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

Pull s390 updates from Martin Schwidefsky:

 - Add the CPU id for the new z13s machine

 - Add a s390 specific XOR template for RAID-5 checksumming based on the
   XC instruction.  Remove all other alternatives, XC is always faster

 - The merge of our four different stack tracers into a single one

 - Tidy up the code related to page tables, several large inline
   functions are now out-of-line.  Bloat-o-meter reports ~11K text size
   reduction

 - A binary interface for the priviledged CLP instruction to retrieve
   the hardware view of the installed PCI functions

 - Improvements for the dasd format code

 - Bug fixes and cleanups

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (31 commits)
  s390/pci: enforce fmb page boundary rule
  s390: fix floating pointer register corruption (again)
  s390/cpumf: add missing lpp magic initialization
  s390: Fix misspellings in comments
  s390/mm: split arch/s390/mm/pgtable.c
  s390/mm: uninline pmdp_xxx functions from pgtable.h
  s390/mm: uninline ptep_xxx functions from pgtable.h
  s390/pci: add ioctl interface for CLP
  s390: Use pr_warn instead of pr_warning
  s390/dasd: remove casts to dasd_*_private
  s390/dasd: Refactor dasd format functions
  s390/dasd: Simplify code in format logic
  s390/dasd: Improve dasd format code
  s390/percpu: remove this_cpu_cmpxchg_double_4
  s390/cpumf: Improve guest detection heuristics
  s390/fault: merge report_user_fault implementations
  s390/dis: use correct escape sequence for '%' character
  s390/kvm: simplify set_guest_storage_key
  s390/oprofile: add z13/z13s model numbers
  s390: add z13s model number to z13 elf platform
  ...

arch/s390/Kconfig

@@ -254,12 +254,12 @@ config MARCH_ZEC12
 	  older machines.
 
 config MARCH_Z13
-	bool "IBM z13"
+	bool "IBM z13s and z13"
 	select HAVE_MARCH_Z13_FEATURES
 	help
-	  Select this to enable optimizations for IBM z13 (2964 series).
-	  The kernel will be slightly faster but will not work on older
-	  machines.
+	  Select this to enable optimizations for IBM z13s and z13 (2965 and
+	  2964 series). The kernel will be slightly faster but will not work on
+	  older machines.
 
 endchoice
 

arch/s390/include/asm/clp.h

@@ -4,14 +4,23 @@
 /* CLP common request & response block size */
 #define CLP_BLK_SIZE			PAGE_SIZE
 
+#define CLP_LPS_BASE	0
+#define CLP_LPS_PCI	2
+
 struct clp_req_hdr {
 	u16 len;
 	u16 cmd;
+	u32 fmt		: 4;
+	u32 reserved1	: 28;
+	u64 reserved2;
 } __packed;
 
 struct clp_rsp_hdr {
 	u16 len;
 	u16 rsp;
+	u32 fmt		: 4;
+	u32 reserved1	: 28;
+	u64 reserved2;
 } __packed;
 
 /* CLP Response Codes */
@@ -25,4 +34,22 @@ struct clp_rsp_hdr {
 #define CLP_RC_NODATA			0x0080	/* No data available */
 #define CLP_RC_FC_UNKNOWN		0x0100	/* Function code not recognized */
 
+/* Store logical-processor characteristics request */
+struct clp_req_slpc {
+	struct clp_req_hdr hdr;
+} __packed;
+
+struct clp_rsp_slpc {
+	struct clp_rsp_hdr hdr;
+	u32 reserved2[4];
+	u32 lpif[8];
+	u32 reserved3[8];
+	u32 lpic[8];
+} __packed;
+
+struct clp_req_rsp_slpc {
+	struct clp_req_slpc request;
+	struct clp_rsp_slpc response;
+} __packed;
+
 #endif

arch/s390/include/asm/gmap.h

+/*
+ *  KVM guest address space mapping code
+ *
+ *    Copyright IBM Corp. 2007, 2016
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _ASM_S390_GMAP_H
+#define _ASM_S390_GMAP_H
+
+/**
+ * struct gmap_struct - guest address space
+ * @crst_list: list of all crst tables used in the guest address space
+ * @mm: pointer to the parent mm_struct
+ * @guest_to_host: radix tree with guest to host address translation
+ * @host_to_guest: radix tree with pointer to segment table entries
+ * @guest_table_lock: spinlock to protect all entries in the guest page table
+ * @table: pointer to the page directory
+ * @asce: address space control element for gmap page table
+ * @pfault_enabled: defines if pfaults are applicable for the guest
+ */
+struct gmap {
+	struct list_head list;
+	struct list_head crst_list;
+	struct mm_struct *mm;
+	struct radix_tree_root guest_to_host;
+	struct radix_tree_root host_to_guest;
+	spinlock_t guest_table_lock;
+	unsigned long *table;
+	unsigned long asce;
+	unsigned long asce_end;
+	void *private;
+	bool pfault_enabled;
+};
+
+/**
+ * struct gmap_notifier - notify function block for page invalidation
+ * @notifier_call: address of callback function
+ */
+struct gmap_notifier {
+	struct list_head list;
+	void (*notifier_call)(struct gmap *gmap, unsigned long gaddr);
+};
+
+struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit);
+void gmap_free(struct gmap *gmap);
+void gmap_enable(struct gmap *gmap);
+void gmap_disable(struct gmap *gmap);
+int gmap_map_segment(struct gmap *gmap, unsigned long from,
+		     unsigned long to, unsigned long len);
+int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
+unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
+unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
+int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
+int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
+void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
+void __gmap_zap(struct gmap *, unsigned long gaddr);
+void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
+
+void gmap_register_ipte_notifier(struct gmap_notifier *);
+void gmap_unregister_ipte_notifier(struct gmap_notifier *);
+int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
+
+#endif /* _ASM_S390_GMAP_H */

arch/s390/include/asm/pci.h

@@ -45,7 +45,7 @@ struct zpci_fmb {
 	u64 rpcit_ops;
 	u64 dma_rbytes;
 	u64 dma_wbytes;
-} __packed __aligned(16);
+} __packed __aligned(64);
 
 enum zpci_state {
 	ZPCI_FN_STATE_RESERVED,
@@ -66,7 +66,6 @@ struct s390_domain;
 
 /* Private data per function */
 struct zpci_dev {
-	struct pci_dev	*pdev;
 	struct pci_bus	*bus;
 	struct list_head entry;		/* list of all zpci_devices, needed for hotplug, etc. */
 
@@ -192,7 +191,7 @@ int zpci_fmb_disable_device(struct zpci_dev *);
 /* Debug */
 int zpci_debug_init(void);
 void zpci_debug_exit(void);
-void zpci_debug_init_device(struct zpci_dev *);
+void zpci_debug_init_device(struct zpci_dev *, const char *);
 void zpci_debug_exit_device(struct zpci_dev *);
 void zpci_debug_info(struct zpci_dev *, struct seq_file *);
 

arch/s390/include/asm/pci_clp.h

@@ -49,9 +49,6 @@ struct clp_fh_list_entry {
 /* List PCI functions request */
 struct clp_req_list_pci {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u64 resume_token;
 	u64 reserved2;
 } __packed;
@@ -59,9 +56,6 @@ struct clp_req_list_pci {
 /* List PCI functions response */
 struct clp_rsp_list_pci {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u64 resume_token;
 	u32 reserved2;
 	u16 max_fn;
@@ -73,9 +67,6 @@ struct clp_rsp_list_pci {
 /* Query PCI function request */
 struct clp_req_query_pci {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u32 fh;				/* function handle */
 	u32 reserved2;
 	u64 reserved3;
@@ -84,9 +75,6 @@ struct clp_req_query_pci {
 /* Query PCI function response */
 struct clp_rsp_query_pci {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64			: 64;
 	u16 vfn;			/* virtual fn number */
 	u16			:  7;
 	u16 util_str_avail	:  1;	/* utility string available? */
@@ -108,21 +96,15 @@ struct clp_rsp_query_pci {
 /* Query PCI function group request */
 struct clp_req_query_pci_grp {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
-	u32			: 24;
+	u32 reserved2		: 24;
 	u32 pfgid		:  8;	/* function group id */
-	u32 reserved2;
-	u64 reserved3;
+	u32 reserved3;
+	u64 reserved4;
 } __packed;
 
 /* Query PCI function group response */
 struct clp_rsp_query_pci_grp {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u16			:  4;
 	u16 noi			: 12;	/* number of interrupts */
 	u8 version;
@@ -141,9 +123,6 @@ struct clp_rsp_query_pci_grp {
 /* Set PCI function request */
 struct clp_req_set_pci {
 	struct clp_req_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u32 fh;				/* function handle */
 	u16 reserved2;
 	u8 oc;				/* operation controls */
@@ -154,9 +133,6 @@ struct clp_req_set_pci {
 /* Set PCI function response */
 struct clp_rsp_set_pci {
 	struct clp_rsp_hdr hdr;
-	u32 fmt			:  4;	/* cmd request block format */
-	u32			: 28;
-	u64 reserved1;
 	u32 fh;				/* function handle */
 	u32 reserved3;
 	u64 reserved4;

arch/s390/include/asm/percpu.h

@@ -178,7 +178,6 @@
 	ret__;								\
 })
 
-#define this_cpu_cmpxchg_double_4 arch_this_cpu_cmpxchg_double
 #define this_cpu_cmpxchg_double_8 arch_this_cpu_cmpxchg_double
 
 #include <asm-generic/percpu.h>

arch/s390/include/asm/perf_event.h

@@ -21,7 +21,7 @@
 #define PMU_F_ERR_LSDA			0x0200
 #define PMU_F_ERR_MASK			(PMU_F_ERR_IBE|PMU_F_ERR_LSDA)
 
-/* Perf defintions for PMU event attributes in sysfs */
+/* Perf definitions for PMU event attributes in sysfs */
 extern __init const struct attribute_group **cpumf_cf_event_group(void);
 extern ssize_t cpumf_events_sysfs_show(struct device *dev,
 				       struct device_attribute *attr,

arch/s390/include/asm/pgalloc.h

@@ -23,10 +23,6 @@ void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
 extern int page_table_allocate_pgste;
 
-int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
-			  unsigned long key, bool nq);
-unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
-
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
 	typedef struct { char _[n]; } addrtype;

arch/s390/include/asm/processor.h

@@ -184,6 +184,10 @@ struct task_struct;
 struct mm_struct;
 struct seq_file;
 
+typedef int (*dump_trace_func_t)(void *data, unsigned long address);
+void dump_trace(dump_trace_func_t func, void *data,
+		struct task_struct *task, unsigned long sp);
+
 void show_cacheinfo(struct seq_file *m);
 
 /* Free all resources held by a thread. */
@@ -203,6 +207,14 @@ unsigned long get_wchan(struct task_struct *p);
 /* Has task runtime instrumentation enabled ? */
 #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb)
 
+static inline unsigned long current_stack_pointer(void)
+{
+	unsigned long sp;
+
+	asm volatile("la %0,0(15)" : "=a" (sp));
+	return sp;
+}
+
 static inline unsigned short stap(void)
 {
 	unsigned short cpu_address;

arch/s390/include/asm/rwsem.h

@@ -31,7 +31,7 @@
  * This should be totally fair - if anything is waiting, a process that wants a
  * lock will go to the back of the queue. When the currently active lock is
  * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consequtive readers at the
+ * that will be woken up; if there's a bunch of consecutive readers at the
  * front, then they'll all be woken up, but no other readers will be.
  */
 

arch/s390/include/asm/setup.h

@@ -101,6 +101,8 @@ extern void pfault_fini(void);
 #define pfault_fini()		do { } while (0)
 #endif /* CONFIG_PFAULT */
 
+void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault);
+
 extern void cmma_init(void);
 
 extern void (*_machine_restart)(char *command);

arch/s390/include/asm/xor.h

-#include <asm-generic/xor.h>
+/*
+ * Optimited xor routines
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+#ifndef _ASM_S390_XOR_H
+#define _ASM_S390_XOR_H
+
+extern struct xor_block_template xor_block_xc;
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES				\
+do {							\
+	xor_speed(&xor_block_xc);			\
+} while (0)
+
+#define XOR_SELECT_TEMPLATE(FASTEST)	(&xor_block_xc)
+
+#endif /* _ASM_S390_XOR_H */

arch/s390/include/uapi/asm/clp.h

+/*
+ * ioctl interface for /dev/clp
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef _ASM_CLP_H
+#define _ASM_CLP_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+struct clp_req {
+	unsigned int c : 1;
+	unsigned int r : 1;
+	unsigned int lps : 6;
+	unsigned int cmd : 8;
+	unsigned int : 16;
+	unsigned int reserved;
+	__u64 data_p;
+};
+
+#define CLP_IOCTL_MAGIC 'c'
+
+#define CLP_SYNC _IOWR(CLP_IOCTL_MAGIC, 0xC1, struct clp_req)
+
+#endif

arch/s390/kernel/asm-offsets.c

@@ -12,6 +12,7 @@
 #include <asm/idle.h>
 #include <asm/vdso.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that

arch/s390/kernel/cpcmd.c

@@ -96,8 +96,7 @@ int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 			(((unsigned long)response + rlen) >> 31)) {
 		lowbuf = kmalloc(rlen, GFP_KERNEL | GFP_DMA);
 		if (!lowbuf) {
-			pr_warning("The cpcmd kernel function failed to "
-				   "allocate a response buffer\n");
+			pr_warn("The cpcmd kernel function failed to allocate a response buffer\n");
 			return -ENOMEM;
 		}
 		spin_lock_irqsave(&cpcmd_lock, flags);

arch/s390/kernel/debug.c

@@ -699,8 +699,7 @@ debug_info_t *debug_register_mode(const char *name, int pages_per_area,
 	/* Since debugfs currently does not support uid/gid other than root, */
 	/* we do not allow gid/uid != 0 until we get support for that. */
 	if ((uid != 0) || (gid != 0))
-		pr_warning("Root becomes the owner of all s390dbf files "
-			   "in sysfs\n");
+		pr_warn("Root becomes the owner of all s390dbf files in sysfs\n");
 	BUG_ON(!initialized);
 	mutex_lock(&debug_mutex);
 
@@ -1307,8 +1306,7 @@ debug_input_level_fn(debug_info_t * id, struct debug_view *view,
 		new_level = debug_get_uint(str);
 	}
 	if(new_level < 0) {
-		pr_warning("%s is not a valid level for a debug "
-			   "feature\n", str);
+		pr_warn("%s is not a valid level for a debug feature\n", str);
 		rc = -EINVAL;
 	} else {
 		debug_set_level(id, new_level);

arch/s390/kernel/dis.c

@@ -1920,23 +1920,16 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 			}
 			if (separator)
 				ptr += sprintf(ptr, "%c", separator);
-			/*
-			 * Use four '%' characters below because of the
-			 * following two conversions:
-			 *
-			 *  1) sprintf: %%%%r -> %%r
-			 *  2) printk : %%r   -> %r
-			 */
 			if (operand->flags & OPERAND_GPR)
-				ptr += sprintf(ptr, "%%%%r%i", value);
+				ptr += sprintf(ptr, "%%r%i", value);
 			else if (operand->flags & OPERAND_FPR)
-				ptr += sprintf(ptr, "%%%%f%i", value);
+				ptr += sprintf(ptr, "%%f%i", value);
 			else if (operand->flags & OPERAND_AR)
-				ptr += sprintf(ptr, "%%%%a%i", value);
+				ptr += sprintf(ptr, "%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
-				ptr += sprintf(ptr, "%%%%c%i", value);
+				ptr += sprintf(ptr, "%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
-				ptr += sprintf(ptr, "%%%%v%i", value);
+				ptr += sprintf(ptr, "%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);

arch/s390/kernel/dumpstack.c

@@ -19,28 +19,28 @@
 #include <asm/ipl.h>
 
 /*
- * For show_trace we have tree different stack to consider:
+ * For dump_trace we have tree different stack to consider:
  *   - the panic stack which is used if the kernel stack has overflown
  *   - the asynchronous interrupt stack (cpu related)
  *   - the synchronous kernel stack (process related)
- * The stack trace can start at any of the three stack and can potentially
+ * The stack trace can start at any of the three stacks and can potentially
  * touch all of them. The order is: panic stack, async stack, sync stack.
  */
 static unsigned long
-__show_trace(unsigned long sp, unsigned long low, unsigned long high)
+__dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
+	     unsigned long low, unsigned long high)
 {
 	struct stack_frame *sf;
 	struct pt_regs *regs;
-	unsigned long addr;
 
 	while (1) {
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		addr = sf->gprs[8];
-		printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
 		/* Follow the backchain. */
 		while (1) {
+			if (func(data, sf->gprs[8]))
+				return sp;
 			low = sp;
 			sp = sf->back_chain;
 			if (!sp)
@@ -48,46 +48,58 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			addr = sf->gprs[8];
-			printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
 		sp = (unsigned long) (sf + 1);
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		addr = regs->psw.addr;
-		printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
+		if (!user_mode(regs)) {
+			if (func(data, regs->psw.addr))
+				return sp;
+		}
 		low = sp;
 		sp = regs->gprs[15];
 	}
 }
 
-static void show_trace(struct task_struct *task, unsigned long *stack)
+void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
+		unsigned long sp)
 {
-	const unsigned long frame_size =
-		STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-	register unsigned long __r15 asm ("15");
-	unsigned long sp;
+	unsigned long frame_size;
 
-	sp = (unsigned long) stack;
-	if (!sp)
-		sp = task ? task->thread.ksp : __r15;
-	printk("Call Trace:\n");
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
 #ifdef CONFIG_CHECK_STACK
-	sp = __show_trace(sp,
+	sp = __dump_trace(func, data, sp,
 			  S390_lowcore.panic_stack + frame_size - 4096,
 			  S390_lowcore.panic_stack + frame_size);
 #endif
-	sp = __show_trace(sp,
+	sp = __dump_trace(func, data, sp,
 			  S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
 			  S390_lowcore.async_stack + frame_size);
 	if (task)
-		__show_trace(sp, (unsigned long) task_stack_page(task),
-			     (unsigned long) task_stack_page(task) + THREAD_SIZE);
+		__dump_trace(func, data, sp,
+			     (unsigned long)task_stack_page(task),
+			     (unsigned long)task_stack_page(task) + THREAD_SIZE);
 	else
-		__show_trace(sp, S390_lowcore.thread_info,
+		__dump_trace(func, data, sp,
+			     S390_lowcore.thread_info,
 			     S390_lowcore.thread_info + THREAD_SIZE);
+}
+EXPORT_SYMBOL_GPL(dump_trace);
+
+static int show_address(void *data, unsigned long address)
+{
+	printk("([<%016lx>] %pSR)\n", address, (void *)address);
+	return 0;
+}
+
+static void show_trace(struct task_struct *task, unsigned long sp)
+{
+	if (!sp)
+		sp = task ? task->thread.ksp : current_stack_pointer();
+	printk("Call Trace:\n");
+	dump_trace(show_address, NULL, task, sp);
 	if (!task)
 		task = current;
 	debug_show_held_locks(task);
@@ -95,15 +107,16 @@ static void show_trace(struct task_struct *task, unsigned long *stack)
 
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
-	register unsigned long *__r15 asm ("15");
 	unsigned long *stack;
 	int i;
 
-	if (!sp)
-		stack = task ? (unsigned long *) task->thread.ksp : __r15;
-	else
-		stack = sp;
-
+	stack = sp;
+	if (!stack) {
+		if (!task)
+			stack = (unsigned long *)current_stack_pointer();
+		else
+			stack = (unsigned long *)task->thread.ksp;
+	}
 	for (i = 0; i < 20; i++) {
 		if (((addr_t) stack & (THREAD_SIZE-1)) == 0)
 			break;
@@ -112,7 +125,7 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 		printk("%016lx ", *stack++);
 	}
 	printk("\n");
-	show_trace(task, sp);
+	show_trace(task, (unsigned long)sp);
 }
 
 static void show_last_breaking_event(struct pt_regs *regs)
@@ -121,13 +134,9 @@ static void show_last_breaking_event(struct pt_regs *regs)
 	printk(" [<%016lx>] %pSR\n", regs->args[0], (void *)regs->args[0]);
 }
 
-static inline int mask_bits(struct pt_regs *regs, unsigned long bits)
-{
-	return (regs->psw.mask & bits) / ((~bits + 1) & bits);
-}
-
 void show_registers(struct pt_regs *regs)
 {
+	struct psw_bits *psw = &psw_bits(regs->psw);
 	char *mode;
 
 	mode = user_mode(regs) ? "User" : "Krnl";
@@ -136,13 +145,9 @@ void show_registers(struct pt_regs *regs)
 		printk(" (%pSR)", (void *)regs->psw.addr);
 	printk("\n");
 	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
-	       "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
-	       mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
-	       mask_bits(regs, PSW_MASK_EXT), mask_bits(regs, PSW_MASK_KEY),
-	       mask_bits(regs, PSW_MASK_MCHECK), mask_bits(regs, PSW_MASK_WAIT),
-	       mask_bits(regs, PSW_MASK_PSTATE), mask_bits(regs, PSW_MASK_ASC),
-	       mask_bits(regs, PSW_MASK_CC), mask_bits(regs, PSW_MASK_PM));
-	printk(" EA:%x", mask_bits(regs, PSW_MASK_EA | PSW_MASK_BA));
+	       "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e,
+	       psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm);
+	printk(" RI:%x EA:%x", psw->ri, psw->eaba);
 	printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode,
 	       regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]);
 	printk("           %016lx %016lx %016lx %016lx\n",
@@ -160,7 +165,7 @@ void show_regs(struct pt_regs *regs)
 	show_registers(regs);
 	/* Show stack backtrace if pt_regs is from kernel mode */
 	if (!user_mode(regs))
-		show_trace(NULL, (unsigned long *) regs->gprs[15]);
+		show_trace(NULL, regs->gprs[15]);
 	show_last_breaking_event(regs);
 }
 

arch/s390/kernel/entry.S

@@ -186,6 +186,7 @@ ENTRY(__switch_to)
 	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
 	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
+	/* c4 is used in guest detection: arch/s390/kernel/perf_cpum_sf.c */
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
@@ -1199,114 +1200,12 @@ cleanup_critical:
 	.quad	.Lpsw_idle_lpsw
 
 .Lcleanup_save_fpu_regs:
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bor	%r14
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_done)
-	jhe	5f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_fp)
-	jhe	4f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_high)
-	jhe	3f
-	clg	%r9,BASED(.Lcleanup_save_fpu_regs_vx_low)
-	jhe	2f
-	clg	%r9,BASED(.Lcleanup_save_fpu_fpc_end)
-	jhe	1f
-	lg	%r2,__LC_CURRENT
-	aghi	%r2,__TASK_thread
-0:	# Store floating-point controls
-	stfpc	__THREAD_FPU_fpc(%r2)
-1:	# Load register save area and check if VX is active
-	lg	%r3,__THREAD_FPU_regs(%r2)
-	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
-	jz	4f			  # no VX -> store FP regs
-2:	# Store vector registers (V0-V15)
-	VSTM	%v0,%v15,0,%r3		  # vstm 0,15,0(3)
-3:	# Store vector registers (V16-V31)
-	VSTM	%v16,%v31,256,%r3	  # vstm 16,31,256(3)
-	j	5f			  # -> done, set CIF_FPU flag
-4:	# Store floating-point registers
-	std	0,0(%r3)
-	std	1,8(%r3)
-	std	2,16(%r3)
-	std	3,24(%r3)
-	std	4,32(%r3)
-	std	5,40(%r3)
-	std	6,48(%r3)
-	std	7,56(%r3)
-	std	8,64(%r3)
-	std	9,72(%r3)
-	std	10,80(%r3)
-	std	11,88(%r3)
-	std	12,96(%r3)
-	std	13,104(%r3)
-	std	14,112(%r3)
-	std	15,120(%r3)
-5:	# Set CIF_FPU flag
-	oi	__LC_CPU_FLAGS+7,_CIF_FPU
-	lg	%r9,48(%r11)		# return from save_fpu_regs
+	larl	%r9,save_fpu_regs
 	br	%r14
-.Lcleanup_save_fpu_fpc_end:
-	.quad	.Lsave_fpu_regs_fpc_end
-.Lcleanup_save_fpu_regs_vx_low:
-	.quad	.Lsave_fpu_regs_vx_low
-.Lcleanup_save_fpu_regs_vx_high:
-	.quad	.Lsave_fpu_regs_vx_high
-.Lcleanup_save_fpu_regs_fp:
-	.quad	.Lsave_fpu_regs_fp
-.Lcleanup_save_fpu_regs_done:
-	.quad	.Lsave_fpu_regs_done
 
 .Lcleanup_load_fpu_regs:
-	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
-	bnor	%r14
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_done)
-	jhe	1f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_fp)
-	jhe	2f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx_high)
-	jhe	3f
-	clg	%r9,BASED(.Lcleanup_load_fpu_regs_vx)
-	jhe	4f
-	lg	%r4,__LC_CURRENT
-	aghi	%r4,__TASK_thread
-	lfpc	__THREAD_FPU_fpc(%r4)
-	TSTMSK	__LC_MACHINE_FLAGS,MACHINE_FLAG_VX
-	lg	%r4,__THREAD_FPU_regs(%r4)	# %r4 <- reg save area
-	jz	2f				# -> no VX, load FP regs
-4:	# Load V0 ..V15 registers
-	VLM	%v0,%v15,0,%r4
-3:	# Load V16..V31 registers
-	VLM	%v16,%v31,256,%r4
-	j	1f
-2:	# Load floating-point registers
-	ld	0,0(%r4)
-	ld	1,8(%r4)
-	ld	2,16(%r4)
-	ld	3,24(%r4)
-	ld	4,32(%r4)
-	ld	5,40(%r4)
-	ld	6,48(%r4)
-	ld	7,56(%r4)
-	ld	8,64(%r4)
-	ld	9,72(%r4)
-	ld	10,80(%r4)
-	ld	11,88(%r4)
-	ld	12,96(%r4)
-	ld	13,104(%r4)
-	ld	14,112(%r4)
-	ld	15,120(%r4)
-1:	# Clear CIF_FPU bit
-	ni	__LC_CPU_FLAGS+7,255-_CIF_FPU
-	lg	%r9,48(%r11)		# return from load_fpu_regs
+	larl	%r9,load_fpu_regs
 	br	%r14
-.Lcleanup_load_fpu_regs_vx:
-	.quad	.Lload_fpu_regs_vx
-.Lcleanup_load_fpu_regs_vx_high:
-	.quad	.Lload_fpu_regs_vx_high
-.Lcleanup_load_fpu_regs_fp:
-	.quad	.Lload_fpu_regs_fp
-.Lcleanup_load_fpu_regs_done:
-	.quad	.Lload_fpu_regs_done
 
 /*
  * Integer constants

arch/s390/kernel/irq.c

@@ -164,8 +164,7 @@ void do_softirq_own_stack(void)
 {
 	unsigned long old, new;
 
-	/* Get current stack pointer. */
-	asm volatile("la %0,0(15)" : "=a" (old));
+	old = current_stack_pointer();
 	/* Check against async. stack address range. */
 	new = S390_lowcore.async_stack;
 	if (((new - old) >> (PAGE_SHIFT + THREAD_ORDER)) != 0) {

arch/s390/kernel/perf_cpum_cf.c

@@ -383,7 +383,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 	/* Validate the counter that is assigned to this event.
 	 * Because the counter facility can use numerous counters at the
-	 * same time without constraints, it is not necessary to explicity
+	 * same time without constraints, it is not necessary to explicitly
 	 * validate event groups (event->group_leader != event).
 	 */
 	err = validate_event(hwc);

arch/s390/kernel/perf_cpum_sf.c

@@ -1022,10 +1022,13 @@ static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 	/*
 	 * A non-zero guest program parameter indicates a guest
 	 * sample.
-	 * Note that some early samples might be misaccounted to
-	 * the host.
+	 * Note that some early samples or samples from guests without
+	 * lpp usage would be misaccounted to the host. We use the asn
+	 * value as a heuristic to detect most of these guest samples.
+	 * If the value differs from the host hpp value, we assume
+	 * it to be a KVM guest.
 	 */
-	if (sfr->basic.gpp)
+	if (sfr->basic.gpp || sfr->basic.prim_asn != (u16) sfr->basic.hpp)
 		sde_regs->in_guest = 1;
 
 	overflow = 0;

arch/s390/kernel/perf_event.c

@@ -222,67 +222,23 @@ static int __init service_level_perf_register(void)
 }
 arch_initcall(service_level_perf_register);
 
-/* See also arch/s390/kernel/traps.c */
-static unsigned long __store_trace(struct perf_callchain_entry *entry,
-				   unsigned long sp,
-				   unsigned long low, unsigned long high)
+static int __perf_callchain_kernel(void *data, unsigned long address)
 {
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-
-	while (1) {
-		if (sp < low || sp > high - sizeof(*sf))
-			return sp;
-		sf = (struct stack_frame *) sp;
-		perf_callchain_store(entry, sf->gprs[8]);
-		/* Follow the backchain. */
-		while (1) {
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *) sp;
-			perf_callchain_store(entry, sf->gprs[8]);
-		}
-		/* Zero backchain detected, check for interrupt frame. */
-		sp = (unsigned long) (sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *) sp;
-		perf_callchain_store(entry, sf->gprs[8]);
-		low = sp;
-		sp = regs->gprs[15];
-	}
+	struct perf_callchain_entry *entry = data;
+
+	perf_callchain_store(entry, address);
+	return 0;
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)
 {
-	unsigned long head, frame_size;
-	struct stack_frame *head_sf;
-
 	if (user_mode(regs))
 		return;
-
-	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-	head = regs->gprs[15];
-	head_sf = (struct stack_frame *) head;
-
-	if (!head_sf || !head_sf->back_chain)
-		return;
-
-	head = head_sf->back_chain;
-	head = __store_trace(entry, head,
-			     S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
-			     S390_lowcore.async_stack + frame_size);
-
-	__store_trace(entry, head, S390_lowcore.thread_info,
-		      S390_lowcore.thread_info + THREAD_SIZE);
+	dump_trace(__perf_callchain_kernel, entry, NULL, regs->gprs[15]);
 }
 
-/* Perf defintions for PMU event attributes in sysfs */
+/* Perf definitions for PMU event attributes in sysfs */
 ssize_t cpumf_events_sysfs_show(struct device *dev,
 				struct device_attribute *attr, char *page)
 {

arch/s390/kernel/setup.c

@@ -327,6 +327,7 @@ static void __init setup_lowcore(void)
 		+ PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);
 	lc->current_task = (unsigned long) init_thread_union.thread_info.task;
 	lc->thread_info = (unsigned long) &init_thread_union;
+	lc->lpp = LPP_MAGIC;
 	lc->machine_flags = S390_lowcore.machine_flags;
 	lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
@@ -779,6 +780,7 @@ static int __init setup_hwcaps(void)
 		strcpy(elf_platform, "zEC12");
 		break;
 	case 0x2964:
+	case 0x2965:
 		strcpy(elf_platform, "z13");
 		break;
 	}

arch/s390/kernel/stacktrace.c

@@ -10,78 +10,39 @@
 #include <linux/kallsyms.h>
 #include <linux/module.h>
 
-static unsigned long save_context_stack(struct stack_trace *trace,
-					unsigned long sp,
-					unsigned long low,
-					unsigned long high,
-					int savesched)
+static int __save_address(void *data, unsigned long address, int nosched)
 {
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-	unsigned long addr;
+	struct stack_trace *trace = data;
 
-	while(1) {
-		if (sp < low || sp > high)
-			return sp;
-		sf = (struct stack_frame *)sp;
-		while(1) {
-			addr = sf->gprs[8];
-			if (!trace->skip)
-				trace->entries[trace->nr_entries++] = addr;
-			else
-				trace->skip--;
-			if (trace->nr_entries >= trace->max_entries)
-				return sp;
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *)sp;
-		}
-		/* Zero backchain detected, check for interrupt frame. */
-		sp = (unsigned long)(sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *)sp;
-		addr = regs->psw.addr;
-		if (savesched || !in_sched_functions(addr)) {
-			if (!trace->skip)
-				trace->entries[trace->nr_entries++] = addr;
-			else
-				trace->skip--;
-		}
-		if (trace->nr_entries >= trace->max_entries)
-			return sp;
-		low = sp;
-		sp = regs->gprs[15];
+	if (nosched && in_sched_functions(address))
+		return 0;
+	if (trace->skip > 0) {
+		trace->skip--;
+		return 0;
 	}
+	if (trace->nr_entries < trace->max_entries) {
+		trace->entries[trace->nr_entries++] = address;
+		return 0;
+	}
+	return 1;
 }
 
-static void __save_stack_trace(struct stack_trace *trace, unsigned long sp)
+static int save_address(void *data, unsigned long address)
 {
-	unsigned long new_sp, frame_size;
+	return __save_address(data, address, 0);
+}
 
-	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-	new_sp = save_context_stack(trace, sp,
-			S390_lowcore.panic_stack + frame_size - PAGE_SIZE,
-			S390_lowcore.panic_stack + frame_size, 1);
-	new_sp = save_context_stack(trace, new_sp,
-			S390_lowcore.async_stack + frame_size - ASYNC_SIZE,
-			S390_lowcore.async_stack + frame_size, 1);
-	save_context_stack(trace, new_sp,
-			   S390_lowcore.thread_info,
-			   S390_lowcore.thread_info + THREAD_SIZE, 1);
+static int save_address_nosched(void *data, unsigned long address)
+{
+	return __save_address(data, address, 1);
 }
 
 void save_stack_trace(struct stack_trace *trace)
 {
-	register unsigned long r15 asm ("15");
 	unsigned long sp;
 
-	sp = r15;
-	__save_stack_trace(trace, sp);
+	sp = current_stack_pointer();
+	dump_trace(save_address, trace, NULL, sp);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
@@ -89,16 +50,12 @@ EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	unsigned long sp, low, high;
+	unsigned long sp;
 
 	sp = tsk->thread.ksp;
-	if (tsk == current) {
-		/* Get current stack pointer. */
-		asm volatile("la %0,0(15)" : "=a" (sp));
-	}
-	low = (unsigned long) task_stack_page(tsk);
-	high = (unsigned long) task_pt_regs(tsk);
-	save_context_stack(trace, sp, low, high, 0);
+	if (tsk == current)
+		sp = current_stack_pointer();
+	dump_trace(save_address_nosched, trace, tsk, sp);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
@@ -109,7 +66,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	unsigned long sp;
 
 	sp = kernel_stack_pointer(regs);
-	__save_stack_trace(trace, sp);
+	dump_trace(save_address, trace, NULL, sp);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }

arch/s390/kernel/time.c

@@ -499,8 +499,7 @@ static void etr_reset(void)
 		if (etr_port0_online && etr_port1_online)
 			set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 	} else if (etr_port0_online || etr_port1_online) {
-		pr_warning("The real or virtual hardware system does "
-			   "not provide an ETR interface\n");
+		pr_warn("The real or virtual hardware system does not provide an ETR interface\n");
 		etr_port0_online = etr_port1_online = 0;
 	}
 }
@@ -1464,8 +1463,7 @@ static void __init stp_reset(void)
 	if (rc == 0)
 		set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags);
 	else if (stp_online) {
-		pr_warning("The real or virtual hardware system does "
-			   "not provide an STP interface\n");
+		pr_warn("The real or virtual hardware system does not provide an STP interface\n");
 		free_page((unsigned long) stp_page);
 		stp_page = NULL;
 		stp_online = 0;

arch/s390/kernel/traps.c

@@ -22,8 +22,6 @@
 #include <asm/fpu/api.h>
 #include "entry.h"
 
-int show_unhandled_signals = 1;
-
 static inline void __user *get_trap_ip(struct pt_regs *regs)
 {
 	unsigned long address;
@@ -35,21 +33,6 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 	return (void __user *) (address - (regs->int_code >> 16));
 }
 
-static inline void report_user_fault(struct pt_regs *regs, int signr)
-{
-	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
-		return;
-	if (!unhandled_signal(current, signr))
-		return;
-	if (!printk_ratelimit())
-		return;
-	printk("User process fault: interruption code %04x ilc:%d ",
-	       regs->int_code & 0xffff, regs->int_code >> 17);
-	print_vma_addr("in ", regs->psw.addr);
-	printk("\n");
-	show_regs(regs);
-}
-
 int is_valid_bugaddr(unsigned long addr)
 {
 	return 1;
@@ -65,7 +48,7 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 		info.si_code = si_code;
 		info.si_addr = get_trap_ip(regs);
 		force_sig_info(si_signo, &info, current);
-		report_user_fault(regs, si_signo);
+		report_user_fault(regs, si_signo, 0);
         } else {
                 const struct exception_table_entry *fixup;
 		fixup = search_exception_tables(regs->psw.addr);
@@ -111,7 +94,7 @@ NOKPROBE_SYMBOL(do_per_trap);
 void default_trap_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
-		report_user_fault(regs, SIGSEGV);
+		report_user_fault(regs, SIGSEGV, 0);
 		do_exit(SIGSEGV);
 	} else
 		die(regs, "Unknown program exception");

arch/s390/kvm/diag.c

@@ -14,6 +14,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <asm/pgalloc.h>
+#include <asm/gmap.h>
 #include <asm/virtio-ccw.h>
 #include "kvm-s390.h"
 #include "trace.h"

arch/s390/kvm/guestdbg.c

@@ -17,7 +17,7 @@
 /*
  * Extends the address range given by *start and *stop to include the address
  * range starting with estart and the length len. Takes care of overflowing
- * intervals and tries to minimize the overall intervall size.
+ * intervals and tries to minimize the overall interval size.
  */
 static void extend_address_range(u64 *start, u64 *stop, u64 estart, int len)
 {
@@ -72,7 +72,7 @@ static void enable_all_hw_bp(struct kvm_vcpu *vcpu)
 		return;
 
 	/*
-	 * If the guest is not interrested in branching events, we can savely
+	 * If the guest is not interested in branching events, we can safely
 	 * limit them to the PER address range.
 	 */
 	if (!(*cr9 & PER_EVENT_BRANCH))

arch/s390/kvm/interrupt.c

@@ -23,6 +23,7 @@
 #include <asm/uaccess.h>
 #include <asm/sclp.h>
 #include <asm/isc.h>
+#include <asm/gmap.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "trace-s390.h"

arch/s390/kvm/kvm-s390.c

@@ -30,6 +30,7 @@
 #include <asm/lowcore.h>
 #include <asm/etr.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
 #include <asm/isc.h>
@@ -281,7 +282,7 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
 	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
 		address = gfn_to_hva_memslot(memslot, cur_gfn);
 
-		if (gmap_test_and_clear_dirty(address, gmap))
+		if (test_and_clear_guest_dirty(gmap->mm, address))
 			mark_page_dirty(kvm, cur_gfn);
 		if (fatal_signal_pending(current))
 			return;

arch/s390/kvm/priv.c

@@ -23,6 +23,7 @@
 #include <asm/sysinfo.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/gmap.h>
 #include <asm/io.h>
 #include <asm/ptrace.h>
 #include <asm/compat.h>

arch/s390/lib/Makefile

@@ -3,7 +3,7 @@
 #
 
 lib-y += delay.o string.o uaccess.o find.o
-obj-y += mem.o
+obj-y += mem.o xor.o
 lib-$(CONFIG_SMP) += spinlock.o
 lib-$(CONFIG_KPROBES) += probes.o
 lib-$(CONFIG_UPROBES) += probes.o

arch/s390/lib/xor.c

+/*
+ * Optimized xor_block operation for RAID4/5
+ *
+ * Copyright IBM Corp. 2016
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/raid/xor.h>
+
+static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"3:\n"
+		: : "d" (bytes), "a" (p1), "a" (p2)
+		: "0", "1", "cc", "memory");
+}
+
+static void xor_xc_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		     unsigned long *p3)
+{
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	xc	0(256,%1),0(%3)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	la	%3,256(%3)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	ex	%0,6(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"	xc	0(1,%1),0(%3)\n"
+		"3:\n"
+		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3)
+		: : "0", "1", "cc", "memory");
+}
+
+static void xor_xc_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		     unsigned long *p3, unsigned long *p4)
+{
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	xc	0(256,%1),0(%3)\n"
+		"	xc	0(256,%1),0(%4)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	la	%3,256(%3)\n"
+		"	la	%4,256(%4)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	ex	%0,6(1)\n"
+		"	ex	%0,12(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"	xc	0(1,%1),0(%3)\n"
+		"	xc	0(1,%1),0(%4)\n"
+		"3:\n"
+		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4)
+		: : "0", "1", "cc", "memory");
+}
+
+static void xor_xc_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		     unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	/* Get around a gcc oddity */
+	register unsigned long *reg7 asm ("7") = p5;
+
+	asm volatile(
+		"	larl	1,2f\n"
+		"	aghi	%0,-1\n"
+		"	jm	3f\n"
+		"	srlg	0,%0,8\n"
+		"	ltgr	0,0\n"
+		"	jz	1f\n"
+		"0:	xc	0(256,%1),0(%2)\n"
+		"	xc	0(256,%1),0(%3)\n"
+		"	xc	0(256,%1),0(%4)\n"
+		"	xc	0(256,%1),0(%5)\n"
+		"	la	%1,256(%1)\n"
+		"	la	%2,256(%2)\n"
+		"	la	%3,256(%3)\n"
+		"	la	%4,256(%4)\n"
+		"	la	%5,256(%5)\n"
+		"	brctg	0,0b\n"
+		"1:	ex	%0,0(1)\n"
+		"	ex	%0,6(1)\n"
+		"	ex	%0,12(1)\n"
+		"	ex	%0,18(1)\n"
+		"	j	3f\n"
+		"2:	xc	0(1,%1),0(%2)\n"
+		"	xc	0(1,%1),0(%3)\n"
+		"	xc	0(1,%1),0(%4)\n"
+		"	xc	0(1,%1),0(%5)\n"
+		"3:\n"
+		: "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4),
+		  "+a" (reg7)
+		: : "0", "1", "cc", "memory");
+}
+
+struct xor_block_template xor_block_xc = {
+	.name = "xc",
+	.do_2 = xor_xc_2,
+	.do_3 = xor_xc_3,
+	.do_4 = xor_xc_4,
+	.do_5 = xor_xc_5,
+};
+EXPORT_SYMBOL(xor_block_xc);

arch/s390/mm/Makefile

@@ -2,9 +2,11 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-obj-y		:= init.o fault.o extmem.o mmap.o vmem.o pgtable.o maccess.o
+obj-y		:= init.o fault.o extmem.o mmap.o vmem.o maccess.o
 obj-y		+= page-states.o gup.o extable.o pageattr.o mem_detect.o
+obj-y		+= pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_S390_PTDUMP)	+= dump_pagetables.o
+obj-$(CONFIG_PGSTE)		+= gmap.o

arch/s390/mm/extmem.c

@@ -265,7 +265,7 @@ query_segment_type (struct dcss_segment *seg)
 		goto out_free;
 	}
 	if (diag_cc > 1) {
-		pr_warning("Querying a DCSS type failed with rc=%ld\n", vmrc);
+		pr_warn("Querying a DCSS type failed with rc=%ld\n", vmrc);
 		rc = dcss_diag_translate_rc (vmrc);
 		goto out_free;
 	}
@@ -457,8 +457,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 		goto out_resource;
 	}
 	if (diag_cc > 1) {
-		pr_warning("Loading DCSS %s failed with rc=%ld\n", name,
-			   end_addr);
+		pr_warn("Loading DCSS %s failed with rc=%ld\n", name, end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		dcss_diag(&purgeseg_scode, seg->dcss_name,
 				&dummy, &dummy);
@@ -574,8 +573,7 @@ segment_modify_shared (char *name, int do_nonshared)
 		goto out_unlock;
 	}
 	if (atomic_read (&seg->ref_count) != 1) {
-		pr_warning("DCSS %s is in use and cannot be reloaded\n",
-			   name);
+		pr_warn("DCSS %s is in use and cannot be reloaded\n", name);
 		rc = -EAGAIN;
 		goto out_unlock;
 	}
@@ -588,8 +586,8 @@ segment_modify_shared (char *name, int do_nonshared)
 			seg->res->flags |= IORESOURCE_READONLY;
 
 	if (request_resource(&iomem_resource, seg->res)) {
-		pr_warning("DCSS %s overlaps with used memory resources "
-			   "and cannot be reloaded\n", name);
+		pr_warn("DCSS %s overlaps with used memory resources and cannot be reloaded\n",
+			name);
 		rc = -EBUSY;
 		kfree(seg->res);
 		goto out_del_mem;
@@ -607,8 +605,8 @@ segment_modify_shared (char *name, int do_nonshared)
 		goto out_del_res;
 	}
 	if (diag_cc > 1) {
-		pr_warning("Reloading DCSS %s failed with rc=%ld\n", name,
-			   end_addr);
+		pr_warn("Reloading DCSS %s failed with rc=%ld\n",
+			name, end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		goto out_del_res;
 	}

arch/s390/mm/fault.c

@@ -32,6 +32,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/diag.h>
 #include <asm/pgtable.h>
+#include <asm/gmap.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/facility.h>
@@ -183,6 +184,8 @@ static void dump_fault_info(struct pt_regs *regs)
 {
 	unsigned long asce;
 
+	pr_alert("Failing address: %016lx TEID: %016lx\n",
+		 regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
 	pr_alert("Fault in ");
 	switch (regs->int_parm_long & 3) {
 	case 3:
@@ -218,7 +221,9 @@ static void dump_fault_info(struct pt_regs *regs)
 	dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
 }
 
-static inline void report_user_fault(struct pt_regs *regs, long signr)
+int show_unhandled_signals = 1;
+
+void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
 {
 	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
 		return;
@@ -230,9 +235,8 @@ static inline void report_user_fault(struct pt_regs *regs, long signr)
 	       regs->int_code & 0xffff, regs->int_code >> 17);
 	print_vma_addr(KERN_CONT "in ", regs->psw.addr);
 	printk(KERN_CONT "\n");
-	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
-	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
-	dump_fault_info(regs);
+	if (is_mm_fault)
+		dump_fault_info(regs);
 	show_regs(regs);
 }
 
@@ -244,7 +248,7 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 {
 	struct siginfo si;
 
-	report_user_fault(regs, SIGSEGV);
+	report_user_fault(regs, SIGSEGV, 1);
 	si.si_signo = SIGSEGV;
 	si.si_code = si_code;
 	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
@@ -272,8 +276,6 @@ static noinline void do_no_context(struct pt_regs *regs)
 	else
 		printk(KERN_ALERT "Unable to handle kernel paging request"
 		       " in virtual user address space\n");
-	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
-	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
 	dump_fault_info(regs);
 	die(regs, "Oops");
 	do_exit(SIGKILL);

arch/s390/mm/hugetlbpage.c

@@ -105,11 +105,10 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
 	pmd_t *pmdp = (pmd_t *) ptep;
-	pte_t pte = huge_ptep_get(ptep);
+	pmd_t old;
 
-	pmdp_flush_direct(mm, addr, pmdp);
-	pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
-	return pte;
+	old = pmdp_xchg_direct(mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
+	return __pmd_to_pte(old);
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,

arch/s390/mm/pageattr.c

@@ -65,19 +65,17 @@ static pte_t *walk_page_table(unsigned long addr)
 static void change_page_attr(unsigned long addr, int numpages,
 			     pte_t (*set) (pte_t))
 {
-	pte_t *ptep, pte;
+	pte_t *ptep;
 	int i;
 
 	for (i = 0; i < numpages; i++) {
 		ptep = walk_page_table(addr);
 		if (WARN_ON_ONCE(!ptep))
 			break;
-		pte = *ptep;
-		pte = set(pte);
-		__ptep_ipte(addr, ptep);
-		*ptep = pte;
+		*ptep = set(*ptep);
 		addr += PAGE_SIZE;
 	}
+	__tlb_flush_kernel();
 }
 
 int set_memory_ro(unsigned long addr, int numpages)

arch/s390/mm/pgalloc.c

+/*
+ *  Page table allocation functions
+ *
+ *    Copyright IBM Corp. 2016
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/sysctl.h>
+#include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
+#include <asm/gmap.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+
+#ifdef CONFIG_PGSTE
+
+static int page_table_allocate_pgste_min = 0;
+static int page_table_allocate_pgste_max = 1;
+int page_table_allocate_pgste = 0;
+EXPORT_SYMBOL(page_table_allocate_pgste);
+
+static struct ctl_table page_table_sysctl[] = {
+	{
+		.procname	= "allocate_pgste",
+		.data		= &page_table_allocate_pgste,
+		.maxlen		= sizeof(int),
+		.mode		= S_IRUGO | S_IWUSR,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &page_table_allocate_pgste_min,
+		.extra2		= &page_table_allocate_pgste_max,
+	},
+	{ }
+};
+
+static struct ctl_table page_table_sysctl_dir[] = {
+	{
+		.procname	= "vm",
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= page_table_sysctl,
+	},
+	{ }
+};
+
+static int __init page_table_register_sysctl(void)
+{
+	return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM;
+}
+__initcall(page_table_register_sysctl);
+
+#endif /* CONFIG_PGSTE */
+
+unsigned long *crst_table_alloc(struct mm_struct *mm)
+{
+	struct page *page = alloc_pages(GFP_KERNEL, 2);
+
+	if (!page)
+		return NULL;
+	return (unsigned long *) page_to_phys(page);
+}
+
+void crst_table_free(struct mm_struct *mm, unsigned long *table)
+{
+	free_pages((unsigned long) table, 2);
+}
+
+static void __crst_table_upgrade(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (current->active_mm == mm) {
+		clear_user_asce();
+		set_user_asce(mm);
+	}
+	__tlb_flush_local();
+}
+
+int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
+{
+	unsigned long *table, *pgd;
+	unsigned long entry;
+	int flush;
+
+	BUG_ON(limit > TASK_MAX_SIZE);
+	flush = 0;
+repeat:
+	table = crst_table_alloc(mm);
+	if (!table)
+		return -ENOMEM;
+	spin_lock_bh(&mm->page_table_lock);
+	if (mm->context.asce_limit < limit) {
+		pgd = (unsigned long *) mm->pgd;
+		if (mm->context.asce_limit <= (1UL << 31)) {
+			entry = _REGION3_ENTRY_EMPTY;
+			mm->context.asce_limit = 1UL << 42;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_REGION3;
+		} else {
+			entry = _REGION2_ENTRY_EMPTY;
+			mm->context.asce_limit = 1UL << 53;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_REGION2;
+		}
+		crst_table_init(table, entry);
+		pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
+		mm->pgd = (pgd_t *) table;
+		mm->task_size = mm->context.asce_limit;
+		table = NULL;
+		flush = 1;
+	}
+	spin_unlock_bh(&mm->page_table_lock);
+	if (table)
+		crst_table_free(mm, table);
+	if (mm->context.asce_limit < limit)
+		goto repeat;
+	if (flush)
+		on_each_cpu(__crst_table_upgrade, mm, 0);
+	return 0;
+}
+
+void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
+{
+	pgd_t *pgd;
+
+	if (current->active_mm == mm) {
+		clear_user_asce();
+		__tlb_flush_mm(mm);
+	}
+	while (mm->context.asce_limit > limit) {
+		pgd = mm->pgd;
+		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
+		case _REGION_ENTRY_TYPE_R2:
+			mm->context.asce_limit = 1UL << 42;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_REGION3;
+			break;
+		case _REGION_ENTRY_TYPE_R3:
+			mm->context.asce_limit = 1UL << 31;
+			mm->context.asce_bits = _ASCE_TABLE_LENGTH |
+						_ASCE_USER_BITS |
+						_ASCE_TYPE_SEGMENT;
+			break;
+		default:
+			BUG();
+		}
+		mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
+		mm->task_size = mm->context.asce_limit;
+		crst_table_free(mm, (unsigned long *) pgd);
+	}
+	if (current->active_mm == mm)
+		set_user_asce(mm);
+}
+
+static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
+{
+	unsigned int old, new;
+
+	do {
+		old = atomic_read(v);
+		new = old ^ bits;
+	} while (atomic_cmpxchg(v, old, new) != old);
+	return new;
+}
+
+/*
+ * page table entry allocation/free routines.
+ */
+unsigned long *page_table_alloc(struct mm_struct *mm)
+{
+	unsigned long *table;
+	struct page *page;
+	unsigned int mask, bit;
+
+	/* Try to get a fragment of a 4K page as a 2K page table */
+	if (!mm_alloc_pgste(mm)) {
+		table = NULL;
+		spin_lock_bh(&mm->context.list_lock);
+		if (!list_empty(&mm->context.pgtable_list)) {
+			page = list_first_entry(&mm->context.pgtable_list,
+						struct page, lru);
+			mask = atomic_read(&page->_mapcount);
+			mask = (mask | (mask >> 4)) & 3;
+			if (mask != 3) {
+				table = (unsigned long *) page_to_phys(page);
+				bit = mask & 1;		/* =1 -> second 2K */
+				if (bit)
+					table += PTRS_PER_PTE;
+				atomic_xor_bits(&page->_mapcount, 1U << bit);
+				list_del(&page->lru);
+			}
+		}
+		spin_unlock_bh(&mm->context.list_lock);
+		if (table)
+			return table;
+	}
+	/* Allocate a fresh page */
+	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	if (!page)
+		return NULL;
+	if (!pgtable_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	/* Initialize page table */
+	table = (unsigned long *) page_to_phys(page);
+	if (mm_alloc_pgste(mm)) {
+		/* Return 4K page table with PGSTEs */
+		atomic_set(&page->_mapcount, 3);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
+		clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	} else {
+		/* Return the first 2K fragment of the page */
+		atomic_set(&page->_mapcount, 1);
+		clear_table(table, _PAGE_INVALID, PAGE_SIZE);
+		spin_lock_bh(&mm->context.list_lock);
+		list_add(&page->lru, &mm->context.pgtable_list);
+		spin_unlock_bh(&mm->context.list_lock);
+	}
+	return table;
+}
+
+void page_table_free(struct mm_struct *mm, unsigned long *table)
+{
+	struct page *page;
+	unsigned int bit, mask;
+
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (!mm_alloc_pgste(mm)) {
+		/* Free 2K page table fragment of a 4K page */
+		bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));
+		spin_lock_bh(&mm->context.list_lock);
+		mask = atomic_xor_bits(&page->_mapcount, 1U << bit);
+		if (mask & 3)
+			list_add(&page->lru, &mm->context.pgtable_list);
+		else
+			list_del(&page->lru);
+		spin_unlock_bh(&mm->context.list_lock);
+		if (mask != 0)
+			return;
+	}
+
+	pgtable_page_dtor(page);
+	atomic_set(&page->_mapcount, -1);
+	__free_page(page);
+}
+
+void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
+			 unsigned long vmaddr)
+{
+	struct mm_struct *mm;
+	struct page *page;
+	unsigned int bit, mask;
+
+	mm = tlb->mm;
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (mm_alloc_pgste(mm)) {
+		gmap_unlink(mm, table, vmaddr);
+		table = (unsigned long *) (__pa(table) | 3);
+		tlb_remove_table(tlb, table);
+		return;
+	}
+	bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));
+	spin_lock_bh(&mm->context.list_lock);
+	mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);
+	if (mask & 3)
+		list_add_tail(&page->lru, &mm->context.pgtable_list);
+	else
+		list_del(&page->lru);
+	spin_unlock_bh(&mm->context.list_lock);
+	table = (unsigned long *) (__pa(table) | (1U << bit));
+	tlb_remove_table(tlb, table);
+}
+
+static void __tlb_remove_table(void *_table)
+{
+	unsigned int mask = (unsigned long) _table & 3;
+	void *table = (void *)((unsigned long) _table ^ mask);
+	struct page *page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+
+	switch (mask) {
+	case 0:		/* pmd or pud */
+		free_pages((unsigned long) table, 2);
+		break;
+	case 1:		/* lower 2K of a 4K page table */
+	case 2:		/* higher 2K of a 4K page table */
+		if (atomic_xor_bits(&page->_mapcount, mask << 4) != 0)
+			break;
+		/* fallthrough */
+	case 3:		/* 4K page table with pgstes */
+		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
+		__free_page(page);
+		break;
+	}
+}
+
+static void tlb_remove_table_smp_sync(void *arg)
+{
+	/* Simply deliver the interrupt */
+}
+
+static void tlb_remove_table_one(void *table)
+{
+	/*
+	 * This isn't an RCU grace period and hence the page-tables cannot be
+	 * assumed to be actually RCU-freed.
+	 *
+	 * It is however sufficient for software page-table walkers that rely
+	 * on IRQ disabling. See the comment near struct mmu_table_batch.
+	 */
+	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	__tlb_remove_table(table);
+}
+
+static void tlb_remove_table_rcu(struct rcu_head *head)
+{
+	struct mmu_table_batch *batch;
+	int i;
+
+	batch = container_of(head, struct mmu_table_batch, rcu);
+
+	for (i = 0; i < batch->nr; i++)
+		__tlb_remove_table(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+void tlb_table_flush(struct mmu_gather *tlb)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	if (*batch) {
+		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
+		*batch = NULL;
+	}
+}
+
+void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	struct mmu_table_batch **batch = &tlb->batch;
+
+	tlb->mm->context.flush_mm = 1;
+	if (*batch == NULL) {
+		*batch = (struct mmu_table_batch *)
+			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
+		if (*batch == NULL) {
+			__tlb_flush_mm_lazy(tlb->mm);
+			tlb_remove_table_one(table);
+			return;
+		}
+		(*batch)->nr = 0;
+	}
+	(*batch)->tables[(*batch)->nr++] = table;
+	if ((*batch)->nr == MAX_TABLE_BATCH)
+		tlb_flush_mmu(tlb);
+}

arch/s390/oprofile/Makefile

@@ -6,5 +6,5 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o  \
 		timer_int.o )
 
-oprofile-y :=	$(DRIVER_OBJS) init.o backtrace.o
+oprofile-y :=	$(DRIVER_OBJS) init.o
 oprofile-y +=	hwsampler.o

arch/s390/oprofile/init.c

@@ -20,8 +20,6 @@
 
 #include "../../../drivers/oprofile/oprof.h"
 
-extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
-
 #include "hwsampler.h"
 #include "op_counter.h"
 
@@ -456,6 +454,7 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops)
 		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
 		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
 		case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
+		case 0x2964: case 0x2965: ops->cpu_type = "s390/z13"; break;
 		default: return -ENODEV;
 		}
 	}
@@ -494,6 +493,24 @@ static void oprofile_hwsampler_exit(void)
 	hwsampler_shutdown();
 }
 
+static int __s390_backtrace(void *data, unsigned long address)
+{
+	unsigned int *depth = data;
+
+	if (*depth == 0)
+		return 1;
+	(*depth)--;
+	oprofile_add_trace(address);
+	return 0;
+}
+
+static void s390_backtrace(struct pt_regs *regs, unsigned int depth)
+{
+	if (user_mode(regs))
+		return;
+	dump_trace(__s390_backtrace, &depth, NULL, regs->gprs[15]);
+}
+
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	ops->backtrace = s390_backtrace;

arch/s390/pci/pci_debug.c

@@ -128,10 +128,9 @@ static const struct file_operations debugfs_pci_perf_fops = {
 	.release = single_release,
 };
 
-void zpci_debug_init_device(struct zpci_dev *zdev)
+void zpci_debug_init_device(struct zpci_dev *zdev, const char *name)
 {
-	zdev->debugfs_dev = debugfs_create_dir(dev_name(&zdev->pdev->dev),
-					       debugfs_root);
+	zdev->debugfs_dev = debugfs_create_dir(name, debugfs_root);
 	if (IS_ERR(zdev->debugfs_dev))
 		zdev->debugfs_dev = NULL;