Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

5 files changed, 136 insertions, 45 deletions

diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index fb988a48a754..2a7458134544 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -5,3 +5,4 @@
 obj-y    := init.o fault.o extmem.o mmap.o vmem.o pgtable.o
 obj-$(CONFIG_CMM) += cmm.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_PAGE_STATES) += page-states.o
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index fa31de6ae97a..05598649b326 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -44,37 +44,34 @@ char  empty_zero_page[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
 
 void show_mem(void)
 {
-        int i, total = 0, reserved = 0;
-        int shared = 0, cached = 0;
+        unsigned long i, total = 0, reserved = 0;
+        unsigned long shared = 0, cached = 0;
+        unsigned long flags;
         struct page *page;
+        pg_data_t *pgdat;
 
         printk("Mem-info:\n");
         show_free_areas();
-        i = max_mapnr;
-        while (i-- > 0) {
-                if (!pfn_valid(i))
-                        continue;
-                page = pfn_to_page(i);
-                total++;
-                if (PageReserved(page))
-                        reserved++;
-                else if (PageSwapCache(page))
-                        cached++;
-                else if (page_count(page))
-                        shared += page_count(page) - 1;
+        for_each_online_pgdat(pgdat) {
+                pgdat_resize_lock(pgdat, &flags);
+                for (i = 0; i < pgdat->node_spanned_pages; i++) {
+                        if (!pfn_valid(pgdat->node_start_pfn + i))
+                                continue;
+                        page = pfn_to_page(pgdat->node_start_pfn + i);
+                        total++;
+                        if (PageReserved(page))
+                                reserved++;
+                        else if (PageSwapCache(page))
+                                cached++;
+                        else if (page_count(page))
+                                shared += page_count(page) - 1;
+                }
+                pgdat_resize_unlock(pgdat, &flags);
         }
-        printk("%d pages of RAM\n", total);
-        printk("%d reserved pages\n", reserved);
-        printk("%d pages shared\n", shared);
-        printk("%d pages swap cached\n", cached);
-
-        printk("%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
-        printk("%lu pages writeback\n", global_page_state(NR_WRITEBACK));
-        printk("%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
-        printk("%lu pages slab\n",
-               global_page_state(NR_SLAB_RECLAIMABLE) +
-               global_page_state(NR_SLAB_UNRECLAIMABLE));
-        printk("%lu pages pagetables\n", global_page_state(NR_PAGETABLE));
+        printk("%ld pages of RAM\n", total);
+        printk("%ld reserved pages\n", reserved);
+        printk("%ld pages shared\n", shared);
+        printk("%ld pages swap cached\n", cached);
 }
 
 /*
@@ -126,6 +123,9 @@ void __init mem_init(void)
         /* clear the zero-page */
         memset(empty_zero_page, 0, PAGE_SIZE);
 
+        /* Setup guest page hinting */
+        cmma_init();
+
         /* this will put all low memory onto the freelists */
         totalram_pages += free_all_bootmem();
 
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
new file mode 100644
index 000000000000..fc0ad73ffd90
--- /dev/null
+++ b/arch/s390/mm/page-states.c
@@ -0,0 +1,79 @@
+/*
+ * arch/s390/mm/page-states.c
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Guest page hinting for unused pages.
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+
+#define ESSA_SET_STABLE         1
+#define ESSA_SET_UNUSED         2
+
+static int cmma_flag;
+
+static int __init cmma(char *str)
+{
+        char *parm;
+        parm = strstrip(str);
+        if (strcmp(parm, "yes") == 0 || strcmp(parm, "on") == 0) {
+                cmma_flag = 1;
+                return 1;
+        }
+        cmma_flag = 0;
+        if (strcmp(parm, "no") == 0 || strcmp(parm, "off") == 0)
+                return 1;
+        return 0;
+}
+
+__setup("cmma=", cmma);
+
+void __init cmma_init(void)
+{
+        register unsigned long tmp asm("0") = 0;
+        register int rc asm("1") = -EOPNOTSUPP;
+
+        if (!cmma_flag)
+                return;
+        asm volatile(
+                "       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
+                "0:     la      %0,0\n"
+                "1:\n"
+                EX_TABLE(0b,1b)
+                : "+&d" (rc), "+&d" (tmp));
+        if (rc)
+                cmma_flag = 0;
+}
+
+void arch_free_page(struct page *page, int order)
+{
+        int i, rc;
+
+        if (!cmma_flag)
+                return;
+        for (i = 0; i < (1 << order); i++)
+                asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0"
+                             : "=&d" (rc)
+                             : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT),
+                               "i" (ESSA_SET_UNUSED));
+}
+
+void arch_alloc_page(struct page *page, int order)
+{
+        int i, rc;
+
+        if (!cmma_flag)
+                return;
+        for (i = 0; i < (1 << order); i++)
+                asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0"
+                             : "=&d" (rc)
+                             : "a" ((page_to_pfn(page) + i) << PAGE_SHIFT),
+                               "i" (ESSA_SET_STABLE));
+}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 5c1aea97cd12..3d98ba82ea67 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -254,36 +254,46 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
 int s390_enable_sie(void)
 {
         struct task_struct *tsk = current;
-        struct mm_struct *mm;
-        int rc;
+        struct mm_struct *mm, *old_mm;
 
-        task_lock(tsk);
-
-        rc = 0;
+        /* Do we have pgstes? if yes, we are done */
         if (tsk->mm->context.pgstes)
-                goto unlock;
+                return 0;
 
-        rc = -EINVAL;
+        /* lets check if we are allowed to replace the mm */
+        task_lock(tsk);
         if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
-            tsk->mm != tsk->active_mm || tsk->mm->ioctx_list)
-                goto unlock;
+            tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {
+                task_unlock(tsk);
+                return -EINVAL;
+        }
+        task_unlock(tsk);
 
-        tsk->mm->context.pgstes = 1;    /* dirty little tricks .. */
+        /* we copy the mm with pgstes enabled */
+        tsk->mm->context.pgstes = 1;
         mm = dup_mm(tsk);
         tsk->mm->context.pgstes = 0;
-
-        rc = -ENOMEM;
         if (!mm)
-                goto unlock;
-        mmput(tsk->mm);
+                return -ENOMEM;
+
+        /* Now lets check again if somebody attached ptrace etc */
+        task_lock(tsk);
+        if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
+            tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {
+                mmput(mm);
+                task_unlock(tsk);
+                return -EINVAL;
+        }
+
+        /* ok, we are alone. No ptrace, no threads, etc. */
+        old_mm = tsk->mm;
         tsk->mm = tsk->active_mm = mm;
         preempt_disable();
         update_mm(mm, tsk);
         cpu_set(smp_processor_id(), mm->cpu_vm_mask);
         preempt_enable();
-        rc = 0;
-unlock:
         task_unlock(tsk);
-        return rc;
+        mmput(old_mm);
+        return 0;
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index beccacf907f3..e4868bfc672f 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -60,7 +60,7 @@ static inline pmd_t *vmem_pmd_alloc(void)
         return pmd;
 }
 
-static pte_t __init_refok *vmem_pte_alloc(void)
+static pte_t __ref *vmem_pte_alloc(void)
 {
         pte_t *pte;
 
@@ -221,6 +221,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
                         *pt_dir = pte;
                 }
         }
+        memset(start, 0, nr * sizeof(struct page));
         ret = 0;
 out:
         flush_tlb_kernel_range(start_addr, end_addr);
@@ -235,7 +236,7 @@ static int insert_memory_segment(struct memory_segment *seg)
 {
         struct memory_segment *tmp;
 
-        if (seg->start + seg->size >= VMEM_MAX_PHYS ||
+        if (seg->start + seg->size > VMEM_MAX_PHYS ||
             seg->start + seg->size < seg->start)
                 return -ERANGE;