Merge branch 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6

* 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6:
  [S390] dynamic page tables.
  [S390] Add four level page tables for CONFIG_64BIT=y.
  [S390] 1K/2K page table pages.
  [S390] Remove a.out header file.
  [S390] sclp_vt220: Fix vt220 initialization
  [S390] qdio: avoid hang when establishing qdio queues
  [S390] VMEM_MAX_PHYS overflow on 31 bit.
  [S390] zcrypt: Do not start ap poll thread per default
  [S390] Fix __ffs_word_loop/__ffz_word_loop inlnie assembly.
  [S390] Wire up new timerfd syscalls.
  [S390] Update default configuration.

12 files changed, 275 insertions, 265 deletions

diff --git a/include/asm-s390/a.out.h b/include/asm-s390/a.out.h
deleted file mode 100644
index 8d6bd9c2952e..000000000000
--- a/include/asm-s390/a.out.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- *  include/asm-s390/a.out.h
- *
- *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *
- *  Derived from "include/asm-i386/a.out.h"
- *    Copyright (C) 1992, Linus Torvalds
- *
- * I don't think we'll ever need a.out ...
- */
-
-#ifndef __S390_A_OUT_H__
-#define __S390_A_OUT_H__
-
-struct exec
-{
-  unsigned long a_info;		/* Use macros N_MAGIC, etc for access */
-  unsigned a_text;		/* length of text, in bytes */
-  unsigned a_data;		/* length of data, in bytes */
-  unsigned a_bss;		/* length of uninitialized data area for file, in bytes */
-  unsigned a_syms;		/* length of symbol table data in file, in bytes */
-  unsigned a_entry;		/* start address */
-  unsigned a_trsize;		/* length of relocation info for text, in bytes */
-  unsigned a_drsize;		/* length of relocation info for data, in bytes */
-};
-
-#define N_TRSIZE(a)	((a).a_trsize)
-#define N_DRSIZE(a)	((a).a_drsize)
-#define N_SYMSIZE(a)	((a).a_syms)
-
-#endif /* __A_OUT_GNU_H__ */
diff --git a/include/asm-s390/bitops.h b/include/asm-s390/bitops.h
index 882db054110c..ab83c844d04c 100644
--- a/include/asm-s390/bitops.h
+++ b/include/asm-s390/bitops.h
@@ -472,7 +472,7 @@ static inline unsigned long __ffz_word_loop(const unsigned long *addr,
 		"	brct	%1,0b\n"
 		"1:\n"
 #endif
-		: "+a" (bytes), "+d" (size)
+		: "+&a" (bytes), "+&d" (size)
 		: "d" (-1UL), "a" (addr), "m" (*(addrtype *) addr)
 		: "cc" );
 	return bytes;
@@ -507,7 +507,7 @@ static inline unsigned long __ffs_word_loop(const unsigned long *addr,
 		"	brct	%1,0b\n"
 		"1:\n"
 #endif
-		: "+a" (bytes), "+a" (size)
+		: "+&a" (bytes), "+&a" (size)
 		: "d" (0UL), "a" (addr), "m" (*(addrtype *) addr)
 		: "cc" );
 	return bytes;
diff --git a/include/asm-s390/elf.h b/include/asm-s390/elf.h
index b73a424d0f97..b3ac262c4582 100644
--- a/include/asm-s390/elf.h
+++ b/include/asm-s390/elf.h
@@ -115,6 +115,7 @@ typedef s390_regs elf_gregset_t;
 
 #include <linux/sched.h>	/* for task_struct */
 #include <asm/system.h>		/* for save_access_regs */
+#include <asm/mmu_context.h>
 
 /*
  * This is used to ensure we don't load something for the wrong architecture.
@@ -137,14 +138,7 @@ typedef s390_regs elf_gregset_t;
    use of this is to invoke "./ld.so someprog" to test out a new version of
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
-
-#ifndef __s390x__
-#define ELF_ET_DYN_BASE         ((TASK_SIZE & 0x80000000) \
-                                ? TASK_SIZE / 3 * 2 \
-                                : 2 * TASK_SIZE / 3)
-#else /* __s390x__ */
-#define ELF_ET_DYN_BASE         (TASK_SIZE / 3 * 2)
-#endif /* __s390x__ */
+#define ELF_ET_DYN_BASE		(STACK_TOP / 3 * 2)
 
 /* Wow, the "main" arch needs arch dependent functions too.. :) */
 
@@ -214,4 +208,16 @@ do {							\
 } while (0)
 #endif /* __s390x__ */
 
+/*
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically.
+ */
+#define elf_read_implies_exec(ex, executable_stack)	\
+({							\
+	if (current->mm->context.noexec &&		\
+	    executable_stack != EXSTACK_DISABLE_X)	\
+		disable_noexec(current->mm, current);	\
+	current->mm->context.noexec == 0;		\
+})
+
 #endif
diff --git a/include/asm-s390/mmu.h b/include/asm-s390/mmu.h
index ccd36d26615a..1698e29c5b20 100644
--- a/include/asm-s390/mmu.h
+++ b/include/asm-s390/mmu.h
@@ -1,7 +1,12 @@
 #ifndef __MMU_H
 #define __MMU_H
 
-/* Default "unsigned long" context */
-typedef unsigned long mm_context_t;
+typedef struct {
+	struct list_head crst_list;
+	struct list_head pgtable_list;
+	unsigned long asce_bits;
+	unsigned long asce_limit;
+	int noexec;
+} mm_context_t;
 
 #endif
diff --git a/include/asm-s390/mmu_context.h b/include/asm-s390/mmu_context.h
index a77d4ba3c8eb..b5a34c6f91a9 100644
--- a/include/asm-s390/mmu_context.h
+++ b/include/asm-s390/mmu_context.h
@@ -10,15 +10,19 @@
 #define __S390_MMU_CONTEXT_H
 
 #include <asm/pgalloc.h>
+#include <asm/uaccess.h>
 #include <asm-generic/mm_hooks.h>
 
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
-	mm->context = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
+	mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
 #ifdef CONFIG_64BIT
-	mm->context |= _ASCE_TYPE_REGION3;
+	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
+	mm->context.noexec = s390_noexec;
+	mm->context.asce_limit = STACK_TOP_MAX;
+	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
 }
 
@@ -32,24 +36,25 @@ static inline int init_new_context(struct task_struct *tsk,
 
 static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
 {
-	S390_lowcore.user_asce = mm->context | __pa(mm->pgd);
+	pgd_t *pgd = mm->pgd;
+
+	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
 	if (switch_amode) {
 		/* Load primary space page table origin. */
-		pgd_t *shadow_pgd = get_shadow_table(mm->pgd) ? : mm->pgd;
-		S390_lowcore.user_exec_asce = mm->context | __pa(shadow_pgd);
+		pgd = mm->context.noexec ? get_shadow_table(pgd) : pgd;
+		S390_lowcore.user_exec_asce = mm->context.asce_bits | __pa(pgd);
 		asm volatile(LCTL_OPCODE" 1,1,%0\n"
 			     : : "m" (S390_lowcore.user_exec_asce) );
 	} else
 		/* Load home space page table origin. */
 		asm volatile(LCTL_OPCODE" 13,13,%0"
 			     : : "m" (S390_lowcore.user_asce) );
+	set_fs(current->thread.mm_segment);
 }
 
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
-	if (unlikely(prev == next))
-		return;
 	cpu_set(smp_processor_id(), next->cpu_vm_mask);
 	update_mm(next, tsk);
 }
@@ -61,7 +66,6 @@ static inline void activate_mm(struct mm_struct *prev,
                                struct mm_struct *next)
 {
         switch_mm(prev, next, current);
-	set_fs(current->thread.mm_segment);
 }
 
 #endif /* __S390_MMU_CONTEXT_H */
diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h
index 7f29a981f48c..fe7f92b6ae6d 100644
--- a/include/asm-s390/page.h
+++ b/include/asm-s390/page.h
@@ -74,43 +74,17 @@ static inline void copy_page(void *to, void *from)
 
 typedef struct { unsigned long pgprot; } pgprot_t;
 typedef struct { unsigned long pte; } pte_t;
-
-#define pte_val(x)      ((x).pte)
-#define pgprot_val(x)   ((x).pgprot)
-
-#ifndef __s390x__
-
 typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pud; } pud_t;
-typedef struct {
-        unsigned long pgd0;
-        unsigned long pgd1;
-        unsigned long pgd2;
-        unsigned long pgd3;
-        } pgd_t;
-
-#define pmd_val(x)      ((x).pmd)
-#define pud_val(x)	((x).pud)
-#define pgd_val(x)      ((x).pgd0)
-
-#else /* __s390x__ */
-
-typedef struct { 
-        unsigned long pmd0;
-        unsigned long pmd1; 
-        } pmd_t;
-typedef struct { unsigned long pud; } pud_t;
 typedef struct { unsigned long pgd; } pgd_t;
+typedef pte_t *pgtable_t;
 
-#define pmd_val(x)      ((x).pmd0)
-#define pmd_val1(x)     ((x).pmd1)
+#define pgprot_val(x)	((x).pgprot)
+#define pte_val(x)	((x).pte)
+#define pmd_val(x)	((x).pmd)
 #define pud_val(x)	((x).pud)
 #define pgd_val(x)      ((x).pgd)
 
-#endif /* __s390x__ */
-
-typedef struct page *pgtable_t;
-
 #define __pte(x)        ((pte_t) { (x) } )
 #define __pmd(x)        ((pmd_t) { (x) } )
 #define __pgd(x)        ((pgd_t) { (x) } )
@@ -167,7 +141,7 @@ static inline int pfn_valid(unsigned long pfn)
 #define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
-#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
+#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #include <asm-generic/memory_model.h>
diff --git a/include/asm-s390/pgalloc.h b/include/asm-s390/pgalloc.h
index 900d44807e10..f5b2bf3d7c1d 100644
--- a/include/asm-s390/pgalloc.h
+++ b/include/asm-s390/pgalloc.h
@@ -20,10 +20,11 @@
 #define check_pgt_cache()	do {} while (0)
 
 unsigned long *crst_table_alloc(struct mm_struct *, int);
-void crst_table_free(unsigned long *);
+void crst_table_free(struct mm_struct *, unsigned long *);
 
-unsigned long *page_table_alloc(int);
-void page_table_free(unsigned long *);
+unsigned long *page_table_alloc(struct mm_struct *);
+void page_table_free(struct mm_struct *, unsigned long *);
+void disable_noexec(struct mm_struct *, struct task_struct *);
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
@@ -72,23 +73,49 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 
 static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 {
-	return _REGION3_ENTRY_EMPTY;
+	if (mm->context.asce_limit <= (1UL << 31))
+		return _SEGMENT_ENTRY_EMPTY;
+	if (mm->context.asce_limit <= (1UL << 42))
+		return _REGION3_ENTRY_EMPTY;
+	return _REGION2_ENTRY_EMPTY;
 }
 
-#define pud_alloc_one(mm,address)		({ BUG(); ((pud_t *)2); })
-#define pud_free(mm, x)				do { } while (0)
+int crst_table_upgrade(struct mm_struct *, unsigned long limit);
+void crst_table_downgrade(struct mm_struct *, unsigned long limit);
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+	unsigned long *table = crst_table_alloc(mm, mm->context.noexec);
+	if (table)
+		crst_table_init(table, _REGION3_ENTRY_EMPTY);
+	return (pud_t *) table;
+}
+#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *crst = crst_table_alloc(mm, s390_noexec);
-	if (crst)
-		crst_table_init(crst, _SEGMENT_ENTRY_EMPTY);
-	return (pmd_t *) crst;
+	unsigned long *table = crst_table_alloc(mm, mm->context.noexec);
+	if (table)
+		crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+	return (pmd_t *) table;
 }
-#define pmd_free(mm, pmd) crst_table_free((unsigned long *)pmd)
+#define pmd_free(mm, pmd) crst_table_free(mm, (unsigned long *) pmd)
 
-#define pgd_populate(mm, pgd, pud)		BUG()
-#define pgd_populate_kernel(mm, pgd, pud)	BUG()
+static inline void pgd_populate_kernel(struct mm_struct *mm,
+				       pgd_t *pgd, pud_t *pud)
+{
+	pgd_val(*pgd) = _REGION2_ENTRY | __pa(pud);
+}
+
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+{
+	pgd_populate_kernel(mm, pgd, pud);
+	if (mm->context.noexec) {
+		pgd = get_shadow_table(pgd);
+		pud = get_shadow_table(pud);
+		pgd_populate_kernel(mm, pgd, pud);
+	}
+}
 
 static inline void pud_populate_kernel(struct mm_struct *mm,
 				       pud_t *pud, pmd_t *pmd)
@@ -98,63 +125,50 @@ static inline void pud_populate_kernel(struct mm_struct *mm,
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pud_t *shadow_pud = get_shadow_table(pud);
-	pmd_t *shadow_pmd = get_shadow_table(pmd);
-
-	if (shadow_pud && shadow_pmd)
-		pud_populate_kernel(mm, shadow_pud, shadow_pmd);
 	pud_populate_kernel(mm, pud, pmd);
+	if (mm->context.noexec) {
+		pud = get_shadow_table(pud);
+		pmd = get_shadow_table(pmd);
+		pud_populate_kernel(mm, pud, pmd);
+	}
 }
 
 #endif /* __s390x__ */
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	unsigned long *crst = crst_table_alloc(mm, s390_noexec);
-	if (crst)
-		crst_table_init(crst, pgd_entry_type(mm));
-	return (pgd_t *) crst;
+	INIT_LIST_HEAD(&mm->context.crst_list);
+	INIT_LIST_HEAD(&mm->context.pgtable_list);
+	return (pgd_t *) crst_table_alloc(mm, s390_noexec);
 }
-#define pgd_free(mm, pgd) crst_table_free((unsigned long *) pgd)
+#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
 
-static inline void 
-pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+				       pmd_t *pmd, pte_t *pte)
 {
-#ifndef __s390x__
-	pmd_val(pmd[0]) = _SEGMENT_ENTRY + __pa(pte);
-	pmd_val(pmd[1]) = _SEGMENT_ENTRY + __pa(pte+256);
-	pmd_val(pmd[2]) = _SEGMENT_ENTRY + __pa(pte+512);
-	pmd_val(pmd[3]) = _SEGMENT_ENTRY + __pa(pte+768);
-#else /* __s390x__ */
 	pmd_val(*pmd) = _SEGMENT_ENTRY + __pa(pte);
-	pmd_val1(*pmd) = _SEGMENT_ENTRY + __pa(pte+256);
-#endif /* __s390x__ */
 }
 
-static inline void
-pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page)
+static inline void pmd_populate(struct mm_struct *mm,
+				pmd_t *pmd, pgtable_t pte)
 {
-	pte_t *pte = (pte_t *)page_to_phys(page);
-	pmd_t *shadow_pmd = get_shadow_table(pmd);
-	pte_t *shadow_pte = get_shadow_pte(pte);
-
 	pmd_populate_kernel(mm, pmd, pte);
-	if (shadow_pmd && shadow_pte)
-		pmd_populate_kernel(mm, shadow_pmd, shadow_pte);
+	if (mm->context.noexec) {
+		pmd = get_shadow_table(pmd);
+		pmd_populate_kernel(mm, pmd, pte + PTRS_PER_PTE);
+	}
 }
-#define pmd_pgtable(pmd) pmd_page(pmd)
+
+#define pmd_pgtable(pmd) \
+	(pgtable_t)(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)
 
 /*
  * page table entry allocation/free routines.
  */
-#define pte_alloc_one_kernel(mm, vmaddr) \
-	((pte_t *) page_table_alloc(s390_noexec))
-#define pte_alloc_one(mm, vmaddr) \
-	virt_to_page(page_table_alloc(s390_noexec))
-
-#define pte_free_kernel(mm, pte) \
-	page_table_free((unsigned long *) pte)
-#define pte_free(mm, pte) \
-	page_table_free((unsigned long *) page_to_phys((struct page *) pte))
+#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
+#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
+
+#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
+#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
 
 #endif /* _S390_PGALLOC_H */
diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h
index 3f520754e71c..65154dc9a9e5 100644
--- a/include/asm-s390/pgtable.h
+++ b/include/asm-s390/pgtable.h
@@ -57,21 +57,21 @@ extern char empty_zero_page[PAGE_SIZE];
  * PGDIR_SHIFT determines what a third-level page table entry can map
  */
 #ifndef __s390x__
-# define PMD_SHIFT	22
-# define PUD_SHIFT	22
-# define PGDIR_SHIFT	22
+# define PMD_SHIFT	20
+# define PUD_SHIFT	20
+# define PGDIR_SHIFT	20
 #else /* __s390x__ */
-# define PMD_SHIFT	21
+# define PMD_SHIFT	20
 # define PUD_SHIFT	31
-# define PGDIR_SHIFT	31
+# define PGDIR_SHIFT	42
 #endif /* __s390x__ */
 
 #define PMD_SIZE        (1UL << PMD_SHIFT)
 #define PMD_MASK        (~(PMD_SIZE-1))
 #define PUD_SIZE	(1UL << PUD_SHIFT)
 #define PUD_MASK	(~(PUD_SIZE-1))
-#define PGDIR_SIZE      (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK      (~(PGDIR_SIZE-1))
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 /*
  * entries per page directory level: the S390 is two-level, so
@@ -79,17 +79,15 @@ extern char empty_zero_page[PAGE_SIZE];
  * for S390 segment-table entries are combined to one PGD
  * that leads to 1024 pte per pgd
  */
+#define PTRS_PER_PTE	256
 #ifndef __s390x__
-# define PTRS_PER_PTE    1024
-# define PTRS_PER_PMD    1
-# define PTRS_PER_PUD	1
-# define PTRS_PER_PGD    512
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PUD	1
 #else /* __s390x__ */
-# define PTRS_PER_PTE    512
-# define PTRS_PER_PMD    1024
-# define PTRS_PER_PUD	1
-# define PTRS_PER_PGD    2048
+#define PTRS_PER_PMD	2048
+#define PTRS_PER_PUD	2048
 #endif /* __s390x__ */
+#define PTRS_PER_PGD	2048
 
 #define FIRST_USER_ADDRESS  0
 
@@ -127,8 +125,9 @@ extern char empty_zero_page[PAGE_SIZE];
  * mapping. This needs to be calculated at compile time since the size of the
  * VMEM_MAP is static but the size of struct page can change.
  */
-#define VMEM_MAX_PHYS	min(VMALLOC_START, ((VMEM_MAP_END - VMALLOC_END) / \
-			  sizeof(struct page) * PAGE_SIZE) & ~((16 << 20) - 1))
+#define VMEM_MAX_PAGES	((VMEM_MAP_END - VMALLOC_END) / sizeof(struct page))
+#define VMEM_MAX_PFN	min(VMALLOC_START >> PAGE_SHIFT, VMEM_MAX_PAGES)
+#define VMEM_MAX_PHYS	((VMEM_MAX_PFN << PAGE_SHIFT) & ~((16 << 20) - 1))
 #define VMEM_MAP	((struct page *) VMALLOC_END)
 
 /*
@@ -375,24 +374,6 @@ extern char empty_zero_page[PAGE_SIZE];
 # define PxD_SHADOW_SHIFT	2
 #endif /* __s390x__ */
 
-static inline struct page *get_shadow_page(struct page *page)
-{
-	if (s390_noexec && page->index)
-		return virt_to_page((void *)(addr_t) page->index);
-	return NULL;
-}
-
-static inline void *get_shadow_pte(void *table)
-{
-	unsigned long addr, offset;
-	struct page *page;
-
-	addr = (unsigned long) table;
-	offset = addr & (PAGE_SIZE - 1);
-	page = virt_to_page((void *)(addr ^ offset));
-	return (void *)(addr_t)(page->index ? (page->index | offset) : 0UL);
-}
-
 static inline void *get_shadow_table(void *table)
 {
 	unsigned long addr, offset;
@@ -410,17 +391,16 @@ static inline void *get_shadow_table(void *table)
  * hook is made available.
  */
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *pteptr, pte_t pteval)
+			      pte_t *ptep, pte_t entry)
 {
-	pte_t *shadow_pte = get_shadow_pte(pteptr);
-
-	*pteptr = pteval;
-	if (shadow_pte) {
-		if (!(pte_val(pteval) & _PAGE_INVALID) &&
-		    (pte_val(pteval) & _PAGE_SWX))
-			pte_val(*shadow_pte) = pte_val(pteval) | _PAGE_RO;
+	*ptep = entry;
+	if (mm->context.noexec) {
+		if (!(pte_val(entry) & _PAGE_INVALID) &&
+		    (pte_val(entry) & _PAGE_SWX))
+			pte_val(entry) |= _PAGE_RO;
 		else
-			pte_val(*shadow_pte) = _PAGE_TYPE_EMPTY;
+			pte_val(entry) = _PAGE_TYPE_EMPTY;
+		ptep[PTRS_PER_PTE] = entry;
 	}
 }
 
@@ -439,24 +419,58 @@ static inline int pud_bad(pud_t pud)	 { return 0; }
 
 #else /* __s390x__ */
 
-static inline int pgd_present(pgd_t pgd) { return 1; }
-static inline int pgd_none(pgd_t pgd)	 { return 0; }
-static inline int pgd_bad(pgd_t pgd)	 { return 0; }
+static inline int pgd_present(pgd_t pgd)
+{
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
+		return 1;
+	return (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) != 0UL;
+}
+
+static inline int pgd_none(pgd_t pgd)
+{
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
+		return 0;
+	return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL;
+}
+
+static inline int pgd_bad(pgd_t pgd)
+{
+	/*
+	 * With dynamic page table levels the pgd can be a region table
+	 * entry or a segment table entry. Check for the bit that are
+	 * invalid for either table entry.
+	 */
+	unsigned long mask =
+		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
+		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
+	return (pgd_val(pgd) & mask) != 0;
+}
 
 static inline int pud_present(pud_t pud)
 {
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
+		return 1;
 	return (pud_val(pud) & _REGION_ENTRY_ORIGIN) != 0UL;
 }
 
 static inline int pud_none(pud_t pud)
 {
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
+		return 0;
 	return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL;
 }
 
 static inline int pud_bad(pud_t pud)
 {
-	unsigned long mask = ~_REGION_ENTRY_ORIGIN & ~_REGION_ENTRY_INV;
-	return (pud_val(pud) & mask) != _REGION3_ENTRY;
+	/*
+	 * With dynamic page table levels the pud can be a region table
+	 * entry or a segment table entry. Check for the bit that are
+	 * invalid for either table entry.
+	 */
+	unsigned long mask =
+		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV &
+		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
+	return (pud_val(pud) & mask) != 0;
 }
 
 #endif /* __s390x__ */
@@ -535,24 +549,30 @@ static inline int pte_young(pte_t pte)
 #define pgd_clear(pgd)		do { } while (0)
 #define pud_clear(pud)		do { } while (0)
 
-static inline void pmd_clear_kernel(pmd_t * pmdp)
+#else /* __s390x__ */
+
+static inline void pgd_clear_kernel(pgd_t * pgd)
 {
-	pmd_val(pmdp[0]) = _SEGMENT_ENTRY_EMPTY;
-	pmd_val(pmdp[1]) = _SEGMENT_ENTRY_EMPTY;
-	pmd_val(pmdp[2]) = _SEGMENT_ENTRY_EMPTY;
-	pmd_val(pmdp[3]) = _SEGMENT_ENTRY_EMPTY;
+	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
+		pgd_val(*pgd) = _REGION2_ENTRY_EMPTY;
 }
 
-#else /* __s390x__ */
+static inline void pgd_clear(pgd_t * pgd)
+{
+	pgd_t *shadow = get_shadow_table(pgd);
 
-#define pgd_clear(pgd)		do { } while (0)
+	pgd_clear_kernel(pgd);
+	if (shadow)
+		pgd_clear_kernel(shadow);
+}
 
 static inline void pud_clear_kernel(pud_t *pud)
 {
-	pud_val(*pud) = _REGION3_ENTRY_EMPTY;
+	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+		pud_val(*pud) = _REGION3_ENTRY_EMPTY;
 }
 
-static inline void pud_clear(pud_t * pud)
+static inline void pud_clear(pud_t *pud)
 {
 	pud_t *shadow = get_shadow_table(pud);
 
@@ -561,30 +581,27 @@ static inline void pud_clear(pud_t * pud)
 		pud_clear_kernel(shadow);
 }
 
+#endif /* __s390x__ */
+
 static inline void pmd_clear_kernel(pmd_t * pmdp)
 {
 	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
-	pmd_val1(*pmdp) = _SEGMENT_ENTRY_EMPTY;
 }
 
-#endif /* __s390x__ */
-
-static inline void pmd_clear(pmd_t * pmdp)
+static inline void pmd_clear(pmd_t *pmd)
 {
-	pmd_t *shadow_pmd = get_shadow_table(pmdp);
+	pmd_t *shadow = get_shadow_table(pmd);
 
-	pmd_clear_kernel(pmdp);
-	if (shadow_pmd)
-		pmd_clear_kernel(shadow_pmd);
+	pmd_clear_kernel(pmd);
+	if (shadow)
+		pmd_clear_kernel(shadow);
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	pte_t *shadow_pte = get_shadow_pte(ptep);
-
 	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
-	if (shadow_pte)
-		pte_val(*shadow_pte) = _PAGE_TYPE_EMPTY;
+	if (mm->context.noexec)
+		pte_val(ptep[PTRS_PER_PTE]) = _PAGE_TYPE_EMPTY;
 }
 
 /*
@@ -665,7 +682,7 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 {
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
 #ifndef __s390x__
-		/* S390 has 1mb segments, we are emulating 4MB segments */
+		/* pto must point to the start of the segment table */
 		pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
 #else
 		/* ipte in zarch mode can do the math */
@@ -679,12 +696,12 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 	pte_val(*ptep) = _PAGE_TYPE_EMPTY;
 }
 
-static inline void ptep_invalidate(unsigned long address, pte_t *ptep)
+static inline void ptep_invalidate(struct mm_struct *mm,
+				   unsigned long address, pte_t *ptep)
 {
 	__ptep_ipte(address, ptep);
-	ptep = get_shadow_pte(ptep);
-	if (ptep)
-		__ptep_ipte(address, ptep);
+	if (mm->context.noexec)
+		__ptep_ipte(address, ptep + PTRS_PER_PTE);
 }
 
 /*
@@ -706,7 +723,7 @@ static inline void ptep_invalidate(unsigned long address, pte_t *ptep)
 	pte_t __pte = *(__ptep);					\
 	if (atomic_read(&(__mm)->mm_users) > 1 ||			\
 	    (__mm) != current->active_mm)				\
-		ptep_invalidate(__address, __ptep);			\
+		ptep_invalidate(__mm, __address, __ptep);		\
 	else								\
 		pte_clear((__mm), (__address), (__ptep));		\
 	__pte;								\
@@ -717,7 +734,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 				     unsigned long address, pte_t *ptep)
 {
 	pte_t pte = *ptep;
-	ptep_invalidate(address, ptep);
+	ptep_invalidate(vma->vm_mm, address, ptep);
 	return pte;
 }
 
@@ -738,7 +755,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	if (full)
 		pte_clear(mm, addr, ptep);
 	else
-		ptep_invalidate(addr, ptep);
+		ptep_invalidate(mm, addr, ptep);
 	return pte;
 }
 
@@ -749,7 +766,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	if (pte_write(__pte)) {						\
 		if (atomic_read(&(__mm)->mm_users) > 1 ||		\
 		    (__mm) != current->active_mm)			\
-			ptep_invalidate(__addr, __ptep);		\
+			ptep_invalidate(__mm, __addr, __ptep);		\
 		set_pte_at(__mm, __addr, __ptep, pte_wrprotect(__pte));	\
 	}								\
 })
@@ -759,7 +776,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 ({									\
 	int __changed = !pte_same(*(__ptep), __entry);			\
 	if (__changed) {						\
-		ptep_invalidate(__addr, __ptep);			\
+		ptep_invalidate((__vma)->vm_mm, __addr, __ptep);	\
 		set_pte_at((__vma)->vm_mm, __addr, __ptep, __entry);	\
 	}								\
 	__changed;							\
@@ -840,13 +857,21 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
 
 #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
 #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
-#define pgd_deref(pgd) ({ BUG(); 0UL; })
+#define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
 
-#define pud_offset(pgd, address) ((pud_t *) pgd)
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+	pud_t *pud = (pud_t *) pgd;
+	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
+		pud = (pud_t *) pgd_deref(*pgd);
+	return pud  + pud_index(address);
+}
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 {
-	pmd_t *pmd = (pmd_t *) pud_deref(*pud);
+	pmd_t *pmd = (pmd_t *) pud;
+	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
+		pmd = (pmd_t *) pud_deref(*pud);
 	return pmd + pmd_index(address);
 }
 
diff --git a/include/asm-s390/processor.h b/include/asm-s390/processor.h
index e8785634cbdb..51d88912aa20 100644
--- a/include/asm-s390/processor.h
+++ b/include/asm-s390/processor.h
@@ -64,24 +64,29 @@ extern int get_cpu_capability(unsigned int *);
  */
 #ifndef __s390x__
 
-# define TASK_SIZE		(0x80000000UL)
-# define TASK_UNMAPPED_BASE	(TASK_SIZE / 2)
-# define DEFAULT_TASK_SIZE	(0x80000000UL)
+#define TASK_SIZE		(1UL << 31)
+#define TASK_UNMAPPED_BASE	(1UL << 30)
 
 #else /* __s390x__ */
 
-# define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_31BIT) ? \
-					(0x80000000UL) : (0x40000000000UL))
-# define TASK_SIZE		TASK_SIZE_OF(current)
-# define TASK_UNMAPPED_BASE	(TASK_SIZE / 2)
-# define DEFAULT_TASK_SIZE	(0x40000000000UL)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk,TIF_31BIT) ? \
+					(1UL << 31) : (1UL << 53))
+#define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_31BIT) ? \
+					(1UL << 30) : (1UL << 41))
+#define TASK_SIZE		TASK_SIZE_OF(current)
 
 #endif /* __s390x__ */
 
 #ifdef __KERNEL__
 
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		DEFAULT_TASK_SIZE
+#ifndef __s390x__
+#define STACK_TOP		(1UL << 31)
+#define STACK_TOP_MAX		(1UL << 31)
+#else /* __s390x__ */
+#define STACK_TOP		(1UL << (test_thread_flag(TIF_31BIT) ? 31:42))
+#define STACK_TOP_MAX		(1UL << 42)
+#endif /* __s390x__ */
+
 
 #endif
 
@@ -138,8 +143,6 @@ struct stack_frame {
 /*
  * Do necessary setup to start up a new thread.
  */
-#ifndef __s390x__
-
 #define start_thread(regs, new_psw, new_stackp) do {            \
 	set_fs(USER_DS);					\
 	regs->psw.mask	= psw_user_bits;			\
@@ -147,24 +150,6 @@ struct stack_frame {
         regs->gprs[15]  = new_stackp ;                          \
 } while (0)
 
-#else /* __s390x__ */
-
-#define start_thread(regs, new_psw, new_stackp) do {            \
-	set_fs(USER_DS);					\
-	regs->psw.mask	= psw_user_bits;			\
-        regs->psw.addr  = new_psw;                              \
-        regs->gprs[15]  = new_stackp;                           \
-} while (0)
-
-#define start_thread31(regs, new_psw, new_stackp) do {          \
-	set_fs(USER_DS);					\
-	regs->psw.mask	= psw_user32_bits;			\
-        regs->psw.addr  = new_psw;                              \
-        regs->gprs[15]  = new_stackp;                           \
-} while (0)
-
-#endif /* __s390x__ */
-
 /* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
diff --git a/include/asm-s390/tlb.h b/include/asm-s390/tlb.h
index 3c8177fa9e06..3d8a96d39d9d 100644
--- a/include/asm-s390/tlb.h
+++ b/include/asm-s390/tlb.h
@@ -38,7 +38,7 @@ struct mmu_gather {
 	struct mm_struct *mm;
 	unsigned int fullmm;
 	unsigned int nr_ptes;
-	unsigned int nr_pmds;
+	unsigned int nr_pxds;
 	void *array[TLB_NR_PTRS];
 };
 
@@ -53,7 +53,7 @@ static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm,
 	tlb->fullmm = full_mm_flush || (num_online_cpus() == 1) ||
 		(atomic_read(&mm->mm_users) <= 1 && mm == current->active_mm);
 	tlb->nr_ptes = 0;
-	tlb->nr_pmds = TLB_NR_PTRS;
+	tlb->nr_pxds = TLB_NR_PTRS;
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
 	return tlb;
@@ -62,12 +62,13 @@ static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm,
 static inline void tlb_flush_mmu(struct mmu_gather *tlb,
 				 unsigned long start, unsigned long end)
 {
-	if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pmds < TLB_NR_PTRS))
+	if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < TLB_NR_PTRS))
 		__tlb_flush_mm(tlb->mm);
 	while (tlb->nr_ptes > 0)
 		pte_free(tlb->mm, tlb->array[--tlb->nr_ptes]);
-	while (tlb->nr_pmds < TLB_NR_PTRS)
-		pmd_free(tlb->mm, (pmd_t *) tlb->array[tlb->nr_pmds++]);
+	while (tlb->nr_pxds < TLB_NR_PTRS)
+		/* pgd_free frees the pointer as region or segment table */
+		pgd_free(tlb->mm, tlb->array[tlb->nr_pxds++]);
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
@@ -95,33 +96,57 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.
  */
-static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t page)
+static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte)
 {
 	if (!tlb->fullmm) {
-		tlb->array[tlb->nr_ptes++] = page;
-		if (tlb->nr_ptes >= tlb->nr_pmds)
+		tlb->array[tlb->nr_ptes++] = pte;
+		if (tlb->nr_ptes >= tlb->nr_pxds)
 			tlb_flush_mmu(tlb, 0, 0);
 	} else
-		pte_free(tlb->mm, page);
+		pte_free(tlb->mm, pte);
 }
 
 /*
  * pmd_free_tlb frees a pmd table and clears the CRSTE for the
  * segment table entry from the tlb.
+ * If the mm uses a two level page table the single pmd is freed
+ * as the pgd. pmd_free_tlb checks the asce_limit against 2GB
+ * to avoid the double free of the pmd in this case.
  */
 static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
 #ifdef __s390x__
+	if (tlb->mm->context.asce_limit <= (1UL << 31))
+		return;
 	if (!tlb->fullmm) {
-		tlb->array[--tlb->nr_pmds] = (struct page *) pmd;
-		if (tlb->nr_ptes >= tlb->nr_pmds)
+		tlb->array[--tlb->nr_pxds] = pmd;
+		if (tlb->nr_ptes >= tlb->nr_pxds)
 			tlb_flush_mmu(tlb, 0, 0);
 	} else
 		pmd_free(tlb->mm, pmd);
 #endif
 }
 
-#define pud_free_tlb(tlb, pud)			do { } while (0)
+/*
+ * pud_free_tlb frees a pud table and clears the CRSTE for the
+ * region third table entry from the tlb.
+ * If the mm uses a three level page table the single pud is freed
+ * as the pgd. pud_free_tlb checks the asce_limit against 4TB
+ * to avoid the double free of the pud in this case.
+ */
+static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
+{
+#ifdef __s390x__
+	if (tlb->mm->context.asce_limit <= (1UL << 42))
+		return;
+	if (!tlb->fullmm) {
+		tlb->array[--tlb->nr_pxds] = pud;
+		if (tlb->nr_ptes >= tlb->nr_pxds)
+			tlb_flush_mmu(tlb, 0, 0);
+	} else
+		pud_free(tlb->mm, pud);
+#endif
+}
 
 #define tlb_start_vma(tlb, vma)			do { } while (0)
 #define tlb_end_vma(tlb, vma)			do { } while (0)
diff --git a/include/asm-s390/tlbflush.h b/include/asm-s390/tlbflush.h
index 70fa5ae58180..35fb4f9127b2 100644
--- a/include/asm-s390/tlbflush.h
+++ b/include/asm-s390/tlbflush.h
@@ -61,11 +61,12 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * only ran on the local cpu.
 	 */
 	if (MACHINE_HAS_IDTE) {
-		pgd_t *shadow = get_shadow_table(mm->pgd);
-
-		if (shadow)
-			__tlb_flush_idte((unsigned long) shadow | mm->context);
-		__tlb_flush_idte((unsigned long) mm->pgd | mm->context);
+		if (mm->context.noexec)
+			__tlb_flush_idte((unsigned long)
+					 get_shadow_table(mm->pgd) |
+					 mm->context.asce_bits);
+		__tlb_flush_idte((unsigned long) mm->pgd |
+				 mm->context.asce_bits);
 		return;
 	}
 	preempt_disable();
diff --git a/include/asm-s390/unistd.h b/include/asm-s390/unistd.h
index f04acb2670a8..583da807ea97 100644
--- a/include/asm-s390/unistd.h
+++ b/include/asm-s390/unistd.h
@@ -256,7 +256,10 @@
 #define __NR_signalfd		316
 #define __NR_timerfd		317
 #define __NR_eventfd		318
-#define NR_syscalls 319
+#define __NR_timerfd_create	319
+#define __NR_timerfd_settime	320
+#define __NR_timerfd_gettime	321
+#define NR_syscalls 322
 
 /* 
  * There are some system calls that are not present on 64 bit, some