Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/s390/linux

Pull s390 updates from Martin Schwidefsky:
 "There is only one new feature in this pull for the 4.4 merge window,
  most of it is small enhancements, cleanup and bug fixes:

   - Add the s390 backend for the software dirty bit tracking.  This
     adds two new pgtable functions pte_clear_soft_dirty and
     pmd_clear_soft_dirty which is why there is a hit to
     arch/x86/include/asm/pgtable.h in this pull request.

   - A series of cleanup patches for the AP bus, this includes the
     removal of the support for two outdated crypto cards (PCICC and
     PCICA).

   - The irq handling / signaling on buffer full in the runtime
     instrumentation code is dropped.

   - Some micro optimizations: remove unnecessary memory barriers for a
     couple of functions: [smb_]rmb, [smb_]wmb, atomics, bitops, and for
     spin_unlock.  Use the builtin bswap if available and make
     test_and_set_bit_lock more cache friendly.

   - Statistics and a tracepoint for the diagnose calls to the
     hypervisor.

   - The CPU measurement facility support to sample KVM guests is
     improved.

   - The vector instructions are now always enabled for user space
     processes if the hardware has the vector facility.  This simplifies
     the FPU handling code.  The fpu-internal.h header is split into fpu
     internals, api and types just like x86.

   - Cleanup and improvements for the common I/O layer.

   - Rework udelay to solve a problem with kprobe.  udelay has busy loop
     semantics but still uses an idle processor state for the wait"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (66 commits)
  s390: remove runtime instrumentation interrupts
  s390/cio: de-duplicate subchannel validation
  s390/css: unneeded initialization in for_each_subchannel
  s390/Kconfig: use builtin bswap
  s390/dasd: fix disconnected device with valid path mask
  s390/dasd: fix invalid PAV assignment after suspend/resume
  s390/dasd: fix double free in dasd_eckd_read_conf
  s390/kernel: fix ptrace peek/poke for floating point registers
  s390/cio: move ccw_device_stlck functions
  s390/cio: move ccw_device_call_handler
  s390/topology: reduce per_cpu() invocations
  s390/nmi: reduce size of percpu variable
  s390/nmi: fix terminology
  s390/nmi: remove casts
  s390/nmi: remove pointless error strings
  s390: don't store registers on disabled wait anymore
  s390: get rid of __set_psw_mask()
  s390/fpu: split fpu-internal.h into fpu internals, api, and type headers
  s390/dasd: fix list_del corruption after lcu changes
  s390/spinlock: remove unneeded serializations at unlock
  ...

arch/s390/Kconfig

@@ -101,6 +101,7 @@ config S390
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -118,6 +119,7 @@ config S390
 	select HAVE_ARCH_EARLY_PFN_TO_NID
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_SOFT_DIRTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES

arch/s390/hypfs/hypfs_diag.c

@@ -15,6 +15,7 @@
 #include <linux/string.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
+#include <asm/diag.h>
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
@@ -336,7 +337,7 @@ static inline __u64 phys_cpu__ctidx(enum diag204_format type, void *hdr)
 
 /* Diagnose 204 functions */
 
-static int diag204(unsigned long subcode, unsigned long size, void *addr)
+static inline int __diag204(unsigned long subcode, unsigned long size, void *addr)
 {
 	register unsigned long _subcode asm("0") = subcode;
 	register unsigned long _size asm("1") = size;
@@ -351,6 +352,12 @@ static int diag204(unsigned long subcode, unsigned long size, void *addr)
 	return _size;
 }
 
+static int diag204(unsigned long subcode, unsigned long size, void *addr)
+{
+	diag_stat_inc(DIAG_STAT_X204);
+	return __diag204(subcode, size, addr);
+}
+
 /*
  * For the old diag subcode 4 with simple data format we have to use real
  * memory. If we use subcode 6 or 7 with extended data format, we can (and
@@ -505,6 +512,7 @@ static int diag224(void *ptr)
 {
 	int rc = -EOPNOTSUPP;
 
+	diag_stat_inc(DIAG_STAT_X224);
 	asm volatile(
 		"	diag	%1,%2,0x224\n"
 		"0:	lhi	%0,0x0\n"

arch/s390/hypfs/hypfs_diag0c.c

@@ -8,6 +8,7 @@
 
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <asm/diag.h>
 #include <asm/hypfs.h>
 #include "hypfs.h"
 
@@ -18,6 +19,7 @@
  */
 static void diag0c(struct hypfs_diag0c_entry *entry)
 {
+	diag_stat_inc(DIAG_STAT_X00C);
 	asm volatile (
 		"	sam31\n"
 		"	diag	%0,%0,0x0c\n"

arch/s390/hypfs/hypfs_sprp.c

@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 #include <asm/compat.h>
+#include <asm/diag.h>
 #include <asm/sclp.h>
 #include "hypfs.h"
 
@@ -22,7 +23,7 @@
 
 #define DIAG304_CMD_MAX		2
 
-static unsigned long hypfs_sprp_diag304(void *data, unsigned long cmd)
+static inline unsigned long __hypfs_sprp_diag304(void *data, unsigned long cmd)
 {
 	register unsigned long _data asm("2") = (unsigned long) data;
 	register unsigned long _rc asm("3");
@@ -34,6 +35,12 @@ static unsigned long hypfs_sprp_diag304(void *data, unsigned long cmd)
 	return _rc;
 }
 
+static unsigned long hypfs_sprp_diag304(void *data, unsigned long cmd)
+{
+	diag_stat_inc(DIAG_STAT_X304);
+	return __hypfs_sprp_diag304(data, cmd);
+}
+
 static void hypfs_sprp_free(const void *data)
 {
 	free_page((unsigned long) data);

arch/s390/hypfs/hypfs_vm.c

@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
+#include <asm/diag.h>
 #include <asm/ebcdic.h>
 #include <asm/timex.h>
 #include "hypfs.h"
@@ -66,6 +67,7 @@ static int diag2fc(int size, char* query, void *addr)
 	memset(parm_list.aci_grp, 0x40, NAME_LEN);
 	rc = -1;
 
+	diag_stat_inc(DIAG_STAT_X2FC);
 	asm volatile(
 		"	diag    %0,%1,0x2fc\n"
 		"0:\n"

arch/s390/include/asm/appldata.h

@@ -7,6 +7,7 @@
 #ifndef _ASM_S390_APPLDATA_H
 #define _ASM_S390_APPLDATA_H
 
+#include <asm/diag.h>
 #include <asm/io.h>
 
 #define APPLDATA_START_INTERVAL_REC	0x80
@@ -53,6 +54,7 @@ static inline int appldata_asm(struct appldata_product_id *id,
 	parm_list.buffer_length = length;
 	parm_list.product_id_addr = (unsigned long) id;
 	parm_list.buffer_addr = virt_to_phys(buffer);
+	diag_stat_inc(DIAG_STAT_X0DC);
 	asm volatile(
 		"	diag	%1,%0,0xdc"
 		: "=d" (ry)

arch/s390/include/asm/atomic.h

@@ -36,7 +36,6 @@
 									\
 	typecheck(atomic_t *, ptr);					\
 	asm volatile(							\
-		__barrier						\
 		op_string "	%0,%2,%1\n"				\
 		__barrier						\
 		: "=d" (old_val), "+Q" ((ptr)->counter)			\
@@ -180,7 +179,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 									\
 	typecheck(atomic64_t *, ptr);					\
 	asm volatile(							\
-		__barrier						\
 		op_string "	%0,%2,%1\n"				\
 		__barrier						\
 		: "=d" (old_val), "+Q" ((ptr)->counter)			\

arch/s390/include/asm/barrier.h

@@ -22,10 +22,10 @@
 
 #define mb() do {  asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
 
-#define rmb()				mb()
-#define wmb()				mb()
-#define dma_rmb()			rmb()
-#define dma_wmb()			wmb()
+#define rmb()				barrier()
+#define wmb()				barrier()
+#define dma_rmb()			mb()
+#define dma_wmb()			mb()
 #define smp_mb()			mb()
 #define smp_rmb()			rmb()
 #define smp_wmb()			wmb()

arch/s390/include/asm/bitops.h

@@ -11,30 +11,25 @@
  * big-endian system because, unlike little endian, the number of each
  * bit depends on the word size.
  *
- * The bitop functions are defined to work on unsigned longs, so for an
- * s390x system the bits end up numbered:
+ * The bitop functions are defined to work on unsigned longs, so the bits
+ * end up numbered:
  *   |63..............0|127............64|191...........128|255...........192|
- * and on s390:
- *   |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
  *
  * There are a few little-endian macros used mostly for filesystem
- * bitmaps, these work on similar bit arrays layouts, but
- * byte-oriented:
+ * bitmaps, these work on similar bit array layouts, but byte-oriented:
  *   |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
  *
- * The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
- * number field needs to be reversed compared to the big-endian bit
- * fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
+ * The main difference is that bit 3-5 in the bit number field needs to be
+ * reversed compared to the big-endian bit fields. This can be achieved by
+ * XOR with 0x38.
  *
- * We also have special functions which work with an MSB0 encoding:
- * on an s390x system the bits are numbered:
+ * We also have special functions which work with an MSB0 encoding.
+ * The bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
- * and on s390:
- *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  *
- * The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit
- * number field needs to be reversed compared to the LSB0 encoded bit
- * fields. This can be achieved by XOR with 0x3f (64b) or 0x1f (32b).
+ * The main difference is that bit 0-63 in the bit number field needs to be
+ * reversed compared to the LSB0 encoded bit fields. This can be achieved by
+ * XOR with 0x3f.
  *
  */
 
@@ -64,7 +59,6 @@
 								\
 	typecheck(unsigned long *, (__addr));			\
 	asm volatile(						\
-		__barrier					\
 		__op_string "	%0,%2,%1\n"			\
 		__barrier					\
 		: "=d" (__old),	"+Q" (*(__addr))		\
@@ -276,12 +270,32 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static inline int test_and_set_bit_lock(unsigned long nr,
+					volatile unsigned long *ptr)
+{
+	if (test_bit(nr, ptr))
+		return 1;
+	return test_and_set_bit(nr, ptr);
+}
+
+static inline void clear_bit_unlock(unsigned long nr,
+				    volatile unsigned long *ptr)
+{
+	smp_mb__before_atomic();
+	clear_bit(nr, ptr);
+}
+
+static inline void __clear_bit_unlock(unsigned long nr,
+				      volatile unsigned long *ptr)
+{
+	smp_mb();
+	__clear_bit(nr, ptr);
+}
+
 /*
  * Functions which use MSB0 bit numbering.
- * On an s390x system the bits are numbered:
+ * The bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
- * and on s390:
- *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  */
 unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size);
 unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size,
@@ -446,7 +460,6 @@ static inline int fls(int word)
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic-setbit.h>

arch/s390/include/asm/cio.h

@@ -5,6 +5,7 @@
 #define _ASM_S390_CIO_H_
 
 #include <linux/spinlock.h>
+#include <linux/bitops.h>
 #include <asm/types.h>
 
 #define LPM_ANYPATH 0xff
@@ -296,6 +297,15 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1,
 	return 0;
 }
 
+/**
+ * pathmask_to_pos() - find the position of the left-most bit in a pathmask
+ * @mask: pathmask with at least one bit set
+ */
+static inline u8 pathmask_to_pos(u8 mask)
+{
+	return 8 - ffs(mask);
+}
+
 void channel_subsystem_reinit(void);
 extern void css_schedule_reprobe(void);
 

arch/s390/include/asm/cmb.h

@@ -6,6 +6,7 @@
 struct ccw_device;
 extern int enable_cmf(struct ccw_device *cdev);
 extern int disable_cmf(struct ccw_device *cdev);
+extern int __disable_cmf(struct ccw_device *cdev);
 extern u64 cmf_read(struct ccw_device *cdev, int index);
 extern int cmf_readall(struct ccw_device *cdev, struct cmbdata *data);
 

arch/s390/include/asm/cmpxchg.h

@@ -32,15 +32,15 @@
 	__old;								\
 })
 
-#define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn)		\
+#define __cmpxchg_double(p1, p2, o1, o2, n1, n2)			\
 ({									\
 	register __typeof__(*(p1)) __old1 asm("2") = (o1);		\
 	register __typeof__(*(p2)) __old2 asm("3") = (o2);		\
 	register __typeof__(*(p1)) __new1 asm("4") = (n1);		\
 	register __typeof__(*(p2)) __new2 asm("5") = (n2);		\
 	int cc;								\
 	asm volatile(							\
-			insn   " %[old],%[new],%[ptr]\n"		\
+		"	cdsg	%[old],%[new],%[ptr]\n"			\
 		"	ipm	%[cc]\n"				\
 		"	srl	%[cc],28"				\
 		: [cc] "=d" (cc), [old] "+d" (__old1), "+d" (__old2)	\
@@ -50,38 +50,14 @@
 	!cc;								\
 })
 
-#define __cmpxchg_double_4(p1, p2, o1, o2, n1, n2) \
-	__cmpxchg_double_op(p1, p2, o1, o2, n1, n2, "cds")
-
-#define __cmpxchg_double_8(p1, p2, o1, o2, n1, n2) \
-	__cmpxchg_double_op(p1, p2, o1, o2, n1, n2, "cdsg")
-
-extern void __cmpxchg_double_called_with_bad_pointer(void);
-
-#define __cmpxchg_double(p1, p2, o1, o2, n1, n2)			\
-({									\
-	int __ret;							\
-	switch (sizeof(*(p1))) {					\
-	case 4:								\
-		__ret = __cmpxchg_double_4(p1, p2, o1, o2, n1, n2);	\
-		break;							\
-	case 8:								\
-		__ret = __cmpxchg_double_8(p1, p2, o1, o2, n1, n2);	\
-		break;							\
-	default:							\
-		__cmpxchg_double_called_with_bad_pointer();		\
-	}								\
-	__ret;								\
-})
-
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
 	__typeof__(p1) __p1 = (p1);					\
 	__typeof__(p2) __p2 = (p2);					\
 	BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long));			\
 	BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long));			\
 	VM_BUG_ON((unsigned long)((__p1) + 1) != (unsigned long)(__p2));\
-	__cmpxchg_double_8(__p1, __p2, o1, o2, n1, n2);			\
+	__cmpxchg_double(__p1, __p2, o1, o2, n1, n2);			\
 })
 
 #define system_has_cmpxchg_double()	1

arch/s390/include/asm/cpu_mf.h

@@ -22,15 +22,10 @@
 #define CPU_MF_INT_SF_LSDA	(1 << 22)	/* loss of sample data alert */
 #define CPU_MF_INT_CF_CACA	(1 <<  7)	/* counter auth. change alert */
 #define CPU_MF_INT_CF_LCDA	(1 <<  6)	/* loss of counter data alert */
-#define CPU_MF_INT_RI_HALTED	(1 <<  5)	/* run-time instr. halted */
-#define CPU_MF_INT_RI_BUF_FULL	(1 <<  4)	/* run-time instr. program
-						   buffer full */
-
 #define CPU_MF_INT_CF_MASK	(CPU_MF_INT_CF_CACA|CPU_MF_INT_CF_LCDA)
 #define CPU_MF_INT_SF_MASK	(CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE|	\
 				 CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA|	\
 				 CPU_MF_INT_SF_LSDA)
-#define CPU_MF_INT_RI_MASK	(CPU_MF_INT_RI_HALTED|CPU_MF_INT_RI_BUF_FULL)
 
 /* CPU measurement facility support */
 static inline int cpum_cf_avail(void)

arch/s390/include/asm/ctl_reg.h

@@ -46,8 +46,6 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 	__ctl_load(reg, cr, cr);
 }
 
-void __ctl_set_vx(void);
-
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);