[S390] 1K/2K page table pages.

This patch implements 1K/2K page table pages for s390.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 983ec6e..01dfe20 100644 (file)
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -184,7 +184,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
                pmd = pmd_offset(pud, address);
                pte = pte_offset_kernel(pmd, address);
                if (!enable) {
-                       ptep_invalidate(address, pte);
+                       ptep_invalidate(&init_mm, address, pte);
                        continue;
                }
                *pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW));

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 019f518..809e778 100644 (file)
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -26,8 +26,14 @@
 
 #ifndef CONFIG_64BIT
 #define ALLOC_ORDER    1
+#define TABLES_PER_PAGE        4
+#define FRAG_MASK      15UL
+#define SECOND_HALVES  10UL
 #else
 #define ALLOC_ORDER    2
+#define TABLES_PER_PAGE        2
+#define FRAG_MASK      3UL
+#define SECOND_HALVES  2UL
 #endif
 
 unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
@@ -45,13 +51,20 @@ unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
                }
                page->index = page_to_phys(shadow);
        }
+       spin_lock(&mm->page_table_lock);
+       list_add(&page->lru, &mm->context.crst_list);
+       spin_unlock(&mm->page_table_lock);
        return (unsigned long *) page_to_phys(page);
 }
 
-void crst_table_free(unsigned long *table)
+void crst_table_free(struct mm_struct *mm, unsigned long *table)
 {
        unsigned long *shadow = get_shadow_table(table);
+       struct page *page = virt_to_page(table);
 
+       spin_lock(&mm->page_table_lock);
+       list_del(&page->lru);
+       spin_unlock(&mm->page_table_lock);
        if (shadow)
                free_pages((unsigned long) shadow, ALLOC_ORDER);
        free_pages((unsigned long) table, ALLOC_ORDER);
@@ -60,37 +73,84 @@ void crst_table_free(unsigned long *table)
 /*
  * page table entry allocation/free routines.
  */
-unsigned long *page_table_alloc(int noexec)
+unsigned long *page_table_alloc(struct mm_struct *mm)
 {
-       struct page *page = alloc_page(GFP_KERNEL);
+       struct page *page;
        unsigned long *table;
+       unsigned long bits;
 
-       if (!page)
-               return NULL;
-       page->index = 0;
-       if (noexec) {
-               struct page *shadow = alloc_page(GFP_KERNEL);
-               if (!shadow) {
-                       __free_page(page);
+       bits = mm->context.noexec ? 3UL : 1UL;
+       spin_lock(&mm->page_table_lock);
+       page = NULL;
+       if (!list_empty(&mm->context.pgtable_list)) {
+               page = list_first_entry(&mm->context.pgtable_list,
+                                       struct page, lru);
+               if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
+                       page = NULL;
+       }
+       if (!page) {
+               spin_unlock(&mm->page_table_lock);
+               page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+               if (!page)
                        return NULL;
-               }
-               table = (unsigned long *) page_to_phys(shadow);
+               pgtable_page_ctor(page);
+               page->flags &= ~FRAG_MASK;
+               table = (unsigned long *) page_to_phys(page);
                clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
-               page->index = (addr_t) table;
+               spin_lock(&mm->page_table_lock);
+               list_add(&page->lru, &mm->context.pgtable_list);
        }
-       pgtable_page_ctor(page);
        table = (unsigned long *) page_to_phys(page);
-       clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+       while (page->flags & bits) {
+               table += 256;
+               bits <<= 1;
+       }
+       page->flags |= bits;
+       if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
+               list_move_tail(&page->lru, &mm->context.pgtable_list);
+       spin_unlock(&mm->page_table_lock);
        return table;
 }
 
-void page_table_free(unsigned long *table)
+void page_table_free(struct mm_struct *mm, unsigned long *table)
 {
-       unsigned long *shadow = get_shadow_pte(table);
+       struct page *page;
+       unsigned long bits;
 
-       pgtable_page_dtor(virt_to_page(table));
-       if (shadow)
-               free_page((unsigned long) shadow);
-       free_page((unsigned long) table);
+       bits = mm->context.noexec ? 3UL : 1UL;
+       bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+       page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+       spin_lock(&mm->page_table_lock);
+       page->flags ^= bits;
+       if (page->flags & FRAG_MASK) {
+               /* Page now has some free pgtable fragments. */
+               list_move(&page->lru, &mm->context.pgtable_list);
+               page = NULL;
+       } else
+               /* All fragments of the 4K page have been freed. */
+               list_del(&page->lru);
+       spin_unlock(&mm->page_table_lock);
+       if (page) {
+               pgtable_page_dtor(page);
+               __free_page(page);
+       }
+}
 
+void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
+{
+       struct page *page;
+
+       spin_lock(&mm->page_table_lock);
+       /* Free shadow region and segment tables. */
+       list_for_each_entry(page, &mm->context.crst_list, lru)
+               if (page->index) {
+                       free_pages((unsigned long) page->index, ALLOC_ORDER);
+                       page->index = 0;
+               }
+       /* "Free" second halves of page tables. */
+       list_for_each_entry(page, &mm->context.pgtable_list, lru)
+               page->flags &= ~SECOND_HALVES;
+       spin_unlock(&mm->page_table_lock);
+       mm->context.noexec = 0;
+       update_mm(mm, tsk);
 }

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 7c1287c..434491f 100644 (file)
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -84,13 +84,18 @@ static inline pmd_t *vmem_pmd_alloc(void)
        return pmd;
 }
 
-static inline pte_t *vmem_pte_alloc(void)
+static pte_t __init_refok *vmem_pte_alloc(void)
 {
-       pte_t *pte = vmem_alloc_pages(0);
+       pte_t *pte;
 
+       if (slab_is_available())
+               pte = (pte_t *) page_table_alloc(&init_mm);
+       else
+               pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
        if (!pte)
                return NULL;
-       clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+       clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY,
+                   PTRS_PER_PTE * sizeof(pte_t));
        return pte;
 }
 
@@ -360,6 +365,9 @@ void __init vmem_map_init(void)
 {
        int i;
 
+       INIT_LIST_HEAD(&init_mm.context.crst_list);
+       INIT_LIST_HEAD(&init_mm.context.pgtable_list);
+       init_mm.context.noexec = 0;
        NODE_DATA(0)->node_mem_map = VMEM_MAP;
        for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++)
                vmem_add_mem(memory_chunk[i].addr, memory_chunk[i].size);

diff --git a/include/asm-s390/elf.h b/include/asm-s390/elf.h
index b73a424..8181ca5 100644 (file)
--- 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.
@@ -214,4 +215,16 @@ 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 ccd36d2..13ec421 100644 (file)
--- a/include/asm-s390/mmu.h
+++ b/include/asm-s390/mmu.h
@@ -1,7 +1,11 @@
 #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;
+       int noexec;
+} mm_context_t;
 
 #endif

diff --git a/include/asm-s390/mmu_context.h b/include/asm-s390/mmu_context.h
index a77d4ba..3eaac5e 100644 (file)
--- a/include/asm-s390/mmu_context.h
+++ b/include/asm-s390/mmu_context.h
@@ -10,15 +10,17 @@
 #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;
        return 0;
 }
 
@@ -32,11 +34,13 @@ 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

diff --git a/include/asm-s390/page.h b/include/asm-s390/page.h
index 7f29a98..fe7f92b 100644 (file)
--- 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 900d448..af4aee8 100644 (file)
--- 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)
 {
@@ -80,12 +81,12 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 
 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()
@@ -98,63 +99,55 @@ 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);
+       unsigned long *crst;
+
+       INIT_LIST_HEAD(&mm->context.crst_list);
+       INIT_LIST_HEAD(&mm->context.pgtable_list);
+       crst = crst_table_alloc(mm, s390_noexec);
        if (crst)
                crst_table_init(crst, pgd_entry_type(mm));
        return (pgd_t *) crst;
 }
-#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 65d3338..4fc9377 100644 (file)
--- a/include/asm-s390/pgtable.h
+++ b/include/asm-s390/pgtable.h
@@ -57,11 +57,11 @@ 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
 #endif /* __s390x__ */
@@ -79,17 +79,14 @@ 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
 #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
 #endif /* __s390x__ */
+#define PTRS_PER_PUD   1
+#define PTRS_PER_PGD   2048
 
 #define FIRST_USER_ADDRESS  0
 
@@ -376,24 +373,6 @@ 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;
@@ -411,17 +390,16 @@ 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;
        }
 }
 
@@ -536,14 +514,6 @@ 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)
-{
-       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;
-}
-
 #else /* __s390x__ */
 
 #define pgd_clear(pgd)         do { } while (0)
@@ -562,30 +532,27 @@ 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;
 }
 
 /*
@@ -666,7 +633,7 @@ 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 */
@@ -680,12 +647,12 @@ 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);
 }
 
 /*
@@ -707,7 +674,7 @@ 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;                                                          \
@@ -718,7 +685,7 @@ 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;
 }
 
@@ -739,7 +706,7 @@ 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;
 }
 
@@ -750,7 +717,7 @@ 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)); \
        }                                                               \
 })
@@ -760,7 +727,7 @@ 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;                                                      \

diff --git a/include/asm-s390/tlb.h b/include/asm-s390/tlb.h
index 3c8177f..ecac75e 100644 (file)
--- a/include/asm-s390/tlb.h
+++ b/include/asm-s390/tlb.h
@@ -95,14 +95,14 @@ 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;
+               tlb->array[tlb->nr_ptes++] = pte;
                if (tlb->nr_ptes >= tlb->nr_pmds)
                        tlb_flush_mmu(tlb, 0, 0);
        } else
-               pte_free(tlb->mm, page);
+               pte_free(tlb->mm, pte);
 }
 
 /*

diff --git a/include/asm-s390/tlbflush.h b/include/asm-s390/tlbflush.h
index 70fa5ae..35fb4f9 100644 (file)
--- 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();