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

Pull second round of s390 updates from Martin Schwidefsky:

 - rework of the vdso code to avoid the use of the access register mode

 - use perf AUX buffers for the transport of diagnostic sample data

 - add perf_regs and user stack dump support

 - enable perf call graphs for user space programs

 - add perf register support for floating-point registers

 - all remaining s390 related timer_setup conversions

 - bug fixes and cleanups

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (30 commits)
  s390: remove unused parameter from Makefile
  zfcp: purely mechanical update using timer API, plus blank lines
  s390/scsi: Convert timers to use timer_setup()
  s390/cpum_sf: correctly set the PID and TID in perf samples
  s390/cpum_sf: load program parameter at sampler enablement
  s390/perf: add perf register support for floating-point registers
  s390/perf: extend perf_regs support to include floating-point registers
  s390/perf: define common DWARF register string table
  s390/perf: add support for perf_regs and libdw
  s390/perf: add perf_regs support and user stack dump
  s390/cpum_sf: do not register PMU if no sampling mode is authorized
  s390/cpumf: remove raw event support in basic-only sampling mode
  s390/perf: add callback to perf to enable using AUX buffer
  s390/cpumf: enable using AUX buffer
  s390/cpumf: introduce AUX buffer for dump diagnostic sample data
  s390/disassembler: increase show_code buffer size
  s390: Remove CONFIG_HARDENED_USERCOPY
  s390: enable CPU alternatives unconditionally
  s390/nmi: remove unused code
  s390/mm: remove unused code
  ...

11 files changed, 63 insertions, 104 deletions

diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h
index 6c268f6a51d3..a72002056b54 100644
--- a/arch/s390/include/asm/alternative.h
+++ b/arch/s390/include/asm/alternative.h
@@ -15,14 +15,9 @@ struct alt_instr {
 	u8  replacementlen;	/* length of new instruction */
 } __packed;
 
-#ifdef CONFIG_ALTERNATIVES
-extern void apply_alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
-#else
-static inline void apply_alternative_instructions(void) {};
-static inline void apply_alternatives(struct alt_instr *start,
-				      struct alt_instr *end) {};
-#endif
+void apply_alternative_instructions(void);
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
 /*
  * |661:       |662:	  |6620      |663:
  * +-----------+---------------------+
@@ -109,7 +104,6 @@ static inline void apply_alternatives(struct alt_instr *start,
 	b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n"	\
 	INSTR_LEN_SANITY_CHECK(altinstr_len(num))
 
-#ifdef CONFIG_ALTERNATIVES
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, altinstr, facility) \
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
@@ -130,14 +124,6 @@ static inline void apply_alternatives(struct alt_instr *start,
 	ALTINSTR_ENTRY(facility1, 1)					\
 	ALTINSTR_ENTRY(facility2, 2)					\
 	".popsection\n"
-#else
-/* Alternative instructions are disabled, let's put just oldinstr in */
-#define ALTERNATIVE(oldinstr, altinstr, facility) \
-	oldinstr "\n"
-
-#define ALTERNATIVE_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \
-	oldinstr "\n"
-#endif
 
 /*
  * Alternative instructions for different CPU types or capabilities.
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 05480e4cc5ca..792cda339af1 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -144,6 +144,12 @@ struct hws_trailer_entry {
 	unsigned long long progusage2;	 /*				      */
 } __packed;
 
+/* Load program parameter */
+static inline void lpp(void *pp)
+{
+	asm volatile(".insn s,0xb2800000,0(%0)\n":: "a" (pp) : "memory");
+}
+
 /* Query counter information */
 static inline int qctri(struct cpumf_ctr_info *info)
 {
@@ -167,7 +173,7 @@ static inline int lcctl(u64 ctl)
 		"	.insn	s,0xb2840000,%1\n"
 		"	ipm	%0\n"
 		"	srl	%0,28\n"
-		: "=d" (cc) : "m" (ctl) : "cc");
+		: "=d" (cc) : "Q" (ctl) : "cc");
 	return cc;
 }
 
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 9b5a3469fed9..5e97a4353147 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -26,9 +26,9 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 		u32 __user *uaddr)
 {
 	int oldval = 0, newval, ret;
+	mm_segment_t old_fs;
 
-	load_kernel_asce();
-
+	old_fs = enable_sacf_uaccess();
 	pagefault_disable();
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -55,6 +55,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 		ret = -ENOSYS;
 	}
 	pagefault_enable();
+	disable_sacf_uaccess(old_fs);
 
 	if (!ret)
 		*oval = oldval;
@@ -65,9 +66,10 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 						u32 oldval, u32 newval)
 {
+	mm_segment_t old_fs;
 	int ret;
 
-	load_kernel_asce();
+	old_fs = enable_sacf_uaccess();
 	asm volatile(
 		"   sacf 256\n"
 		"0: cs   %1,%4,0(%5)\n"
@@ -77,6 +79,7 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
 		: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
 		: "cc", "memory");
+	disable_sacf_uaccess(old_fs);
 	*uval = oldval;
 	return ret;
 }
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 9eb36a1592c7..ec6592e8ba36 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -115,33 +115,28 @@ struct lowcore {
 	/* Address space pointer. */
 	__u64	kernel_asce;			/* 0x0378 */
 	__u64	user_asce;			/* 0x0380 */
+	__u64	vdso_asce;			/* 0x0388 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0388 */
-	__u32	current_pid;			/* 0x038c */
+	__u32	lpp;				/* 0x0390 */
+	__u32	current_pid;			/* 0x0394 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0390 */
-	__u32	softirq_pending;		/* 0x0394 */
-	__u64	percpu_offset;			/* 0x0398 */
-	__u64	vdso_per_cpu_data;		/* 0x03a0 */
-	__u64	machine_flags;			/* 0x03a8 */
-	__u32	preempt_count;			/* 0x03b0 */
-	__u8	pad_0x03b4[0x03b8-0x03b4];	/* 0x03b4 */
-	__u64	gmap;				/* 0x03b8 */
-	__u32	spinlock_lockval;		/* 0x03c0 */
-	__u32	spinlock_index;			/* 0x03c4 */
-	__u32	fpu_flags;			/* 0x03c8 */
-	__u8	pad_0x03cc[0x0400-0x03cc];	/* 0x03cc */
-
-	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x0400 */
-
-	__u8	pad_0x04c0[0x0e00-0x0440];	/* 0x0440 */
+	__u32	cpu_nr;				/* 0x0398 */
+	__u32	softirq_pending;		/* 0x039c */
+	__u32	preempt_count;			/* 0x03a0 */
+	__u32	spinlock_lockval;		/* 0x03a4 */
+	__u32	spinlock_index;			/* 0x03a8 */
+	__u32	fpu_flags;			/* 0x03ac */
+	__u64	percpu_offset;			/* 0x03b0 */
+	__u64	vdso_per_cpu_data;		/* 0x03b8 */
+	__u64	machine_flags;			/* 0x03c0 */
+	__u64	gmap;				/* 0x03c8 */
+	__u8	pad_0x03d0[0x0e00-0x03d0];	/* 0x03d0 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -193,14 +188,14 @@ extern struct lowcore *lowcore_ptr[];
 
 static inline void set_prefix(__u32 address)
 {
-	asm volatile("spx %0" : : "m" (address) : "memory");
+	asm volatile("spx %0" : : "Q" (address) : "memory");
 }
 
 static inline __u32 store_prefix(void)
 {
 	__u32 address;
 
-	asm volatile("stpx %0" : "=m" (address));
+	asm volatile("stpx %0" : "=Q" (address));
 	return address;
 }
 
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index cf4c1cb17dcd..f4a07f788f78 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -73,41 +73,38 @@ static inline int init_new_context(struct task_struct *tsk,
 static inline void set_user_asce(struct mm_struct *mm)
 {
 	S390_lowcore.user_asce = mm->context.asce;
-	if (current->thread.mm_segment.ar4)
-		__ctl_load(S390_lowcore.user_asce, 7, 7);
-	set_cpu_flag(CIF_ASCE_PRIMARY);
+	__ctl_load(S390_lowcore.user_asce, 1, 1);
+	clear_cpu_flag(CIF_ASCE_PRIMARY);
 }
 
 static inline void clear_user_asce(void)
 {
 	S390_lowcore.user_asce = S390_lowcore.kernel_asce;
-
-	__ctl_load(S390_lowcore.user_asce, 1, 1);
-	__ctl_load(S390_lowcore.user_asce, 7, 7);
-}
-
-static inline void load_kernel_asce(void)
-{
-	unsigned long asce;
-
-	__ctl_store(asce, 1, 1);
-	if (asce != S390_lowcore.kernel_asce)
-		__ctl_load(S390_lowcore.kernel_asce, 1, 1);
+	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	set_cpu_flag(CIF_ASCE_PRIMARY);
 }
 
+mm_segment_t enable_sacf_uaccess(void);
+void disable_sacf_uaccess(mm_segment_t old_fs);
+
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			     struct task_struct *tsk)
 {
 	int cpu = smp_processor_id();
 
-	S390_lowcore.user_asce = next->context.asce;
 	if (prev == next)
 		return;
+	S390_lowcore.user_asce = next->context.asce;
 	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
-	/* Clear old ASCE by loading the kernel ASCE. */
-	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
-	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
+	/* Clear previous user-ASCE from CR1 and CR7 */
+	if (!test_cpu_flag(CIF_ASCE_PRIMARY)) {
+		__ctl_load(S390_lowcore.kernel_asce, 1, 1);
+		set_cpu_flag(CIF_ASCE_PRIMARY);
+	}
+	if (test_cpu_flag(CIF_ASCE_SECONDARY)) {
+		__ctl_load(S390_lowcore.vdso_asce, 7, 7);
+		clear_cpu_flag(CIF_ASCE_SECONDARY);
+	}
 	cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
 }
 
@@ -117,7 +114,6 @@ static inline void finish_arch_post_lock_switch(void)
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 
-	load_kernel_asce();
 	if (mm) {
 		preempt_disable();
 		while (atomic_read(&mm->context.flush_count))
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 79aa6421fedb..d6c9d1e0dc2d 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -64,27 +64,10 @@ struct perf_sf_sde_regs {
 #define REG_OVERFLOW		1
 #define OVERFLOW_REG(hwc)	((hwc)->extra_reg.config)
 #define SFB_ALLOC_REG(hwc)	((hwc)->extra_reg.alloc)
-#define RAWSAMPLE_REG(hwc)	((hwc)->config)
 #define TEAR_REG(hwc)		((hwc)->last_tag)
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
 #define SAMPL_FLAGS(hwc)	((hwc)->config_base)
 #define SAMPL_DIAG_MODE(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE)
 #define SDB_FULL_BLOCKS(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS)
 
-/* Structure for sampling data entries to be passed as perf raw sample data
- * to user space.  Note that raw sample data must be aligned and, thus, might
- * be padded with zeros.
- */
-struct sf_raw_sample {
-#define SF_RAW_SAMPLE_BASIC	PERF_CPUM_SF_BASIC_MODE
-#define SF_RAW_SAMPLE_DIAG	PERF_CPUM_SF_DIAG_MODE
-	u64			format;
-	u32			 size;	  /* Size of sf_raw_sample */
-	u16			bsdes;	  /* Basic-sampling data entry size */
-	u16			dsdes;	  /* Diagnostic-sampling data entry size */
-	struct hws_basic_entry	basic;	  /* Basic-sampling data entry */
-	struct hws_diag_entry	 diag;	  /* Diagnostic-sampling data entry */
-	u8		    padding[];	  /* Padding to next multiple of 8 */
-} __packed;
-
 #endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index f25bfe888933..bfbfad482289 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -109,9 +109,7 @@ extern void execve_tail(void);
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
 
-typedef struct {
-        __u32 ar4;
-} mm_segment_t;
+typedef unsigned int mm_segment_t;
 
 /*
  * Thread structure
@@ -247,7 +245,7 @@ static inline unsigned short stap(void)
 {
 	unsigned short cpu_address;
 
-	asm volatile("stap %0" : "=m" (cpu_address));
+	asm volatile("stap %0" : "=Q" (cpu_address));
 	return cpu_address;
 }
 
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 2f84e77f1f1b..a3788dafc0e1 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -13,10 +13,12 @@
 #define PIF_SYSCALL		0	/* inside a system call */
 #define PIF_PER_TRAP		1	/* deliver sigtrap on return to user */
 #define PIF_SYSCALL_RESTART	2	/* restart the current system call */
+#define PIF_GUEST_FAULT		3	/* indicates program check in sie64a */
 
 #define _PIF_SYSCALL		_BITUL(PIF_SYSCALL)
 #define _PIF_PER_TRAP		_BITUL(PIF_PER_TRAP)
 #define _PIF_SYSCALL_RESTART	_BITUL(PIF_SYSCALL_RESTART)
+#define _PIF_GUEST_FAULT	_BITUL(PIF_GUEST_FAULT)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 8bc87dcb10eb..2eb0c8a7b664 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -36,7 +36,7 @@
 #define MACHINE_FLAG_SCC	_BITUL(17)
 
 #define LPP_MAGIC		_BITUL(31)
-#define LPP_PFAULT_PID_MASK	_AC(0xffffffff, UL)
+#define LPP_PID_MASK		_AC(0xffffffff, UL)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index cdd0f0d999e2..ad6b91013a05 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -16,7 +16,7 @@
 #include <asm/processor.h>
 #include <asm/ctl_reg.h>
 #include <asm/extable.h>
-
+#include <asm/facility.h>
 
 /*
  * The fs value determines whether argument validity checking should be
@@ -26,27 +26,16 @@
  * For historical reasons, these macros are grossly misnamed.
  */
 
-#define MAKE_MM_SEG(a)  ((mm_segment_t) { (a) })
-
-
-#define KERNEL_DS       MAKE_MM_SEG(0)
-#define USER_DS         MAKE_MM_SEG(1)
+#define KERNEL_DS	(0)
+#define KERNEL_DS_SACF	(1)
+#define USER_DS		(2)
+#define USER_DS_SACF	(3)
 
 #define get_ds()        (KERNEL_DS)
 #define get_fs()        (current->thread.mm_segment)
-#define segment_eq(a,b) ((a).ar4 == (b).ar4)
+#define segment_eq(a,b) (((a) & 2) == ((b) & 2))
 
-static inline void set_fs(mm_segment_t fs)
-{
-	current->thread.mm_segment = fs;
-	if (uaccess_kernel()) {
-		set_cpu_flag(CIF_ASCE_SECONDARY);
-		__ctl_load(S390_lowcore.kernel_asce, 7, 7);
-	} else {
-		clear_cpu_flag(CIF_ASCE_SECONDARY);
-		__ctl_load(S390_lowcore.user_asce, 7, 7);
-	}
-}
+void set_fs(mm_segment_t fs);
 
 static inline int __range_ok(unsigned long addr, unsigned long size)
 {
@@ -95,7 +84,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 
 static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
-	unsigned long spec = 0x810000UL;
+	unsigned long spec = 0x010000UL;
 	int rc;
 
 	switch (size) {
@@ -125,7 +114,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 
 static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
 {
-	unsigned long spec = 0x81UL;
+	unsigned long spec = 0x01UL;
 	int rc;
 
 	switch (size) {
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index ae6261ef97d5..169d7604eb80 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -46,6 +46,7 @@ struct vdso_per_cpu_data {
 };
 
 extern struct vdso_data *vdso_data;
+extern struct vdso_data boot_vdso_data;
 
 void vdso_alloc_boot_cpu(struct lowcore *lowcore);
 int vdso_alloc_per_cpu(struct lowcore *lowcore);