Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-xen-next

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-xen-next: (52 commits)
  xen: add balloon driver
  xen: allow compilation with non-flat memory
  xen: fold xen_sysexit into xen_iret
  xen: allow set_pte_at on init_mm to be lockless
  xen: disable preemption during tlb flush
  xen pvfb: Para-virtual framebuffer, keyboard and pointer driver
  xen: Add compatibility aliases for frontend drivers
  xen: Module autoprobing support for frontend drivers
  xen blkfront: Delay wait for block devices until after the disk is added
  xen/blkfront: use bdget_disk
  xen: Make xen-blkfront write its protocol ABI to xenstore
  xen: import arch generic part of xencomm
  xen: make grant table arch portable
  xen: replace callers of alloc_vm_area()/free_vm_area() with xen_ prefixed one
  xen: make include/xen/page.h portable moving those definitions under asm dir
  xen: add resend_irq_on_evtchn() definition into events.c
  Xen: make events.c portable for ia64/xen support
  xen: move events.c to drivers/xen for IA64/Xen support
  xen: move features.c from arch/x86/xen/features.c to drivers/xen
  xen: add missing definitions in include/xen/interface/vcpu.h which ia64/xen needs
  ...

6 files changed, 283 insertions, 213 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 20941d2954e..b7b3e4c7cfc 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,5 @@
 obj-y	:=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o
+	    pat.o pgtable.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9ec62da85fd..08aa1878fad 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -71,7 +71,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
 		pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
 
-		paravirt_alloc_pd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
@@ -100,7 +100,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 		}
 
-		paravirt_alloc_pt(&init_mm, __pa(page_table) >> PAGE_SHIFT);
+		paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
 		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
 	}
@@ -365,7 +365,7 @@ void __init native_pagetable_setup_start(pgd_t *base)
 
 		pte_clear(NULL, va, pte);
 	}
-	paravirt_alloc_pd(&init_mm, __pa(base) >> PAGE_SHIFT);
+	paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
 }
 
 void __init native_pagetable_setup_done(pgd_t *base)
@@ -457,7 +457,7 @@ void zap_low_mappings(void)
 	 * Note that "pgd_clear()" doesn't do it for
 	 * us, because pgd_clear() is a no-op on i386.
 	 */
-	for (i = 0; i < USER_PTRS_PER_PGD; i++) {
+	for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) {
 #ifdef CONFIG_X86_PAE
 		set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
 #else
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 3a4baf95e24..36a3f7ded62 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -407,7 +407,7 @@ void __init early_ioremap_clear(void)
 
 	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
 	pmd_clear(pmd);
-	paravirt_release_pt(__pa(bm_pte) >> PAGE_SHIFT);
+	paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT);
 	__flush_tlb_all();
 }
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index c29ebd03725..bd5e05c654d 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -483,9 +483,7 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 		goto out_unlock;
 
 	pbase = (pte_t *)page_address(base);
-#ifdef CONFIG_X86_32
-	paravirt_alloc_pt(&init_mm, page_to_pfn(base));
-#endif
+	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
 	ref_prot = pte_pgprot(pte_clrhuge(*kpte));
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
new file mode 100644
index 00000000000..50159764f69
--- /dev/null
+++ b/arch/x86/mm/pgtable.c
@@ -0,0 +1,276 @@
+#include <linux/mm.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+{
+	return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+}
+
+pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+	struct page *pte;
+
+#ifdef CONFIG_HIGHPTE
+	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
+#else
+	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
+#endif
+	if (pte)
+		pgtable_page_ctor(pte);
+	return pte;
+}
+
+void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
+{
+	pgtable_page_dtor(pte);
+	paravirt_release_pte(page_to_pfn(pte));
+	tlb_remove_page(tlb, pte);
+}
+
+#if PAGETABLE_LEVELS > 2
+void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
+{
+	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+	tlb_remove_page(tlb, virt_to_page(pmd));
+}
+
+#if PAGETABLE_LEVELS > 3
+void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
+{
+	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
+	tlb_remove_page(tlb, virt_to_page(pud));
+}
+#endif	/* PAGETABLE_LEVELS > 3 */
+#endif	/* PAGETABLE_LEVELS > 2 */
+
+static inline void pgd_list_add(pgd_t *pgd)
+{
+	struct page *page = virt_to_page(pgd);
+
+	list_add(&page->lru, &pgd_list);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+	struct page *page = virt_to_page(pgd);
+
+	list_del(&page->lru);
+}
+
+#define UNSHARED_PTRS_PER_PGD				\
+	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
+
+static void pgd_ctor(void *p)
+{
+	pgd_t *pgd = p;
+	unsigned long flags;
+
+	/* Clear usermode parts of PGD */
+	memset(pgd, 0, KERNEL_PGD_BOUNDARY*sizeof(pgd_t));
+
+	spin_lock_irqsave(&pgd_lock, flags);
+
+	/* If the pgd points to a shared pagetable level (either the
+	   ptes in non-PAE, or shared PMD in PAE), then just copy the
+	   references from swapper_pg_dir. */
+	if (PAGETABLE_LEVELS == 2 ||
+	    (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
+	    PAGETABLE_LEVELS == 4) {
+		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
+				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+				KERNEL_PGD_PTRS);
+		paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
+					 __pa(swapper_pg_dir) >> PAGE_SHIFT,
+					 KERNEL_PGD_BOUNDARY,
+					 KERNEL_PGD_PTRS);
+	}
+
+	/* list required to sync kernel mapping updates */
+	if (!SHARED_KERNEL_PMD)
+		pgd_list_add(pgd);
+
+	spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+static void pgd_dtor(void *pgd)
+{
+	unsigned long flags; /* can be called from interrupt context */
+
+	if (SHARED_KERNEL_PMD)
+		return;
+
+	spin_lock_irqsave(&pgd_lock, flags);
+	pgd_list_del(pgd);
+	spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+/*
+ * List of all pgd's needed for non-PAE so it can invalidate entries
+ * in both cached and uncached pgd's; not needed for PAE since the
+ * kernel pmd is shared. If PAE were not to share the pmd a similar
+ * tactic would be needed. This is essentially codepath-based locking
+ * against pageattr.c; it is the unique case in which a valid change
+ * of kernel pagetables can't be lazily synchronized by vmalloc faults.
+ * vmalloc faults work because attached pagetables are never freed.
+ * -- wli
+ */
+
+#ifdef CONFIG_X86_PAE
+/*
+ * Mop up any pmd pages which may still be attached to the pgd.
+ * Normally they will be freed by munmap/exit_mmap, but any pmd we
+ * preallocate which never got a corresponding vma will need to be
+ * freed manually.
+ */
+static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
+{
+	int i;
+
+	for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) {
+		pgd_t pgd = pgdp[i];
+
+		if (pgd_val(pgd) != 0) {
+			pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+			pgdp[i] = native_make_pgd(0);
+
+			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+			pmd_free(mm, pmd);
+		}
+	}
+}
+
+/*
+ * In PAE mode, we need to do a cr3 reload (=tlb flush) when
+ * updating the top-level pagetable entries to guarantee the
+ * processor notices the update.  Since this is expensive, and
+ * all 4 top-level entries are used almost immediately in a
+ * new process's life, we just pre-populate them here.
+ *
+ * Also, if we're in a paravirt environment where the kernel pmd is
+ * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
+ * and initialize the kernel pmds here.
+ */
+static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
+{
+	pud_t *pud;
+	unsigned long addr;
+	int i;
+
+	pud = pud_offset(pgd, 0);
+ 	for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD;
+	     i++, pud++, addr += PUD_SIZE) {
+		pmd_t *pmd = pmd_alloc_one(mm, addr);
+
+		if (!pmd) {
+			pgd_mop_up_pmds(mm, pgd);
+			return 0;
+		}
+
+		if (i >= KERNEL_PGD_BOUNDARY)
+			memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
+			       sizeof(pmd_t) * PTRS_PER_PMD);
+
+		pud_populate(mm, pud, pmd);
+	}
+
+	return 1;
+}
+
+void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
+{
+	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
+
+	/* Note: almost everything apart from _PAGE_PRESENT is
+	   reserved at the pmd (PDPT) level. */
+	set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
+
+	/*
+	 * According to Intel App note "TLBs, Paging-Structure Caches,
+	 * and Their Invalidation", April 2007, document 317080-001,
+	 * section 8.1: in PAE mode we explicitly have to flush the
+	 * TLB via cr3 if the top-level pgd is changed...
+	 */
+	if (mm == current->active_mm)
+		write_cr3(read_cr3());
+}
+#else  /* !CONFIG_X86_PAE */
+/* No need to prepopulate any pagetable entries in non-PAE modes. */
+static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
+{
+	return 1;
+}
+
+static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgd)
+{
+}
+#endif	/* CONFIG_X86_PAE */
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+
+	/* so that alloc_pmd can use it */
+	mm->pgd = pgd;
+	if (pgd)
+		pgd_ctor(pgd);
+
+	if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
+		pgd_dtor(pgd);
+		free_page((unsigned long)pgd);
+		pgd = NULL;
+	}
+
+	return pgd;
+}
+
+void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	pgd_mop_up_pmds(mm, pgd);
+	pgd_dtor(pgd);
+	free_page((unsigned long)pgd);
+}
+
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	int changed = !pte_same(*ptep, entry);
+
+	if (changed && dirty) {
+		*ptep = entry;
+		pte_update_defer(vma->vm_mm, address, ptep);
+		flush_tlb_page(vma, address);
+	}
+
+	return changed;
+}
+
+int ptep_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long addr, pte_t *ptep)
+{
+	int ret = 0;
+
+	if (pte_young(*ptep))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 &ptep->pte);
+
+	if (ret)
+		pte_update(vma->vm_mm, addr, ptep);
+
+	return ret;
+}
+
+int ptep_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pte_t *ptep)
+{
+	int young;
+
+	young = ptep_test_and_clear_young(vma, address, ptep);
+	if (young)
+		flush_tlb_page(vma, address);
+
+	return young;
+}
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 6fb9e7c6893..9ee007be914 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -173,210 +173,6 @@ void reserve_top_address(unsigned long reserve)
 	__VMALLOC_RESERVE += reserve;
 }
 
-pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
-{
-	return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-}
-
-pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-	struct page *pte;
-
-#ifdef CONFIG_HIGHPTE
-	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
-#else
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
-#endif
-	if (pte)
-		pgtable_page_ctor(pte);
-	return pte;
-}
-
-/*
- * List of all pgd's needed for non-PAE so it can invalidate entries
- * in both cached and uncached pgd's; not needed for PAE since the
- * kernel pmd is shared. If PAE were not to share the pmd a similar
- * tactic would be needed. This is essentially codepath-based locking
- * against pageattr.c; it is the unique case in which a valid change
- * of kernel pagetables can't be lazily synchronized by vmalloc faults.
- * vmalloc faults work because attached pagetables are never freed.
- * -- wli
- */
-static inline void pgd_list_add(pgd_t *pgd)
-{
-	struct page *page = virt_to_page(pgd);
-
-	list_add(&page->lru, &pgd_list);
-}
-
-static inline void pgd_list_del(pgd_t *pgd)
-{
-	struct page *page = virt_to_page(pgd);
-
-	list_del(&page->lru);
-}
-
-#define UNSHARED_PTRS_PER_PGD				\
-	(SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)
-
-static void pgd_ctor(void *p)
-{
-	pgd_t *pgd = p;
-	unsigned long flags;
-
-	/* Clear usermode parts of PGD */
-	memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
-
-	spin_lock_irqsave(&pgd_lock, flags);
-
-	/* If the pgd points to a shared pagetable level (either the
-	   ptes in non-PAE, or shared PMD in PAE), then just copy the
-	   references from swapper_pg_dir. */
-	if (PAGETABLE_LEVELS == 2 ||
-	    (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) {
-		clone_pgd_range(pgd + USER_PTRS_PER_PGD,
-				swapper_pg_dir + USER_PTRS_PER_PGD,
-				KERNEL_PGD_PTRS);
-		paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
-					__pa(swapper_pg_dir) >> PAGE_SHIFT,
-					USER_PTRS_PER_PGD,
-					KERNEL_PGD_PTRS);
-	}
-
-	/* list required to sync kernel mapping updates */
-	if (!SHARED_KERNEL_PMD)
-		pgd_list_add(pgd);
-
-	spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-static void pgd_dtor(void *pgd)
-{
-	unsigned long flags; /* can be called from interrupt context */
-
-	if (SHARED_KERNEL_PMD)
-		return;
-
-	spin_lock_irqsave(&pgd_lock, flags);
-	pgd_list_del(pgd);
-	spin_unlock_irqrestore(&pgd_lock, flags);
-}
-
-#ifdef CONFIG_X86_PAE
-/*
- * Mop up any pmd pages which may still be attached to the pgd.
- * Normally they will be freed by munmap/exit_mmap, but any pmd we
- * preallocate which never got a corresponding vma will need to be
- * freed manually.
- */
-static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
-{
-	int i;
-
-	for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) {
-		pgd_t pgd = pgdp[i];
-
-		if (pgd_val(pgd) != 0) {
-			pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
-
-			pgdp[i] = native_make_pgd(0);
-
-			paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT);
-			pmd_free(mm, pmd);
-		}
-	}
-}
-
-/*
- * In PAE mode, we need to do a cr3 reload (=tlb flush) when
- * updating the top-level pagetable entries to guarantee the
- * processor notices the update.  Since this is expensive, and
- * all 4 top-level entries are used almost immediately in a
- * new process's life, we just pre-populate them here.
- *
- * Also, if we're in a paravirt environment where the kernel pmd is
- * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
- * and initialize the kernel pmds here.
- */
-static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
-{
-	pud_t *pud;
-	unsigned long addr;
-	int i;
-
-	pud = pud_offset(pgd, 0);
- 	for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD;
-	     i++, pud++, addr += PUD_SIZE) {
-		pmd_t *pmd = pmd_alloc_one(mm, addr);
-
-		if (!pmd) {
-			pgd_mop_up_pmds(mm, pgd);
-			return 0;
-		}
-
-		if (i >= USER_PTRS_PER_PGD)
-			memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
-			       sizeof(pmd_t) * PTRS_PER_PMD);
-
-		pud_populate(mm, pud, pmd);
-	}
-
-	return 1;
-}
-#else  /* !CONFIG_X86_PAE */
-/* No need to prepopulate any pagetable entries in non-PAE modes. */
-static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
-{
-	return 1;
-}
-
-static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
-{
-}
-#endif	/* CONFIG_X86_PAE */
-
-pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-
-	/* so that alloc_pd can use it */
-	mm->pgd = pgd;
-	if (pgd)
-		pgd_ctor(pgd);
-
-	if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
-		pgd_dtor(pgd);
-		free_page((unsigned long)pgd);
-		pgd = NULL;
-	}
-
-	return pgd;
-}
-
-void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	pgd_mop_up_pmds(mm, pgd);
-	pgd_dtor(pgd);
-	free_page((unsigned long)pgd);
-}
-
-void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
-{
-	pgtable_page_dtor(pte);
-	paravirt_release_pt(page_to_pfn(pte));
-	tlb_remove_page(tlb, pte);
-}
-
-#ifdef CONFIG_X86_PAE
-
-void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
-{
-	paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
-	tlb_remove_page(tlb, virt_to_page(pmd));
-}
-
-#endif
-
 int pmd_bad(pmd_t pmd)
 {
 	WARN_ON_ONCE(pmd_bad_v1(pmd) != pmd_bad_v2(pmd));