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: (48 commits)
  [S390] topology: export cpu topology via proc/sysinfo
  [S390] topology: move topology sysinfo code
  [S390] topology: clean up facility detection
  [S390] cleanup facility list handling
  [S390] enable ARCH_DMA_ADDR_T_64BIT with 64BIT
  [S390] dasd: ignore unsolicited interrupts for DIAG
  [S390] kvm: Enable z196 instruction facilities
  [S390] dasd: fix unsolicited interrupt recognition
  [S390] dasd: fix use after free in dbf
  [S390] kvm: Fix badness at include/asm/mmu_context.h:83
  [S390] cio: fix I/O cancel function
  [S390] topology: change default
  [S390] smp: use correct cpu address in print_cpu_info()
  [S390] remove ieee_instruction_pointer from thread_struct
  [S390] cleanup system call parameter setup
  [S390] correct alignment of cpuid structure
  [S390] cleanup lowcore access from external interrupts
  [S390] cleanup lowcore access from program checks
  [S390] pgtable: move pte_mkhuge() from hugetlb.h to pgtable.h
  [S390] fix SIGBUS handling
  ...

Documentation/kernel-parameters.txt

@@ -2438,7 +2438,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			topology informations if the hardware supports these.
 			The scheduler will make use of these informations and
 			e.g. base its process migration decisions on it.
-			Default is off.
+			Default is on.
 
 	tp720=		[HW,PS2]
 

arch/s390/Kbuild

@@ -0,0 +1,6 @@
+obj-y += kernel/
+obj-y += mm/
+obj-y += crypto/
+obj-y += appldata/
+obj-y += hypfs/
+obj-y += kvm/

arch/s390/Kconfig

@@ -60,6 +60,9 @@ config NO_IOMEM
 config NO_DMA
 	def_bool y
 
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool 64BIT
+
 config GENERIC_LOCKBREAK
 	bool
 	default y
@@ -101,6 +104,7 @@ config S390
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
+	select HAVE_GET_USER_PAGES_FAST
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
@@ -286,6 +290,14 @@ config MARCH_Z10
 	  machines such as the z990, z890, z900, z800, z9-109, z9-ec
 	  and z9-bc.
 
+config MARCH_Z196
+	bool "IBM zEnterprise 196"
+	help
+	  Select this to enable optimizations for IBM zEnterprise 196.
+	  The kernel will be slightly faster but will not work on older
+	  machines such as the z990, z890, z900, z800, z9-109, z9-ec,
+	  z9-bc, z10-ec and z10-bc.
+
 endchoice
 
 config PACK_STACK

arch/s390/Makefile

@@ -40,6 +40,7 @@ cflags-$(CONFIG_MARCH_Z900) += $(call cc-option,-march=z900)
 cflags-$(CONFIG_MARCH_Z990) += $(call cc-option,-march=z990)
 cflags-$(CONFIG_MARCH_Z9_109) += $(call cc-option,-march=z9-109)
 cflags-$(CONFIG_MARCH_Z10) += $(call cc-option,-march=z10)
+cflags-$(CONFIG_MARCH_Z196) += $(call cc-option,-march=z196)
 
 #KBUILD_IMAGE is necessary for make rpm
 KBUILD_IMAGE	:=arch/s390/boot/image
@@ -94,8 +95,8 @@ head-y		:= arch/s390/kernel/head.o
 head-y		+= arch/s390/kernel/$(if $(CONFIG_64BIT),head64.o,head31.o)
 head-y		+= arch/s390/kernel/init_task.o
 
-core-y		+= arch/s390/mm/ arch/s390/kernel/ arch/s390/crypto/ \
-		   arch/s390/appldata/ arch/s390/hypfs/ arch/s390/kvm/
+# See arch/s390/Kbuild for content of core part of the kernel
+core-y		+= arch/s390/
 
 libs-y		+= arch/s390/lib/
 drivers-y	+= drivers/s390/

arch/s390/crypto/crypt_s390.h

@@ -297,7 +297,7 @@ static inline int crypt_s390_func_available(int func)
 	int ret;
 
 	/* check if CPACF facility (bit 17) is available */
-	if (!(stfl() & 1ULL << (31 - 17)))
+	if (!test_facility(17))
 		return 0;
 
 	switch (func & CRYPT_S390_OP_MASK) {

arch/s390/include/asm/ccwdev.h

@@ -91,6 +91,16 @@ struct ccw_device {
 	void (*handler) (struct ccw_device *, unsigned long, struct irb *);
 };
 
+/*
+ * Possible events used by the path_event notifier.
+ */
+#define PE_NONE				0x0
+#define PE_PATH_GONE			0x1 /* A path is no longer available. */
+#define PE_PATH_AVAILABLE		0x2 /* A path has become available and
+					       was successfully verified. */
+#define PE_PATHGROUP_ESTABLISHED	0x4 /* A pathgroup was reset and had
+					       to be established again. */
+
 /*
  * Possible CIO actions triggered by the unit check handler.
  */
@@ -109,6 +119,7 @@ enum uc_todo {
  * @set_online: called when setting device online
  * @set_offline: called when setting device offline
  * @notify: notify driver of device state changes
+ * @path_event: notify driver of channel path events
  * @shutdown: called at device shutdown
  * @prepare: prepare for pm state transition
  * @complete: undo work done in @prepare
@@ -127,6 +138,7 @@ struct ccw_driver {
 	int (*set_online) (struct ccw_device *);
 	int (*set_offline) (struct ccw_device *);
 	int (*notify) (struct ccw_device *, int);
+	void (*path_event) (struct ccw_device *, int *);
 	void (*shutdown) (struct ccw_device *);
 	int (*prepare) (struct ccw_device *);
 	void (*complete) (struct ccw_device *);

arch/s390/include/asm/cpu.h

@@ -20,7 +20,7 @@ struct cpuid
 	unsigned int ident   : 24;
 	unsigned int machine : 16;
 	unsigned int unused  : 16;
-} __packed;
+} __attribute__ ((packed, aligned(8)));
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_S390_CPU_H */

arch/s390/include/asm/hugetlb.h

@@ -37,32 +37,6 @@ static inline int prepare_hugepage_range(struct file *file,
 int arch_prepare_hugepage(struct page *page);
 void arch_release_hugepage(struct page *page);
 
-static inline pte_t pte_mkhuge(pte_t pte)
-{
-	/*
-	 * PROT_NONE needs to be remapped from the pte type to the ste type.
-	 * The HW invalid bit is also different for pte and ste. The pte
-	 * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE
-	 * bit, so we don't have to clear it.
-	 */
-	if (pte_val(pte) & _PAGE_INVALID) {
-		if (pte_val(pte) & _PAGE_SWT)
-			pte_val(pte) |= _HPAGE_TYPE_NONE;
-		pte_val(pte) |= _SEGMENT_ENTRY_INV;
-	}
-	/*
-	 * Clear SW pte bits SWT and SWX, there are no SW bits in a segment
-	 * table entry.
-	 */
-	pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX);
-	/*
-	 * Also set the change-override bit because we don't need dirty bit
-	 * tracking for hugetlbfs pages.
-	 */
-	pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
-	return pte;
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	pte_val(pte) |= _PAGE_RO;

arch/s390/include/asm/lowcore.h

@@ -150,9 +150,10 @@ struct _lowcore {
 	 */
 	__u32	ipib;				/* 0x0e00 */
 	__u32	ipib_checksum;			/* 0x0e04 */
+	__u8	pad_0x0e08[0x0f00-0x0e08];	/* 0x0e08 */
 
-	/* Align to the top 1k of prefix area */
-	__u8	pad_0x0e08[0x1000-0x0e08];	/* 0x0e08 */
+	/* Extended facility list */
+	__u64	stfle_fac_list[32];		/* 0x0f00 */
 } __packed;
 
 #else /* CONFIG_32BIT */
@@ -285,7 +286,11 @@ struct _lowcore {
 	 */
 	__u64	ipib;				/* 0x0e00 */
 	__u32	ipib_checksum;			/* 0x0e08 */
-	__u8	pad_0x0e0c[0x11b8-0x0e0c];	/* 0x0e0c */
+	__u8	pad_0x0e0c[0x0f00-0x0e0c];	/* 0x0e0c */
+
+	/* Extended facility list */
+	__u64	stfle_fac_list[32];		/* 0x0f00 */
+	__u8	pad_0x1000[0x11b8-0x1000];	/* 0x1000 */
 
 	/* 64 bit extparam used for pfault/diag 250: defined by architecture */
 	__u64	ext_params2;			/* 0x11B8 */

arch/s390/include/asm/page.h

@@ -108,9 +108,13 @@ typedef pte_t *pgtable_t;
 #define __pgprot(x)     ((pgprot_t) { (x) } )
 
 static inline void
-page_set_storage_key(unsigned long addr, unsigned int skey)
+page_set_storage_key(unsigned long addr, unsigned int skey, int mapped)
 {
-	asm volatile("sske %0,%1" : : "d" (skey), "a" (addr));
+	if (!mapped)
+		asm volatile(".insn rrf,0xb22b0000,%0,%1,8,0"
+			     : : "d" (skey), "a" (addr));
+	else
+		asm volatile("sske %0,%1" : : "d" (skey), "a" (addr));
 }
 
 static inline unsigned int

arch/s390/include/asm/pgalloc.h

@@ -21,9 +21,11 @@
 
 unsigned long *crst_table_alloc(struct mm_struct *, int);
 void crst_table_free(struct mm_struct *, unsigned long *);
+void crst_table_free_rcu(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *);
 void page_table_free(struct mm_struct *, unsigned long *);
+void page_table_free_rcu(struct mm_struct *, unsigned long *);
 void disable_noexec(struct mm_struct *, struct task_struct *);
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
@@ -176,4 +178,6 @@ static inline void pmd_populate(struct mm_struct *mm,
 #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)
 
+extern void rcu_table_freelist_finish(void);
+
 #endif /* _S390_PGALLOC_H */

arch/s390/include/asm/pgtable.h

@@ -38,6 +38,7 @@
 extern pgd_t swapper_pg_dir[] __attribute__ ((aligned (4096)));
 extern void paging_init(void);
 extern void vmem_map_init(void);
+extern void fault_init(void);
 
 /*
  * The S390 doesn't have any external MMU info: the kernel page
@@ -46,11 +47,27 @@ extern void vmem_map_init(void);
 #define update_mmu_cache(vma, address, ptep)     do { } while (0)
 
 /*
- * ZERO_PAGE is a global shared page that is always zero: used
+ * ZERO_PAGE is a global shared page that is always zero; used
  * for zero-mapped memory areas etc..
  */
-extern char empty_zero_page[PAGE_SIZE];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+extern unsigned long empty_zero_page;
+extern unsigned long zero_page_mask;
+
+#define ZERO_PAGE(vaddr) \
+	(virt_to_page((void *)(empty_zero_page + \
+	 (((unsigned long)(vaddr)) &zero_page_mask))))
+
+#define is_zero_pfn is_zero_pfn
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+}
+
+#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+
 #endif /* !__ASSEMBLY__ */
 
 /*
@@ -300,6 +317,7 @@ extern unsigned long VMALLOC_START;
 
 /* Bits in the segment table entry */
 #define _SEGMENT_ENTRY_ORIGIN	0x7fffffc0UL	/* page table origin	    */
+#define _SEGMENT_ENTRY_RO	0x200	/* page protection bit		    */
 #define _SEGMENT_ENTRY_INV	0x20	/* invalid segment table entry	    */
 #define _SEGMENT_ENTRY_COMMON	0x10	/* common segment bit		    */
 #define _SEGMENT_ENTRY_PTL	0x0f	/* page table length		    */
@@ -572,7 +590,7 @@ static inline void rcp_unlock(pte_t *ptep)
 }
 
 /* forward declaration for SetPageUptodate in page-flags.h*/
-static inline void page_clear_dirty(struct page *page);
+static inline void page_clear_dirty(struct page *page, int mapped);
 #include <linux/page-flags.h>
 
 static inline void ptep_rcp_copy(pte_t *ptep)
@@ -754,6 +772,34 @@ static inline pte_t pte_mkspecial(pte_t pte)
 	return pte;
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	/*
+	 * PROT_NONE needs to be remapped from the pte type to the ste type.
+	 * The HW invalid bit is also different for pte and ste. The pte
+	 * invalid bit happens to be the same as the ste _SEGMENT_ENTRY_LARGE
+	 * bit, so we don't have to clear it.
+	 */
+	if (pte_val(pte) & _PAGE_INVALID) {
+		if (pte_val(pte) & _PAGE_SWT)
+			pte_val(pte) |= _HPAGE_TYPE_NONE;
+		pte_val(pte) |= _SEGMENT_ENTRY_INV;
+	}
+	/*
+	 * Clear SW pte bits SWT and SWX, there are no SW bits in a segment
+	 * table entry.
+	 */
+	pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX);
+	/*
+	 * Also set the change-override bit because we don't need dirty bit
+	 * tracking for hugetlbfs pages.
+	 */
+	pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO);
+	return pte;
+}
+#endif
+
 #ifdef CONFIG_PGSTE
 /*
  * Get (and clear) the user dirty bit for a PTE.
@@ -782,7 +828,7 @@ static inline int kvm_s390_test_and_clear_page_dirty(struct mm_struct *mm,
 	}
 	dirty = test_and_clear_bit_simple(KVM_UD_BIT, pgste);
 	if (skey & _PAGE_CHANGED)
-		page_clear_dirty(page);
+		page_clear_dirty(page, 1);
 	rcp_unlock(ptep);
 	return dirty;
 }
@@ -957,9 +1003,9 @@ static inline int page_test_dirty(struct page *page)
 }
 
 #define __HAVE_ARCH_PAGE_CLEAR_DIRTY
-static inline void page_clear_dirty(struct page *page)
+static inline void page_clear_dirty(struct page *page, int mapped)
 {
-	page_set_storage_key(page_to_phys(page), PAGE_DEFAULT_KEY);
+	page_set_storage_key(page_to_phys(page), PAGE_DEFAULT_KEY, mapped);
 }
 
 /*

arch/s390/include/asm/processor.h

@@ -82,8 +82,6 @@ struct thread_struct {
         unsigned long prot_addr;        /* address of protection-excep.     */
         unsigned int trap_no;
         per_struct per_info;
-	/* Used to give failing instruction back to user for ieee exceptions */
-	unsigned long ieee_instruction_pointer; 
         /* pfault_wait is used to block the process on a pfault event */
 	unsigned long pfault_wait;
 };

arch/s390/include/asm/ptrace.h

@@ -481,8 +481,7 @@ struct user_regs_struct
 	 * watchpoints. This is the way intel does it.
 	 */
 	per_struct per_info;
-	unsigned long ieee_instruction_pointer; 
-	/* Used to give failing instruction back to user for ieee exceptions */
+	unsigned long ieee_instruction_pointer;	/* obsolete, always 0 */
 };
 
 #ifdef __KERNEL__

arch/s390/include/asm/s390_ext.h

@@ -12,7 +12,7 @@
 
 #include <linux/types.h>
 
-typedef void (*ext_int_handler_t)(__u16 code);
+typedef void (*ext_int_handler_t)(unsigned int, unsigned int, unsigned long);
 
 typedef struct ext_int_info_t {
 	struct ext_int_info_t *next;

arch/s390/include/asm/scatterlist.h

@@ -1 +1,3 @@
 #include <asm-generic/scatterlist.h>
+
+#define ARCH_HAS_SG_CHAIN

arch/s390/include/asm/setup.h

@@ -73,6 +73,7 @@ extern unsigned int user_mode;
 #define MACHINE_FLAG_PFMF	(1UL << 11)
 #define MACHINE_FLAG_LPAR	(1UL << 12)
 #define MACHINE_FLAG_SPP	(1UL << 13)
+#define MACHINE_FLAG_TOPOLOGY	(1UL << 14)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -90,6 +91,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_HPAGE	(0)
 #define MACHINE_HAS_PFMF	(0)
 #define MACHINE_HAS_SPP		(0)
+#define MACHINE_HAS_TOPOLOGY	(0)
 #else /* __s390x__ */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -100,6 +102,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_HPAGE	(S390_lowcore.machine_flags & MACHINE_FLAG_HPAGE)
 #define MACHINE_HAS_PFMF	(S390_lowcore.machine_flags & MACHINE_FLAG_PFMF)
 #define MACHINE_HAS_SPP		(S390_lowcore.machine_flags & MACHINE_FLAG_SPP)
+#define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
 #endif /* __s390x__ */
 
 #define ZFCPDUMP_HSA_SIZE	(32UL<<20)

arch/s390/include/asm/syscall.h

@@ -65,8 +65,6 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	if (test_tsk_thread_flag(task, TIF_31BIT))
 		mask = 0xffffffff;
 #endif
-	if (i + n == 6)
-		args[--n] = regs->args[0] & mask;
 	while (n-- > 0)
 		if (i + n > 0)
 			args[n] = regs->gprs[2 + i + n] & mask;
@@ -80,8 +78,6 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 const unsigned long *args)
 {
 	BUG_ON(i + n > 6);
-	if (i + n == 6)
-		regs->args[0] = args[--n];
 	while (n-- > 0)
 		if (i + n > 0)
 			regs->gprs[2 + i + n] = args[n];

arch/s390/include/asm/sysinfo.h

@@ -14,8 +14,13 @@
 #ifndef __ASM_S390_SYSINFO_H
 #define __ASM_S390_SYSINFO_H
 
+#include <asm/bitsperlong.h>
+
 struct sysinfo_1_1_1 {
-	char reserved_0[32];
+	unsigned short :16;
+	unsigned char ccr;
+	unsigned char cai;
+	char reserved_0[28];
 	char manufacturer[16];
 	char type[4];
 	char reserved_1[12];
@@ -104,6 +109,39 @@ struct sysinfo_3_2_2 {
 	char reserved_544[3552];
 };
 
+#define TOPOLOGY_CPU_BITS	64
+#define TOPOLOGY_NR_MAG		6
+
+struct topology_cpu {
+	unsigned char reserved0[4];
+	unsigned char :6;
+	unsigned char pp:2;
+	unsigned char reserved1;
+	unsigned short origin;
+	unsigned long mask[TOPOLOGY_CPU_BITS / BITS_PER_LONG];
+};
+
+struct topology_container {
+	unsigned char reserved[7];
+	unsigned char id;
+};
+
+union topology_entry {
+	unsigned char nl;
+	struct topology_cpu cpu;
+	struct topology_container container;
+};
+
+struct sysinfo_15_1_x {
+	unsigned char reserved0[2];
+	unsigned short length;
+	unsigned char mag[TOPOLOGY_NR_MAG];
+	unsigned char reserved1;
+	unsigned char mnest;
+	unsigned char reserved2[4];
+	union topology_entry tle[0];
+};
+
 static inline int stsi(void *sysinfo, int fc, int sel1, int sel2)
 {
 	register int r0 asm("0") = (fc << 28) | sel1;

arch/s390/include/asm/system.h

@@ -85,14 +85,16 @@ static inline void restore_access_regs(unsigned int *acrs)
 	asm volatile("lam 0,15,%0" : : "Q" (*acrs));
 }
 
-#define switch_to(prev,next,last) do {					     \
-	if (prev == next)						     \
-		break;							     \
-	save_fp_regs(&prev->thread.fp_regs);				     \
-	restore_fp_regs(&next->thread.fp_regs);				     \
-	save_access_regs(&prev->thread.acrs[0]);			     \
-	restore_access_regs(&next->thread.acrs[0]);			     \
-	prev = __switch_to(prev,next);					     \
+#define switch_to(prev,next,last) do {					\
+	if (prev->mm) {							\
+		save_fp_regs(&prev->thread.fp_regs);			\
+		save_access_regs(&prev->thread.acrs[0]);		\
+	}								\
+	if (next->mm) {							\
+		restore_fp_regs(&next->thread.fp_regs);			\
+		restore_access_regs(&next->thread.acrs[0]);		\
+	}								\
+	prev = __switch_to(prev,next);					\
 } while (0)
 
 extern void account_vtime(struct task_struct *, struct task_struct *);
@@ -418,30 +420,21 @@ extern void smp_ctl_clear_bit(int cr, int bit);
 
 #endif /* CONFIG_SMP */
 
-static inline unsigned int stfl(void)
-{
-	asm volatile(
-		"	.insn	s,0xb2b10000,0(0)\n" /* stfl */
-		"0:\n"
-		EX_TABLE(0b,0b));
-	return S390_lowcore.stfl_fac_list;
-}
+#define MAX_FACILITY_BIT (256*8)	/* stfle_fac_list has 256 bytes */
 
-static inline int __stfle(unsigned long long *list, int doublewords)
+/*
+ * The test_facility function uses the bit odering where the MSB is bit 0.
+ * That makes it easier to query facility bits with the bit number as
+ * documented in the Principles of Operation.
+ */
+static inline int test_facility(unsigned long nr)
 {
-	typedef struct { unsigned long long _[doublewords]; } addrtype;
-	register unsigned long __nr asm("0") = doublewords - 1;
+	unsigned char *ptr;
 
-	asm volatile(".insn s,0xb2b00000,%0" /* stfle */
-		     : "=m" (*(addrtype *) list), "+d" (__nr) : : "cc");
-	return __nr + 1;
-}
-
-static inline int stfle(unsigned long long *list, int doublewords)
-{
-	if (!(stfl() & (1UL << 24)))
-		return -EOPNOTSUPP;
-	return __stfle(list, doublewords);
+	if (nr >= MAX_FACILITY_BIT)
+		return 0;
+	ptr = (unsigned char *) &S390_lowcore.stfle_fac_list + (nr >> 3);
+	return (*ptr & (0x80 >> (nr & 7))) != 0;
 }
 
 static inline unsigned short stap(void)