1 files changed, 128 insertions, 42 deletions

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5e92b61ad574..02d752460371 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -46,6 +46,7 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/seq_file.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -78,8 +79,7 @@
 
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
- * Also protects non-atomic updates of current_pages and driver_pages, and
- * balloon lists.
+ * Also protects non-atomic updates of current_pages and balloon lists.
  */
 DEFINE_SPINLOCK(xen_reservation_lock);
 
@@ -416,8 +416,12 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 	if (val & _PAGE_PRESENT) {
 		unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
 		pteval_t flags = val & PTE_FLAGS_MASK;
-		unsigned long mfn = pfn_to_mfn(pfn);
+		unsigned long mfn;
 
+		if (!xen_feature(XENFEAT_auto_translated_physmap))
+			mfn = get_phys_to_machine(pfn);
+		else
+			mfn = pfn;
 		/*
 		 * If there's no mfn for the pfn, then just create an
 		 * empty non-present pte.  Unfortunately this loses
@@ -427,8 +431,18 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
 		if (unlikely(mfn == INVALID_P2M_ENTRY)) {
 			mfn = 0;
 			flags = 0;
+		} else {
+			/*
+			 * Paramount to do this test _after_ the
+			 * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
+			 * IDENTITY_FRAME_BIT resolves to true.
+			 */
+			mfn &= ~FOREIGN_FRAME_BIT;
+			if (mfn & IDENTITY_FRAME_BIT) {
+				mfn &= ~IDENTITY_FRAME_BIT;
+				flags |= _PAGE_IOMAP;
+			}
 		}
-
 		val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
 	}
 
@@ -532,6 +546,41 @@ pte_t xen_make_pte(pteval_t pte)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
 
+#ifdef CONFIG_XEN_DEBUG
+pte_t xen_make_pte_debug(pteval_t pte)
+{
+	phys_addr_t addr = (pte & PTE_PFN_MASK);
+	phys_addr_t other_addr;
+	bool io_page = false;
+	pte_t _pte;
+
+	if (pte & _PAGE_IOMAP)
+		io_page = true;
+
+	_pte = xen_make_pte(pte);
+
+	if (!addr)
+		return _pte;
+
+	if (io_page &&
+	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+		other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
+		WARN_ONCE(addr != other_addr,
+			"0x%lx is using VM_IO, but it is 0x%lx!\n",
+			(unsigned long)addr, (unsigned long)other_addr);
+	} else {
+		pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
+		other_addr = (_pte.pte & PTE_PFN_MASK);
+		WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
+			"0x%lx is missing VM_IO (and wasn't fixed)!\n",
+			(unsigned long)addr);
+	}
+
+	return _pte;
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
+#endif
+
 pgd_t xen_make_pgd(pgdval_t pgd)
 {
 	pgd = pte_pfn_to_mfn(pgd);
@@ -986,10 +1035,9 @@ static void xen_pgd_pin(struct mm_struct *mm)
  */
 void xen_mm_pin_all(void)
 {
-	unsigned long flags;
 	struct page *page;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
 		if (!PagePinned(page)) {
@@ -998,7 +1046,7 @@ void xen_mm_pin_all(void)
 		}
 	}
 
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 }
 
 /*
@@ -1006,7 +1054,7 @@ void xen_mm_pin_all(void)
  * that's before we have page structures to store the bits.  So do all
  * the book-keeping now.
  */
-static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page,
+static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 				  enum pt_level level)
 {
 	SetPagePinned(page);
@@ -1099,10 +1147,9 @@ static void xen_pgd_unpin(struct mm_struct *mm)
  */
 void xen_mm_unpin_all(void)
 {
-	unsigned long flags;
 	struct page *page;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
 		if (PageSavePinned(page)) {
@@ -1112,7 +1159,7 @@ void xen_mm_unpin_all(void)
 		}
 	}
 
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 }
 
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
@@ -1140,7 +1187,7 @@ static void drop_other_mm_ref(void *info)
 
 	active_mm = percpu_read(cpu_tlbstate.active_mm);
 
-	if (active_mm == mm)
+	if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
 		leave_mm(smp_processor_id());
 
 	/* If this cpu still has a stale cr3 reference, then make sure
@@ -1224,13 +1271,27 @@ void xen_exit_mmap(struct mm_struct *mm)
 	spin_unlock(&mm->page_table_lock);
 }
 
-static __init void xen_pagetable_setup_start(pgd_t *base)
+static void __init xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
+static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+{
+	/* reserve the range used */
+	native_pagetable_reserve(start, end);
+
+	/* set as RW the rest */
+	printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
+			PFN_PHYS(pgt_buf_top));
+	while (end < PFN_PHYS(pgt_buf_top)) {
+		make_lowmem_page_readwrite(__va(end));
+		end += PAGE_SIZE;
+	}
+}
+
 static void xen_post_allocator_init(void);
 
-static __init void xen_pagetable_setup_done(pgd_t *base)
+static void __init xen_pagetable_setup_done(pgd_t *base)
 {
 	xen_setup_shared_info();
 	xen_post_allocator_init();
@@ -1426,32 +1487,39 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
 
-static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
-{
-	unsigned long pfn = pte_pfn(pte);
-
 #ifdef CONFIG_X86_32
+static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
+{
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
-#endif
+
+	return pte;
+}
+#else /* CONFIG_X86_64 */
+static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
 
 	/*
 	 * If the new pfn is within the range of the newly allocated
 	 * kernel pagetable, and it isn't being mapped into an
-	 * early_ioremap fixmap slot, make sure it is RO.
+	 * early_ioremap fixmap slot as a freshly allocated page, make sure
+	 * it is RO.
 	 */
-	if (!is_early_ioremap_ptep(ptep) &&
-	    pfn >= e820_table_start && pfn < e820_table_end)
+	if (((!is_early_ioremap_ptep(ptep) &&
+			pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
+			(is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
 		pte = pte_wrprotect(pte);
 
 	return pte;
 }
+#endif /* CONFIG_X86_64 */
 
 /* Init-time set_pte while constructing initial pagetables, which
    doesn't allow RO pagetable pages to be remapped RW */
-static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
+static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
 	pte = mask_rw_pte(ptep, pte);
 
@@ -1469,7 +1537,7 @@ static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
-static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
+static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
 	BUG_ON(mem_map);	/* should only be used early */
@@ -1479,7 +1547,7 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
 }
 
 /* Used for pmd and pud */
-static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
+static void __init xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
 {
 #ifdef CONFIG_FLATMEM
 	BUG_ON(mem_map);	/* should only be used early */
@@ -1489,13 +1557,13 @@ static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
 
 /* Early release_pte assumes that all pts are pinned, since there's
    only init_mm and anything attached to that is pinned. */
-static __init void xen_release_pte_init(unsigned long pfn)
+static void __init xen_release_pte_init(unsigned long pfn)
 {
 	pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
-static __init void xen_release_pmd_init(unsigned long pfn)
+static void __init xen_release_pmd_init(unsigned long pfn)
 {
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
@@ -1621,7 +1689,7 @@ static void set_page_prot(void *addr, pgprot_t prot)
 		BUG();
 }
 
-static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
+static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 {
 	unsigned pmdidx, pteidx;
 	unsigned ident_pte;
@@ -1653,9 +1721,6 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 
-			if (pfn > max_pfn_mapped)
-				max_pfn_mapped = pfn;
-
 			if (!pte_none(pte_page[pteidx]))
 				continue;
 
@@ -1697,7 +1762,7 @@ static void convert_pfn_mfn(void *v)
 }
 
 /*
- * Set up the inital kernel pagetable.
+ * Set up the initial kernel pagetable.
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
@@ -1707,12 +1772,18 @@ static void convert_pfn_mfn(void *v)
  * of the physical mapping once some sort of allocator has been set
  * up.
  */
-__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 					 unsigned long max_pfn)
 {
 	pud_t *l3;
 	pmd_t *l2;
 
+	/* max_pfn_mapped is the last pfn mapped in the initial memory
+	 * mappings. Considering that on Xen after the kernel mappings we
+	 * have the mappings of some pages that don't exist in pfn space, we
+	 * set max_pfn_mapped to the last real pfn mapped. */
+	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+
 	/* Zap identity mapping */
 	init_level4_pgt[0] = __pgd(0);
 
@@ -1772,7 +1843,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
 static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
 
-static __init void xen_write_cr3_init(unsigned long cr3)
+static void __init xen_write_cr3_init(unsigned long cr3)
 {
 	unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
 
@@ -1809,7 +1880,7 @@ static __init void xen_write_cr3_init(unsigned long cr3)
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 
-__init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
+pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 					 unsigned long max_pfn)
 {
 	pmd_t *kernel_pmd;
@@ -1817,9 +1888,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 	initial_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
-				  xen_start_info->nr_pt_frames * PAGE_SIZE +
-				  512*1024);
+	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
@@ -1917,7 +1986,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
-__init void xen_ident_map_ISA(void)
+void __init xen_ident_map_ISA(void)
 {
 	unsigned long pa;
 
@@ -1940,8 +2009,11 @@ __init void xen_ident_map_ISA(void)
 	xen_flush_tlb();
 }
 
-static __init void xen_post_allocator_init(void)
+static void __init xen_post_allocator_init(void)
 {
+#ifdef CONFIG_XEN_DEBUG
+	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
+#endif
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
@@ -1974,7 +2046,7 @@ static void xen_leave_lazy_mmu(void)
 	preempt_enable();
 }
 
-static const struct pv_mmu_ops xen_mmu_ops __initdata = {
+static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.read_cr2 = xen_read_cr2,
 	.write_cr2 = xen_write_cr2,
 
@@ -2047,6 +2119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 void __init xen_init_mmu_ops(void)
 {
+	x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
 	x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
 	x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
 	pv_mmu_ops = xen_mmu_ops;
@@ -2074,7 +2147,7 @@ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order,
 			in_frames[i] = virt_to_mfn(vaddr);
 
 		MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
-		set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+		__set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
 
 		if (out_frames)
 			out_frames[i] = virt_to_pfn(vaddr);
@@ -2353,6 +2426,18 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
 
 #ifdef CONFIG_XEN_DEBUG_FS
 
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+	.open		= p2m_dump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct dentry *d_mmu_debug;
 
 static int __init xen_mmu_debugfs(void)
@@ -2408,6 +2493,7 @@ static int __init xen_mmu_debugfs(void)
 	debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
 			   &mmu_stats.prot_commit_batched);
 
+	debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
 	return 0;
 }
 fs_initcall(xen_mmu_debugfs);