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:
  [S390] kprobes: Fix the return address of multiple kretprobes
  [S390] kprobes: disable interrupts throughout
  [S390] ftrace: build without frame pointers on s390
  [S390] mm: add devmem_is_allowed() for STRICT_DEVMEM checking
  [S390] vmlogrdr: purge after recording is switched off
  [S390] cio: fix incorrect ccw_device_init_count
  [S390] tape: add medium state notifications
  [S390] fix get_user_pages_fast

8 files changed, 167 insertions, 44 deletions

diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 45e0c6199f36..05221b13ffb1 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -6,6 +6,18 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
+config STRICT_DEVMEM
+        def_bool y
+        prompt "Filter access to /dev/mem"
+        ---help---
+          This option restricts access to /dev/mem.  If this option is
+          disabled, you allow userspace access to all memory, including
+          kernel and userspace memory. Accidental memory access is likely
+          to be disastrous.
+          Memory access is required for experts who want to debug the kernel.
+
+          If you are unsure, say Y.
+
 config DEBUG_STRICT_USER_COPY_CHECKS
         bool "Strict user copy size checks"
         ---help---
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index a8729ea7e9ac..3c987e9ec8d6 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -130,6 +130,11 @@ struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
 
+static inline int devmem_is_allowed(unsigned long pfn)
+{
+        return 0;
+}
+
 #define HAVE_ARCH_FREE_PAGE
 #define HAVE_ARCH_ALLOC_PAGE
 
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index d60fc4398516..2564793ec2b6 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -30,6 +30,7 @@
 #include <asm/sections.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/hardirq.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
@@ -212,7 +213,7 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
         /* Set the PER control regs, turns on single step for this address */
         __ctl_load(kprobe_per_regs, 9, 11);
         regs->psw.mask |= PSW_MASK_PER;
-        regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK);
+        regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
 }
 
 static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
@@ -239,7 +240,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
         __get_cpu_var(current_kprobe) = p;
         /* Save the interrupt and per flags */
         kcb->kprobe_saved_imask = regs->psw.mask &
-            (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK);
+                (PSW_MASK_PER | PSW_MASK_IO | PSW_MASK_EXT);
         /* Save the control regs that govern PER */
         __ctl_store(kcb->kprobe_saved_ctl, 9, 11);
 }
@@ -316,8 +317,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
                 return 1;
 
 ss_probe:
-        if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO))
-                local_irq_disable();
         prepare_singlestep(p, regs);
         kcb->kprobe_status = KPROBE_HIT_SS;
         return 1;
@@ -350,6 +349,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
         struct hlist_node *node, *tmp;
         unsigned long flags, orig_ret_address = 0;
         unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+        kprobe_opcode_t *correct_ret_addr = NULL;
 
         INIT_HLIST_HEAD(&empty_rp);
         kretprobe_hash_lock(current, &head, &flags);
@@ -372,10 +372,32 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
                         /* another task is sharing our hash bucket */
                         continue;
 
-                if (ri->rp && ri->rp->handler)
-                        ri->rp->handler(ri, regs);
+                orig_ret_address = (unsigned long)ri->ret_addr;
+
+                if (orig_ret_address != trampoline_address)
+                        /*
+                         * This is the real return address. Any other
+                         * instances associated with this task are for
+                         * other calls deeper on the call stack
+                         */
+                        break;
+        }
+
+        kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+        correct_ret_addr = ri->ret_addr;
+        hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+                if (ri->task != current)
+                        /* another task is sharing our hash bucket */
+                        continue;
 
                 orig_ret_address = (unsigned long)ri->ret_addr;
+
+                if (ri->rp && ri->rp->handler) {
+                        ri->ret_addr = correct_ret_addr;
+                        ri->rp->handler(ri, regs);
+                }
+
                 recycle_rp_inst(ri, &empty_rp);
 
                 if (orig_ret_address != trampoline_address) {
@@ -387,7 +409,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
                         break;
                 }
         }
-        kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
         regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE;
 
         reset_current_kprobe();
@@ -465,8 +487,6 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs)
                 goto out;
         }
         reset_current_kprobe();
-        if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO))
-                local_irq_enable();
 out:
         preempt_enable_no_resched();
 
@@ -482,7 +502,7 @@ out:
         return 1;
 }
 
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 {
         struct kprobe *cur = kprobe_running();
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -508,8 +528,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
                         restore_previous_kprobe(kcb);
                 else {
                         reset_current_kprobe();
-                        if (regs->psw.mask & (PSW_MASK_PER | PSW_MASK_IO))
-                                local_irq_enable();
                 }
                 preempt_enable_no_resched();
                 break;
@@ -553,6 +571,18 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
         return 0;
 }
 
+int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+        int ret;
+
+        if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+                local_irq_disable();
+        ret = kprobe_trap_handler(regs, trapnr);
+        if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+                local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
+        return ret;
+}
+
 /*
  * Wrapper routine to for handling exceptions.
  */
@@ -560,8 +590,12 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
                                        unsigned long val, void *data)
 {
         struct die_args *args = (struct die_args *)data;
+        struct pt_regs *regs = args->regs;
         int ret = NOTIFY_DONE;
 
+        if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+                local_irq_disable();
+
         switch (val) {
         case DIE_BPT:
                 if (kprobe_handler(args->regs))
@@ -572,16 +606,17 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
                         ret = NOTIFY_STOP;
                 break;
         case DIE_TRAP:
-                /* kprobe_running() needs smp_processor_id() */
-                preempt_disable();
-                if (kprobe_running() &&
-                    kprobe_fault_handler(args->regs, args->trapnr))
+                if (!preemptible() && kprobe_running() &&
+                    kprobe_trap_handler(args->regs, args->trapnr))
                         ret = NOTIFY_STOP;
-                preempt_enable();
                 break;
         default:
                 break;
         }
+
+        if (regs->psw.mask & (PSW_MASK_IO | PSW_MASK_EXT))
+                local_irq_restore(regs->psw.mask & ~PSW_MASK_PER);
+
         return ret;
 }
 
@@ -595,6 +630,7 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 
         /* setup return addr to the jprobe handler routine */
         regs->psw.addr = (unsigned long)(jp->entry) | PSW_ADDR_AMODE;
+        regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
 
         /* r14 is the function return address */
         kcb->jprobe_saved_r14 = (unsigned long)regs->gprs[14];
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
index 38e641cdd977..45b405ca2567 100644
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -20,18 +20,17 @@
 static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
                 unsigned long end, int write, struct page **pages, int *nr)
 {
-        unsigned long mask, result;
+        unsigned long mask;
         pte_t *ptep, pte;
         struct page *page;
 
-        result = write ? 0 : _PAGE_RO;
-        mask = result | _PAGE_INVALID | _PAGE_SPECIAL;
+        mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
 
         ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
         do {
                 pte = *ptep;
                 barrier();
-                if ((pte_val(pte) & mask) != result)
+                if ((pte_val(pte) & mask) != 0)
                         return 0;
                 VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
                 page = pte_page(pte);
diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c
index 6c408670e08d..b3a3e8e8656e 100644
--- a/drivers/s390/char/tape_core.c
+++ b/drivers/s390/char/tape_core.c
@@ -209,29 +209,79 @@ tape_state_set(struct tape_device *device, enum tape_state newstate)
         wake_up(&device->state_change_wq);
 }
 
+struct tape_med_state_work_data {
+        struct tape_device *device;
+        enum tape_medium_state state;
+        struct work_struct  work;
+};
+
+static void
+tape_med_state_work_handler(struct work_struct *work)
+{
+        static char env_state_loaded[] = "MEDIUM_STATE=LOADED";
+        static char env_state_unloaded[] = "MEDIUM_STATE=UNLOADED";
+        struct tape_med_state_work_data *p =
+                container_of(work, struct tape_med_state_work_data, work);
+        struct tape_device *device = p->device;
+        char *envp[] = { NULL, NULL };
+
+        switch (p->state) {
+        case MS_UNLOADED:
+                pr_info("%s: The tape cartridge has been successfully "
+                        "unloaded\n", dev_name(&device->cdev->dev));
+                envp[0] = env_state_unloaded;
+                kobject_uevent_env(&device->cdev->dev.kobj, KOBJ_CHANGE, envp);
+                break;
+        case MS_LOADED:
+                pr_info("%s: A tape cartridge has been mounted\n",
+                        dev_name(&device->cdev->dev));
+                envp[0] = env_state_loaded;
+                kobject_uevent_env(&device->cdev->dev.kobj, KOBJ_CHANGE, envp);
+                break;
+        default:
+                break;
+        }
+        tape_put_device(device);
+        kfree(p);
+}
+
+static void
+tape_med_state_work(struct tape_device *device, enum tape_medium_state state)
+{
+        struct tape_med_state_work_data *p;
+
+        p = kzalloc(sizeof(*p), GFP_ATOMIC);
+        if (p) {
+                INIT_WORK(&p->work, tape_med_state_work_handler);
+                p->device = tape_get_device(device);
+                p->state = state;
+                schedule_work(&p->work);
+        }
+}
+
 void
 tape_med_state_set(struct tape_device *device, enum tape_medium_state newstate)
 {
-        if (device->medium_state == newstate)
+        enum tape_medium_state oldstate;
+
+        oldstate = device->medium_state;
+        if (oldstate == newstate)
                 return;
+        device->medium_state = newstate;
         switch(newstate){
         case MS_UNLOADED:
                 device->tape_generic_status |= GMT_DR_OPEN(~0);
-                if (device->medium_state == MS_LOADED)
-                        pr_info("%s: The tape cartridge has been successfully "
-                                "unloaded\n", dev_name(&device->cdev->dev));
+                if (oldstate == MS_LOADED)
+                        tape_med_state_work(device, MS_UNLOADED);
                 break;
         case MS_LOADED:
                 device->tape_generic_status &= ~GMT_DR_OPEN(~0);
-                if (device->medium_state == MS_UNLOADED)
-                        pr_info("%s: A tape cartridge has been mounted\n",
-                                dev_name(&device->cdev->dev));
+                if (oldstate == MS_UNLOADED)
+                        tape_med_state_work(device, MS_LOADED);
                 break;
         default:
-                // print nothing
                 break;
         }
-        device->medium_state = newstate;
         wake_up(&device->state_change_wq);
 }
 
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 9f661426e4a1..1cc726b98ec8 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -249,27 +249,25 @@ static int vmlogrdr_recording(struct vmlogrdr_priv_t * logptr,
         char cp_command[80];
         char cp_response[160];
         char *onoff, *qid_string;
+        int rc;
 
-        memset(cp_command, 0x00, sizeof(cp_command));
-        memset(cp_response, 0x00, sizeof(cp_response));
-
-        onoff = ((action == 1) ? "ON" : "OFF");
+        onoff = ((action == 1) ? "ON" : "OFF");
         qid_string = ((recording_class_AB == 1) ? " QID * " : "");
 
-        /*
+        /*
          * The recording commands needs to be called with option QID
          * for guests that have previlege classes A or B.
          * Purging has to be done as separate step, because recording
          * can't be switched on as long as records are on the queue.
          * Doing both at the same time doesn't work.
          */
-
-        if (purge) {
+        if (purge && (action == 1)) {
+                memset(cp_command, 0x00, sizeof(cp_command));
+                memset(cp_response, 0x00, sizeof(cp_response));
                 snprintf(cp_command, sizeof(cp_command),
                          "RECORDING %s PURGE %s",
                          logptr->recording_name,
                          qid_string);
-
                 cpcmd(cp_command, cp_response, sizeof(cp_response), NULL);
         }
 
@@ -279,19 +277,33 @@ static int vmlogrdr_recording(struct vmlogrdr_priv_t * logptr,
                 logptr->recording_name,
                 onoff,
                 qid_string);
-
         cpcmd(cp_command, cp_response, sizeof(cp_response), NULL);
         /* The recording command will usually answer with 'Command complete'
          * on success, but when the specific service was never connected
          * before then there might be an additional informational message
          * 'HCPCRC8072I Recording entry not found' before the
-         * 'Command complete'. So I use strstr rather then the strncmp.
+         * 'Command complete'. So I use strstr rather then the strncmp.
          */
         if (strstr(cp_response,"Command complete"))
-                return 0;
+                rc = 0;
         else
-                return -EIO;
+                rc = -EIO;
+        /*
+         * If we turn recording off, we have to purge any remaining records
+         * afterwards, as a large number of queued records may impact z/VM
+         * performance.
+         */
+        if (purge && (action == 0)) {
+                memset(cp_command, 0x00, sizeof(cp_command));
+                memset(cp_response, 0x00, sizeof(cp_response));
+                snprintf(cp_command, sizeof(cp_command),
+                         "RECORDING %s PURGE %s",
+                         logptr->recording_name,
+                         qid_string);
+                cpcmd(cp_command, cp_response, sizeof(cp_response), NULL);
+        }
 
+        return rc;
 }
 
 
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 2ff8a22d4257..e8391b89eff4 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1455,7 +1455,16 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
                 break;
         case IO_SCH_UNREG_ATTACH:
         case IO_SCH_UNREG:
-                if (cdev)
+                if (!cdev)
+                        break;
+                if (cdev->private->state == DEV_STATE_SENSE_ID) {
+                        /*
+                         * Note: delayed work triggered by this event
+                         * and repeated calls to sch_event are synchronized
+                         * by the above check for work_pending(cdev).
+                         */
+                        dev_fsm_event(cdev, DEV_EVENT_NOTOPER);
+                } else
                         ccw_device_set_notoper(cdev);
                 break;
         case IO_SCH_NOP:
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bcdef88..ea37e2ff4164 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -126,7 +126,7 @@ if FTRACE
 config FUNCTION_TRACER
         bool "Kernel Function Tracer"
         depends on HAVE_FUNCTION_TRACER
-        select FRAME_POINTER if (!ARM_UNWIND)
+        select FRAME_POINTER if !ARM_UNWIND && !S390
         select KALLSYMS
         select GENERIC_TRACER
         select CONTEXT_SWITCH_TRACER