTRS_PER_PUD; pudidx++) {
pmd_t *pmd;
- unsigned long pmd_limit;
- pud_next = pud_addr_end(addr, pud_limit);
-
- if (pud_next < limit)
- pmd_limit = pud_next;
- else
- pmd_limit = limit;
+ if (pgdidx == pgdidx_limit &&
+ pudidx > pudidx_limit)
+ goto out;
- if (pud_none(*pud))
+ if (pud_none(pud[pudidx]))
continue;
- pmd = pmd_offset(pud, 0);
+ pmd = pmd_offset(&pud[pudidx], 0);
if (PTRS_PER_PMD > 1) /* not folded */
flush |= (*func)(virt_to_page(pmd), PT_PMD);
- for (; addr != pmd_limit; pmd++) {
- addr += (PAGE_SIZE * PTRS_PER_PTE);
- if ((pmd_limit-1) < (addr-1)) {
- addr = pmd_limit;
- break;
- }
+ for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) {
+ struct page *pte;
- if (pmd_none(*pmd))
+ if (pgdidx == pgdidx_limit &&
+ pudidx == pudidx_limit &&
+ pmdidx > pmdidx_limit)
+ goto out;
+
+ if (pmd_none(pmd[pmdidx]))
continue;
- flush |= (*func)(pmd_page(*pmd), PT_PTE);
+ pte = pmd_page(pmd[pmdidx]);
+ flush |= (*func)(pte, PT_PTE);
}
}
}
-
- flush |= (*func)(virt_to_page(pgd_base), PT_PGD);
+out:
return flush;
}
{
xen_mc_batch();
- if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
+ if (pgd_walk(pgd, pin_page, USER_LIMIT)) {
/* re-enable interrupts for kmap_flush_unused */
xen_mc_issue(0);
kmap_flush_unused();
xen_mc_batch();
}
+#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) {
+ pin_page(virt_to_page(user_pgd), PT_PGD);
+ xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(user_pgd)));
+ }
+ }
+#else /* CONFIG_X86_32 */
+#ifdef CONFIG_X86_PAE
+ /* Need to make sure unshared kernel PMD is pinnable */
+ pin_page(virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])), PT_PMD);
+#endif
xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
+#endif /* CONFIG_X86_64 */
xen_mc_issue(0);
}
xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- pgd_walk(pgd, unpin_page, TASK_SIZE);
+#ifdef CONFIG_X86_64
+ {
+ pgd_t *user_pgd = xen_get_user_pgd(pgd);
+
+ if (user_pgd) {
+ xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(user_pgd)));
+ unpin_page(virt_to_page(user_pgd), PT_PGD);
+ }
+ }
+#endif
+
+#ifdef CONFIG_X86_PAE
+ /* Need to make sure unshared kernel PMD is unpinned */
+ pin_page(virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])), PT_PMD);
+#endif
+
+ pgd_walk(pgd, unpin_page, USER_LIMIT);
xen_mc_issue(0);
}
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);
}
projects / linux-2.6-omap-h63xx.git / blobdiff