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

* 'for-linus' of git://git390.osdl.marist.edu/pub/scm/linux-2.6: (56 commits)
  [S390] replace lock_cpu_hotplug with get_online_cpus
  [S390] usage of s390dbf: shrink number of debug areas to use.
  [S390] constify function pointer tables.
  [S390] do local_irq_restore while spinning in spin_lock_irqsave.
  [S390] add smp_call_function_mask
  [S390] dasd: fix loop in request expiration handling
  [S390] Unused field / extern declaration in processor.h
  [S390] Remove TOPDIR from Makefile
  [S390] dasd: add hyper PAV support to DASD device driver, part 1
  [S390] single-step cleanup
  [S390] Move NOTES and BUG_TABLE.
  [S390] drivers/s390/: Spelling fixes
  [S390] include/asm-s390/: Spelling fixes
  [S390] arch/s390/: Spelling fixes
  [S390] Use diag308 subcodes 3 and 6 for reboot and dump when possible.
  [S390] vmemmap: allocate struct pages before 1:1 mapping
  [S390] Initialize sclp_ipl_info
  [S390] Allocate and free cpu lowcores and stacks when needed/possible.
  [S390] use LIST_HEAD instead of LIST_HEAD_INIT
  [S390] Load disabled wait psw instead of stopping cpu on halt.
  ...

Documentation/DocBook/s390-drivers.tmpl

@@ -116,6 +116,7 @@
 !Iinclude/asm-s390/ccwdev.h
 !Edrivers/s390/cio/device.c
 !Edrivers/s390/cio/device_ops.c
+!Edrivers/s390/cio/airq.c
     </sect1>
     <sect1 id="cmf">
      <title>The channel-measurement facility</title>

Documentation/cpu-hotplug.txt

@@ -50,7 +50,7 @@ additional_cpus=n (*)	Use this to limit hotpluggable cpus. This option sets
   			cpu_possible_map = cpu_present_map + additional_cpus
 
 (*) Option valid only for following architectures
-- x86_64, ia64, s390
+- x86_64, ia64
 
 ia64 and x86_64 use the number of disabled local apics in ACPI tables MADT
 to determine the number of potentially hot-pluggable cpus. The implementation

Documentation/kernel-parameters.txt

@@ -370,7 +370,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			configured.  Potentially dangerous and should only be
 			used if you are entirely sure of the consequences.
 
-	chandev=	[HW,NET] Generic channel device initialisation
+	ccw_timeout_log [S390]
+			See Documentation/s390/CommonIO for details.
 
 	checkreqprot	[SELINUX] Set initial checkreqprot flag value.
 			Format: { "0" | "1" }
@@ -382,6 +383,12 @@ and is between 256 and 4096 characters. It is defined in the file
 			Value can be changed at runtime via
 				/selinux/checkreqprot.
 
+	cio_ignore=	[S390]
+			See Documentation/s390/CommonIO for details.
+
+	cio_msg=	[S390]
+			See Documentation/s390/CommonIO for details.
+
 	clock=		[BUGS=X86-32, HW] gettimeofday clocksource override.
 			[Deprecated]
 			Forces specified clocksource (if available) to be used

Documentation/s390/CommonIO

@@ -4,6 +4,11 @@ S/390 common I/O-Layer - command line parameters, procfs and debugfs entries
 Command line parameters
 -----------------------
 
+* ccw_timeout_log
+
+  Enable logging of debug information in case of ccw device timeouts.
+
+
 * cio_msg = yes | no
   
   Determines whether information on found devices and sensed device 

arch/s390/Kconfig

@@ -276,9 +276,6 @@ source "kernel/Kconfig.preempt"
 
 source "mm/Kconfig"
 
-config HOLES_IN_ZONE
-	def_bool y
-
 comment "I/O subsystem configuration"
 
 config MACHCHK_WARNING

arch/s390/crypto/Kconfig

-config CRYPTO_SHA1_S390
-	tristate "SHA1 digest algorithm"
-	depends on S390
-	select CRYPTO_ALGAPI
-	help
-	  This is the s390 hardware accelerated implementation of the
-	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
-
-config CRYPTO_SHA256_S390
-	tristate "SHA256 digest algorithm"
-	depends on S390
-	select CRYPTO_ALGAPI
-	help
-	  This is the s390 hardware accelerated implementation of the
-	  SHA256 secure hash standard (DFIPS 180-2).
-
-	  This version of SHA implements a 256 bit hash with 128 bits of
-	  security against collision attacks.
-
-config CRYPTO_DES_S390
-	tristate "DES and Triple DES cipher algorithms"
-	depends on S390
-	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
-	help
-	  This us the s390 hardware accelerated implementation of the
-	  DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3).
-
-config CRYPTO_AES_S390
-	tristate "AES cipher algorithms"
-	depends on S390
-	select CRYPTO_ALGAPI
-	select CRYPTO_BLKCIPHER
-	help
-	  This is the s390 hardware accelerated implementation of the
-	  AES cipher algorithms (FIPS-197). AES uses the Rijndael
-	  algorithm.
-
-	  Rijndael appears to be consistently a very good performer in
-	  both hardware and software across a wide range of computing
-	  environments regardless of its use in feedback or non-feedback
-	  modes. Its key setup time is excellent, and its key agility is
-	  good. Rijndael's very low memory requirements make it very well
-	  suited for restricted-space environments, in which it also
-	  demonstrates excellent performance. Rijndael's operations are
-	  among the easiest to defend against power and timing attacks.
-
-	  On s390 the System z9-109 currently only supports the key size
-	  of 128 bit.
-
-config S390_PRNG
-	tristate "Pseudo random number generator device driver"
-	depends on S390
-	default "m"
-	help
-	  Select this option if you want to use the s390 pseudo random number
-	  generator. The PRNG is part of the cryptographic processor functions
-	  and uses triple-DES to generate secure random numbers like the
-	  ANSI X9.17 standard. The PRNG is usable via the char device
-	  /dev/prandom.

arch/s390/crypto/aes_s390.c

@@ -516,7 +516,7 @@ static int __init aes_init(void)
 	/* z9 109 and z9 BC/EC only support 128 bit key length */
 	if (keylen_flag == AES_KEYLEN_128)
 		printk(KERN_INFO
-		       "aes_s390: hardware acceleration only available for"
+		       "aes_s390: hardware acceleration only available for "
 		       "128 bit keys\n");
 
 	ret = crypto_register_alg(&aes_alg);

arch/s390/crypto/prng.c

@@ -90,7 +90,7 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes,
 	int ret = 0;
 	int tmp;
 
-	/* nbytes can be arbitrary long, we spilt it into chunks */
+	/* nbytes can be arbitrary length, we split it into chunks */
 	while (nbytes) {
 		/* same as in extract_entropy_user in random.c */
 		if (need_resched()) {
@@ -146,7 +146,7 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes,
 	return ret;
 }
 
-static struct file_operations prng_fops = {
+static const struct file_operations prng_fops = {
 	.owner		= THIS_MODULE,
 	.open		= &prng_open,
 	.release	= NULL,

arch/s390/kernel/Makefile

@@ -31,7 +31,3 @@ S390_KEXEC_OBJS := machine_kexec.o crash.o
 S390_KEXEC_OBJS += $(if $(CONFIG_64BIT),relocate_kernel64.o,relocate_kernel.o)
 obj-$(CONFIG_KEXEC) += $(S390_KEXEC_OBJS)
 
-#
-# This is just to get the dependencies...
-#
-binfmt_elf32.o:	$(TOPDIR)/fs/binfmt_elf.c

arch/s390/kernel/early.c

@@ -276,7 +276,7 @@ void __init startup_init(void)
 	create_kernel_nss();
 	sort_main_extable();
 	setup_lowcore_early();
-	sclp_readinfo_early();
+	sclp_read_info_early();
 	sclp_facilities_detect();
 	memsize = sclp_memory_detect();
 #ifndef CONFIG_64BIT

arch/s390/kernel/head64.S

@@ -157,7 +157,7 @@ startup_continue:
 	.long	0xb2b10000		# store facility list
 	tm	0xc8,0x08		# check bit for clearing-by-ASCE
 	bno	0f-.LPG1(%r13)
-	lhi	%r1,2094
+	lhi	%r1,2048
 	lhi	%r2,0
 	.long	0xb98e2001
 	oi	7(%r12),0x80		# set IDTE flag

arch/s390/kernel/process.c

@@ -36,7 +36,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/notifier.h>
-
+#include <linux/utsname.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -182,13 +182,15 @@ void cpu_idle(void)
 
 void show_regs(struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
-
-        printk("CPU:    %d    %s\n", task_thread_info(tsk)->cpu, print_tainted());
-        printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
-	       current->comm, task_pid_nr(current), (void *) tsk,
-	       (void *) tsk->thread.ksp);
-
+	print_modules();
+	printk("CPU: %d %s %s %.*s\n",
+	       task_thread_info(current)->cpu, print_tainted(),
+	       init_utsname()->release,
+	       (int)strcspn(init_utsname()->version, " "),
+	       init_utsname()->version);
+	printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
+	       current->comm, current->pid, current,
+	       (void *) current->thread.ksp);
 	show_registers(regs);
 	/* Show stack backtrace if pt_regs is from kernel mode */
 	if (!(regs->psw.mask & PSW_MASK_PSTATE))

arch/s390/kernel/ptrace.c

@@ -86,13 +86,13 @@ FixPerRegisters(struct task_struct *task)
 		per_info->control_regs.bits.storage_alt_space_ctl = 0;
 }
 
-static void set_single_step(struct task_struct *task)
+void user_enable_single_step(struct task_struct *task)
 {
 	task->thread.per_info.single_step = 1;
 	FixPerRegisters(task);
 }
 
-static void clear_single_step(struct task_struct *task)
+void user_disable_single_step(struct task_struct *task)
 {
 	task->thread.per_info.single_step = 0;
 	FixPerRegisters(task);
@@ -107,7 +107,7 @@ void
 ptrace_disable(struct task_struct *child)
 {
 	/* make sure the single step bit is not set. */
-	clear_single_step(child);
+	user_disable_single_step(child);
 }
 
 #ifndef CONFIG_64BIT
@@ -651,7 +651,7 @@ do_ptrace(struct task_struct *child, long request, long addr, long data)
 			clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 		child->exit_code = data;
 		/* make sure the single step bit is not set. */
-		clear_single_step(child);
+		user_disable_single_step(child);
 		wake_up_process(child);
 		return 0;
 
@@ -665,7 +665,7 @@ do_ptrace(struct task_struct *child, long request, long addr, long data)
 			return 0;
 		child->exit_code = SIGKILL;
 		/* make sure the single step bit is not set. */
-		clear_single_step(child);
+		user_disable_single_step(child);
 		wake_up_process(child);
 		return 0;
 
@@ -675,10 +675,7 @@ do_ptrace(struct task_struct *child, long request, long addr, long data)
 			return -EIO;
 		clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 		child->exit_code = data;
-		if (data)
-			set_tsk_thread_flag(child, TIF_SINGLE_STEP);
-		else
-			set_single_step(child);
+		user_enable_single_step(child);
 		/* give it a chance to run. */
 		wake_up_process(child);
 		return 0;

arch/s390/kernel/setup.c

@@ -125,75 +125,6 @@ void __cpuinit cpu_init(void)
         enter_lazy_tlb(&init_mm, current);
 }
 
-/*
- * VM halt and poweroff setup routines
- */
-char vmhalt_cmd[128] = "";
-char vmpoff_cmd[128] = "";
-static char vmpanic_cmd[128] = "";
-
-static void strncpy_skip_quote(char *dst, char *src, int n)
-{
-        int sx, dx;
-
-        dx = 0;
-        for (sx = 0; src[sx] != 0; sx++) {
-                if (src[sx] == '"') continue;
-                dst[dx++] = src[sx];
-                if (dx >= n) break;
-        }
-}
-
-static int __init vmhalt_setup(char *str)
-{
-        strncpy_skip_quote(vmhalt_cmd, str, 127);
-        vmhalt_cmd[127] = 0;
-        return 1;
-}
-
-__setup("vmhalt=", vmhalt_setup);
-
-static int __init vmpoff_setup(char *str)
-{
-        strncpy_skip_quote(vmpoff_cmd, str, 127);
-        vmpoff_cmd[127] = 0;
-        return 1;
-}
-
-__setup("vmpoff=", vmpoff_setup);
-
-static int vmpanic_notify(struct notifier_block *self, unsigned long event,
-			  void *data)
-{
-	if (MACHINE_IS_VM && strlen(vmpanic_cmd) > 0)
-		cpcmd(vmpanic_cmd, NULL, 0, NULL);
-
-	return NOTIFY_OK;
-}
-
-#define PANIC_PRI_VMPANIC	0
-
-static struct notifier_block vmpanic_nb = {
-	.notifier_call = vmpanic_notify,
-	.priority = PANIC_PRI_VMPANIC
-};
-
-static int __init vmpanic_setup(char *str)
-{
-	static int register_done __initdata = 0;
-
-	strncpy_skip_quote(vmpanic_cmd, str, 127);
-	vmpanic_cmd[127] = 0;
-	if (!register_done) {
-		register_done = 1;
-		atomic_notifier_chain_register(&panic_notifier_list,
-					       &vmpanic_nb);
-	}
-	return 1;
-}
-
-__setup("vmpanic=", vmpanic_setup);
-
 /*
  * condev= and conmode= setup parameter.
  */
@@ -308,38 +239,6 @@ static void __init setup_zfcpdump(unsigned int console_devno)
 static inline void setup_zfcpdump(unsigned int console_devno) {}
 #endif /* CONFIG_ZFCPDUMP */
 
-#ifdef CONFIG_SMP
-void (*_machine_restart)(char *command) = machine_restart_smp;
-void (*_machine_halt)(void) = machine_halt_smp;
-void (*_machine_power_off)(void) = machine_power_off_smp;
-#else
-/*
- * Reboot, halt and power_off routines for non SMP.
- */
-static void do_machine_restart_nonsmp(char * __unused)
-{
-	do_reipl();
-}
-
-static void do_machine_halt_nonsmp(void)
-{
-        if (MACHINE_IS_VM && strlen(vmhalt_cmd) > 0)
-		__cpcmd(vmhalt_cmd, NULL, 0, NULL);
-        signal_processor(smp_processor_id(), sigp_stop_and_store_status);
-}
-
-static void do_machine_power_off_nonsmp(void)
-{
-        if (MACHINE_IS_VM && strlen(vmpoff_cmd) > 0)
-		__cpcmd(vmpoff_cmd, NULL, 0, NULL);
-        signal_processor(smp_processor_id(), sigp_stop_and_store_status);
-}
-
-void (*_machine_restart)(char *command) = do_machine_restart_nonsmp;
-void (*_machine_halt)(void) = do_machine_halt_nonsmp;
-void (*_machine_power_off)(void) = do_machine_power_off_nonsmp;
-#endif
-
  /*
  * Reboot, halt and power_off stubs. They just call _machine_restart,
  * _machine_halt or _machine_power_off. 
@@ -559,7 +458,9 @@ setup_resources(void)
 	data_resource.start = (unsigned long) &_etext;
 	data_resource.end = (unsigned long) &_edata - 1;
 
-	for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) {
+	for (i = 0; i < MEMORY_CHUNKS; i++) {
+		if (!memory_chunk[i].size)
+			continue;
 		res = alloc_bootmem_low(sizeof(struct resource));
 		res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
 		switch (memory_chunk[i].type) {
@@ -617,7 +518,7 @@ EXPORT_SYMBOL_GPL(real_memory_size);
 static void __init setup_memory_end(void)
 {
 	unsigned long memory_size;
-	unsigned long max_mem, max_phys;
+	unsigned long max_mem;
 	int i;
 
 #if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)
@@ -625,10 +526,31 @@ static void __init setup_memory_end(void)
 		memory_end = ZFCPDUMP_HSA_SIZE;
 #endif
 	memory_size = 0;
-	max_phys = VMALLOC_END_INIT - VMALLOC_MIN_SIZE;
 	memory_end &= PAGE_MASK;
 
-	max_mem = memory_end ? min(max_phys, memory_end) : max_phys;
+	max_mem = memory_end ? min(VMALLOC_START, memory_end) : VMALLOC_START;
+	memory_end = min(max_mem, memory_end);
+
+	/*
+	 * Make sure all chunks are MAX_ORDER aligned so we don't need the
+	 * extra checks that HOLES_IN_ZONE would require.
+	 */
+	for (i = 0; i < MEMORY_CHUNKS; i++) {
+		unsigned long start, end;
+		struct mem_chunk *chunk;
+		unsigned long align;
+
+		chunk = &memory_chunk[i];
+		align = 1UL << (MAX_ORDER + PAGE_SHIFT - 1);
+		start = (chunk->addr + align - 1) & ~(align - 1);
+		end = (chunk->addr + chunk->size) & ~(align - 1);
+		if (start >= end)
+			memset(chunk, 0, sizeof(*chunk));
+		else {
+			chunk->addr = start;
+			chunk->size = end - start;
+		}
+	}
 
 	for (i = 0; i < MEMORY_CHUNKS; i++) {
 		struct mem_chunk *chunk = &memory_chunk[i];
@@ -890,7 +812,7 @@ setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
-	setup_ipl_info();
+	setup_ipl();
 	setup_memory_end();
 	setup_addressing_mode();
 	setup_memory();
@@ -899,7 +821,6 @@ setup_arch(char **cmdline_p)
 
         cpu_init();
         __cpu_logical_map[0] = S390_lowcore.cpu_data.cpu_addr;
-	smp_setup_cpu_possible_map();
 
 	/*
 	 * Setup capabilities (ELF_HWCAP & ELF_PLATFORM).
@@ -920,7 +841,7 @@ setup_arch(char **cmdline_p)
 
 void __cpuinit print_cpu_info(struct cpuinfo_S390 *cpuinfo)
 {
-   printk("cpu %d "
+   printk(KERN_INFO "cpu %d "
 #ifdef CONFIG_SMP
            "phys_idx=%d "
 #endif
@@ -996,7 +917,7 @@ static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 static void c_stop(struct seq_file *m, void *v)
 {
 }
-struct seq_operations cpuinfo_op = {
+const struct seq_operations cpuinfo_op = {
 	.start	= c_start,
 	.next	= c_next,
 	.stop	= c_stop,

arch/s390/kernel/signal.c

@@ -471,6 +471,7 @@ void do_signal(struct pt_regs *regs)
 
 	if (signr > 0) {
 		/* Whee!  Actually deliver the signal.  */
+		int ret;
 #ifdef CONFIG_COMPAT
 		if (test_thread_flag(TIF_31BIT)) {
 			extern int handle_signal32(unsigned long sig,
@@ -478,15 +479,12 @@ void do_signal(struct pt_regs *regs)
 						   siginfo_t *info,
 						   sigset_t *oldset,
 						   struct pt_regs *regs);
-			if (handle_signal32(
-				    signr, &ka, &info, oldset, regs) == 0) {
-				if (test_thread_flag(TIF_RESTORE_SIGMASK))
-					clear_thread_flag(TIF_RESTORE_SIGMASK);
-			}
-			return;
+			ret = handle_signal32(signr, &ka, &info, oldset, regs);
 	        }
+		else
 #endif
-		if (handle_signal(signr, &ka, &info, oldset, regs) == 0) {
+			ret = handle_signal(signr, &ka, &info, oldset, regs);
+		if (!ret) {
 			/*
 			 * A signal was successfully delivered; the saved
 			 * sigmask will have been stored in the signal frame,
@@ -495,6 +493,14 @@ void do_signal(struct pt_regs *regs)
 			 */
 			if (test_thread_flag(TIF_RESTORE_SIGMASK))
 				clear_thread_flag(TIF_RESTORE_SIGMASK);
+
+			/*
+			 * If we would have taken a single-step trap
+			 * for a normal instruction, act like we took
+			 * one for the handler setup.
+			 */
+			if (current->thread.per_info.single_step)
+				set_thread_flag(TIF_SINGLE_STEP);
 		}
 		return;
 	}

arch/s390/kernel/smp.c

@@ -42,6 +42,7 @@
 #include <asm/tlbflush.h>
 #include <asm/timer.h>
 #include <asm/lowcore.h>
+#include <asm/sclp.h>
 #include <asm/cpu.h>
 
 /*
@@ -53,11 +54,27 @@ EXPORT_SYMBOL(lowcore_ptr);
 cpumask_t cpu_online_map = CPU_MASK_NONE;
 EXPORT_SYMBOL(cpu_online_map);
 
-cpumask_t cpu_possible_map = CPU_MASK_NONE;
+cpumask_t cpu_possible_map = CPU_MASK_ALL;
 EXPORT_SYMBOL(cpu_possible_map);
 
 static struct task_struct *current_set[NR_CPUS];
 
+static u8 smp_cpu_type;
+static int smp_use_sigp_detection;
+
+enum s390_cpu_state {
+	CPU_STATE_STANDBY,
+	CPU_STATE_CONFIGURED,
+};
+
+#ifdef CONFIG_HOTPLUG_CPU
+static DEFINE_MUTEX(smp_cpu_state_mutex);
+#endif
+static int smp_cpu_state[NR_CPUS];
+
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
+
 static void smp_ext_bitcall(int, ec_bit_sig);
 
 /*
@@ -193,6 +210,33 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
+/**
+ * smp_call_function_mask(): Run a function on a set of other CPUs.
+ * @mask: The set of cpus to run on.  Must not include the current cpu.
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ *
+ * Returns 0 on success, else a negative status code.
+ *
+ * If @wait is true, then returns once @func has returned; otherwise
+ * it returns just before the target cpu calls @func.
+ *
+ * You must not call this function with disabled interrupts or from a
+ * hardware interrupt handler or from a bottom half handler.
+ */
+int
+smp_call_function_mask(cpumask_t mask,
+			void (*func)(void *), void *info,
+			int wait)
+{
+	preempt_disable();
+	__smp_call_function_map(func, info, 0, wait, mask);
+	preempt_enable();
+	return 0;
+}
+EXPORT_SYMBOL(smp_call_function_mask);
+
 void smp_send_stop(void)
 {
 	int cpu, rc;
@@ -216,33 +260,6 @@ void smp_send_stop(void)
 	}
 }
 
-/*
- * Reboot, halt and power_off routines for SMP.
- */
-void machine_restart_smp(char *__unused)
-{
-	smp_send_stop();
-	do_reipl();
-}
-
-void machine_halt_smp(void)
-{
-	smp_send_stop();
-	if (MACHINE_IS_VM && strlen(vmhalt_cmd) > 0)
-		__cpcmd(vmhalt_cmd, NULL, 0, NULL);
-	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
-	for (;;);
-}
-
-void machine_power_off_smp(void)
-{
-	smp_send_stop();
-	if (MACHINE_IS_VM && strlen(vmpoff_cmd) > 0)
-		__cpcmd(vmpoff_cmd, NULL, 0, NULL);
-	signal_processor(smp_processor_id(), sigp_stop_and_store_status);
-	for (;;);
-}
-
 /*
  * This is the main routine where commands issued by other
  * cpus are handled.
@@ -355,6 +372,13 @@ void smp_ctl_clear_bit(int cr, int bit)
 }
 EXPORT_SYMBOL(smp_ctl_clear_bit);
 
+/*
+ * In early ipl state a temp. logically cpu number is needed, so the sigp
+ * functions can be used to sense other cpus. Since NR_CPUS is >= 2 on
+ * CONFIG_SMP and the ipl cpu is logical cpu 0, it must be 1.
+ */
+#define CPU_INIT_NO	1
+
 #if defined(CONFIG_ZFCPDUMP) || defined(CONFIG_ZFCPDUMP_MODULE)
 
 /*
@@ -375,9 +399,10 @@ static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu)
 		       "kernel was compiled with NR_CPUS=%i\n", cpu, NR_CPUS);
 		return;
 	}
-	zfcpdump_save_areas[cpu] = alloc_bootmem(sizeof(union save_area));
-	__cpu_logical_map[1] = (__u16) phy_cpu;
-	while (signal_processor(1, sigp_stop_and_store_status) == sigp_busy)
+	zfcpdump_save_areas[cpu] = kmalloc(sizeof(union save_area), GFP_KERNEL);
+	__cpu_logical_map[CPU_INIT_NO] = (__u16) phy_cpu;
+	while (signal_processor(CPU_INIT_NO, sigp_stop_and_store_status) ==
+	       sigp_busy)
 		cpu_relax();
 	memcpy(zfcpdump_save_areas[cpu],
 	       (void *)(unsigned long) store_prefix() + SAVE_AREA_BASE,
@@ -397,32 +422,155 @@ static inline void smp_get_save_area(unsigned int cpu, unsigned int phy_cpu) { }
 
 #endif /* CONFIG_ZFCPDUMP || CONFIG_ZFCPDUMP_MODULE */
 
-/*
- * Lets check how many CPUs we have.
- */
-static unsigned int __init smp_count_cpus(void)
+static int cpu_stopped(int cpu)
 {
-	unsigned int cpu, num_cpus;
-	__u16 boot_cpu_addr;
+	__u32 status;
 
-	/*
-	 * cpu 0 is the boot cpu. See smp_prepare_boot_cpu.
-	 */
+	/* Check for stopped state */
+	if (signal_processor_ps(&status, 0, cpu, sigp_sense) ==
+	    sigp_status_stored) {
+		if (status & 0x40)
+			return 1;
+	}
+	return 0;
+}
+
+static int cpu_known(int cpu_id)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		if (__cpu_logical_map[cpu] == cpu_id)
+			return 1;
+	}
+	return 0;
+}
+
+static int smp_rescan_cpus_sigp(cpumask_t avail)
+{
+	int cpu_id, logical_cpu;
+
+	logical_cpu = first_cpu(avail);
+	if (logical_cpu == NR_CPUS)
+		return 0;
+	for (cpu_id = 0; cpu_id <= 65535; cpu_id++) {
+		if (cpu_known(cpu_id))
+			continue;
+		__cpu_logical_map[logical_cpu] = cpu_id;
+		if (!cpu_stopped(logical_cpu))
+			continue;
+		cpu_set(logical_cpu, cpu_present_map);
+		smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
+		logical_cpu = next_cpu(logical_cpu, avail);
+		if (logical_cpu == NR_CPUS)
+			break;
+	}
+	return 0;
+}
+
+static int smp_rescan_cpus_sclp(cpumask_t avail)
+{
+	struct sclp_cpu_info *info;
+	int cpu_id, logical_cpu, cpu;
+	int rc;
+
+	logical_cpu = first_cpu(avail);
+	if (logical_cpu == NR_CPUS)
+		return 0;
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+	rc = sclp_get_cpu_info(info);
+	if (rc)
+		goto out;
+	for (cpu = 0; cpu < info->combined; cpu++) {
+		if (info->has_cpu_type && info->cpu[cpu].type != smp_cpu_type)
+			continue;
+		cpu_id = info->cpu[cpu].address;
+		if (cpu_known(cpu_id))
+			continue;
+		__cpu_logical_map[logical_cpu] = cpu_id;
+		cpu_set(logical_cpu, cpu_present_map);
+		if (cpu >= info->configured)
+			smp_cpu_state[logical_cpu] = CPU_STATE_STANDBY;
+		else
+			smp_cpu_state[logical_cpu] = CPU_STATE_CONFIGURED;
+		logical_cpu = next_cpu(logical_cpu, avail);
+		if (logical_cpu == NR_CPUS)
+			break;
+	}
+out:
+	kfree(info);
+	return rc;
+}
+
+static int smp_rescan_cpus(void)
+{
+	cpumask_t avail;
+
+	cpus_xor(avail, cpu_possible_map, cpu_present_map);
+	if (smp_use_sigp_detection)
+		return smp_rescan_cpus_sigp(avail);
+	else
+		return smp_rescan_cpus_sclp(avail);
+}
+
+static void __init smp_detect_cpus(void)
+{
+	unsigned int cpu, c_cpus, s_cpus;
+	struct sclp_cpu_info *info;
+	u16 boot_cpu_addr, cpu_addr;
+
+	c_cpus = 1;
+	s_cpus = 0;
 	boot_cpu_addr = S390_lowcore.cpu_data.cpu_addr;
-	current_thread_info()->cpu = 0;
-	num_cpus = 1;
-	for (cpu = 0; cpu <= 65535; cpu++) {
-		if ((__u16) cpu == boot_cpu_addr)
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		panic("smp_detect_cpus failed to allocate memory\n");
+	/* Use sigp detection algorithm if sclp doesn't work. */
+	if (sclp_get_cpu_info(info)) {
+		smp_use_sigp_detection = 1;
+		for (cpu = 0; cpu <= 65535; cpu++) {
+			if (cpu == boot_cpu_addr)
+				continue;
+			__cpu_logical_map[CPU_INIT_NO] = cpu;
+			if (!cpu_stopped(CPU_INIT_NO))
+				continue;
+			smp_get_save_area(c_cpus, cpu);
+			c_cpus++;
+		}
+		goto out;
+	}
+
+	if (info->has_cpu_type) {
+		for (cpu = 0; cpu < info->combined; cpu++) {
+			if (info->cpu[cpu].address == boot_cpu_addr) {
+				smp_cpu_type = info->cpu[cpu].type;
+				break;
+			}
+		}
+	}
+
+	for (cpu = 0; cpu < info->combined; cpu++) {
+		if (info->has_cpu_type && info->cpu[cpu].type != smp_cpu_type)
+			continue;
+		cpu_addr = info->cpu[cpu].address;
+		if (cpu_addr == boot_cpu_addr)
 			continue;
-		__cpu_logical_map[1] = (__u16) cpu;
-		if (signal_processor(1, sigp_sense) == sigp_not_operational)
+		__cpu_logical_map[CPU_INIT_NO] = cpu_addr;
+		if (!cpu_stopped(CPU_INIT_NO)) {
+			s_cpus++;
 			continue;
-		smp_get_save_area(num_cpus, cpu);
-		num_cpus++;
+		}
+		smp_get_save_area(c_cpus, cpu_addr);
+		c_cpus++;
 	}
-	printk("Detected %d CPU's\n", (int) num_cpus);
-	printk("Boot cpu address %2X\n", boot_cpu_addr);
-	return num_cpus;
+out:
+	kfree(info);
+	printk(KERN_INFO "CPUs: %d configured, %d standby\n", c_cpus, s_cpus);
+	get_online_cpus();
+	smp_rescan_cpus();
+	put_online_cpus();
 }
 
 /*
@@ -453,8 +601,6 @@ int __cpuinit start_secondary(void *cpuvoid)
 	return 0;
 }
 
-DEFINE_PER_CPU(struct s390_idle_data, s390_idle);
-
 static void __init smp_create_idle(unsigned int cpu)
 {
 	struct task_struct *p;
@@ -470,37 +616,82 @@ static void __init smp_create_idle(unsigned int cpu)
 	spin_lock_init(&(&per_cpu(s390_idle, cpu))->lock);
 }
 
-static int cpu_stopped(int cpu)
+static int __cpuinit smp_alloc_lowcore(int cpu)
 {
-	__u32 status;
+	unsigned long async_stack, panic_stack;
+	struct _lowcore *lowcore;
+	int lc_order;
+
+	lc_order = sizeof(long) == 8 ? 1 : 0;
+	lowcore = (void *) __get_free_pages(GFP_KERNEL | GFP_DMA, lc_order);
+	if (!lowcore)
+		return -ENOMEM;
+	async_stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
+	if (!async_stack)
+		goto out_async_stack;
+	panic_stack = __get_free_page(GFP_KERNEL);
+	if (!panic_stack)
+		goto out_panic_stack;
+
+	*lowcore = S390_lowcore;
+	lowcore->async_stack = async_stack + ASYNC_SIZE;
+	lowcore->panic_stack = panic_stack + PAGE_SIZE;
 
-	/* Check for stopped state */
-	if (signal_processor_ps(&status, 0, cpu, sigp_sense) ==
-	    sigp_status_stored) {
-		if (status & 0x40)
-			return 1;
+#ifndef CONFIG_64BIT
+	if (MACHINE_HAS_IEEE) {
+		unsigned long save_area;
+
+		save_area = get_zeroed_page(GFP_KERNEL);
+		if (!save_area)
+			goto out_save_area;
+		lowcore->extended_save_area_addr = (u32) save_area;
 	}
+#endif
+	lowcore_ptr[cpu] = lowcore;
 	return 0;
+
+#ifndef CONFIG_64BIT
+out_save_area:
+	free_page(panic_stack);
+#endif
+out_panic_stack:
+	free_pages(async_stack, ASYNC_ORDER);
+out_async_stack:
+	free_pages((unsigned long) lowcore, lc_order);
+	return -ENOMEM;
 }
 
-/* Upping and downing of CPUs */
+#ifdef CONFIG_HOTPLUG_CPU
+static void smp_free_lowcore(int cpu)
+{
+	struct _lowcore *lowcore;
+	int lc_order;
+
+	lc_order = sizeof(long) == 8 ? 1 : 0;
+	lowcore = lowcore_ptr[cpu];
+#ifndef CONFIG_64BIT
+	if (MACHINE_HAS_IEEE)
+		free_page((unsigned long) lowcore->extended_save_area_addr);
+#endif
+	free_page(lowcore->panic_stack - PAGE_SIZE);
+	free_pages(lowcore->async_stack - ASYNC_SIZE, ASYNC_ORDER);
+	free_pages((unsigned long) lowcore, lc_order);
+	lowcore_ptr[cpu] = NULL;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
 
-int __cpu_up(unsigned int cpu)
+/* Upping and downing of CPUs */
+int __cpuinit __cpu_up(unsigned int cpu)
 {
 	struct task_struct *idle;
 	struct _lowcore *cpu_lowcore;
 	struct stack_frame *sf;
 	sigp_ccode ccode;
-	int curr_cpu;
 
-	for (curr_cpu = 0; curr_cpu <= 65535; curr_cpu++) {
-		__cpu_logical_map[cpu] = (__u16) curr_cpu;
-		if (cpu_stopped(cpu))
-			break;
-	}
-
-	if (!cpu_stopped(cpu))
-		return -ENODEV;
+	if (smp_cpu_state[cpu] != CPU_STATE_CONFIGURED)
+		return -EIO;
+	if (smp_alloc_lowcore(cpu))
+		return -ENOMEM;
 
 	ccode = signal_processor_p((__u32)(unsigned long)(lowcore_ptr[cpu]),
 				   cpu, sigp_set_prefix);
@@ -515,6 +706,7 @@ int __cpu_up(unsigned int cpu)
 	cpu_lowcore = lowcore_ptr[cpu];
 	cpu_lowcore->kernel_stack = (unsigned long)
 		task_stack_page(idle) + THREAD_SIZE;
+	cpu_lowcore->thread_info = (unsigned long) task_thread_info(idle);
 	sf = (struct stack_frame *) (cpu_lowcore->kernel_stack
 				     - sizeof(struct pt_regs)
 				     - sizeof(struct stack_frame));
@@ -528,6 +720,8 @@ int __cpu_up(unsigned int cpu)
 	cpu_lowcore->percpu_offset = __per_cpu_offset[cpu];
 	cpu_lowcore->current_task = (unsigned long) idle;
 	cpu_lowcore->cpu_data.cpu_nr = cpu;
+	cpu_lowcore->softirq_pending = 0;
+	cpu_lowcore->ext_call_fast = 0;
 	eieio();
 
 	while (signal_processor(cpu, sigp_restart) == sigp_busy)
@@ -538,44 +732,20 @@ int __cpu_up(unsigned int cpu)
 	return 0;
 }
 
-static unsigned int __initdata additional_cpus;
-static unsigned int __initdata possible_cpus;
-
-void __init smp_setup_cpu_possible_map(void)
+static int __init setup_possible_cpus(char *s)
 {
-	unsigned int phy_cpus, pos_cpus, cpu;
-
-	phy_cpus = smp_count_cpus();
-	pos_cpus = min(phy_cpus + additional_cpus, (unsigned int) NR_CPUS);
-
-	if (possible_cpus)
-		pos_cpus = min(possible_cpus, (unsigned int) NR_CPUS);
+	int pcpus, cpu;
 
-	for (cpu = 0; cpu < pos_cpus; cpu++)
+	pcpus = simple_strtoul(s, NULL, 0);
+	cpu_possible_map = cpumask_of_cpu(0);
+	for (cpu = 1; cpu < pcpus && cpu < NR_CPUS; cpu++)
 		cpu_set(cpu, cpu_possible_map);
-
-	phy_cpus = min(phy_cpus, pos_cpus);
-
-	for (cpu = 0; cpu < phy_cpus; cpu++)
-		cpu_set(cpu, cpu_present_map);
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-static int __init setup_additional_cpus(char *s)
-{
-	additional_cpus = simple_strtoul(s, NULL, 0);
-	return 0;
-}
-early_param("additional_cpus", setup_additional_cpus);
-
-static int __init setup_possible_cpus(char *s)
-{
-	possible_cpus = simple_strtoul(s, NULL, 0);
 	return 0;
 }
 early_param("possible_cpus", setup_possible_cpus);
 
+#ifdef CONFIG_HOTPLUG_CPU
+
 int __cpu_disable(void)
 {
 	struct ec_creg_mask_parms cr_parms;
@@ -612,7 +782,8 @@ void __cpu_die(unsigned int cpu)
 	/* Wait until target cpu is down */
 	while (!smp_cpu_not_running(cpu))
 		cpu_relax();
-	printk("Processor %d spun down\n", cpu);
+	smp_free_lowcore(cpu);
+	printk(KERN_INFO "Processor %d spun down\n", cpu);
 }
 
 void cpu_die(void)
@@ -625,49 +796,19 @@ void cpu_die(void)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-/*
- *	Cycle through the processors and setup structures.
- */
-
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	unsigned long stack;
 	unsigned int cpu;
-	int i;
+
+	smp_detect_cpus();
 
 	/* request the 0x1201 emergency signal external interrupt */
 	if (register_external_interrupt(0x1201, do_ext_call_interrupt) != 0)
 		panic("Couldn't request external interrupt 0x1201");
 	memset(lowcore_ptr, 0, sizeof(lowcore_ptr));
-	/*
-	 *  Initialize prefix pages and stacks for all possible cpus
-	 */
 	print_cpu_info(&S390_lowcore.cpu_data);
+	smp_alloc_lowcore(smp_processor_id());
 
-	for_each_possible_cpu(i) {
-		lowcore_ptr[i] = (struct _lowcore *)
-			__get_free_pages(GFP_KERNEL | GFP_DMA,
-					 sizeof(void*) == 8 ? 1 : 0);
-		stack = __get_free_pages(GFP_KERNEL, ASYNC_ORDER);
-		if (!lowcore_ptr[i] || !stack)
-			panic("smp_boot_cpus failed to allocate memory\n");
-
-		*(lowcore_ptr[i]) = S390_lowcore;
-		lowcore_ptr[i]->async_stack = stack + ASYNC_SIZE;
-		stack = __get_free_pages(GFP_KERNEL, 0);
-		if (!stack)
-			panic("smp_boot_cpus failed to allocate memory\n");
-		lowcore_ptr[i]->panic_stack = stack + PAGE_SIZE;
-#ifndef CONFIG_64BIT
-		if (MACHINE_HAS_IEEE) {
-			lowcore_ptr[i]->extended_save_area_addr =
-				(__u32) __get_free_pages(GFP_KERNEL, 0);
-			if (!lowcore_ptr[i]->extended_save_area_addr)
-				panic("smp_boot_cpus failed to "
-				      "allocate memory\n");
-		}
-#endif
-	}
 #ifndef CONFIG_64BIT
 	if (MACHINE_HAS_IEEE)
 		ctl_set_bit(14, 29); /* enable extended save area */
@@ -683,15 +824,17 @@ void __init smp_prepare_boot_cpu(void)
 {
 	BUG_ON(smp_processor_id() != 0);
 
+	current_thread_info()->cpu = 0;
+	cpu_set(0, cpu_present_map);
 	cpu_set(0, cpu_online_map);
 	S390_lowcore.percpu_offset = __per_cpu_offset[0];
 	current_set[0] = current;
+	smp_cpu_state[0] = CPU_STATE_CONFIGURED;
 	spin_lock_init(&(&__get_cpu_var(s390_idle))->lock);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	cpu_present_map = cpu_possible_map;
 }
 
 /*
@@ -705,7 +848,79 @@ int setup_profiling_timer(unsigned int multiplier)
 	return 0;
 }
 
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
+#ifdef CONFIG_HOTPLUG_CPU
+static ssize_t cpu_configure_show(struct sys_device *dev, char *buf)
+{
+	ssize_t count;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	count = sprintf(buf, "%d\n", smp_cpu_state[dev->id]);
+	mutex_unlock(&smp_cpu_state_mutex);
+	return count;
+}
+
+static ssize_t cpu_configure_store(struct sys_device *dev, const char *buf,
+				   size_t count)
+{
+	int cpu = dev->id;
+	int val, rc;
+	char delim;
+
+	if (sscanf(buf, "%d %c", &val, &delim) != 1)
+		return -EINVAL;
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	get_online_cpus();
+	rc = -EBUSY;
+	if (cpu_online(cpu))
+		goto out;
+	rc = 0;
+	switch (val) {
+	case 0:
+		if (smp_cpu_state[cpu] == CPU_STATE_CONFIGURED) {
+			rc = sclp_cpu_deconfigure(__cpu_logical_map[cpu]);
+			if (!rc)
+				smp_cpu_state[cpu] = CPU_STATE_STANDBY;
+		}
+		break;
+	case 1:
+		if (smp_cpu_state[cpu] == CPU_STATE_STANDBY) {
+			rc = sclp_cpu_configure(__cpu_logical_map[cpu]);
+			if (!rc)
+				smp_cpu_state[cpu] = CPU_STATE_CONFIGURED;
+		}
+		break;
+	default:
+		break;
+	}
+out:
+	put_online_cpus();
+	mutex_unlock(&smp_cpu_state_mutex);
+	return rc ? rc : count;
+}
+static SYSDEV_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static ssize_t show_cpu_address(struct sys_device *dev, char *buf)
+{
+	return sprintf(buf, "%d\n", __cpu_logical_map[dev->id]);
+}
+static SYSDEV_ATTR(address, 0444, show_cpu_address, NULL);
+
+
+static struct attribute *cpu_common_attrs[] = {
+#ifdef CONFIG_HOTPLUG_CPU
+	&attr_configure.attr,
+#endif
+	&attr_address.attr,
+	NULL,
+};
+
+static struct attribute_group cpu_common_attr_group = {
+	.attrs = cpu_common_attrs,
+};
 
 static ssize_t show_capability(struct sys_device *dev, char *buf)
 {
@@ -750,15 +965,15 @@ static ssize_t show_idle_time(struct sys_device *dev, char *buf)
 }
 static SYSDEV_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
-static struct attribute *cpu_attrs[] = {
+static struct attribute *cpu_online_attrs[] = {
 	&attr_capability.attr,
 	&attr_idle_count.attr,
 	&attr_idle_time_us.attr,
 	NULL,
 };
 
-static struct attribute_group cpu_attr_group = {
-	.attrs = cpu_attrs,
+static struct attribute_group cpu_online_attr_group = {
+	.attrs = cpu_online_attrs,
 };
 
 static int __cpuinit smp_cpu_notify(struct notifier_block *self,
@@ -778,12 +993,12 @@ static int __cpuinit smp_cpu_notify(struct notifier_block *self,
 		idle->idle_time = 0;
 		idle->idle_count = 0;
 		spin_unlock_irq(&idle->lock);
-		if (sysfs_create_group(&s->kobj, &cpu_attr_group))
+		if (sysfs_create_group(&s->kobj, &cpu_online_attr_group))
 			return NOTIFY_BAD;
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		sysfs_remove_group(&s->kobj, &cpu_attr_group);
+		sysfs_remove_group(&s->kobj, &cpu_online_attr_group);
 		break;
 	}
 	return NOTIFY_OK;
@@ -793,6 +1008,62 @@ static struct notifier_block __cpuinitdata smp_cpu_nb = {
 	.notifier_call = smp_cpu_notify,
 };
 
+static int smp_add_present_cpu(int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct sys_device *s = &c->sysdev;
+	int rc;
+
+	c->hotpluggable = 1;
+	rc = register_cpu(c, cpu);
+	if (rc)
+		goto out;
+	rc = sysfs_create_group(&s->kobj, &cpu_common_attr_group);
+	if (rc)
+		goto out_cpu;
+	if (!cpu_online(cpu))
+		goto out;
+	rc = sysfs_create_group(&s->kobj, &cpu_online_attr_group);
+	if (!rc)
+		return 0;
+	sysfs_remove_group(&s->kobj, &cpu_common_attr_group);
+out_cpu:
+#ifdef CONFIG_HOTPLUG_CPU
+	unregister_cpu(c);
+#endif
+out:
+	return rc;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static ssize_t rescan_store(struct sys_device *dev, const char *buf,
+			    size_t count)
+{
+	cpumask_t newcpus;
+	int cpu;
+	int rc;
+
+	mutex_lock(&smp_cpu_state_mutex);
+	get_online_cpus();
+	newcpus = cpu_present_map;
+	rc = smp_rescan_cpus();
+	if (rc)
+		goto out;
+	cpus_andnot(newcpus, cpu_present_map, newcpus);
+	for_each_cpu_mask(cpu, newcpus) {
+		rc = smp_add_present_cpu(cpu);
+		if (rc)
+			cpu_clear(cpu, cpu_present_map);
+	}
+	rc = 0;
+out:
+	put_online_cpus();
+	mutex_unlock(&smp_cpu_state_mutex);
+	return rc ? rc : count;
+}
+static SYSDEV_ATTR(rescan, 0200, NULL, rescan_store);
+#endif /* CONFIG_HOTPLUG_CPU */
+
 static int __init topology_init(void)
 {
 	int cpu;
@@ -800,16 +1071,14 @@ static int __init topology_init(void)
 
 	register_cpu_notifier(&smp_cpu_nb);
 
-	for_each_possible_cpu(cpu) {
-		struct cpu *c = &per_cpu(cpu_devices, cpu);
-		struct sys_device *s = &c->sysdev;
-
-		c->hotpluggable = 1;
-		register_cpu(c, cpu);
-		if (!cpu_online(cpu))
-			continue;
-		s = &c->sysdev;
-		rc = sysfs_create_group(&s->kobj, &cpu_attr_group);
+#ifdef CONFIG_HOTPLUG_CPU
+	rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+			       &attr_rescan.attr);
+	if (rc)
+		return rc;
+#endif
+	for_each_present_cpu(cpu) {
+		rc = smp_add_present_cpu(cpu);
 		if (rc)
 			return rc;
 	}

arch/s390/kernel/traps.c

@@ -31,6 +31,7 @@
 #include <linux/reboot.h>
 #include <linux/kprobes.h>
 #include <linux/bug.h>
+#include <linux/utsname.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -168,9 +169,16 @@ void show_stack(struct task_struct *task, unsigned long *sp)
  */
 void dump_stack(void)
 {
+	printk("CPU: %d %s %s %.*s\n",
+	       task_thread_info(current)->cpu, print_tainted(),
+	       init_utsname()->release,
+	       (int)strcspn(init_utsname()->version, " "),
+	       init_utsname()->version);
+	printk("Process %s (pid: %d, task: %p, ksp: %p)\n",
+	       current->comm, current->pid, current,
+	       (void *) current->thread.ksp);
 	show_stack(NULL, NULL);
 }
-
 EXPORT_SYMBOL(dump_stack);
 
 static inline int mask_bits(struct pt_regs *regs, unsigned long bits)
@@ -258,8 +266,14 @@ void die(const char * str, struct pt_regs * regs, long err)
 	console_verbose();
 	spin_lock_irq(&die_lock);
 	bust_spinlocks(1);
-	printk("%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter);
-	print_modules();
+	printk("%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+#ifdef CONFIG_PREEMPT
+	printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+	printk("SMP");
+#endif
+	printk("\n");
 	notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV);
 	show_regs(regs);
 	bust_spinlocks(0);

arch/s390/kernel/vmlinux.lds.S

@@ -17,6 +17,12 @@ ENTRY(_start)
 jiffies = jiffies_64;
 #endif
 
+PHDRS {
+	text PT_LOAD FLAGS(5);	/* R_E */
+	data PT_LOAD FLAGS(7);	/* RWE */
+	note PT_NOTE FLAGS(0);	/* ___ */
+}
+
 SECTIONS
 {
 	. = 0x00000000;
@@ -33,6 +39,9 @@ SECTIONS
 
 	_etext = .;		/* End of text section */
 
+	NOTES :text :note
+	BUG_TABLE :text
+
 	RODATA
 
 #ifdef CONFIG_SHARED_KERNEL
@@ -49,9 +58,6 @@ SECTIONS
 		__stop___ex_table = .;
 	}
 
-	NOTES
-	BUG_TABLE
-
 	.data : {		/* Data */
 		DATA_DATA
 		CONSTRUCTORS

arch/s390/lib/spinlock.c

@@ -39,7 +39,7 @@ static inline void _raw_yield_cpu(int cpu)
 		_raw_yield();
 }
 
-void _raw_spin_lock_wait(raw_spinlock_t *lp, unsigned int pc)
+void _raw_spin_lock_wait(raw_spinlock_t *lp)
 {
 	int count = spin_retry;
 	unsigned int cpu = ~smp_processor_id();
@@ -53,15 +53,36 @@ void _raw_spin_lock_wait(raw_spinlock_t *lp, unsigned int pc)
 		}
 		if (__raw_spin_is_locked(lp))
 			continue;
-		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) {
-			lp->owner_pc = pc;
+		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
 			return;
-		}
 	}
 }
 EXPORT_SYMBOL(_raw_spin_lock_wait);
 
-int _raw_spin_trylock_retry(raw_spinlock_t *lp, unsigned int pc)
+void _raw_spin_lock_wait_flags(raw_spinlock_t *lp, unsigned long flags)
+{
+	int count = spin_retry;
+	unsigned int cpu = ~smp_processor_id();
+
+	local_irq_restore(flags);
+	while (1) {
+		if (count-- <= 0) {
+			unsigned int owner = lp->owner_cpu;
+			if (owner != 0)
+				_raw_yield_cpu(~owner);
+			count = spin_retry;
+		}
+		if (__raw_spin_is_locked(lp))
+			continue;
+		local_irq_disable();
+		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
+			return;
+		local_irq_restore(flags);
+	}
+}
+EXPORT_SYMBOL(_raw_spin_lock_wait_flags);
+
+int _raw_spin_trylock_retry(raw_spinlock_t *lp)
 {
 	unsigned int cpu = ~smp_processor_id();
 	int count;
@@ -69,10 +90,8 @@ int _raw_spin_trylock_retry(raw_spinlock_t *lp, unsigned int pc)
 	for (count = spin_retry; count > 0; count--) {
 		if (__raw_spin_is_locked(lp))
 			continue;
-		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0) {
-			lp->owner_pc = pc;
+		if (_raw_compare_and_swap(&lp->owner_cpu, 0, cpu) == 0)
 			return 1;
-		}
 	}
 	return 0;
 }

arch/s390/mm/extmem.c

@@ -83,7 +83,7 @@ struct dcss_segment {
 };
 
 static DEFINE_MUTEX(dcss_lock);
-static struct list_head dcss_list = LIST_HEAD_INIT(dcss_list);
+static LIST_HEAD(dcss_list);
 static char *segtype_string[] = { "SW", "EW", "SR", "ER", "SN", "EN", "SC",
 					"EW/EN-MIXED" };
 

arch/s390/mm/vmem.c

@@ -15,10 +15,6 @@
 #include <asm/setup.h>
 #include <asm/tlbflush.h>
 
-unsigned long vmalloc_end;
-EXPORT_SYMBOL(vmalloc_end);
-
-static struct page *vmem_map;
 static DEFINE_MUTEX(vmem_mutex);
 
 struct memory_segment {
@@ -188,8 +184,8 @@ static int vmem_add_mem_map(unsigned long start, unsigned long size)
 	pte_t  pte;
 	int ret = -ENOMEM;
 
-	map_start = vmem_map + PFN_DOWN(start);
-	map_end	= vmem_map + PFN_DOWN(start + size);
+	map_start = VMEM_MAP + PFN_DOWN(start);
+	map_end	= VMEM_MAP + PFN_DOWN(start + size);
 
 	start_addr = (unsigned long) map_start & PAGE_MASK;
 	end_addr = PFN_ALIGN((unsigned long) map_end);
@@ -240,10 +236,10 @@ static int vmem_add_mem(unsigned long start, unsigned long size)
 {
 	int ret;
 
-	ret = vmem_add_range(start, size);
+	ret = vmem_add_mem_map(start, size);
 	if (ret)
 		return ret;
-	return vmem_add_mem_map(start, size);
+	return vmem_add_range(start, size);
 }
 
 /*
@@ -254,7 +250,7 @@ static int insert_memory_segment(struct memory_segment *seg)
 {
 	struct memory_segment *tmp;
 
-	if (PFN_DOWN(seg->start + seg->size) > max_pfn ||
+	if (seg->start + seg->size >= VMALLOC_START ||
 	    seg->start + seg->size < seg->start)
 		return -ERANGE;
 
@@ -357,17 +353,15 @@ int add_shared_memory(unsigned long start, unsigned long size)
 
 /*
  * map whole physical memory to virtual memory (identity mapping)
+ * we reserve enough space in the vmalloc area for vmemmap to hotplug
+ * additional memory segments.
  */
 void __init vmem_map_init(void)
 {
-	unsigned long map_size;
 	int i;
 
-	map_size = ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * sizeof(struct page);
-	vmalloc_end = PFN_ALIGN(VMALLOC_END_INIT) - PFN_ALIGN(map_size);
-	vmem_map = (struct page *) vmalloc_end;
-	NODE_DATA(0)->node_mem_map = vmem_map;
-
+	BUILD_BUG_ON((unsigned long)VMEM_MAP + VMEM_MAP_SIZE > VMEM_MAP_MAX);
+	NODE_DATA(0)->node_mem_map = VMEM_MAP;
 	for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++)
 		vmem_add_mem(memory_chunk[i].addr, memory_chunk[i].size);
 }
@@ -382,7 +376,7 @@ static int __init vmem_convert_memory_chunk(void)
 	int i;
 
 	mutex_lock(&vmem_mutex);
-	for (i = 0; i < MEMORY_CHUNKS && memory_chunk[i].size > 0; i++) {
+	for (i = 0; i < MEMORY_CHUNKS; i++) {
 		if (!memory_chunk[i].size)
 			continue;
 		seg = kzalloc(sizeof(*seg), GFP_KERNEL);

drivers/crypto/Kconfig

@@ -48,8 +48,6 @@ config CRYPTO_DEV_PADLOCK_SHA
 	  If unsure say M. The compiled module will be
 	  called padlock-sha.ko
 
-source "arch/s390/crypto/Kconfig"
-
 config CRYPTO_DEV_GEODE
 	tristate "Support for the Geode LX AES engine"
 	depends on X86_32 && PCI
@@ -83,6 +81,67 @@ config ZCRYPT_MONOLITHIC
 	  that contains all parts of the crypto device driver (ap bus,
 	  request router and all the card drivers).
 
+config CRYPTO_SHA1_S390
+	tristate "SHA1 digest algorithm"
+	depends on S390
+	select CRYPTO_ALGAPI
+	help
+	  This is the s390 hardware accelerated implementation of the
+	  SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2).
+
+config CRYPTO_SHA256_S390
+	tristate "SHA256 digest algorithm"
+	depends on S390
+	select CRYPTO_ALGAPI
+	help
+	  This is the s390 hardware accelerated implementation of the
+	  SHA256 secure hash standard (DFIPS 180-2).
+
+	  This version of SHA implements a 256 bit hash with 128 bits of
+	  security against collision attacks.
+
+config CRYPTO_DES_S390
+	tristate "DES and Triple DES cipher algorithms"
+	depends on S390
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
+	help
+	  This us the s390 hardware accelerated implementation of the
+	  DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3).
+
+config CRYPTO_AES_S390
+	tristate "AES cipher algorithms"
+	depends on S390
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
+	help
+	  This is the s390 hardware accelerated implementation of the
+	  AES cipher algorithms (FIPS-197). AES uses the Rijndael
+	  algorithm.
+
+	  Rijndael appears to be consistently a very good performer in
+	  both hardware and software across a wide range of computing
+	  environments regardless of its use in feedback or non-feedback
+	  modes. Its key setup time is excellent, and its key agility is
+	  good. Rijndael's very low memory requirements make it very well
+	  suited for restricted-space environments, in which it also
+	  demonstrates excellent performance. Rijndael's operations are
+	  among the easiest to defend against power and timing attacks.
+
+	  On s390 the System z9-109 currently only supports the key size
+	  of 128 bit.
+
+config S390_PRNG
+	tristate "Pseudo random number generator device driver"
+	depends on S390
+	default "m"
+	help
+	  Select this option if you want to use the s390 pseudo random number
+	  generator. The PRNG is part of the cryptographic processor functions
+	  and uses triple-DES to generate secure random numbers like the
+	  ANSI X9.17 standard. The PRNG is usable via the char device
+	  /dev/prandom.
+
 config CRYPTO_DEV_HIFN_795X
 	tristate "Driver HIFN 795x crypto accelerator chips"
 	select CRYPTO_DES

drivers/s390/block/Makefile

@@ -2,8 +2,8 @@
 # S/390 block devices
 #
 
-dasd_eckd_mod-objs := dasd_eckd.o dasd_3990_erp.o dasd_9343_erp.o
-dasd_fba_mod-objs  := dasd_fba.o dasd_3370_erp.o dasd_9336_erp.o
+dasd_eckd_mod-objs := dasd_eckd.o dasd_3990_erp.o dasd_alias.o
+dasd_fba_mod-objs  := dasd_fba.o
 dasd_diag_mod-objs := dasd_diag.o
 dasd_mod-objs      := dasd.o dasd_ioctl.o dasd_proc.o dasd_devmap.o \
 			dasd_genhd.o dasd_erp.o

drivers/s390/block/dasd_3370_erp.c

-/*
- * File...........: linux/drivers/s390/block/dasd_3370_erp.c
- * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
- * Bugreports.to..: <Linux390@de.ibm.com>
- * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 2000
- *
- */
-
-#define PRINTK_HEADER "dasd_erp(3370)"
-
-#include "dasd_int.h"
-
-
-/*
- * DASD_3370_ERP_EXAMINE
- *
- * DESCRIPTION
- *   Checks only for fatal/no/recover error.
- *   A detailed examination of the sense data is done later outside
- *   the interrupt handler.
- *
- *   The logic is based on the 'IBM 3880 Storage Control Reference' manual
- *   'Chapter 7. 3370 Sense Data'.
- *
- * RETURN VALUES
- *   dasd_era_none	no error
- *   dasd_era_fatal	for all fatal (unrecoverable errors)
- *   dasd_era_recover	for all others.
- */
-dasd_era_t
-dasd_3370_erp_examine(struct dasd_ccw_req * cqr, struct irb * irb)
-{
-	char *sense = irb->ecw;
-
-	/* check for successful execution first */
-	if (irb->scsw.cstat == 0x00 &&
-	    irb->scsw.dstat == (DEV_STAT_CHN_END | DEV_STAT_DEV_END))
-		return dasd_era_none;
-	if (sense[0] & 0x80) {	/* CMD reject */
-		return dasd_era_fatal;
-	}
-	if (sense[0] & 0x40) {	/* Drive offline */
-		return dasd_era_recover;
-	}
-	if (sense[0] & 0x20) {	/* Bus out parity */
-		return dasd_era_recover;
-	}
-	if (sense[0] & 0x10) {	/* equipment check */
-		if (sense[1] & 0x80) {
-			return dasd_era_fatal;
-		}
-		return dasd_era_recover;
-	}
-	if (sense[0] & 0x08) {	/* data check */
-		if (sense[1] & 0x80) {
-			return dasd_era_fatal;
-		}
-		return dasd_era_recover;
-	}
-	if (sense[0] & 0x04) {	/* overrun */
-		if (sense[1] & 0x80) {
-			return dasd_era_fatal;
-		}
-		return dasd_era_recover;
-	}
-	if (sense[1] & 0x40) {	/* invalid blocksize */
-		return dasd_era_fatal;
-	}
-	if (sense[1] & 0x04) {	/* file protected */
-		return dasd_era_recover;
-	}
-	if (sense[1] & 0x01) {	/* operation incomplete */
-		return dasd_era_recover;
-	}
-	if (sense[2] & 0x80) {	/* check data erroor */
-		return dasd_era_recover;
-	}
-	if (sense[2] & 0x10) {	/* Env. data present */
-		return dasd_era_recover;
-	}
-	/* examine the 24 byte sense data */
-	return dasd_era_recover;
-
-}				/* END dasd_3370_erp_examine */

drivers/s390/block/dasd_9336_erp.c

-/*
- * File...........: linux/drivers/s390/block/dasd_9336_erp.c
- * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
- * Bugreports.to..: <Linux390@de.ibm.com>
- * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 2000
- *
- */
-
-#define PRINTK_HEADER "dasd_erp(9336)"
-
-#include "dasd_int.h"
-
-
-/*
- * DASD_9336_ERP_EXAMINE
- *
- * DESCRIPTION
- *   Checks only for fatal/no/recover error.
- *   A detailed examination of the sense data is done later outside
- *   the interrupt handler.
- *
- *   The logic is based on the 'IBM 3880 Storage Control Reference' manual
- *   'Chapter 7. 9336 Sense Data'.
- *
- * RETURN VALUES
- *   dasd_era_none	no error
- *   dasd_era_fatal	for all fatal (unrecoverable errors)
- *   dasd_era_recover	for all others.
- */
-dasd_era_t
-dasd_9336_erp_examine(struct dasd_ccw_req * cqr, struct irb * irb)
-{
-	/* check for successful execution first */
-	if (irb->scsw.cstat == 0x00 &&
-	    irb->scsw.dstat == (DEV_STAT_CHN_END | DEV_STAT_DEV_END))
-		return dasd_era_none;
-
-	/* examine the 24 byte sense data */
-	return dasd_era_recover;
-
-}				/* END dasd_9336_erp_examine */

drivers/s390/block/dasd_9343_erp.c

-/*
- * File...........: linux/drivers/s390/block/dasd_9345_erp.c
- * Author(s)......: Holger Smolinski <Holger.Smolinski@de.ibm.com>
- * Bugreports.to..: <Linux390@de.ibm.com>
- * (C) IBM Corporation, IBM Deutschland Entwicklung GmbH, 2000
- *
- */
-
-#define PRINTK_HEADER "dasd_erp(9343)"
-
-#include "dasd_int.h"
-
-dasd_era_t
-dasd_9343_erp_examine(struct dasd_ccw_req * cqr, struct irb * irb)
-{
-	if (irb->scsw.cstat == 0x00 &&
-	    irb->scsw.dstat == (DEV_STAT_CHN_END | DEV_STAT_DEV_END))
-		return dasd_era_none;
-
-	return dasd_era_recover;
-}

drivers/s390/block/dasd_devmap.c

@@ -48,22 +48,6 @@ struct dasd_devmap {
 	struct dasd_uid uid;
 };
 
-/*
- * dasd_server_ssid_map contains a globally unique storage server subsystem ID.
- * dasd_server_ssid_list contains the list of all subsystem IDs accessed by
- * the DASD device driver.
- */
-struct dasd_server_ssid_map {
-	struct list_head list;
-	struct system_id {
-		char vendor[4];
-		char serial[15];
-		__u16 ssid;
-	} sid;
-};
-
-static struct list_head dasd_server_ssid_list;
-
 /*
  * Parameter parsing functions for dasd= parameter. The syntax is:
  *   <devno>		: (0x)?[0-9a-fA-F]+
@@ -721,8 +705,9 @@ dasd_ro_store(struct device *dev, struct device_attribute *attr,
 		devmap->features &= ~DASD_FEATURE_READONLY;
 	if (devmap->device)
 		devmap->device->features = devmap->features;
-	if (devmap->device && devmap->device->gdp)
-		set_disk_ro(devmap->device->gdp, val);
+	if (devmap->device && devmap->device->block
+	    && devmap->device->block->gdp)
+		set_disk_ro(devmap->device->block->gdp, val);
 	spin_unlock(&dasd_devmap_lock);
 	return count;
 }
@@ -893,12 +878,16 @@ dasd_alias_show(struct device *dev, struct device_attribute *attr, char *buf)
 
 	devmap = dasd_find_busid(dev->bus_id);
 	spin_lock(&dasd_devmap_lock);
-	if (!IS_ERR(devmap))
-		alias = devmap->uid.alias;
+	if (IS_ERR(devmap) || strlen(devmap->uid.vendor) == 0) {
+		spin_unlock(&dasd_devmap_lock);
+		return sprintf(buf, "0\n");
+	}
+	if (devmap->uid.type == UA_BASE_PAV_ALIAS ||
+	    devmap->uid.type == UA_HYPER_PAV_ALIAS)
+		alias = 1;
 	else
 		alias = 0;
 	spin_unlock(&dasd_devmap_lock);
-
 	return sprintf(buf, alias ? "1\n" : "0\n");
 }
 
@@ -930,19 +919,36 @@ static ssize_t
 dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct dasd_devmap *devmap;
-	char uid[UID_STRLEN];
+	char uid_string[UID_STRLEN];
+	char ua_string[3];
+	struct dasd_uid *uid;
 
 	devmap = dasd_find_busid(dev->bus_id);
 	spin_lock(&dasd_devmap_lock);
-	if (!IS_ERR(devmap) && strlen(devmap->uid.vendor) > 0)
-		snprintf(uid, sizeof(uid), "%s.%s.%04x.%02x",
-			 devmap->uid.vendor, devmap->uid.serial,
-			 devmap->uid.ssid, devmap->uid.unit_addr);
-	else
-		uid[0] = 0;
+	if (IS_ERR(devmap) || strlen(devmap->uid.vendor) == 0) {
+		spin_unlock(&dasd_devmap_lock);
+		return sprintf(buf, "\n");
+	}
+	uid = &devmap->uid;
+	switch (uid->type) {
+	case UA_BASE_DEVICE:
+		sprintf(ua_string, "%02x", uid->real_unit_addr);
+		break;
+	case UA_BASE_PAV_ALIAS:
+		sprintf(ua_string, "%02x", uid->base_unit_addr);
+		break;
+	case UA_HYPER_PAV_ALIAS:
+		sprintf(ua_string, "xx");
+		break;
+	default:
+		/* should not happen, treat like base device */
+		sprintf(ua_string, "%02x", uid->real_unit_addr);
+		break;
+	}
+	snprintf(uid_string, sizeof(uid_string), "%s.%s.%04x.%s",
+		 uid->vendor, uid->serial, uid->ssid, ua_string);
 	spin_unlock(&dasd_devmap_lock);
-
-	return snprintf(buf, PAGE_SIZE, "%s\n", uid);
+	return snprintf(buf, PAGE_SIZE, "%s\n", uid_string);
 }
 
 static DEVICE_ATTR(uid, 0444, dasd_uid_show, NULL);
@@ -1040,39 +1046,16 @@ int
 dasd_set_uid(struct ccw_device *cdev, struct dasd_uid *uid)
 {
 	struct dasd_devmap *devmap;
-	struct dasd_server_ssid_map *srv, *tmp;
 
 	devmap = dasd_find_busid(cdev->dev.bus_id);
 	if (IS_ERR(devmap))
 		return PTR_ERR(devmap);
 
-	/* generate entry for server_ssid_map */
-	srv = (struct dasd_server_ssid_map *)
-		kzalloc(sizeof(struct dasd_server_ssid_map), GFP_KERNEL);
-	if (!srv)
-		return -ENOMEM;
-	strncpy(srv->sid.vendor, uid->vendor, sizeof(srv->sid.vendor) - 1);
-	strncpy(srv->sid.serial, uid->serial, sizeof(srv->sid.serial) - 1);
-	srv->sid.ssid = uid->ssid;
-
-	/* server is already contained ? */
 	spin_lock(&dasd_devmap_lock);
 	devmap->uid = *uid;
-	list_for_each_entry(tmp, &dasd_server_ssid_list, list) {
-		if (!memcmp(&srv->sid, &tmp->sid,
-			    sizeof(struct system_id))) {
-			kfree(srv);
-			srv = NULL;
-			break;
-		}
-	}
-
-	/* add servermap to serverlist */
-	if (srv)
-		list_add(&srv->list, &dasd_server_ssid_list);
 	spin_unlock(&dasd_devmap_lock);
 
-	return (srv ? 1 : 0);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(dasd_set_uid);
 
@@ -1138,9 +1121,6 @@ dasd_devmap_init(void)
 	dasd_max_devindex = 0;
 	for (i = 0; i < 256; i++)
 		INIT_LIST_HEAD(&dasd_hashlists[i]);
-
-	/* Initialize servermap structure. */
-	INIT_LIST_HEAD(&dasd_server_ssid_list);
 	return 0;
 }
 

drivers/s390/block/dasd_diag.c

@@ -142,7 +142,7 @@ dasd_diag_erp(struct dasd_device *device)
 	int rc;
 
 	mdsk_term_io(device);
-	rc = mdsk_init_io(device, device->bp_block, 0, NULL);
+	rc = mdsk_init_io(device, device->block->bp_block, 0, NULL);
 	if (rc)
 		DEV_MESSAGE(KERN_WARNING, device, "DIAG ERP unsuccessful, "
 			    "rc=%d", rc);
@@ -158,11 +158,11 @@ dasd_start_diag(struct dasd_ccw_req * cqr)
 	struct dasd_diag_req *dreq;
 	int rc;
 
-	device = cqr->device;
+	device = cqr->startdev;
 	if (cqr->retries < 0) {
 		DEV_MESSAGE(KERN_WARNING, device, "DIAG start_IO: request %p "
 			    "- no retry left)", cqr);
-		cqr->status = DASD_CQR_FAILED;
+		cqr->status = DASD_CQR_ERROR;
 		return -EIO;
 	}
 	private = (struct dasd_diag_private *) device->private;
@@ -184,7 +184,7 @@ dasd_start_diag(struct dasd_ccw_req * cqr)
 	switch (rc) {
 	case 0: /* Synchronous I/O finished successfully */
 		cqr->stopclk = get_clock();
-		cqr->status = DASD_CQR_DONE;
+		cqr->status = DASD_CQR_SUCCESS;
 		/* Indicate to calling function that only a dasd_schedule_bh()
 		   and no timer is needed */
                 rc = -EACCES;
@@ -209,12 +209,12 @@ dasd_diag_term_IO(struct dasd_ccw_req * cqr)
 {
 	struct dasd_device *device;
 
-	device = cqr->device;
+	device = cqr->startdev;
 	mdsk_term_io(device);
-	mdsk_init_io(device, device->bp_block, 0, NULL);
-	cqr->status = DASD_CQR_CLEAR;
+	mdsk_init_io(device, device->block->bp_block, 0, NULL);
+	cqr->status = DASD_CQR_CLEAR_PENDING;
 	cqr->stopclk = get_clock();
-	dasd_schedule_bh(device);
+	dasd_schedule_device_bh(device);
 	return 0;
 }
 
@@ -247,7 +247,7 @@ dasd_ext_handler(__u16 code)
 		return;
 	}
 	cqr = (struct dasd_ccw_req *) ip;
-	device = (struct dasd_device *) cqr->device;
+	device = (struct dasd_device *) cqr->startdev;
 	if (strncmp(device->discipline->ebcname, (char *) &cqr->magic, 4)) {
 		DEV_MESSAGE(KERN_WARNING, device,
 			    " magic number of dasd_ccw_req 0x%08X doesn't"
@@ -260,10 +260,10 @@ dasd_ext_handler(__u16 code)
 	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
 
 	/* Check for a pending clear operation */
-	if (cqr->status == DASD_CQR_CLEAR) {
-		cqr->status = DASD_CQR_QUEUED;
-		dasd_clear_timer(device);
-		dasd_schedule_bh(device);
+	if (cqr->status == DASD_CQR_CLEAR_PENDING) {
+		cqr->status = DASD_CQR_CLEARED;
+		dasd_device_clear_timer(device);
+		dasd_schedule_device_bh(device);
 		spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 		return;
 	}
@@ -272,11 +272,11 @@ dasd_ext_handler(__u16 code)
 
 	expires = 0;
 	if (status == 0) {
-		cqr->status = DASD_CQR_DONE;
+		cqr->status = DASD_CQR_SUCCESS;
 		/* Start first request on queue if possible -> fast_io. */
 		if (!list_empty(&device->ccw_queue)) {
 			next = list_entry(device->ccw_queue.next,
-					  struct dasd_ccw_req, list);
+					  struct dasd_ccw_req, devlist);
 			if (next->status == DASD_CQR_QUEUED) {
 				rc = dasd_start_diag(next);
 				if (rc == 0)
@@ -296,10 +296,10 @@ dasd_ext_handler(__u16 code)
 	}
 
 	if (expires != 0)
-		dasd_set_timer(device, expires);
+		dasd_device_set_timer(device, expires);
 	else
-		dasd_clear_timer(device);
-	dasd_schedule_bh(device);
+		dasd_device_clear_timer(device);
+	dasd_schedule_device_bh(device);
 
 	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 }
@@ -309,6 +309,7 @@ dasd_ext_handler(__u16 code)
 static int
 dasd_diag_check_device(struct dasd_device *device)
 {
+	struct dasd_block *block;
 	struct dasd_diag_private *private;
 	struct dasd_diag_characteristics *rdc_data;
 	struct dasd_diag_bio bio;
@@ -328,6 +329,16 @@ dasd_diag_check_device(struct dasd_device *device)
 		ccw_device_get_id(device->cdev, &private->dev_id);
 		device->private = (void *) private;
 	}
+	block = dasd_alloc_block();
+	if (IS_ERR(block)) {
+		DEV_MESSAGE(KERN_WARNING, device, "%s",
+			    "could not allocate dasd block structure");
+		kfree(device->private);
+		return PTR_ERR(block);
+	}
+	device->block = block;
+	block->base = device;
+
 	/* Read Device Characteristics */
 	rdc_data = (void *) &(private->rdc_data);
 	rdc_data->dev_nr = private->dev_id.devno;
@@ -409,14 +420,14 @@ dasd_diag_check_device(struct dasd_device *device)
 		  sizeof(DASD_DIAG_CMS1)) == 0) {
 		/* get formatted blocksize from label block */
 		bsize = (unsigned int) label->block_size;
-		device->blocks = (unsigned long) label->block_count;
+		block->blocks = (unsigned long) label->block_count;
 	} else
-		device->blocks = end_block;
-	device->bp_block = bsize;
-	device->s2b_shift = 0;	/* bits to shift 512 to get a block */
+		block->blocks = end_block;
+	block->bp_block = bsize;
+	block->s2b_shift = 0;	/* bits to shift 512 to get a block */
 	for (sb = 512; sb < bsize; sb = sb << 1)
-		device->s2b_shift++;
-	rc = mdsk_init_io(device, device->bp_block, 0, NULL);
+		block->s2b_shift++;
+	rc = mdsk_init_io(device, block->bp_block, 0, NULL);
 	if (rc) {
 		DEV_MESSAGE(KERN_WARNING, device, "DIAG initialization "
 			"failed (rc=%d)", rc);
@@ -424,9 +435,9 @@ dasd_diag_check_device(struct dasd_device *device)
 	} else {
 		DEV_MESSAGE(KERN_INFO, device,
 			    "(%ld B/blk): %ldkB",
-			    (unsigned long) device->bp_block,
-			    (unsigned long) (device->blocks <<
-				device->s2b_shift) >> 1);
+			    (unsigned long) block->bp_block,
+			    (unsigned long) (block->blocks <<
+				block->s2b_shift) >> 1);
 	}
 out:
 	free_page((long) label);
@@ -436,22 +447,16 @@ dasd_diag_check_device(struct dasd_device *device)
 /* Fill in virtual disk geometry for device. Return zero on success, non-zero
  * otherwise. */
 static int
-dasd_diag_fill_geometry(struct dasd_device *device, struct hd_geometry *geo)
+dasd_diag_fill_geometry(struct dasd_block *block, struct hd_geometry *geo)
 {
-	if (dasd_check_blocksize(device->bp_block) != 0)
+	if (dasd_check_blocksize(block->bp_block) != 0)
 		return -EINVAL;
-	geo->cylinders = (device->blocks << device->s2b_shift) >> 10;
+	geo->cylinders = (block->blocks << block->s2b_shift) >> 10;
 	geo->heads = 16;
-	geo->sectors = 128 >> device->s2b_shift;
+	geo->sectors = 128 >> block->s2b_shift;
 	return 0;
 }
 
-static dasd_era_t
-dasd_diag_examine_error(struct dasd_ccw_req * cqr, struct irb * stat)
-{
-	return dasd_era_fatal;
-}
-
 static dasd_erp_fn_t
 dasd_diag_erp_action(struct dasd_ccw_req * cqr)
 {
@@ -466,8 +471,9 @@ dasd_diag_erp_postaction(struct dasd_ccw_req * cqr)
 
 /* Create DASD request from block device request. Return pointer to new
  * request on success, ERR_PTR otherwise. */
-static struct dasd_ccw_req *
-dasd_diag_build_cp(struct dasd_device * device, struct request *req)
+static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
+					       struct dasd_block *block,
+					       struct request *req)
 {
 	struct dasd_ccw_req *cqr;
 	struct dasd_diag_req *dreq;
@@ -486,17 +492,17 @@ dasd_diag_build_cp(struct dasd_device * device, struct request *req)
 		rw_cmd = MDSK_WRITE_REQ;
 	else
 		return ERR_PTR(-EINVAL);
-	blksize = device->bp_block;
+	blksize = block->bp_block;
 	/* Calculate record id of first and last block. */
-	first_rec = req->sector >> device->s2b_shift;
-	last_rec = (req->sector + req->nr_sectors - 1) >> device->s2b_shift;
+	first_rec = req->sector >> block->s2b_shift;
+	last_rec = (req->sector + req->nr_sectors - 1) >> block->s2b_shift;
 	/* Check struct bio and count the number of blocks for the request. */
 	count = 0;
 	rq_for_each_segment(bv, req, iter) {
 		if (bv->bv_len & (blksize - 1))
 			/* Fba can only do full blocks. */
 			return ERR_PTR(-EINVAL);
-		count += bv->bv_len >> (device->s2b_shift + 9);
+		count += bv->bv_len >> (block->s2b_shift + 9);
 	}
 	/* Paranoia. */
 	if (count != last_rec - first_rec + 1)
@@ -505,7 +511,7 @@ dasd_diag_build_cp(struct dasd_device * device, struct request *req)
 	datasize = sizeof(struct dasd_diag_req) +
 		count*sizeof(struct dasd_diag_bio);
 	cqr = dasd_smalloc_request(dasd_diag_discipline.name, 0,
-				   datasize, device);
+				   datasize, memdev);
 	if (IS_ERR(cqr))
 		return cqr;
 
@@ -529,7 +535,9 @@ dasd_diag_build_cp(struct dasd_device * device, struct request *req)
 	cqr->buildclk = get_clock();
 	if (req->cmd_flags & REQ_FAILFAST)
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
-	cqr->device = device;
+	cqr->startdev = memdev;
+	cqr->memdev = memdev;
+	cqr->block = block;
 	cqr->expires = DIAG_TIMEOUT;
 	cqr->status = DASD_CQR_FILLED;
 	return cqr;
@@ -543,10 +551,15 @@ dasd_diag_free_cp(struct dasd_ccw_req *cqr, struct request *req)
 	int status;
 
 	status = cqr->status == DASD_CQR_DONE;
-	dasd_sfree_request(cqr, cqr->device);
+	dasd_sfree_request(cqr, cqr->memdev);
 	return status;
 }
 
+static void dasd_diag_handle_terminated_request(struct dasd_ccw_req *cqr)
+{
+	cqr->status = DASD_CQR_FILLED;
+};
+
 /* Fill in IOCTL data for device. */
 static int
 dasd_diag_fill_info(struct dasd_device * device,
@@ -583,7 +596,7 @@ static struct dasd_discipline dasd_diag_discipline = {
 	.fill_geometry = dasd_diag_fill_geometry,
 	.start_IO = dasd_start_diag,
 	.term_IO = dasd_diag_term_IO,
-	.examine_error = dasd_diag_examine_error,
+	.handle_terminated_request = dasd_diag_handle_terminated_request,
 	.erp_action = dasd_diag_erp_action,
 	.erp_postaction = dasd_diag_erp_postaction,
 	.build_cp = dasd_diag_build_cp,

drivers/s390/block/dasd_eckd.h

@@ -39,6 +39,8 @@
 #define DASD_ECKD_CCW_READ_CKD_MT	 0x9e
 #define DASD_ECKD_CCW_WRITE_CKD_MT	 0x9d
 #define DASD_ECKD_CCW_RESERVE		 0xB4
+#define DASD_ECKD_CCW_PFX		 0xE7
+#define DASD_ECKD_CCW_RSCK		 0xF9
 
 /*
  * Perform Subsystem Function / Sub-Orders
@@ -137,6 +139,25 @@ struct LO_eckd_data {
 	__u16 length;
 } __attribute__ ((packed));
 
+/* Prefix data for format 0x00 and 0x01 */
+struct PFX_eckd_data {
+	unsigned char format;
+	struct {
+		unsigned char define_extend:1;
+		unsigned char time_stamp:1;
+		unsigned char verify_base:1;
+		unsigned char hyper_pav:1;
+		unsigned char reserved:4;
+	} __attribute__ ((packed)) validity;
+	__u8 base_address;
+	__u8 aux;
+	__u8 base_lss;
+	__u8 reserved[7];
+	struct DE_eckd_data define_extend;
+	struct LO_eckd_data locate_record;
+	__u8 LO_extended_data[4];
+} __attribute__ ((packed));
+
 struct dasd_eckd_characteristics {
 	__u16 cu_type;
 	struct {
@@ -254,7 +275,9 @@ struct dasd_eckd_confdata {
 		} __attribute__ ((packed)) ned;
 		struct {
 			unsigned char flags;            /* byte  0    */
-			unsigned char res2[7];          /* byte  1- 7 */
+			unsigned char res1;		/* byte  1    */
+			__u16 format;			/* byte  2-3  */
+			unsigned char res2[4];		/* byte  4-7  */
 			unsigned char sua_flags;	/* byte  8    */
 			__u8 base_unit_addr;            /* byte  9    */
 			unsigned char res3[22];	        /* byte 10-31 */
@@ -343,6 +366,11 @@ struct dasd_eckd_path {
 	__u8 npm;
 };
 
+struct dasd_rssd_features {
+	char feature[256];
+} __attribute__((packed));
+
+
 /*
  * Perform Subsystem Function - Prepare for Read Subsystem Data
  */
@@ -365,4 +393,99 @@ struct dasd_psf_ssc_data {
 	unsigned char reserved[59];
 } __attribute__((packed));
 
+
+/*
+ * some structures and definitions for alias handling
+ */
+struct dasd_unit_address_configuration {
+	struct {
+		char ua_type;
+		char base_ua;
+	} unit[256];
+} __attribute__((packed));
+
+
+#define MAX_DEVICES_PER_LCU 256
+
+/* flags on the LCU  */
+#define NEED_UAC_UPDATE  0x01
+#define UPDATE_PENDING	0x02
+
+enum pavtype {NO_PAV, BASE_PAV, HYPER_PAV};
+
+
+struct alias_root {
+	struct list_head serverlist;
+	spinlock_t lock;
+};
+
+struct alias_server {
+	struct list_head server;
+	struct dasd_uid uid;
+	struct list_head lculist;
+};
+
+struct summary_unit_check_work_data {
+	char reason;
+	struct dasd_device *device;
+	struct work_struct worker;
+};
+
+struct read_uac_work_data {
+	struct dasd_device *device;
+	struct delayed_work dwork;
+};
+
+struct alias_lcu {
+	struct list_head lcu;
+	struct dasd_uid uid;
+	enum pavtype pav;
+	char flags;
+	spinlock_t lock;
+	struct list_head grouplist;
+	struct list_head active_devices;
+	struct list_head inactive_devices;
+	struct dasd_unit_address_configuration *uac;
+	struct summary_unit_check_work_data suc_data;
+	struct read_uac_work_data ruac_data;
+	struct dasd_ccw_req *rsu_cqr;
+};
+
+struct alias_pav_group {
+	struct list_head group;
+	struct dasd_uid uid;
+	struct alias_lcu *lcu;
+	struct list_head baselist;
+	struct list_head aliaslist;
+	struct dasd_device *next;
+};
+
+
+struct dasd_eckd_private {
+	struct dasd_eckd_characteristics rdc_data;
+	struct dasd_eckd_confdata conf_data;
+	struct dasd_eckd_path path_data;
+	struct eckd_count count_area[5];
+	int init_cqr_status;
+	int uses_cdl;
+	struct attrib_data_t attrib;	/* e.g. cache operations */
+	struct dasd_rssd_features features;
+
+	/* alias managemnet */
+	struct dasd_uid uid;
+	struct alias_pav_group *pavgroup;
+	struct alias_lcu *lcu;
+	int count;
+};
+
+
+
+int dasd_alias_make_device_known_to_lcu(struct dasd_device *);
+void dasd_alias_disconnect_device_from_lcu(struct dasd_device *);
+int dasd_alias_add_device(struct dasd_device *);
+int dasd_alias_remove_device(struct dasd_device *);
+struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *);
+void dasd_alias_handle_summary_unit_check(struct dasd_device *, struct irb *);
+void dasd_eckd_reset_ccw_to_base_io(struct dasd_ccw_req *);
+
 #endif				/* DASD_ECKD_H */

drivers/s390/block/dasd_eer.c

@@ -336,7 +336,7 @@ static void dasd_eer_write_snss_trigger(struct dasd_device *device,
 	unsigned long flags;
 	struct eerbuffer *eerb;
 
-	snss_rc = (cqr->status == DASD_CQR_FAILED) ? -EIO : 0;
+	snss_rc = (cqr->status == DASD_CQR_DONE) ? 0 : -EIO;
 	if (snss_rc)
 		data_size = 0;
 	else
@@ -404,10 +404,11 @@ void dasd_eer_snss(struct dasd_device *device)
 		set_bit(DASD_FLAG_EER_SNSS, &device->flags);
 		return;
 	}
+	/* cdev is already locked, can't use dasd_add_request_head */
 	clear_bit(DASD_FLAG_EER_SNSS, &device->flags);
 	cqr->status = DASD_CQR_QUEUED;
-	list_add(&cqr->list, &device->ccw_queue);
-	dasd_schedule_bh(device);
+	list_add(&cqr->devlist, &device->ccw_queue);
+	dasd_schedule_device_bh(device);
 }
 
 /*
@@ -415,7 +416,7 @@ void dasd_eer_snss(struct dasd_device *device)
  */
 static void dasd_eer_snss_cb(struct dasd_ccw_req *cqr, void *data)
 {
-        struct dasd_device *device = cqr->device;
+	struct dasd_device *device = cqr->startdev;
 	unsigned long flags;
 
 	dasd_eer_write(device, cqr, DASD_EER_STATECHANGE);
@@ -458,7 +459,7 @@ int dasd_eer_enable(struct dasd_device *device)
 	if (!cqr)
 		return -ENOMEM;
 
-	cqr->device = device;
+	cqr->startdev = device;
 	cqr->retries = 255;
 	cqr->expires = 10 * HZ;
 	clear_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);