4 files changed, 40 insertions, 13 deletions

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index cce577fea..19288c1b3 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -250,6 +250,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 
 	report_user_fault(regs, SIGSEGV, 1);
 	si.si_signo = SIGSEGV;
+	si.si_errno = 0;
 	si.si_code = si_code;
 	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
 	force_sig_info(SIGSEGV, &si, current);
@@ -631,6 +632,29 @@ void pfault_fini(void)
 static DEFINE_SPINLOCK(pfault_lock);
 static LIST_HEAD(pfault_list);
 
+#define PF_COMPLETE	0x0080
+
+/*
+ * The mechanism of our pfault code: if Linux is running as guest, runs a user
+ * space process and the user space process accesses a page that the host has
+ * paged out we get a pfault interrupt.
+ *
+ * This allows us, within the guest, to schedule a different process. Without
+ * this mechanism the host would have to suspend the whole virtual cpu until
+ * the page has been paged in.
+ *
+ * So when we get such an interrupt then we set the state of the current task
+ * to uninterruptible and also set the need_resched flag. Both happens within
+ * interrupt context(!). If we later on want to return to user space we
+ * recognize the need_resched flag and then call schedule().  It's not very
+ * obvious how this works...
+ *
+ * Of course we have a lot of additional fun with the completion interrupt (->
+ * host signals that a page of a process has been paged in and the process can
+ * continue to run). This interrupt can arrive on any cpu and, since we have
+ * virtual cpus, actually appear before the interrupt that signals that a page
+ * is missing.
+ */
 static void pfault_interrupt(struct ext_code ext_code,
 			     unsigned int param32, unsigned long param64)
 {
@@ -639,10 +663,9 @@ static void pfault_interrupt(struct ext_code ext_code,
 	pid_t pid;
 
 	/*
-	 * Get the external interruption subcode & pfault
-	 * initial/completion signal bit. VM stores this 
-	 * in the 'cpu address' field associated with the
-         * external interrupt. 
+	 * Get the external interruption subcode & pfault initial/completion
+	 * signal bit. VM stores this in the 'cpu address' field associated
+	 * with the external interrupt.
 	 */
 	subcode = ext_code.subcode;
 	if ((subcode & 0xff00) != __SUBCODE_MASK)
@@ -658,7 +681,7 @@ static void pfault_interrupt(struct ext_code ext_code,
 	if (!tsk)
 		return;
 	spin_lock(&pfault_lock);
-	if (subcode & 0x0080) {
+	if (subcode & PF_COMPLETE) {
 		/* signal bit is set -> a page has been swapped in by VM */
 		if (tsk->thread.pfault_wait == 1) {
 			/* Initial interrupt was faster than the completion
@@ -687,8 +710,7 @@ static void pfault_interrupt(struct ext_code ext_code,
 			goto out;
 		if (tsk->thread.pfault_wait == 1) {
 			/* Already on the list with a reference: put to sleep */
-			__set_task_state(tsk, TASK_UNINTERRUPTIBLE);
-			set_tsk_need_resched(tsk);
+			goto block;
 		} else if (tsk->thread.pfault_wait == -1) {
 			/* Completion interrupt was faster than the initial
 			 * interrupt (pfault_wait == -1). Set pfault_wait
@@ -703,7 +725,11 @@ static void pfault_interrupt(struct ext_code ext_code,
 			get_task_struct(tsk);
 			tsk->thread.pfault_wait = 1;
 			list_add(&tsk->thread.list, &pfault_list);
-			__set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+block:
+			/* Since this must be a userspace fault, there
+			 * is no kernel task state to trample. Rely on the
+			 * return to userspace schedule() to block. */
+			__set_current_state(TASK_UNINTERRUPTIBLE);
 			set_tsk_need_resched(tsk);
 		}
 	}
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 89cf09e5f..eb9df2822 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -22,6 +22,7 @@
  * Started by Ingo Molnar <mingo@elte.hu>
  */
 
+#include <linux/elf-randomize.h>
 #include <linux/personality.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e8b5962ac..e2565d2d0 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 			return table;
 	}
 	/* Allocate a fresh page */
-	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	page = alloc_page(GFP_KERNEL);
 	if (!page)
 		return NULL;
 	if (!pgtable_page_ctor(page)) {
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index d27fccbad..d48cf25cf 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -56,7 +56,7 @@ static inline pmd_t *vmem_pmd_alloc(void)
 	return pmd;
 }
 
-static pte_t __ref *vmem_pte_alloc(unsigned long address)
+static pte_t __ref *vmem_pte_alloc(void)
 {
 	pte_t *pte;
 
@@ -121,7 +121,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 			continue;
 		}
 		if (pmd_none(*pm_dir)) {
-			pt_dir = vmem_pte_alloc(address);
+			pt_dir = vmem_pte_alloc();
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);
@@ -233,7 +233,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 				address = (address + PMD_SIZE) & PMD_MASK;
 				continue;
 			}
-			pt_dir = vmem_pte_alloc(address);
+			pt_dir = vmem_pte_alloc();
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);
@@ -370,7 +370,7 @@ void __init vmem_map_init(void)
 	ro_end = (unsigned long)&_eshared & PAGE_MASK;
 	for_each_memblock(memory, reg) {
 		start = reg->base;
-		end = reg->base + reg->size - 1;
+		end = reg->base + reg->size;
 		if (start >= ro_end || end <= ro_start)
 			vmem_add_mem(start, end - start, 0);
 		else if (start >= ro_start && end <= ro_end)