5 files changed, 43 insertions, 64 deletions

diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 8af549e95730..993f35381496 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -167,7 +167,7 @@ static int __kprobes swap_instruction(void *aref)
          * shall not cross any page boundaries (vmalloc area!) when writing
          * the new instruction.
          */
-        addr = (u32 *)ALIGN((unsigned long)args->ptr, 4);
+        addr = (u32 *)((unsigned long)args->ptr & -4UL);
         if ((unsigned long)args->ptr & 2)
                 instr = ((*addr) & 0xffff0000) | args->new;
         else
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index ab782bb46ac1..e810e4a44ed4 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -65,7 +65,7 @@ static const u8 DASD_DIAG_CMS1[] = { 0xc3, 0xd4, 0xe2, 0xf1 };/* EBCDIC CMS1 */
  * resulting condition code and DIAG return code. */
 static inline int dia250(void *iob, int cmd)
 {
-        register unsigned long reg0 asm ("0") = (unsigned long) iob;
+        register unsigned long reg2 asm ("2") = (unsigned long) iob;
         typedef union {
                 struct dasd_diag_init_io init_io;
                 struct dasd_diag_rw_io rw_io;
@@ -74,15 +74,15 @@ static inline int dia250(void *iob, int cmd)
 
         rc = 3;
         asm volatile(
-                "       diag    0,%2,0x250\n"
+                "       diag    2,%2,0x250\n"
                 "0:     ipm     %0\n"
                 "       srl     %0,28\n"
-                "       or      %0,1\n"
+                "       or      %0,3\n"
                 "1:\n"
                 EX_TABLE(0b,1b)
                 : "+d" (rc), "=m" (*(addr_type *) iob)
-                : "d" (cmd), "d" (reg0), "m" (*(addr_type *) iob)
-                : "1", "cc");
+                : "d" (cmd), "d" (reg2), "m" (*(addr_type *) iob)
+                : "3", "cc");
         return rc;
 }
 
diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c
index 6b1caea622ea..25d99bd28089 100644
--- a/drivers/s390/cio/device_status.c
+++ b/drivers/s390/cio/device_status.c
@@ -263,7 +263,11 @@ ccw_device_accumulate_irb(struct ccw_device *cdev, struct irb *irb)
                 cdev_irb->scsw.cpa = irb->scsw.cpa;
         /* Accumulate device status, but not the device busy flag. */
         cdev_irb->scsw.dstat &= ~DEV_STAT_BUSY;
-        cdev_irb->scsw.dstat |= irb->scsw.dstat;
+        /* dstat is not always valid. */
+        if (irb->scsw.stctl &
+            (SCSW_STCTL_PRIM_STATUS | SCSW_STCTL_SEC_STATUS
+             | SCSW_STCTL_INTER_STATUS | SCSW_STCTL_ALERT_STATUS))
+                cdev_irb->scsw.dstat |= irb->scsw.dstat;
         /* Accumulate subchannel status. */
         cdev_irb->scsw.cstat |= irb->scsw.cstat;
         /* Copy residual count if it is valid. */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 181b51772b1b..bf37cdf43fae 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -505,6 +505,9 @@ static int ap_device_remove(struct device *dev)
         spin_lock_bh(&ap_device_lock);
         list_del_init(&ap_dev->list);
         spin_unlock_bh(&ap_device_lock);
+        spin_lock_bh(&ap_dev->lock);
+        atomic_sub(ap_dev->queue_count, &ap_poll_requests);
+        spin_unlock_bh(&ap_dev->lock);
         return 0;
 }
 
@@ -757,10 +760,16 @@ static void ap_scan_bus(struct work_struct *unused)
                                       (void *)(unsigned long)qid,
                                       __ap_scan_bus);
                 rc = ap_query_queue(qid, &queue_depth, &device_type);
-                if (dev && rc) {
-                        put_device(dev);
-                        device_unregister(dev);
-                        continue;
+                if (dev) {
+                        ap_dev = to_ap_dev(dev);
+                        spin_lock_bh(&ap_dev->lock);
+                        if (rc || ap_dev->unregistered) {
+                                spin_unlock_bh(&ap_dev->lock);
+                                put_device(dev);
+                                device_unregister(dev);
+                                continue;
+                        } else
+                                spin_unlock_bh(&ap_dev->lock);
                 }
                 if (dev) {
                         put_device(dev);
@@ -861,6 +870,7 @@ static int ap_poll_read(struct ap_device *ap_dev, unsigned long *flags)
         case AP_RESPONSE_NO_PENDING_REPLY:
                 if (status.queue_empty) {
                         /* The card shouldn't forget requests but who knows. */
+                        atomic_sub(ap_dev->queue_count, &ap_poll_requests);
                         ap_dev->queue_count = 0;
                         list_splice_init(&ap_dev->pendingq, &ap_dev->requestq);
                         ap_dev->requestq_count += ap_dev->pendingq_count;
@@ -994,7 +1004,7 @@ void ap_queue_message(struct ap_device *ap_dev, struct ap_message *ap_msg)
                         ap_dev->unregistered = 1;
         } else {
                 ap_dev->drv->receive(ap_dev, ap_msg, ERR_PTR(-ENODEV));
-                rc = 0;
+                rc = -ENODEV;
         }
         spin_unlock_bh(&ap_dev->lock);
         if (rc == -ENODEV)
@@ -1044,18 +1054,12 @@ static void ap_poll_timeout(unsigned long unused)
  */
 static int __ap_poll_all(struct ap_device *ap_dev, unsigned long *flags)
 {
-        int rc;
-
         spin_lock(&ap_dev->lock);
         if (!ap_dev->unregistered) {
-                rc = ap_poll_queue(ap_dev, flags);
-                if (rc)
+                if (ap_poll_queue(ap_dev, flags))
                         ap_dev->unregistered = 1;
-        } else
-                rc = 0;
+        }
         spin_unlock(&ap_dev->lock);
-        if (rc)
-                device_unregister(&ap_dev->device);
         return 0;
 }
 
diff --git a/include/asm-s390/checksum.h b/include/asm-s390/checksum.h
index 0a3cd7ec8451..d5a8e7c1477c 100644
--- a/include/asm-s390/checksum.h
+++ b/include/asm-s390/checksum.h
@@ -121,50 +121,21 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
                    unsigned short len, unsigned short proto,
                    __wsum sum)
 {
-#ifndef __s390x__
-        asm volatile(
-                "       alr     %0,%1\n" /* sum += saddr */
-                "       brc     12,0f\n"
-                "       ahi     %0,1\n"  /* add carry */
-                "0:"
-                : "+&d" (sum) : "d" (saddr) : "cc");
-        asm volatile(
-                "       alr     %0,%1\n" /* sum += daddr */
-                "       brc     12,1f\n"
-                "       ahi     %0,1\n"  /* add carry */
-                "1:"
-                : "+&d" (sum) : "d" (daddr) : "cc");
-        asm volatile(
-                "       alr     %0,%1\n" /* sum += len + proto */
-                "       brc     12,2f\n"
-                "       ahi     %0,1\n"  /* add carry */
-                "2:"
-                : "+&d" (sum)
-                : "d" (len + proto)
-                : "cc");
-#else /* __s390x__ */
-        asm volatile(
-                "       lgfr    %0,%0\n"
-                "       algr    %0,%1\n"  /* sum += saddr */
-                "       brc     12,0f\n"
-                "       aghi    %0,1\n"   /* add carry */
-                "0:     algr    %0,%2\n"  /* sum += daddr */
-                "       brc     12,1f\n"
-                "       aghi    %0,1\n"   /* add carry */
-                "1:     algfr   %0,%3\n"  /* sum += len + proto */
-                "       brc     12,2f\n"
-                "       aghi    %0,1\n"   /* add carry */
-                "2:     srlg    0,%0,32\n"
-                "       alr     %0,0\n"   /* fold to 32 bits */
-                "       brc     12,3f\n"
-                "       ahi     %0,1\n"   /* add carry */
-                "3:     llgfr   %0,%0"
-                : "+&d" (sum)
-                : "d" (saddr), "d" (daddr),
-                  "d" (len + proto)
-                : "cc", "0");
-#endif /* __s390x__ */
-        return sum;
+        __u32 csum = (__force __u32)sum;
+
+        csum += (__force __u32)saddr;
+        if (csum < (__force __u32)saddr)
+                csum++;
+
+        csum += (__force __u32)daddr;
+        if (csum < (__force __u32)daddr)
+                csum++;
+
+        csum += len + proto;
+        if (csum < len + proto)
+                csum++;
+
+        return (__force __wsum)csum;
 }
 
 /*