Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Martin Schwidefsky:

 - The remaining patches for the z13 machine support: kernel build
   option for z13, the cache synonym avoidance, SMT support,
   compare-and-delay for spinloops and the CES5S crypto adapater.

 - The ftrace support for function tracing with the gcc hotpatch option.
   This touches common code Makefiles, Steven is ok with the changes.

 - The hypfs file system gets an extension to access diagnose 0x0c data
   in user space for performance analysis for Linux running under z/VM.

 - The iucv hvc console gets wildcard spport for the user id filtering.

 - The cacheinfo code is converted to use the generic infrastructure.

 - Cleanup and bug fixes.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (42 commits)
  s390/process: free vx save area when releasing tasks
  s390/hypfs: Eliminate hypfs interval
  s390/hypfs: Add diagnose 0c support
  s390/cacheinfo: don't use smp_processor_id() in preemptible context
  s390/zcrypt: fixed domain scanning problem (again)
  s390/smp: increase maximum value of NR_CPUS to 512
  s390/jump label: use different nop instruction
  s390/jump label: add sanity checks
  s390/mm: correct missing space when reporting user process faults
  s390/dasd: cleanup profiling
  s390/dasd: add locking for global_profile access
  s390/ftrace: hotpatch support for function tracing
  ftrace: let notrace function attribute disable hotpatching if necessary
  ftrace: allow architectures to specify ftrace compile options
  s390: reintroduce diag 44 calls for cpu_relax()
  s390/zcrypt: Add support for new crypto express (CEX5S) adapter.
  s390/zcrypt: Number of supported ap domains is not retrievable.
  s390/spinlock: add compare-and-delay to lock wait loops
  s390/tape: remove redundant if statement
  s390/hvc_iucv: add simple wildcard matches to the iucv allow filter
  ...

13 files changed, 78 insertions, 17 deletions

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index cb700d54bd83..5243a8679a1d 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -189,6 +189,20 @@ static inline int ecctr(u64 ctr, u64 *val)
 	return cc;
 }
 
+/* Store CPU counter multiple for the MT utilization counter set */
+static inline int stcctm5(u64 num, u64 *val)
+{
+	typedef struct { u64 _[num]; } addrtype;
+	int cc;
+
+	asm volatile (
+		"	.insn	rsy,0xeb0000000017,%2,5,%1\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc), "=Q" (*(addrtype *) val)  : "d" (num) : "cc");
+	return cc;
+}
+
 /* Query sampling information */
 static inline int qsi(struct hws_qsi_info_block *info)
 {
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index f6e43d39e3d8..c9df40b5c0ac 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -163,8 +163,8 @@ extern unsigned int vdso_enabled;
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
 
-extern unsigned long randomize_et_dyn(unsigned long base);
-#define ELF_ET_DYN_BASE		(randomize_et_dyn(STACK_TOP / 3 * 2))
+extern unsigned long randomize_et_dyn(void);
+#define ELF_ET_DYN_BASE		randomize_et_dyn()
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */
@@ -209,7 +209,9 @@ do {								\
 } while (0)
 #endif /* CONFIG_COMPAT */
 
-#define STACK_RND_MASK	0x7ffUL
+extern unsigned long mmap_rnd_mask;
+
+#define STACK_RND_MASK	(mmap_rnd_mask)
 
 #define ARCH_DLINFO							    \
 do {									    \
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index abb618f1ead2..836c56290499 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -3,8 +3,12 @@
 
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 
+#ifdef CC_USING_HOTPATCH
+#define MCOUNT_INSN_SIZE	6
+#else
 #define MCOUNT_INSN_SIZE	24
 #define MCOUNT_RETURN_FIXUP	18
+#endif
 
 #ifndef __ASSEMBLY__
 
@@ -37,18 +41,29 @@ struct ftrace_insn {
 static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn)
 {
 #ifdef CONFIG_FUNCTION_TRACER
+#ifdef CC_USING_HOTPATCH
+	/* brcl 0,0 */
+	insn->opc = 0xc004;
+	insn->disp = 0;
+#else
 	/* jg .+24 */
 	insn->opc = 0xc0f4;
 	insn->disp = MCOUNT_INSN_SIZE / 2;
 #endif
+#endif
 }
 
 static inline int is_ftrace_nop(struct ftrace_insn *insn)
 {
 #ifdef CONFIG_FUNCTION_TRACER
+#ifdef CC_USING_HOTPATCH
+	if (insn->disp == 0)
+		return 1;
+#else
 	if (insn->disp == MCOUNT_INSN_SIZE / 2)
 		return 1;
 #endif
+#endif
 	return 0;
 }
 
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 346b1c85ffb4..58642fd29c87 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 
 #define JUMP_LABEL_NOP_SIZE 6
+#define JUMP_LABEL_NOP_OFFSET 2
 
 #ifdef CONFIG_64BIT
 #define ASM_PTR ".quad"
@@ -13,9 +14,13 @@
 #define ASM_ALIGN ".balign 4"
 #endif
 
+/*
+ * We use a brcl 0,2 instruction for jump labels at compile time so it
+ * can be easily distinguished from a hotpatch generated instruction.
+ */
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm_volatile_goto("0:	brcl 0,0\n"
+	asm_volatile_goto("0:	brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
 		".pushsection __jump_table, \"aw\"\n"
 		ASM_ALIGN "\n"
 		ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index ffb1d8ce97ae..0441ec24ae87 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1758,6 +1758,10 @@ extern int s390_enable_sie(void);
 extern int s390_enable_skey(void);
 extern void s390_reset_cmma(struct mm_struct *mm);
 
+/* s390 has a private copy of get unmapped area to deal with cache synonyms */
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
 /*
  * No page table caches to initialise
  */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index bed05ea7ec27..e7cbbdcdee13 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -215,10 +215,7 @@ static inline unsigned short stap(void)
 /*
  * Give up the time slice of the virtual PU.
  */
-static inline void cpu_relax(void)
-{
-	barrier();
-}
+void cpu_relax(void);
 
 #define cpu_relax_lowlatency()  barrier()
 
diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h
index 804578587a7a..72786067b300 100644
--- a/arch/s390/include/asm/reset.h
+++ b/arch/s390/include/asm/reset.h
@@ -15,5 +15,6 @@ struct reset_call {
 
 extern void register_reset_call(struct reset_call *reset);
 extern void unregister_reset_call(struct reset_call *reset);
-extern void s390_reset_system(void (*func)(void *), void *data);
+extern void s390_reset_system(void (*fn_pre)(void),
+			      void (*fn_post)(void *), void *data);
 #endif /* _ASM_S390_RESET_H */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 1aba89b53cb9..edb453cfc2c6 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -27,7 +27,7 @@ struct sclp_ipl_info {
 };
 
 struct sclp_cpu_entry {
-	u8 address;
+	u8 core_id;
 	u8 reserved0[2];
 	u8 : 3;
 	u8 siif : 1;
@@ -51,6 +51,9 @@ int sclp_cpu_deconfigure(u8 cpu);
 unsigned long long sclp_get_rnmax(void);
 unsigned long long sclp_get_rzm(void);
 unsigned int sclp_get_max_cpu(void);
+unsigned int sclp_get_mtid(u8 cpu_type);
+unsigned int sclp_get_mtid_max(void);
+unsigned int sclp_get_mtid_prev(void);
 int sclp_sdias_blk_count(void);
 int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
 int sclp_chp_configure(struct chp_id chpid);
@@ -68,4 +71,6 @@ void sclp_early_detect(void);
 int sclp_has_siif(void);
 unsigned int sclp_get_ibc(void);
 
+long _sclp_print_early(const char *);
+
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 7736fdd72595..b8d1e54b4733 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -57,6 +57,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_FLAG_TE		(1UL << 15)
 #define MACHINE_FLAG_TLB_LC	(1UL << 17)
 #define MACHINE_FLAG_VX		(1UL << 18)
+#define MACHINE_FLAG_CAD	(1UL << 19)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -80,6 +81,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TE		(0)
 #define MACHINE_HAS_TLB_LC	(0)
 #define MACHINE_HAS_VX		(0)
+#define MACHINE_HAS_CAD		(0)
 #else /* CONFIG_64BIT */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -93,6 +95,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
 #define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
+#define MACHINE_HAS_CAD		(S390_lowcore.machine_flags & MACHINE_FLAG_CAD)
 #endif /* CONFIG_64BIT */
 
 /*
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index fad4ae23ece0..ec60cf7fa0a2 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -16,6 +16,7 @@
 #define SIGP_SET_ARCHITECTURE	     18
 #define SIGP_COND_EMERGENCY_SIGNAL   19
 #define SIGP_SENSE_RUNNING	     21
+#define SIGP_SET_MULTI_THREADING     22
 #define SIGP_STORE_ADDITIONAL_STATUS 23
 
 /* SIGP condition codes */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 762d4f88af5a..b3bd0282dd98 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -16,6 +16,8 @@
 #define raw_smp_processor_id()	(S390_lowcore.cpu_nr)
 
 extern struct mutex smp_cpu_state_mutex;
+extern unsigned int smp_cpu_mt_shift;
+extern unsigned int smp_cpu_mtid;
 
 extern int __cpu_up(unsigned int cpu, struct task_struct *tidle);
 
@@ -35,6 +37,8 @@ extern void smp_fill_possible_mask(void);
 
 #else /* CONFIG_SMP */
 
+#define smp_cpu_mtid	0
+
 static inline void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
 	func(data);
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index f92428e459f8..73f12d21af4d 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -90,7 +90,11 @@ struct sysinfo_2_2_2 {
 	unsigned short cpus_reserved;
 	char name[8];
 	unsigned int caf;
-	char reserved_2[16];
+	char reserved_2[8];
+	unsigned char mt_installed;
+	unsigned char mt_general;
+	unsigned char mt_psmtid;
+	char reserved_3[5];
 	unsigned short cpus_dedicated;
 	unsigned short cpus_shared;
 };
@@ -120,26 +124,28 @@ struct sysinfo_3_2_2 {
 
 extern int topology_max_mnest;
 
-#define TOPOLOGY_CPU_BITS	64
+#define TOPOLOGY_CORE_BITS	64
 #define TOPOLOGY_NR_MAG		6
 
-struct topology_cpu {
-	unsigned char reserved0[4];
+struct topology_core {
+	unsigned char nl;
+	unsigned char reserved0[3];
 	unsigned char :6;
 	unsigned char pp:2;
 	unsigned char reserved1;
 	unsigned short origin;
-	unsigned long mask[TOPOLOGY_CPU_BITS / BITS_PER_LONG];
+	unsigned long mask[TOPOLOGY_CORE_BITS / BITS_PER_LONG];
 };
 
 struct topology_container {
-	unsigned char reserved[7];
+	unsigned char nl;
+	unsigned char reserved[6];
 	unsigned char id;
 };
 
 union topology_entry {
 	unsigned char nl;
-	struct topology_cpu cpu;
+	struct topology_core cpu;
 	struct topology_container container;
 };
 
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 56af53093d24..c4fbb9527c5c 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -9,9 +9,11 @@ struct cpu;
 #ifdef CONFIG_SCHED_BOOK
 
 struct cpu_topology_s390 {
+	unsigned short thread_id;
 	unsigned short core_id;
 	unsigned short socket_id;
 	unsigned short book_id;
+	cpumask_t thread_mask;
 	cpumask_t core_mask;
 	cpumask_t book_mask;
 };
@@ -19,6 +21,8 @@ struct cpu_topology_s390 {
 extern struct cpu_topology_s390 cpu_topology[NR_CPUS];
 
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
+#define topology_thread_id(cpu)			(cpu_topology[cpu].thread_id)
+#define topology_thread_cpumask(cpu)		(&cpu_topology[cpu].thread_mask)
 #define topology_core_id(cpu)			(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)		(&cpu_topology[cpu].core_mask)
 #define topology_book_id(cpu)			(cpu_topology[cpu].book_id)