Merge branch 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6

* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (21 commits)
  [S390] use siginfo for sigtrap signals
  [S390] dasd: add enhanced DASD statistics interface
  [S390] kvm: make sigp emerg smp capable
  [S390] disable cpu measurement alerts on a dying cpu
  [S390] initial cr0 bits
  [S390] iucv cr0 enablement bit
  [S390] race safe external interrupt registration
  [S390] remove tape block docu
  [S390] ap: toleration support for ap device type 10
  [S390] cleanup program check handler prototypes
  [S390] remove kvm mmu reload on s390
  [S390] Use gmap translation for accessing guest memory
  [S390] use gmap address spaces for kvm guest images
  [S390] kvm guest address space mapping
  [S390] fix s390 assembler code alignments
  [S390] move sie code to entry.S
  [S390] kvm: handle tprot intercepts
  [S390] qdio: clear shared DSCI before scheduling the queue handler
  [S390] reference bit testing for unmapped pages
  [S390] irqs: Do not trace arch_local_{*,irq_*} functions
  ...

Documentation/s390/TAPE

-Channel attached Tape device driver 
-
------------------------------WARNING-----------------------------------------
-This driver is considered to be EXPERIMENTAL. Do NOT use it in 
-production environments. Feel free to test it and report problems back to us. 
------------------------------------------------------------------------------
-
-The LINUX for zSeries tape device driver manages channel attached tape drives 
-which are compatible to IBM 3480 or IBM 3490 magnetic tape subsystems. This 
-includes various models of these devices (for example the 3490E). 
-
-
-Tape driver features 
-
-The device driver supports a maximum of 128 tape devices. 
-No official LINUX device major number is assigned to the zSeries tape device 
-driver. It allocates major numbers dynamically and reports them on system 
-startup. 
-Typically it will get major number 254 for both the character device front-end 
-and the block device front-end. 
-
-The tape device driver needs no kernel parameters. All supported devices 
-present are detected on driver initialization at system startup or module load.
-The devices detected are ordered by their subchannel numbers. The device with 
-the lowest subchannel number becomes device 0, the next one will be device 1 
-and so on. 
-
-
-Tape character device front-end 
-
-The usual way to read or write to the tape device is through the character 
-device front-end. The zSeries tape device driver provides two character devices
-for each physical device -- the first of these will rewind automatically when 
-it is closed, the second will not rewind automatically. 
-
-The character device nodes are named /dev/rtibm0 (rewinding) and /dev/ntibm0 
-(non-rewinding) for the first device, /dev/rtibm1 and /dev/ntibm1 for the 
-second, and so on. 
-
-The character device front-end can be used as any other LINUX tape device. You 
-can write to it and read from it using LINUX facilities such as GNU tar. The 
-tool mt can be used to perform control operations, such as rewinding the tape 
-or skipping a file. 
-
-Most LINUX tape software should work with either tape character device. 
-
-
-Tape block device front-end 
-
-The tape device may also be accessed as a block device in read-only mode. 
-This could be used for software installation in the same way as it is used with 
-other operation systems on the zSeries platform (and most LINUX 
-distributions are shipped on compact disk using ISO9660 filesystems). 
-
-One block device node is provided for each physical device. These are named 
-/dev/btibm0 for the first device, /dev/btibm1 for the second and so on. 
-You should only use the ISO9660 filesystem on LINUX for zSeries tapes because 
-the physical tape devices cannot perform fast seeks and the ISO9660 system is 
-optimized for this situation. 
-
-
-Tape block device example 
-
-In this example a tape with an ISO9660 filesystem is created using the first 
-tape device. ISO9660 filesystem support must be built into your system kernel
-for this. 
-The mt command is used to issue tape commands and the mkisofs command to 
-create an ISO9660 filesystem: 
-
-- create a LINUX directory (somedir) with the contents of the filesystem 
-     mkdir somedir
-     cp contents somedir 
-
-- insert a tape 
-
-- ensure the tape is at the beginning 
-     mt -f /dev/ntibm0 rewind 
-
-- set the blocksize of the character driver. The blocksize 2048 bytes
-  is commonly used on ISO9660 CD-Roms
-     mt -f /dev/ntibm0 setblk 2048 
-
-- write the filesystem to the character device driver 
-     mkisofs -o /dev/ntibm0 somedir 
-
-- rewind the tape again 
-     mt -f /dev/ntibm0 rewind 
-
-- Now you can mount your new filesystem as a block device: 
-     mount -t iso9660 -o ro,block=2048 /dev/btibm0 /mnt 
-
-TODO List 
-
-   - Driver has to be stabilized still
-
-BUGS 
-
-This driver is considered BETA, which means some weaknesses may still
-be in it.
-If an error occurs which cannot be handled by the code you will get a 
-sense-data dump.In that case please do the following: 
-
-1. set the tape driver debug level to maximum: 
-     echo 6 >/proc/s390dbf/tape/level 
-
-2. re-perform the actions which produced the bug. (Hopefully the bug will 
-   reappear.) 
-
-3. get a snapshot from the debug-feature: 
-     cat /proc/s390dbf/tape/hex_ascii >somefile 
-
-4. Now put the snapshot together with a detailed description of the situation 
-   that led to the bug: 
- - Which tool did you use? 
- - Which hardware do you have? 
- - Was your tape unit online? 
- - Is it a shared tape unit? 
-
-5. Send an email with your bug report to: 
-     mailto:Linux390@de.ibm.com 
-
-

arch/s390/boot/compressed/head31.S

@@ -7,14 +7,14 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 #include "sizes.h"
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack

arch/s390/boot/compressed/head64.S

@@ -7,14 +7,14 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 #include "sizes.h"
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack

arch/s390/include/asm/irqflags.h

@@ -29,42 +29,42 @@
 })
 
 /* set system mask. */
-static inline void __arch_local_irq_ssm(unsigned long flags)
+static inline notrace void __arch_local_irq_ssm(unsigned long flags)
 {
 	asm volatile("ssm   %0" : : "Q" (flags) : "memory");
 }
 
-static inline unsigned long arch_local_save_flags(void)
+static inline notrace unsigned long arch_local_save_flags(void)
 {
 	return __arch_local_irq_stosm(0x00);
 }
 
-static inline unsigned long arch_local_irq_save(void)
+static inline notrace unsigned long arch_local_irq_save(void)
 {
 	return __arch_local_irq_stnsm(0xfc);
 }
 
-static inline void arch_local_irq_disable(void)
+static inline notrace void arch_local_irq_disable(void)
 {
 	arch_local_irq_save();
 }
 
-static inline void arch_local_irq_enable(void)
+static inline notrace void arch_local_irq_enable(void)
 {
 	__arch_local_irq_stosm(0x03);
 }
 
-static inline void arch_local_irq_restore(unsigned long flags)
+static inline notrace void arch_local_irq_restore(unsigned long flags)
 {
 	__arch_local_irq_ssm(flags);
 }
 
-static inline bool arch_irqs_disabled_flags(unsigned long flags)
+static inline notrace bool arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & (3UL << (BITS_PER_LONG - 8)));
 }
 
-static inline bool arch_irqs_disabled(void)
+static inline notrace bool arch_irqs_disabled(void)
 {
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }

arch/s390/include/asm/kvm_host.h

@@ -93,9 +93,7 @@ struct kvm_s390_sie_block {
 	__u32	scaol;			/* 0x0064 */
 	__u8	reserved68[4];		/* 0x0068 */
 	__u32	todpr;			/* 0x006c */
-	__u8	reserved70[16];		/* 0x0070 */
-	__u64	gmsor;			/* 0x0080 */
-	__u64	gmslm;			/* 0x0088 */
+	__u8	reserved70[32];		/* 0x0070 */
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
@@ -138,6 +136,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_chsc;
 	u32 instruction_stsi;
 	u32 instruction_stfl;
+	u32 instruction_tprot;
 	u32 instruction_sigp_sense;
 	u32 instruction_sigp_emergency;
 	u32 instruction_sigp_stop;
@@ -175,6 +174,10 @@ struct kvm_s390_prefix_info {
 	__u32 address;
 };
 
+struct kvm_s390_emerg_info {
+	__u16 code;
+};
+
 struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
@@ -182,6 +185,7 @@ struct kvm_s390_interrupt_info {
 		struct kvm_s390_io_info io;
 		struct kvm_s390_ext_info ext;
 		struct kvm_s390_pgm_info pgm;
+		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_prefix_info prefix;
 	};
 };
@@ -226,6 +230,7 @@ struct kvm_vcpu_arch {
 		struct cpuid	cpu_id;
 		u64		stidp_data;
 	};
+	struct gmap *gmap;
 };
 
 struct kvm_vm_stat {
@@ -236,6 +241,7 @@ struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
+	struct gmap *gmap;
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, unsigned long *);

arch/s390/include/asm/linkage.h

 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
-/* Nothing to see here... */
+#include <linux/stringify.h>
+
+#define __ALIGN .align 4, 0x07
+#define __ALIGN_STR __stringify(__ALIGN)
 
 #endif

arch/s390/include/asm/lowcore.h

@@ -268,7 +268,7 @@ struct _lowcore {
 	__u64	vdso_per_cpu_data;		/* 0x0358 */
 	__u64	machine_flags;			/* 0x0360 */
 	__u64	ftrace_func;			/* 0x0368 */
-	__u64	sie_hook;			/* 0x0370 */
+	__u64	gmap;				/* 0x0370 */
 	__u64	cmf_hpp;			/* 0x0378 */
 
 	/* Interrupt response block. */

arch/s390/include/asm/mmu.h

@@ -6,6 +6,7 @@ typedef struct {
 	unsigned int flush_mm;
 	spinlock_t list_lock;
 	struct list_head pgtable_list;
+	struct list_head gmap_list;
 	unsigned long asce_bits;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
@@ -17,6 +18,7 @@ typedef struct {
 
 #define INIT_MM_CONTEXT(name)						      \
 	.context.list_lock    = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \
-	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),
+	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),    \
+	.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
 
 #endif

arch/s390/include/asm/pgalloc.h

@@ -20,7 +20,7 @@
 unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
 
-unsigned long *page_table_alloc(struct mm_struct *);
+unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
@@ -115,6 +115,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	spin_lock_init(&mm->context.list_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
+	INIT_LIST_HEAD(&mm->context.gmap_list);
 	return (pgd_t *) crst_table_alloc(mm);
 }
 #define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd)
@@ -133,8 +134,8 @@ static inline void pmd_populate(struct mm_struct *mm,
 /*
  * page table entry allocation/free routines.
  */
-#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
-#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm))
+#define pte_alloc_one_kernel(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))
+#define pte_alloc_one(mm, vmaddr) ((pte_t *) page_table_alloc(mm, vmaddr))
 
 #define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
 #define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)

arch/s390/include/asm/pgtable.h

@@ -654,6 +654,48 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
 #endif
 }
 
+/**
+ * struct gmap_struct - guest address space
+ * @mm: pointer to the parent mm_struct
+ * @table: pointer to the page directory
+ * @crst_list: list of all crst tables used in the guest address space
+ */
+struct gmap {
+	struct list_head list;
+	struct mm_struct *mm;
+	unsigned long *table;
+	struct list_head crst_list;
+};
+
+/**
+ * struct gmap_rmap - reverse mapping for segment table entries
+ * @next: pointer to the next gmap_rmap structure in the list
+ * @entry: pointer to a segment table entry
+ */
+struct gmap_rmap {
+	struct list_head list;
+	unsigned long *entry;
+};
+
+/**
+ * struct gmap_pgtable - gmap information attached to a page table
+ * @vmaddr: address of the 1MB segment in the process virtual memory
+ * @mapper: list of segment table entries maping a page table
+ */
+struct gmap_pgtable {
+	unsigned long vmaddr;
+	struct list_head mapper;
+};
+
+struct gmap *gmap_alloc(struct mm_struct *mm);
+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 length);
+int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
+unsigned long gmap_fault(unsigned long address, struct gmap *);
+
 /*
  * Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following

arch/s390/include/asm/processor.h

@@ -80,6 +80,7 @@ struct thread_struct {
 	mm_segment_t mm_segment;
         unsigned long prot_addr;        /* address of protection-excep.     */
         unsigned int trap_no;
+	unsigned long gmap_addr;	/* address of last gmap fault. */
 	struct per_regs per_user;	/* User specified PER registers */
 	struct per_event per_event;	/* Cause of the last PER trap */
         /* pfault_wait is used to block the process on a pfault event */

arch/s390/include/asm/thread_info.h

@@ -94,6 +94,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing active */
 #define TIF_SECCOMP		10	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	11	/* syscall tracepoint instrumentation */
+#define TIF_SIE			12	/* guest execution active */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling
 					   TIF_NEED_RESCHED */
 #define TIF_31BIT		17	/* 32bit process */
@@ -113,6 +114,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SIE		(1<<TIF_SIE)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_31BIT		(1<<TIF_31BIT)
 #define _TIF_SINGLE_STEP	(1<<TIF_FREEZE)

arch/s390/include/asm/tlbflush.h

@@ -80,7 +80,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
 	 * on all cpus instead of doing a local flush if the mm
 	 * only ran on the local cpu.
 	 */
-	if (MACHINE_HAS_IDTE)
+	if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
 		__tlb_flush_idte((unsigned long) mm->pgd |
 				 mm->context.asce_bits);
 	else

arch/s390/kernel/asm-offsets.c

@@ -151,7 +151,7 @@ int main(void)
 	DEFINE(__LC_FP_CREG_SAVE_AREA, offsetof(struct _lowcore, fpt_creg_save_area));
 	DEFINE(__LC_LAST_BREAK, offsetof(struct _lowcore, breaking_event_addr));
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
-	DEFINE(__LC_SIE_HOOK, offsetof(struct _lowcore, sie_hook));
+	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
 #endif /* CONFIG_32BIT */
 	return 0;

arch/s390/kernel/base.S

@@ -6,13 +6,13 @@
  *		 Michael Holzheu <holzheu@de.ibm.com>
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_64BIT
 
-	.globl	s390_base_mcck_handler
-s390_base_mcck_handler:
+ENTRY(s390_base_mcck_handler)
 	basr	%r13,0
 0:	lg	%r15,__LC_PANIC_STACK	# load panic stack
 	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -26,13 +26,13 @@ s390_base_mcck_handler:
 	lpswe	__LC_MCK_OLD_PSW
 
 	.section .bss
+	.align 8
 	.globl	s390_base_mcck_handler_fn
 s390_base_mcck_handler_fn:
 	.quad	0
 	.previous
 
-	.globl	s390_base_ext_handler
-s390_base_ext_handler:
+ENTRY(s390_base_ext_handler)
 	stmg	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -46,13 +46,13 @@ s390_base_ext_handler:
 	lpswe	__LC_EXT_OLD_PSW
 
 	.section .bss
+	.align 8
 	.globl s390_base_ext_handler_fn
 s390_base_ext_handler_fn:
 	.quad	0
 	.previous
 
-	.globl	s390_base_pgm_handler
-s390_base_pgm_handler:
+ENTRY(s390_base_pgm_handler)
 	stmg	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -70,6 +70,7 @@ disabled_wait_psw:
 	.quad	0x0002000180000000,0x0000000000000000 + s390_base_pgm_handler
 
 	.section .bss
+	.align 8
 	.globl s390_base_pgm_handler_fn
 s390_base_pgm_handler_fn:
 	.quad	0
@@ -77,8 +78,7 @@ s390_base_pgm_handler_fn:
 
 #else /* CONFIG_64BIT */
 
-	.globl	s390_base_mcck_handler
-s390_base_mcck_handler:
+ENTRY(s390_base_mcck_handler)
 	basr	%r13,0
 0:	l	%r15,__LC_PANIC_STACK	# load panic stack
 	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -93,13 +93,13 @@ s390_base_mcck_handler:
 2:	.long	s390_base_mcck_handler_fn
 
 	.section .bss
+	.align 4
 	.globl	s390_base_mcck_handler_fn
 s390_base_mcck_handler_fn:
 	.long	0
 	.previous
 
-	.globl	s390_base_ext_handler
-s390_base_ext_handler:
+ENTRY(s390_base_ext_handler)
 	stm	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -115,13 +115,13 @@ s390_base_ext_handler:
 2:	.long	s390_base_ext_handler_fn
 
 	.section .bss
+	.align 4
 	.globl	s390_base_ext_handler_fn
 s390_base_ext_handler_fn:
 	.long	0
 	.previous
 
-	.globl	s390_base_pgm_handler
-s390_base_pgm_handler:
+ENTRY(s390_base_pgm_handler)
 	stm	%r0,%r15,__LC_SAVE_AREA
 	basr	%r13,0
 0:	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -142,6 +142,7 @@ disabled_wait_psw:
 	.long	0x000a0000,0x00000000 + s390_base_pgm_handler
 
 	.section .bss
+	.align 4
 	.globl	s390_base_pgm_handler_fn
 s390_base_pgm_handler_fn:
 	.long	0

arch/s390/kernel/entry.S

@@ -9,8 +9,8 @@
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
-#include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
@@ -197,8 +197,7 @@ STACK_SIZE  = 1 << STACK_SHIFT
  * Returns:
  *  gpr2 = prev
  */
-	.globl	__switch_to
-__switch_to:
+ENTRY(__switch_to)
 	basr	%r1,0
 0:	l	%r4,__THREAD_info(%r2)		# get thread_info of prev
 	l	%r5,__THREAD_info(%r3)		# get thread_info of next
@@ -224,8 +223,7 @@ __critical_start:
  * are executed with interrupts enabled.
  */
 
-	.globl	system_call
-system_call:
+ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
 sysc_saveall:
 	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
@@ -388,8 +386,7 @@ sysc_tracenogo:
 #
 # a new process exits the kernel with ret_from_fork
 #
-	.globl	ret_from_fork
-ret_from_fork:
+ENTRY(ret_from_fork)
 	l	%r13,__LC_SVC_NEW_PSW+4
 	l	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
@@ -405,8 +402,7 @@ ret_from_fork:
 # kernel_execve function needs to deal with pt_regs that is not
 # at the usual place
 #
-	.globl	kernel_execve
-kernel_execve:
+ENTRY(kernel_execve)
 	stm	%r12,%r15,48(%r15)
 	lr	%r14,%r15
 	l	%r13,__LC_SVC_NEW_PSW+4
@@ -438,8 +434,7 @@ kernel_execve:
  * Program check handler routine
  */
 
-	.globl	pgm_check_handler
-pgm_check_handler:
+ENTRY(pgm_check_handler)
 /*
  * First we need to check for a special case:
  * Single stepping an instruction that disables the PER event mask will
@@ -565,8 +560,7 @@ kernel_per:
  * IO interrupt handler routine
  */
 
-	.globl io_int_handler
-io_int_handler:
+ENTRY(io_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+16
@@ -703,8 +697,7 @@ io_notify_resume:
  * External interrupt handler routine
  */
 
-	.globl	ext_int_handler
-ext_int_handler:
+ENTRY(ext_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+16
@@ -731,8 +724,7 @@ __critical_end:
  * Machine check handler routines
  */
 
-	.globl mcck_int_handler
-mcck_int_handler:
+ENTRY(mcck_int_handler)
 	stck	__LC_MCCK_CLOCK
 	spt	__LC_CPU_TIMER_SAVE_AREA	# revalidate cpu timer
 	lm	%r0,%r15,__LC_GPREGS_SAVE_AREA	# revalidate gprs
@@ -818,8 +810,7 @@ mcck_return:
  */
 #ifdef CONFIG_SMP
 	__CPUINIT
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	spt	restart_vtime-restart_base(%r1)
@@ -848,8 +839,7 @@ restart_vtime:
 /*
  * If we do not run with SMP enabled, let the new CPU crash ...
  */
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	lpsw	restart_crash-restart_base(%r1)

arch/s390/kernel/entry.h

@@ -5,10 +5,9 @@
 #include <linux/signal.h>
 #include <asm/ptrace.h>
 
-typedef void pgm_check_handler_t(struct pt_regs *, long, unsigned long);
-extern pgm_check_handler_t *pgm_check_table[128];
-pgm_check_handler_t do_protection_exception;
-pgm_check_handler_t do_dat_exception;
+void do_protection_exception(struct pt_regs *, long, unsigned long);
+void do_dat_exception(struct pt_regs *, long, unsigned long);
+void do_asce_exception(struct pt_regs *, long, unsigned long);
 
 extern int sysctl_userprocess_debug;
 

arch/s390/kernel/entry64.S

@@ -9,8 +9,8 @@
  *		 Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
-#include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
@@ -56,15 +56,28 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		 _TIF_MCCK_PENDING)
 _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
 		_TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8)
+_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
 
 #define BASED(name) name-system_call(%r13)
 
+	.macro SPP newpp
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
+	jz	.+8
+	.insn	s,0xb2800000,\newpp
+#endif
+	.endm
+
 	.macro	HANDLE_SIE_INTERCEPT
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
-	lg	%r3,__LC_SIE_HOOK
-	ltgr	%r3,%r3
+	tm	__TI_flags+6(%r12),_TIF_SIE>>8
 	jz	0f
-	basr	%r14,%r3
+	SPP	__LC_CMF_HPP			# set host id
+	clc	SP_PSW+8(8,%r15),BASED(.Lsie_loop)
+	jl	0f
+	clc	SP_PSW+8(8,%r15),BASED(.Lsie_done)
+	jhe	0f
+	mvc	SP_PSW+8(8,%r15),BASED(.Lsie_loop)
 0:
 #endif
 	.endm
@@ -206,8 +219,7 @@ _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
  * Returns:
  *  gpr2 = prev
  */
-	.globl	__switch_to
-__switch_to:
+ENTRY(__switch_to)
 	lg	%r4,__THREAD_info(%r2)		# get thread_info of prev
 	lg	%r5,__THREAD_info(%r3)		# get thread_info of next
 	tm	__TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending?
@@ -232,8 +244,7 @@ __critical_start:
  * are executed with interrupts enabled.
  */
 
-	.globl	system_call
-system_call:
+ENTRY(system_call)
 	stpt	__LC_SYNC_ENTER_TIMER
 sysc_saveall:
 	SAVE_ALL_SVC __LC_SVC_OLD_PSW,__LC_SAVE_AREA
@@ -395,8 +406,7 @@ sysc_tracenogo:
 #
 # a new process exits the kernel with ret_from_fork
 #
-	.globl	ret_from_fork
-ret_from_fork:
+ENTRY(ret_from_fork)
 	lg	%r13,__LC_SVC_NEW_PSW+8
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	SP_PSW+1(%r15),0x01	# forking a kernel thread ?
@@ -411,8 +421,7 @@ ret_from_fork:
 # kernel_execve function needs to deal with pt_regs that is not
 # at the usual place
 #
-	.globl	kernel_execve
-kernel_execve:
+ENTRY(kernel_execve)
 	stmg	%r12,%r15,96(%r15)
 	lgr	%r14,%r15
 	aghi	%r15,-SP_SIZE
@@ -442,8 +451,7 @@ kernel_execve:
  * Program check handler routine
  */
 
-	.globl	pgm_check_handler
-pgm_check_handler:
+ENTRY(pgm_check_handler)
 /*
  * First we need to check for a special case:
  * Single stepping an instruction that disables the PER event mask will
@@ -465,6 +473,7 @@ pgm_check_handler:
 	xc	SP_ILC(4,%r15),SP_ILC(%r15)
 	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	pgm_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -472,7 +481,6 @@ pgm_check_handler:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
 	LAST_BREAK
 pgm_no_vtime:
-	HANDLE_SIE_INTERCEPT
 	stg	%r11,SP_ARGS(%r15)
 	lgf	%r3,__LC_PGM_ILC	# load program interruption code
 	lg	%r4,__LC_TRANS_EXC_CODE
@@ -507,6 +515,7 @@ pgm_per_std:
 	CREATE_STACK_FRAME __LC_SAVE_AREA
 	mvc	SP_PSW(16,%r15),__LC_PGM_OLD_PSW
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	pgm_no_vtime2
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_SYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -514,7 +523,6 @@ pgm_per_std:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
 	LAST_BREAK
 pgm_no_vtime2:
-	HANDLE_SIE_INTERCEPT
 	lg	%r1,__TI_task(%r12)
 	tm	SP_PSW+1(%r15),0x01	# kernel per event ?
 	jz	kernel_per
@@ -571,14 +579,14 @@ kernel_per:
 /*
  * IO interrupt handler routine
  */
-	.globl io_int_handler
-io_int_handler:
+ENTRY(io_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_IO_OLD_PSW,__LC_SAVE_AREA+40
 	CREATE_STACK_FRAME __LC_SAVE_AREA+40
 	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	io_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -586,7 +594,6 @@ io_int_handler:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
 	LAST_BREAK
 io_no_vtime:
-	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
 	brasl	%r14,do_IRQ		# call standard irq handler
@@ -706,14 +713,14 @@ io_notify_resume:
 /*
  * External interrupt handler routine
  */
-	.globl	ext_int_handler
-ext_int_handler:
+ENTRY(ext_int_handler)
 	stck	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
 	SAVE_ALL_ASYNC __LC_EXT_OLD_PSW,__LC_SAVE_AREA+40
 	CREATE_STACK_FRAME __LC_SAVE_AREA+40
 	mvc	SP_PSW(16,%r15),0(%r12)	# move user PSW to stack
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	ext_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_ASYNC_ENTER_TIMER,__LC_USER_TIMER
@@ -721,7 +728,6 @@ ext_int_handler:
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_ASYNC_ENTER_TIMER
 	LAST_BREAK
 ext_no_vtime:
-	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	lghi	%r1,4096
 	la	%r2,SP_PTREGS(%r15)	# address of register-save area
@@ -736,8 +742,7 @@ __critical_end:
 /*
  * Machine check handler routines
  */
-	.globl mcck_int_handler
-mcck_int_handler:
+ENTRY(mcck_int_handler)
 	stck	__LC_MCCK_CLOCK
 	la	%r1,4095		# revalidate r1
 	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# revalidate cpu timer
@@ -785,6 +790,7 @@ mcck_int_main:
 	lg	%r12,__LC_THREAD_INFO	# load pointer to thread_info struct
 	tm	__LC_MCCK_CODE+2,0x08	# mwp of old psw valid?
 	jno	mcck_no_vtime		# no -> no timer update
+	HANDLE_SIE_INTERCEPT
 	tm	SP_PSW+1(%r15),0x01	# interrupting from user ?
 	jz	mcck_no_vtime
 	UPDATE_VTIME __LC_EXIT_TIMER,__LC_MCCK_ENTER_TIMER,__LC_USER_TIMER
@@ -804,7 +810,6 @@ mcck_no_vtime:
 	stosm	__SF_EMPTY(%r15),0x04	# turn dat on
 	tm	__TI_flags+7(%r12),_TIF_MCCK_PENDING
 	jno	mcck_return
-	HANDLE_SIE_INTERCEPT
 	TRACE_IRQS_OFF
 	brasl	%r14,s390_handle_mcck
 	TRACE_IRQS_ON
@@ -823,8 +828,7 @@ mcck_done:
  */
 #ifdef CONFIG_SMP
 	__CPUINIT
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	spt	restart_vtime-restart_base(%r1)
@@ -851,8 +855,7 @@ restart_vtime:
 /*
  * If we do not run with SMP enabled, let the new CPU crash ...
  */
-	.globl restart_int_handler
-restart_int_handler:
+ENTRY(restart_int_handler)
 	basr	%r1,0
 restart_base:
 	lpswe	restart_crash-restart_base(%r1)
@@ -1036,6 +1039,56 @@ cleanup_io_restore_insn:
 .Lcritical_end:
 		.quad	__critical_end
 
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+/*
+ * sie64a calling convention:
+ * %r2 pointer to sie control block
+ * %r3 guest register save area
+ */
+ENTRY(sie64a)
+	stmg	%r6,%r14,__SF_GPRS(%r15)	# save kernel registers
+	stg	%r2,__SF_EMPTY(%r15)		# save control block pointer
+	stg	%r3,__SF_EMPTY+8(%r15)		# save guest register save area
+	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+	oi	__TI_flags+6(%r14),_TIF_SIE>>8
+sie_loop:
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
+	jnz	sie_exit
+	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
+	SPP	__SF_EMPTY(%r15)		# set guest id
+	sie	0(%r14)
+sie_done:
+	SPP	__LC_CMF_HPP			# set host id
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+sie_exit:
+	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
+	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
+	lghi	%r2,0
+	br	%r14
+sie_fault:
+	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
+	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
+	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
+	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
+	lmg	%r6,%r14,__SF_GPRS(%r15)	# restore kernel registers
+	lghi	%r2,-EFAULT
+	br	%r14
+
+	.align	8
+.Lsie_loop:
+	.quad	sie_loop
+.Lsie_done:
+	.quad	sie_done
+
+	.section __ex_table,"a"
+	.quad	sie_loop,sie_fault
+	.previous
+#endif
+
 		.section .rodata, "a"
 #define SYSCALL(esa,esame,emu)	.long esame
 	.globl	sys_call_table

arch/s390/kernel/head.S

@@ -22,6 +22,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
@@ -383,8 +384,7 @@ iplstart:
 # doesn't need a builtin ipl record.
 #
 	.org	0x800
-	.globl	start
-start:
+ENTRY(start)
 	stm	%r0,%r15,0x07b0		# store registers
 	basr	%r12,%r0
 .base:
@@ -448,8 +448,7 @@ start:
 # or linload or SALIPL
 #
 	.org	0x10000
-	.globl	startup
-startup:
+ENTRY(startup)
 	basr	%r13,0			# get base
 .LPG0:
 	xc	0x200(256),0x200	# partially clear lowcore

arch/s390/kernel/head31.S

@@ -11,13 +11,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	basr	%r13,0			# get base
 .LPG1:
 
@@ -45,7 +45,7 @@ startup_continue:
 					# virtual and never return ...
 	.align	8
 .Lentry:.long	0x00080000,0x80000000 + _stext
-.Lctl:	.long	0x04b50002		# cr0: various things
+.Lctl:	.long	0x04b50000		# cr0: various things
 	.long	0			# cr1: primary space segment table
 	.long	.Lduct			# cr2: dispatchable unit control table
 	.long	0			# cr3: instruction authorization
@@ -78,8 +78,7 @@ startup_continue:
 .Lbase_cc:
 	.long	sched_clock_base_cc
 
-	.globl	_ehead
-_ehead:
+ENTRY(_ehead)
 
 #ifdef CONFIG_SHARED_KERNEL
 	.org	0x100000 - 0x11000	# head.o ends at 0x11000
@@ -88,8 +87,8 @@ _ehead:
 #
 # startup-code, running in absolute addressing mode
 #
-	.globl	_stext
-_stext:	basr	%r13,0			# get base
+ENTRY(_stext)
+	basr	%r13,0			# get base
 .LPG3:
 # check control registers
 	stctl	%c0,%c15,0(%r15)

arch/s390/kernel/head64.S

@@ -11,13 +11,13 @@
  */
 
 #include <linux/init.h>
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
 
 __HEAD
-	.globl	startup_continue
-startup_continue:
+ENTRY(startup_continue)
 	larl	%r1,sched_clock_base_cc
 	mvc	0(8,%r1),__LC_LAST_UPDATE_CLOCK
 	larl	%r13,.LPG1		# get base
@@ -46,7 +46,7 @@ startup_continue:
 	.align	16
 .LPG1:
 .Lentry:.quad	0x0000000180000000,_stext
-.Lctl:	.quad	0x04350002		# cr0: various things
+.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
 	.quad	0			# cr1: primary space segment table
 	.quad	.Lduct			# cr2: dispatchable unit control table
 	.quad	0			# cr3: instruction authorization
@@ -76,8 +76,7 @@ startup_continue:
 	.long	0x80000000,0,0,0	# invalid access-list entries
 	.endr
 
-	.globl	_ehead
-_ehead:
+ENTRY(_ehead)
 
 #ifdef CONFIG_SHARED_KERNEL
 	.org	0x100000 - 0x11000	# head.o ends at 0x11000
@@ -86,8 +85,8 @@ _ehead:
 #
 # startup-code, running in absolute addressing mode
 #
-	.globl	_stext
-_stext:	basr	%r13,0			# get base
+ENTRY(_stext)
+	basr	%r13,0			# get base
 .LPG3:
 # check control registers
 	stctg	%c0,%c15,0(%r15)

arch/s390/kernel/irq.c

@@ -87,15 +87,6 @@ int show_interrupts(struct seq_file *p, void *v)
         return 0;
 }
 
-/*
- * For compatibilty only. S/390 specific setup of interrupts et al. is done
- * much later in init_channel_subsystem().
- */
-void __init init_IRQ(void)
-{
-	/* nothing... */
-}
-
 /*
  * Switch to the asynchronous interrupt stack for softirq execution.
  */
@@ -144,28 +135,45 @@ void init_irq_proc(void)
 #endif
 
 /*
- * ext_int_hash[index] is the start of the list for all external interrupts
- * that hash to this index. With the current set of external interrupts
- * (0x1202 external call, 0x1004 cpu timer, 0x2401 hwc console, 0x4000
- * iucv and 0x2603 pfault) this is always the first element.
+ * ext_int_hash[index] is the list head for all external interrupts that hash
+ * to this index.
  */
+static struct list_head ext_int_hash[256];
 
 struct ext_int_info {
-	struct ext_int_info *next;
 	ext_int_handler_t handler;
 	u16 code;
+	struct list_head entry;
+	struct rcu_head rcu;
 };
 
-static struct ext_int_info *ext_int_hash[256];
+/* ext_int_hash_lock protects the handler lists for external interrupts */
+DEFINE_SPINLOCK(ext_int_hash_lock);
+
+static void __init init_external_interrupts(void)
+{
+	int idx;
+
+	for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++)
+		INIT_LIST_HEAD(&ext_int_hash[idx]);
+}
 
 static inline int ext_hash(u16 code)
 {
 	return (code + (code >> 9)) & 0xff;
 }
 
+static void ext_int_hash_update(struct rcu_head *head)
+{
+	struct ext_int_info *p = container_of(head, struct ext_int_info, rcu);
+
+	kfree(p);
+}
+
 int register_external_interrupt(u16 code, ext_int_handler_t handler)
 {
 	struct ext_int_info *p;
+	unsigned long flags;
 	int index;
 
 	p = kmalloc(sizeof(*p), GFP_ATOMIC);
@@ -174,33 +182,27 @@ int register_external_interrupt(u16 code, ext_int_handler_t handler)
 	p->code = code;
 	p->handler = handler;
 	index = ext_hash(code);
-	p->next = ext_int_hash[index];
-	ext_int_hash[index] = p;
+
+	spin_lock_irqsave(&ext_int_hash_lock, flags);
+	list_add_rcu(&p->entry, &ext_int_hash[index]);
+	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
 EXPORT_SYMBOL(register_external_interrupt);
 
 int unregister_external_interrupt(u16 code, ext_int_handler_t handler)
 {
-	struct ext_int_info *p, *q;
-	int index;
+	struct ext_int_info *p;
+	unsigned long flags;
+	int index = ext_hash(code);
 
-	index = ext_hash(code);
-	q = NULL;
-	p = ext_int_hash[index];
-	while (p) {
-		if (p->code == code && p->handler == handler)
-			break;
-		q = p;
-		p = p->next;
+	spin_lock_irqsave(&ext_int_hash_lock, flags);
+	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
+		if (p->code == code && p->handler == handler) {
+			list_del_rcu(&p->entry);
+			call_rcu(&p->rcu, ext_int_hash_update);
 		}
-	if (!p)
-		return -ENOENT;
-	if (q)
-		q->next = p->next;
-	else
-		ext_int_hash[index] = p->next;
-	kfree(p);
+	spin_unlock_irqrestore(&ext_int_hash_lock, flags);
 	return 0;
 }
 EXPORT_SYMBOL(unregister_external_interrupt);
@@ -224,15 +226,22 @@ void __irq_entry do_extint(struct pt_regs *regs, unsigned int ext_int_code,
 	kstat_cpu(smp_processor_id()).irqs[EXTERNAL_INTERRUPT]++;
 	if (code != 0x1004)
 		__get_cpu_var(s390_idle).nohz_delay = 1;
+
 	index = ext_hash(code);
-	for (p = ext_int_hash[index]; p; p = p->next) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(p, &ext_int_hash[index], entry)
 		if (likely(p->code == code))
 			p->handler(ext_int_code, param32, param64);
-	}
+	rcu_read_unlock();
 	irq_exit();
 	set_irq_regs(old_regs);
 }
 
+void __init init_IRQ(void)
+{
+	init_external_interrupts();
+}
+
 static DEFINE_SPINLOCK(sc_irq_lock);
 static int sc_irq_refcount;
 

arch/s390/kernel/mcount.S

@@ -5,21 +5,19 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 	.section .kprobes.text, "ax"
 
-	.globl ftrace_stub
-ftrace_stub:
+ENTRY(ftrace_stub)
 	br	%r14
 
-	.globl _mcount
-_mcount:
+ENTRY(_mcount)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	br	%r14
 
-	.globl ftrace_caller
-ftrace_caller:
+ENTRY(ftrace_caller)
 #endif
 	stm	%r2,%r5,16(%r15)
 	bras	%r1,2f
@@ -41,8 +39,7 @@ ftrace_caller:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	l	%r2,100(%r15)
 	l	%r3,152(%r15)
-	.globl	ftrace_graph_caller
-ftrace_graph_caller:
+ENTRY(ftrace_graph_caller)
 # The bras instruction gets runtime patched to call prepare_ftrace_return.
 # See ftrace_enable_ftrace_graph_caller. The patched instruction is:
 #	bras	%r14,prepare_ftrace_return
@@ -56,8 +53,7 @@ ftrace_graph_caller:
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-	.globl	return_to_handler
-return_to_handler:
+ENTRY(return_to_handler)
 	stm	%r2,%r5,16(%r15)
 	st	%r14,56(%r15)
 	lr	%r0,%r15

arch/s390/kernel/mcount64.S

@@ -5,21 +5,19 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 	.section .kprobes.text, "ax"
 
-	.globl ftrace_stub
-ftrace_stub:
+ENTRY(ftrace_stub)
 	br	%r14
 
-	.globl _mcount
-_mcount:
+ENTRY(_mcount)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	br	%r14
 
-	.globl ftrace_caller
-ftrace_caller:
+ENTRY(ftrace_caller)
 #endif
 	larl	%r1,function_trace_stop
 	icm	%r1,0xf,0(%r1)
@@ -37,8 +35,7 @@ ftrace_caller:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	lg	%r2,168(%r15)
 	lg	%r3,272(%r15)
-	.globl	ftrace_graph_caller
-ftrace_graph_caller:
+ENTRY(ftrace_graph_caller)
 # The bras instruction gets runtime patched to call prepare_ftrace_return.
 # See ftrace_enable_ftrace_graph_caller. The patched instruction is:
 #	bras	%r14,prepare_ftrace_return
@@ -52,8 +49,7 @@ ftrace_graph_caller:
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
-	.globl	return_to_handler
-return_to_handler:
+ENTRY(return_to_handler)
 	stmg	%r2,%r5,32(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-160

arch/s390/kernel/reipl.S

@@ -6,14 +6,15 @@
  *    Author(s): Holger Smolinski (Holger.Smolinski@de.ibm.com)
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #
 # do_reipl_asm
 # Parameter: r2 = schid of reipl device
 #
-		.globl	do_reipl_asm
-do_reipl_asm:	basr	%r13,0
+ENTRY(do_reipl_asm)
+		basr	%r13,0
 .Lpg0:		lpsw	.Lnewpsw-.Lpg0(%r13)
 .Lpg1:		# do store status of all registers
 

arch/s390/kernel/reipl64.S

@@ -4,6 +4,7 @@
  *		 Denis Joseph Barrow,
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #
@@ -11,8 +12,8 @@
 # Parameter: r2 = schid of reipl device
 #
 
-		.globl	do_reipl_asm
-do_reipl_asm:	basr	%r13,0
+ENTRY(do_reipl_asm)
+		basr	%r13,0
 .Lpg0:		lpswe	.Lnewpsw-.Lpg0(%r13)
 .Lpg1:		# do store status of all registers
 

arch/s390/kernel/relocate_kernel.S

@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 /*
  * moves the new kernel to its destination...
  * %r2 = pointer to first kimage_entry_t
@@ -22,8 +24,7 @@
  */
 
 	.text
-	.globl		relocate_kernel
-	relocate_kernel:
+ENTRY(relocate_kernel)
 		basr	%r13,0		# base address
 	.base:
 		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
@@ -112,6 +113,7 @@
 		.byte	0
 		.align	8
 	relocate_kernel_end:
+	.align 8
 	.globl	relocate_kernel_len
 	relocate_kernel_len:
 		.quad	relocate_kernel_end - relocate_kernel

arch/s390/kernel/relocate_kernel64.S

@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 /*
  * moves the new kernel to its destination...
  * %r2 = pointer to first kimage_entry_t
@@ -23,8 +25,7 @@
  */
 
 	.text
-	.globl		relocate_kernel
-	relocate_kernel:
+ENTRY(relocate_kernel)
 		basr	%r13,0		# base address
 	.base:
 		stnsm	sys_msk-.base(%r13),0xfb	# disable DAT
@@ -115,6 +116,7 @@
 		.byte	0
 		.align	8
 	relocate_kernel_end:
+	.align 8
 	.globl	relocate_kernel_len
 	relocate_kernel_len:
 		.quad	relocate_kernel_end - relocate_kernel

arch/s390/kernel/s390_ksyms.c

 #include <linux/module.h>
+#include <linux/kvm_host.h>
 #include <asm/ftrace.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+EXPORT_SYMBOL(sie64a);
+#endif

arch/s390/kernel/sclp.S

@@ -8,6 +8,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 LC_EXT_NEW_PSW		= 0x58			# addr of ext int handler
 LC_EXT_NEW_PSW_64	= 0x1b0			# addr of ext int handler 64 bit
 LC_EXT_INT_PARAM	= 0x80			# addr of ext int parameter
@@ -260,8 +262,7 @@ _sclp_print:
 #   R2	= 0 on success, 1 on failure
 #
 
-	.globl _sclp_print_early
-_sclp_print_early:
+ENTRY(_sclp_print_early)
 	stm	%r6,%r15,24(%r15)		# save registers
 	ahi	%r15,-96			# create stack frame
 #ifdef CONFIG_64BIT

arch/s390/kernel/smp.c

@@ -654,7 +654,8 @@ int __cpu_disable(void)
 	/* disable all external interrupts */
 	cr_parms.orvals[0] = 0;
 	cr_parms.andvals[0] = ~(1 << 15 | 1 << 14 | 1 << 13 | 1 << 11 |
-				1 << 10 | 1 <<	9 | 1 <<  6 | 1 <<  4);
+				1 << 10 | 1 <<	9 | 1 <<  6 | 1 <<  5 |
+				1 <<  4);
 	/* disable all I/O interrupts */
 	cr_parms.orvals[6] = 0;
 	cr_parms.andvals[6] = ~(1 << 31 | 1 << 30 | 1 << 29 | 1 << 28 |

arch/s390/kernel/switch_cpu.S

@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 
@@ -16,9 +17,7 @@
 #	     %r6 - destination cpu
 
 	.section .text
-	.align 4
-	.globl smp_switch_to_cpu
-smp_switch_to_cpu:
+ENTRY(smp_switch_to_cpu)
 	stm	%r6,%r15,__SF_GPRS(%r15)
 	lr	%r1,%r15
 	ahi	%r15,-STACK_FRAME_OVERHEAD
@@ -33,8 +32,7 @@ smp_switch_to_cpu:
 	brc	2,2b			/* busy, try again */
 3:	j	3b
 
-	.globl	smp_restart_cpu
-smp_restart_cpu:
+ENTRY(smp_restart_cpu)
 	basr	%r13,0
 0:	la	%r1,.gprregs_addr-0b(%r13)
 	l	%r1,0(%r1)

arch/s390/kernel/switch_cpu64.S

@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 
@@ -16,9 +17,7 @@
 #	     %r6 - destination cpu
 
 	.section .text
-	.align 4
-	.globl smp_switch_to_cpu
-smp_switch_to_cpu:
+ENTRY(smp_switch_to_cpu)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -31,8 +30,7 @@ smp_switch_to_cpu:
 	brc	2,2b			/* busy, try again */
 3:	j	3b
 
-	.globl	smp_restart_cpu
-smp_restart_cpu:
+ENTRY(smp_restart_cpu)
 	larl	%r1,.gprregs
 	lmg	%r0,%r15,0(%r1)
 1:	sigp	%r0,%r5,__SIGP_SENSE	/* Wait for calling CPU */

arch/s390/kernel/swsusp_asm64.S

@@ -7,6 +7,7 @@
  *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
  */
 
+#include <linux/linkage.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -22,9 +23,7 @@
  * This function runs with disabled interrupts.
  */
 	.section .text
-	.align	4
-	.globl swsusp_arch_suspend
-swsusp_arch_suspend:
+ENTRY(swsusp_arch_suspend)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-STACK_FRAME_OVERHEAD
@@ -112,8 +111,7 @@ swsusp_arch_suspend:
  * Then we return to the function that called swsusp_arch_suspend().
  * swsusp_arch_resume() runs with disabled interrupts.
  */
-	.globl swsusp_arch_resume
-swsusp_arch_resume:
+ENTRY(swsusp_arch_resume)
 	stmg	%r6,%r15,__SF_GPRS(%r15)
 	lgr	%r1,%r15
 	aghi	%r15,-STACK_FRAME_OVERHEAD

arch/s390/kernel/traps.c

@@ -18,7 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
-#include <linux/tracehook.h>
+#include <linux/ptrace.h>
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
@@ -43,14 +43,10 @@
 #include <asm/debug.h>
 #include "entry.h"
 
-pgm_check_handler_t *pgm_check_table[128];
+void (*pgm_check_table[128])(struct pt_regs *, long, unsigned long);
 
 int show_unhandled_signals;
 
-extern pgm_check_handler_t do_protection_exception;
-extern pgm_check_handler_t do_dat_exception;
-extern pgm_check_handler_t do_asce_exception;
-
 #define stack_pointer ({ void **sp; asm("la %0,0(15)" : "=&d" (sp)); sp; })
 
 #ifndef CONFIG_64BIT
@@ -329,10 +325,17 @@ static inline void __user *get_psw_address(struct pt_regs *regs,
 
 void __kprobes do_per_trap(struct pt_regs *regs)
 {
+	siginfo_t info;
+
 	if (notify_die(DIE_SSTEP, "sstep", regs, 0, 0, SIGTRAP) == NOTIFY_STOP)
 		return;
-	if (current->ptrace)
-		force_sig(SIGTRAP, current);
+	if (!current->ptrace)
+		return;
+	info.si_signo = SIGTRAP;
+	info.si_errno = 0;
+	info.si_code = TRAP_HWBKPT;
+	info.si_addr = (void *) current->thread.per_event.address;
+	force_sig_info(SIGTRAP, &info, current);
 }
 
 static void default_trap_handler(struct pt_regs *regs, long pgm_int_code,
@@ -425,9 +428,13 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
 		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
 			return;
 		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
-			if (current->ptrace)
-				force_sig(SIGTRAP, current);
-			else
+			if (current->ptrace) {
+				info.si_signo = SIGTRAP;
+				info.si_errno = 0;
+				info.si_code = TRAP_BRKPT;
+				info.si_addr = location;
+				force_sig_info(SIGTRAP, &info, current);
+			} else
 				signal = SIGILL;
 #ifdef CONFIG_MATHEMU
 		} else if (opcode[0] == 0xb3) {
@@ -489,8 +496,7 @@ static void __kprobes illegal_op(struct pt_regs *regs, long pgm_int_code,
 
 
 #ifdef CONFIG_MATHEMU
-asmlinkage void specification_exception(struct pt_regs *regs,
-					long pgm_int_code,
+void specification_exception(struct pt_regs *regs, long pgm_int_code,
 			     unsigned long trans_exc_code)
 {
         __u8 opcode[6];
@@ -648,7 +654,7 @@ static void space_switch_exception(struct pt_regs *regs, long pgm_int_code,
 	do_trap(pgm_int_code, SIGILL, "space switch event", regs, &info);
 }
 
-asmlinkage void __kprobes kernel_stack_overflow(struct pt_regs * regs)
+void __kprobes kernel_stack_overflow(struct pt_regs * regs)
 {
 	bust_spinlocks(1);
 	printk("Kernel stack overflow.\n");

arch/s390/kvm/Makefile

@@ -10,5 +10,5 @@ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o)
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
-kvm-objs := $(common-objs) kvm-s390.o sie64a.o intercept.o interrupt.o priv.o sigp.o diag.o
+kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o
 obj-$(CONFIG_KVM) += kvm.o

arch/s390/kvm/gaccess.h

 /*
- * gaccess.h -  access guest memory
+ * access.h -  access guest memory
  *
  * Copyright IBM Corp. 2008,2009
  *
@@ -22,20 +22,13 @@ static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
 					       unsigned long guestaddr)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestaddr < 2 * PAGE_SIZE)
 		guestaddr += prefix;
 	else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE))
 		guestaddr -= prefix;
 
-	if (guestaddr > memsize)
-		return (void __user __force *) ERR_PTR(-EFAULT);
-
-	guestaddr += origin;
-
-	return (void __user *) guestaddr;
+	return (void __user *) gmap_fault(guestaddr, vcpu->arch.gmap);
 }
 
 static inline int get_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr,
@@ -141,11 +134,11 @@ static inline int put_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr,
 
 static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu,
 				       unsigned long guestdest,
-				       const void *from, unsigned long n)
+				       void *from, unsigned long n)
 {
 	int rc;
 	unsigned long i;
-	const u8 *data = from;
+	u8 *data = from;
 
 	for (i = 0; i < n; i++) {
 		rc = put_guest_u8(vcpu, guestdest++, *(data++));
@@ -155,12 +148,95 @@ static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static inline int __copy_to_guest_fast(struct kvm_vcpu *vcpu,
+				       unsigned long guestdest,
+				       void *from, unsigned long n)
+{
+	int r;
+	void __user *uptr;
+	unsigned long size;
+
+	if (guestdest + n < guestdest)
+		return -EFAULT;
+
+	/* simple case: all within one segment table entry? */
+	if ((guestdest & PMD_MASK) == ((guestdest+n) & PMD_MASK)) {
+		uptr = (void __user *) gmap_fault(guestdest, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_to_user(uptr, from, n);
+
+		if (r)
+			r = -EFAULT;
+
+		goto out;
+	}
+
+	/* copy first segment */
+	uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
+
+	size = PMD_SIZE - (guestdest & ~PMD_MASK);
+
+	r = copy_to_user(uptr, from, size);
+
+	if (r) {
+		r = -EFAULT;
+		goto out;
+	}
+	from += size;
+	n -= size;
+	guestdest += size;
+
+	/* copy full segments */
+	while (n >= PMD_SIZE) {
+		uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_to_user(uptr, from, PMD_SIZE);
+
+		if (r) {
+			r = -EFAULT;
+			goto out;
+		}
+		from += PMD_SIZE;
+		n -= PMD_SIZE;
+		guestdest += PMD_SIZE;
+	}
+
+	/* copy the tail segment */
+	if (n) {
+		uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_to_user(uptr, from, n);
+
+		if (r)
+			r = -EFAULT;
+	}
+out:
+	return r;
+}
+
+static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
+					 unsigned long guestdest,
+					 void *from, unsigned long n)
+{
+	return __copy_to_guest_fast(vcpu, guestdest, from, n);
+}
+
 static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
-				const void *from, unsigned long n)
+				void *from, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
 		goto slowpath;
@@ -177,15 +253,7 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
 	else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE))
 		guestdest -= prefix;
 
-	if (guestdest + n > memsize)
-		return -EFAULT;
-
-	if (guestdest + n < guestdest)
-		return -EFAULT;
-
-	guestdest += origin;
-
-	return copy_to_user((void __user *) guestdest, from, n);
+	return __copy_to_guest_fast(vcpu, guestdest, from, n);
 slowpath:
 	return __copy_to_guest_slow(vcpu, guestdest, from, n);
 }
@@ -206,74 +274,113 @@ static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to,
 	return 0;
 }
 
-static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
-				  unsigned long guestsrc, unsigned long n)
+static inline int __copy_from_guest_fast(struct kvm_vcpu *vcpu, void *to,
+					 unsigned long guestsrc,
+					 unsigned long n)
 {
-	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
+	int r;
+	void __user *uptr;
+	unsigned long size;
 
-	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
-		goto slowpath;
+	if (guestsrc + n < guestsrc)
+		return -EFAULT;
 
-	if ((guestsrc < prefix) && (guestsrc + n > prefix))
-		goto slowpath;
+	/* simple case: all within one segment table entry? */
+	if ((guestsrc & PMD_MASK) == ((guestsrc+n) & PMD_MASK)) {
+		uptr = (void __user *) gmap_fault(guestsrc, vcpu->arch.gmap);
 
-	if ((guestsrc < prefix + 2 * PAGE_SIZE)
-	    && (guestsrc + n > prefix + 2 * PAGE_SIZE))
-		goto slowpath;
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
 
-	if (guestsrc < 2 * PAGE_SIZE)
-		guestsrc += prefix;
-	else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
-		guestsrc -= prefix;
+		r = copy_from_user(to, uptr, n);
 
-	if (guestsrc + n > memsize)
-		return -EFAULT;
+		if (r)
+			r = -EFAULT;
 
-	if (guestsrc + n < guestsrc)
-		return -EFAULT;
+		goto out;
+	}
 
-	guestsrc += origin;
+	/* copy first segment */
+	uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
 
-	return copy_from_user(to, (void __user *) guestsrc, n);
-slowpath:
-	return __copy_from_guest_slow(vcpu, to, guestsrc, n);
-}
+	if (IS_ERR((void __force *) uptr))
+		return PTR_ERR((void __force *) uptr);
 
-static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
-					 unsigned long guestdest,
-					 const void *from, unsigned long n)
-{
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
+	size = PMD_SIZE - (guestsrc & ~PMD_MASK);
 
-	if (guestdest + n > memsize)
-		return -EFAULT;
+	r = copy_from_user(to, uptr, size);
 
-	if (guestdest + n < guestdest)
-		return -EFAULT;
+	if (r) {
+		r = -EFAULT;
+		goto out;
+	}
+	to += size;
+	n -= size;
+	guestsrc += size;
+
+	/* copy full segments */
+	while (n >= PMD_SIZE) {
+		uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
 
-	guestdest += origin;
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
 
-	return copy_to_user((void __user *) guestdest, from, n);
+		r = copy_from_user(to, uptr, PMD_SIZE);
+
+		if (r) {
+			r = -EFAULT;
+			goto out;
+		}
+		to += PMD_SIZE;
+		n -= PMD_SIZE;
+		guestsrc += PMD_SIZE;
+	}
+
+	/* copy the tail segment */
+	if (n) {
+		uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
+
+		if (IS_ERR((void __force *) uptr))
+			return PTR_ERR((void __force *) uptr);
+
+		r = copy_from_user(to, uptr, n);
+
+		if (r)
+			r = -EFAULT;
+	}
+out:
+	return r;
 }
 
 static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
 					   unsigned long guestsrc,
 					   unsigned long n)
 {
-	unsigned long origin  = vcpu->arch.sie_block->gmsor;
-	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
+	return __copy_from_guest_fast(vcpu, to, guestsrc, n);
+}
 
-	if (guestsrc + n > memsize)
-		return -EFAULT;
+static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
+				  unsigned long guestsrc, unsigned long n)
+{
+	unsigned long prefix  = vcpu->arch.sie_block->prefix;
 
-	if (guestsrc + n < guestsrc)
-		return -EFAULT;
+	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
+		goto slowpath;
+
+	if ((guestsrc < prefix) && (guestsrc + n > prefix))
+		goto slowpath;
 
-	guestsrc += origin;
+	if ((guestsrc < prefix + 2 * PAGE_SIZE)
+	    && (guestsrc + n > prefix + 2 * PAGE_SIZE))
+		goto slowpath;
 
-	return copy_from_user(to, (void __user *) guestsrc, n);
+	if (guestsrc < 2 * PAGE_SIZE)
+		guestsrc += prefix;
+	else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
+		guestsrc -= prefix;
+
+	return __copy_from_guest_fast(vcpu, to, guestsrc, n);
+slowpath:
+	return __copy_from_guest_slow(vcpu, to, guestsrc, n);
 }
 #endif

arch/s390/kvm/intercept.c

@@ -105,6 +105,7 @@ static intercept_handler_t instruction_handlers[256] = {
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
+	[0xe5] = kvm_s390_handle_e5,
 	[0xeb] = handle_lctlg,
 };
 
@@ -159,22 +160,42 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 
 static int handle_validity(struct kvm_vcpu *vcpu)
 {
+	unsigned long vmaddr;
 	int viwhy = vcpu->arch.sie_block->ipb >> 16;
 	int rc;
 
 	vcpu->stat.exit_validity++;
-	if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix
-		<= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) {
-		rc = fault_in_pages_writeable((char __user *)
-			 vcpu->arch.sie_block->gmsor +
-			 vcpu->arch.sie_block->prefix,
-			 2*PAGE_SIZE);
-		if (rc)
+	if (viwhy == 0x37) {
+		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix,
+				    vcpu->arch.gmap);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		rc = fault_in_pages_writeable((char __user *) vmaddr,
+			 PAGE_SIZE);
+		if (rc) {
 			/* user will receive sigsegv, exit to user */
 			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE,
+				    vcpu->arch.gmap);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		rc = fault_in_pages_writeable((char __user *) vmaddr,
+			 PAGE_SIZE);
+		if (rc) {
+			/* user will receive sigsegv, exit to user */
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
 	} else
 		rc = -EOPNOTSUPP;
 
+out:
 	if (rc)
 		VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
 			   viwhy);

arch/s390/kvm/interrupt.c

@@ -128,6 +128,10 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		if (rc == -EFAULT)
 			exception = 1;
 
+		rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->emerg.code);
+		if (rc == -EFAULT)
+			exception = 1;
+
 		rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
 			 &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
 		if (rc == -EFAULT)

arch/s390/kvm/kvm-s390.c

@@ -62,6 +62,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
 	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
 	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
 	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
 	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
@@ -189,7 +190,13 @@ int kvm_arch_init_vm(struct kvm *kvm)
 	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
 	VM_EVENT(kvm, 3, "%s", "vm created");
 
+	kvm->arch.gmap = gmap_alloc(current->mm);
+	if (!kvm->arch.gmap)
+		goto out_nogmap;
+
 	return 0;
+out_nogmap:
+	debug_unregister(kvm->arch.dbf);
 out_nodbf:
 	free_page((unsigned long)(kvm->arch.sca));
 out_err:
@@ -234,11 +241,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_vcpus(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
+	gmap_free(kvm->arch.gmap);
 }
 
 /* Section: vcpu related */
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
 	return 0;
 }
 
@@ -284,8 +293,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
-	set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests);
+	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM);
 	vcpu->arch.sie_block->ecb   = 6;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) facilities;
@@ -453,6 +461,7 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
+	gmap_enable(vcpu->arch.gmap);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
@@ -461,6 +470,7 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
+	gmap_disable(vcpu->arch.gmap);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();
@@ -474,17 +484,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	sigset_t sigsaved;
 
 rerun_vcpu:
-	if (vcpu->requests)
-		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
-			kvm_s390_vcpu_set_mem(vcpu);
-
-	/* verify, that memory has been registered */
-	if (!vcpu->arch.sie_block->gmslm) {
-		vcpu_put(vcpu);
-		VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu");
-		return -EINVAL;
-	}
-
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
@@ -545,7 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return rc;
 }
 
-static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
+static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
 		       unsigned long n, int prefix)
 {
 	if (prefix)
@@ -562,7 +561,7 @@ static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
  */
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 {
-	const unsigned char archmode = 1;
+	unsigned char archmode = 1;
 	int prefix;
 
 	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
@@ -680,10 +679,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr)
 		return -EINVAL;
 
-	if (mem->userspace_addr & (PAGE_SIZE - 1))
+	if (mem->userspace_addr & 0xffffful)
 		return -EINVAL;
 
-	if (mem->memory_size & (PAGE_SIZE - 1))
+	if (mem->memory_size & 0xffffful)
 		return -EINVAL;
 
 	if (!user_alloc)
@@ -697,15 +696,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot old,
 				int user_alloc)
 {
-	int i;
-	struct kvm_vcpu *vcpu;
+	int rc;
 
-	/* request update of sie control block for all available vcpus */
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
-			continue;
-		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
-	}
+
+	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
+		mem->guest_phys_addr, mem->memory_size);
+	if (rc)
+		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
+	return;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)

arch/s390/kvm/kvm-s390.h

@@ -58,35 +58,9 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 
-static inline long kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.sie_block->gmslm
-		- vcpu->arch.sie_block->gmsor
-		- VIRTIODESCSPACE + 1ul;
-}
-
-static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
-{
-	int idx;
-	struct kvm_memory_slot *mem;
-	struct kvm_memslots *memslots;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	memslots = kvm_memslots(vcpu->kvm);
-
-	mem = &memslots->memslots[0];
-
-	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
-	vcpu->arch.sie_block->gmslm =
-		mem->userspace_addr +
-		(mem->npages << PAGE_SHIFT) +
-		VIRTIODESCSPACE - 1ul;
-
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);

arch/s390/kvm/priv.c

@@ -326,3 +326,52 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	}
 	return -EOPNOTSUPP;
 }
+
+static int handle_tprot(struct kvm_vcpu *vcpu)
+{
+	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+	u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
+	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+	struct vm_area_struct *vma;
+
+	vcpu->stat.instruction_tprot++;
+
+	/* we only handle the Linux memory detection case:
+	 * access key == 0
+	 * guest DAT == off
+	 * everything else goes to userspace. */
+	if (address2 & 0xf0)
+		return -EOPNOTSUPP;
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
+		return -EOPNOTSUPP;
+
+
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma(current->mm,
+			(unsigned long) __guestaddr_to_user(vcpu, address1));
+	if (!vma) {
+		up_read(&current->mm->mmap_sem);
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	}
+
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (1ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (2ul << 44);
+
+	up_read(&current->mm->mmap_sem);
+	return 0;
+}
+
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
+{
+	/* For e5xx... instructions we only handle TPROT */
+	if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
+		return handle_tprot(vcpu);
+	return -EOPNOTSUPP;
+}
+

arch/s390/kvm/sie64a.S

-/*
- * sie64a.S - low level sie call
- *
- * Copyright IBM Corp. 2008,2010
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
- *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
- *		 Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
- */
-
-#include <linux/errno.h>
-#include <asm/asm-offsets.h>
-#include <asm/setup.h>
-#include <asm/asm-offsets.h>
-#include <asm/ptrace.h>
-#include <asm/thread_info.h>
-
-_TIF_EXIT_SIE = (_TIF_SIGPENDING | _TIF_NEED_RESCHED | _TIF_MCCK_PENDING)
-
-/*
- * offsets into stackframe
- * SP_	= offsets into stack sie64 is called with
- * SPI_ = offsets into irq stack
- */
-SP_GREGS = __SF_EMPTY
-SP_HOOK  = __SF_EMPTY+8
-SP_GPP	 = __SF_EMPTY+16
-SPI_PSW  = STACK_FRAME_OVERHEAD + __PT_PSW
-
-
-	.macro SPP newpp
-	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_SPP
-	jz	0f
-	.insn	s,0xb2800000,\newpp
-0:
-	.endm
-
-sie_irq_handler:
-	SPP	__LC_CMF_HPP			# set host id
-	larl	%r2,sie_inst
-	clg	%r2,SPI_PSW+8(0,%r15)		# intercepted sie
-	jne	1f
-	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
-	lg	%r2,__LC_THREAD_INFO		# pointer thread_info struct
-	tm	__TI_flags+7(%r2),_TIF_EXIT_SIE
-	jz	0f
-	larl	%r2,sie_exit			# work pending, leave sie
-	stg	%r2,SPI_PSW+8(0,%r15)
-	br	%r14
-0:	larl	%r2,sie_reenter			# re-enter with guest id
-	stg	%r2,SPI_PSW+8(0,%r15)
-1:	br	%r14
-
-/*
- * sie64a calling convention:
- * %r2 pointer to sie control block
- * %r3 guest register save area
- */
-	.globl	sie64a
-sie64a:
-	stg	%r3,SP_GREGS(%r15)		# save guest register save area
-	stmg	%r6,%r14,__SF_GPRS(%r15)	# save registers on entry
-	lgr	%r14,%r2			# pointer to sie control block
-	larl	%r5,sie_irq_handler
-	stg	%r2,SP_GPP(%r15)
-	stg	%r5,SP_HOOK(%r15)		# save hook target
-	lmg	%r0,%r13,0(%r3)			# load guest gprs 0-13
-sie_reenter:
-	mvc	__LC_SIE_HOOK(8),SP_HOOK(%r15)
-	SPP	SP_GPP(%r15)			# set guest id
-sie_inst:
-	sie	0(%r14)
-	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
-	SPP	__LC_CMF_HPP			# set host id
-sie_exit:
-	lg	%r14,SP_GREGS(%r15)
-	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
-	lghi	%r2,0
-	lmg	%r6,%r14,__SF_GPRS(%r15)
-	br	%r14
-
-sie_err:
-	xc	__LC_SIE_HOOK(8),__LC_SIE_HOOK
-	SPP	__LC_CMF_HPP			# set host id
-	lg	%r14,SP_GREGS(%r15)
-	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
-	lghi	%r2,-EFAULT
-	lmg	%r6,%r14,__SF_GPRS(%r15)
-	br	%r14
-
-	.section __ex_table,"a"
-	.quad	sie_inst,sie_err
-	.quad	sie_exit,sie_err
-	.quad	sie_reenter,sie_err
-	.previous

arch/s390/kvm/sigp.c

@@ -189,10 +189,8 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
-	if ((copy_from_user(&tmp, (void __user *)
-		(address + vcpu->arch.sie_block->gmsor) , 1)) ||
-	   (copy_from_user(&tmp, (void __user *)(address +
-			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
+	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
+	   copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */
 	}

arch/s390/lib/qrnnd.S

 # S/390 __udiv_qrnnd
 
+#include <linux/linkage.h>
+
 # r2 : &__r
 # r3 : upper half of 64 bit word n
 # r4 : lower half of 64 bit word n
@@ -8,8 +10,7 @@
 # the quotient q is to be returned
 
 	.text
-	.globl __udiv_qrnnd
-__udiv_qrnnd:
+ENTRY(__udiv_qrnnd)
 	st    %r2,24(%r15)	  # store pointer to reminder for later
 	lr    %r0,%r3		  # reload n
 	lr    %r1,%r4

arch/s390/mm/fault.c

@@ -303,9 +303,24 @@ static inline int do_exception(struct pt_regs *regs, int access,
 	flags = FAULT_FLAG_ALLOW_RETRY;
 	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
 		flags |= FAULT_FLAG_WRITE;
-retry:
 	down_read(&mm->mmap_sem);
 
+#ifdef CONFIG_PGSTE
+	if (test_tsk_thread_flag(current, TIF_SIE) && S390_lowcore.gmap) {
+		address = gmap_fault(address,
+				     (struct gmap *) S390_lowcore.gmap);
+		if (address == -EFAULT) {
+			fault = VM_FAULT_BADMAP;
+			goto out_up;
+		}
+		if (address == -ENOMEM) {
+			fault = VM_FAULT_OOM;
+			goto out_up;
+		}
+	}
+#endif
+
+retry:
 	fault = VM_FAULT_BADMAP;
 	vma = find_vma(mm, address);
 	if (!vma)
@@ -356,6 +371,7 @@ static inline int do_exception(struct pt_regs *regs, int access,
 			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
 			 * of starvation. */
 			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			down_read(&mm->mmap_sem);
 			goto retry;
 		}
 	}

arch/s390/mm/hugetlbpage.c

@@ -35,7 +35,7 @@ int arch_prepare_hugepage(struct page *page)
 	if (MACHINE_HAS_HPAGE)
 		return 0;
 
-	ptep = (pte_t *) pte_alloc_one(&init_mm, address);
+	ptep = (pte_t *) pte_alloc_one(&init_mm, addr);
 	if (!ptep)
 		return -ENOMEM;
 

arch/s390/mm/vmem.c

@@ -61,12 +61,12 @@ static inline pmd_t *vmem_pmd_alloc(void)
 	return pmd;
 }
 
-static pte_t __ref *vmem_pte_alloc(void)
+static pte_t __ref *vmem_pte_alloc(unsigned long address)
 {
 	pte_t *pte;
 
 	if (slab_is_available())
-		pte = (pte_t *) page_table_alloc(&init_mm);
+		pte = (pte_t *) page_table_alloc(&init_mm, address);
 	else
 		pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t));
 	if (!pte)
@@ -120,7 +120,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro)
 		}
 #endif
 		if (pmd_none(*pm_dir)) {
-			pt_dir = vmem_pte_alloc();
+			pt_dir = vmem_pte_alloc(address);
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);
@@ -205,7 +205,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 
 		pm_dir = pmd_offset(pu_dir, address);
 		if (pmd_none(*pm_dir)) {
-			pt_dir = vmem_pte_alloc();
+			pt_dir = vmem_pte_alloc(address);
 			if (!pt_dir)
 				goto out;
 			pmd_populate(&init_mm, pm_dir, pt_dir);

drivers/s390/block/dasd_int.h

@@ -382,6 +382,41 @@ struct dasd_path {
 	__u8 npm;
 };
 
+struct dasd_profile_info {
+	/* legacy part of profile data, as in dasd_profile_info_t */
+	unsigned int dasd_io_reqs;	 /* number of requests processed */
+	unsigned int dasd_io_sects;	 /* number of sectors processed */
+	unsigned int dasd_io_secs[32];	 /* histogram of request's sizes */
+	unsigned int dasd_io_times[32];	 /* histogram of requests's times */
+	unsigned int dasd_io_timps[32];	 /* h. of requests's times per sector */
+	unsigned int dasd_io_time1[32];	 /* hist. of time from build to start */
+	unsigned int dasd_io_time2[32];	 /* hist. of time from start to irq */
+	unsigned int dasd_io_time2ps[32]; /* hist. of time from start to irq */
+	unsigned int dasd_io_time3[32];	 /* hist. of time from irq to end */
+	unsigned int dasd_io_nr_req[32]; /* hist. of # of requests in chanq */
+
+	/* new data */
+	struct timespec starttod;	   /* time of start or last reset */
+	unsigned int dasd_io_alias;	   /* requests using an alias */
+	unsigned int dasd_io_tpm;	   /* requests using transport mode */
+	unsigned int dasd_read_reqs;	   /* total number of read  requests */
+	unsigned int dasd_read_sects;	   /* total number read sectors */
+	unsigned int dasd_read_alias;	   /* read request using an alias */
+	unsigned int dasd_read_tpm;	   /* read requests in transport mode */
+	unsigned int dasd_read_secs[32];   /* histogram of request's sizes */
+	unsigned int dasd_read_times[32];  /* histogram of requests's times */
+	unsigned int dasd_read_time1[32];  /* hist. time from build to start */
+	unsigned int dasd_read_time2[32];  /* hist. of time from start to irq */
+	unsigned int dasd_read_time3[32];  /* hist. of time from irq to end */
+	unsigned int dasd_read_nr_req[32]; /* hist. of # of requests in chanq */
+};
+
+struct dasd_profile {
+	struct dentry *dentry;
+	struct dasd_profile_info *data;
+	spinlock_t lock;
+};
+
 struct dasd_device {
 	/* Block device stuff. */
 	struct dasd_block *block;
@@ -431,6 +466,9 @@ struct dasd_device {
 
 	/* default expiration time in s */
 	unsigned long default_expires;
+
+	struct dentry *debugfs_dentry;
+	struct dasd_profile profile;
 };
 
 struct dasd_block {
@@ -453,9 +491,8 @@ struct dasd_block {
 	struct tasklet_struct tasklet;
 	struct timer_list timer;
 
-#ifdef CONFIG_DASD_PROFILE
-	struct dasd_profile_info_t profile;
-#endif
+	struct dentry *debugfs_dentry;
+	struct dasd_profile profile;
 };
 
 
@@ -589,12 +626,13 @@ dasd_check_blocksize(int bsize)
 }
 
 /* externals in dasd.c */
-#define DASD_PROFILE_ON	 1
 #define DASD_PROFILE_OFF	 0
+#define DASD_PROFILE_ON 	 1
+#define DASD_PROFILE_GLOBAL_ONLY 2
 
 extern debug_info_t *dasd_debug_area;
-extern struct dasd_profile_info_t dasd_global_profile;
-extern unsigned int dasd_profile_level;
+extern struct dasd_profile_info dasd_global_profile_data;
+extern unsigned int dasd_global_profile_level;
 extern const struct block_device_operations dasd_device_operations;
 
 extern struct kmem_cache *dasd_page_cache;
@@ -662,6 +700,11 @@ void dasd_device_remove_stop_bits(struct dasd_device *, int);
 
 int dasd_device_is_ro(struct dasd_device *);
 
+void dasd_profile_reset(struct dasd_profile *);
+int dasd_profile_on(struct dasd_profile *);
+void dasd_profile_off(struct dasd_profile *);
+void dasd_global_profile_reset(void);
+char *dasd_get_user_string(const char __user *, size_t);
 
 /* externals in dasd_devmap.c */
 extern int dasd_max_devindex;

drivers/s390/char/Kconfig

@@ -116,9 +116,6 @@ config S390_TAPE
 	  called tape390 and include all selected interfaces and
 	  hardware drivers.
 
-comment "S/390 tape interface support"
-	depends on S390_TAPE
-
 comment "S/390 tape hardware support"
 	depends on S390_TAPE
 

drivers/s390/cio/qdio_thinint.c

@@ -95,9 +95,11 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
 	}
 }
 
-static inline u32 shared_ind_set(void)
+static inline u32 clear_shared_ind(void)
 {
-	return q_indicators[TIQDIO_SHARED_IND].ind;
+	if (!atomic_read(&q_indicators[TIQDIO_SHARED_IND].count))
+		return 0;
+	return xchg(&q_indicators[TIQDIO_SHARED_IND].ind, 0);
 }
 
 /**
@@ -107,7 +109,7 @@ static inline u32 shared_ind_set(void)
  */
 static void tiqdio_thinint_handler(void *alsi, void *data)
 {
-	u32 si_used = shared_ind_set();
+	u32 si_used = clear_shared_ind();
 	struct qdio_q *q;
 
 	last_ai_time = S390_lowcore.int_clock;
@@ -150,13 +152,6 @@ static void tiqdio_thinint_handler(void *alsi, void *data)
 		qperf_inc(q, adapter_int);
 	}
 	rcu_read_unlock();
-
-	/*
-	 * If the shared indicator was used clear it now after all queues
-	 * were processed.
-	 */
-	if (si_used && shared_ind_set())
-		xchg(&q_indicators[TIQDIO_SHARED_IND].ind, 0);
 }
 
 static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset)