Pull miscellaneous into release branch

Conflicts:

	arch/ia64/kernel/mca.c

10 files changed, 214 insertions, 61 deletions

diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 5865130b0a92..230a6f92367f 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -7,6 +7,7 @@
 #define ASM_OFFSETS_C 1
 
 #include <linux/sched.h>
+#include <linux/pid.h>
 #include <linux/clocksource.h>
 
 #include <asm-ia64/processor.h>
@@ -34,6 +35,9 @@ void foo(void)
         DEFINE(SIGFRAME_SIZE, sizeof (struct sigframe));
         DEFINE(UNW_FRAME_INFO_SIZE, sizeof (struct unw_frame_info));
 
+        BUILD_BUG_ON(sizeof(struct upid) != 32);
+        DEFINE(IA64_UPID_SHIFT, 5);
+
         BLANK();
 
         DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
@@ -51,6 +55,9 @@ void foo(void)
         DEFINE(IA64_TASK_BLOCKED_OFFSET,offsetof (struct task_struct, blocked));
         DEFINE(IA64_TASK_CLEAR_CHILD_TID_OFFSET,offsetof (struct task_struct, clear_child_tid));
         DEFINE(IA64_TASK_GROUP_LEADER_OFFSET, offsetof (struct task_struct, group_leader));
+        DEFINE(IA64_TASK_TGIDLINK_OFFSET, offsetof (struct task_struct, pids[PIDTYPE_PID].pid));
+        DEFINE(IA64_PID_LEVEL_OFFSET, offsetof (struct pid, level));
+        DEFINE(IA64_PID_UPID_OFFSET, offsetof (struct pid, numbers[0]));
         DEFINE(IA64_TASK_PENDING_OFFSET,offsetof (struct task_struct, pending));
         DEFINE(IA64_TASK_PID_OFFSET, offsetof (struct task_struct, pid));
         DEFINE(IA64_TASK_REAL_PARENT_OFFSET, offsetof (struct task_struct, real_parent));
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index fbe742ad2fde..90ef338cf46f 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -24,6 +24,7 @@ int kdump_status[NR_CPUS];
 static atomic_t kdump_cpu_frozen;
 atomic_t kdump_in_progress;
 static int kdump_on_init = 1;
+static int kdump_on_fatal_mca = 1;
 
 static inline Elf64_Word
 *append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data,
@@ -118,6 +119,7 @@ machine_crash_shutdown(struct pt_regs *pt)
 static void
 machine_kdump_on_init(void)
 {
+        crash_save_vmcoreinfo();
         local_irq_disable();
         kexec_disable_iosapic();
         machine_kexec(ia64_kimage);
@@ -148,7 +150,7 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
         struct ia64_mca_notify_die *nd;
         struct die_args *args = data;
 
-        if (!kdump_on_init)
+        if (!kdump_on_init && !kdump_on_fatal_mca)
                 return NOTIFY_DONE;
 
         if (!ia64_kimage) {
@@ -173,32 +175,38 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
                 return NOTIFY_DONE;
 
         switch (val) {
-                case DIE_INIT_MONARCH_PROCESS:
+        case DIE_INIT_MONARCH_PROCESS:
+                if (kdump_on_init) {
                         atomic_set(&kdump_in_progress, 1);
                         *(nd->monarch_cpu) = -1;
-                        break;
-                case DIE_INIT_MONARCH_LEAVE:
+                }
+                break;
+        case DIE_INIT_MONARCH_LEAVE:
+                if (kdump_on_init)
                         machine_kdump_on_init();
-                        break;
-                case DIE_INIT_SLAVE_LEAVE:
-                        if (atomic_read(&kdump_in_progress))
-                                unw_init_running(kdump_cpu_freeze, NULL);
-                        break;
-                case DIE_MCA_RENDZVOUS_LEAVE:
-                        if (atomic_read(&kdump_in_progress))
-                                unw_init_running(kdump_cpu_freeze, NULL);
-                        break;
-                case DIE_MCA_MONARCH_LEAVE:
-                     /* die_register->signr indicate if MCA is recoverable */
-                        if (!args->signr)
-                                machine_kdump_on_init();
-                        break;
+                break;
+        case DIE_INIT_SLAVE_LEAVE:
+                if (atomic_read(&kdump_in_progress))
+                        unw_init_running(kdump_cpu_freeze, NULL);
+                break;
+        case DIE_MCA_RENDZVOUS_LEAVE:
+                if (atomic_read(&kdump_in_progress))
+                        unw_init_running(kdump_cpu_freeze, NULL);
+                break;
+        case DIE_MCA_MONARCH_LEAVE:
+                /* die_register->signr indicate if MCA is recoverable */
+                if (kdump_on_fatal_mca && !args->signr) {
+                        atomic_set(&kdump_in_progress, 1);
+                        *(nd->monarch_cpu) = -1;
+                        machine_kdump_on_init();
+                }
+                break;
         }
         return NOTIFY_DONE;
 }
 
 #ifdef CONFIG_SYSCTL
-static ctl_table kdump_on_init_table[] = {
+static ctl_table kdump_ctl_table[] = {
         {
                 .ctl_name = CTL_UNNUMBERED,
                 .procname = "kdump_on_init",
@@ -207,6 +215,14 @@ static ctl_table kdump_on_init_table[] = {
                 .mode = 0644,
                 .proc_handler = &proc_dointvec,
         },
+        {
+                .ctl_name = CTL_UNNUMBERED,
+                .procname = "kdump_on_fatal_mca",
+                .data = &kdump_on_fatal_mca,
+                .maxlen = sizeof(int),
+                .mode = 0644,
+                .proc_handler = &proc_dointvec,
+        },
         { .ctl_name = 0 }
 };
 
@@ -215,7 +231,7 @@ static ctl_table sys_table[] = {
           .ctl_name = CTL_KERN,
           .procname = "kernel",
           .mode = 0555,
-          .child = kdump_on_init_table,
+          .child = kdump_ctl_table,
         },
         { .ctl_name = 0 }
 };
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 357b7e2adc63..c1625c7e1779 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -61,13 +61,29 @@ ENTRY(fsys_getpid)
         .prologue
         .altrp b6
         .body
+        add r17=IA64_TASK_GROUP_LEADER_OFFSET,r16
+        ;;
+        ld8 r17=[r17]                           // r17 = current->group_leader
         add r9=TI_FLAGS+IA64_TASK_SIZE,r16
         ;;
         ld4 r9=[r9]
-        add r8=IA64_TASK_TGID_OFFSET,r16
+        add r17=IA64_TASK_TGIDLINK_OFFSET,r17
         ;;
         and r9=TIF_ALLWORK_MASK,r9
-        ld4 r8=[r8]                             // r8 = current->tgid
+        ld8 r17=[r17]                           // r17 = current->group_leader->pids[PIDTYPE_PID].pid
+        ;;
+        add r8=IA64_PID_LEVEL_OFFSET,r17
+        ;;
+        ld4 r8=[r8]                             // r8 = pid->level
+        add r17=IA64_PID_UPID_OFFSET,r17        // r17 = &pid->numbers[0]
+        ;;
+        shl r8=r8,IA64_UPID_SHIFT
+        ;;
+        add r17=r17,r8                          // r17 = &pid->numbers[pid->level]
+        ;;
+        ld4 r8=[r17]                            // r8 = pid->numbers[pid->level].nr
+        ;;
+        mov r17=0
         ;;
         cmp.ne p8,p0=0,r9
 (p8)    br.spnt.many fsys_fallback_syscall
@@ -126,15 +142,25 @@ ENTRY(fsys_set_tid_address)
         .altrp b6
         .body
         add r9=TI_FLAGS+IA64_TASK_SIZE,r16
+        add r17=IA64_TASK_TGIDLINK_OFFSET,r16
         ;;
         ld4 r9=[r9]
         tnat.z p6,p7=r32                // check argument register for being NaT
+        ld8 r17=[r17]                           // r17 = current->pids[PIDTYPE_PID].pid
         ;;
         and r9=TIF_ALLWORK_MASK,r9
-        add r8=IA64_TASK_PID_OFFSET,r16
+        add r8=IA64_PID_LEVEL_OFFSET,r17
         add r18=IA64_TASK_CLEAR_CHILD_TID_OFFSET,r16
         ;;
-        ld4 r8=[r8]
+        ld4 r8=[r8]                             // r8 = pid->level
+        add r17=IA64_PID_UPID_OFFSET,r17        // r17 = &pid->numbers[0]
+        ;;
+        shl r8=r8,IA64_UPID_SHIFT
+        ;;
+        add r17=r17,r8                          // r17 = &pid->numbers[pid->level]
+        ;;
+        ld4 r8=[r17]                            // r8 = pid->numbers[pid->level].nr
+        ;;
         cmp.ne p8,p0=0,r9
         mov r17=-1
         ;;
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index d8be23fbe6bc..5538471e8d68 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -472,7 +472,7 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
                         static unsigned char count;
                         static long last_time;
 
-                        if (jiffies - last_time > 5*HZ)
+                        if (time_after(jiffies, last_time + 5 * HZ))
                                 count = 0;
                         if (++count < 5) {
                                 last_time = jiffies;
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 8d9a446a0d17..233434f4f88f 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -78,6 +78,20 @@ static enum instruction_type bundle_encoding[32][3] = {
   { u, u, u },                          /* 1F */
 };
 
+/* Insert a long branch code */
+static void __kprobes set_brl_inst(void *from, void *to)
+{
+        s64 rel = ((s64) to - (s64) from) >> 4;
+        bundle_t *brl;
+        brl = (bundle_t *) ((u64) from & ~0xf);
+        brl->quad0.template = 0x05;     /* [MLX](stop) */
+        brl->quad0.slot0 = NOP_M_INST;  /* nop.m 0x0 */
+        brl->quad0.slot1_p0 = ((rel >> 20) & 0x7fffffffff) << 2;
+        brl->quad1.slot1_p1 = (((rel >> 20) & 0x7fffffffff) << 2) >> (64 - 46);
+        /* brl.cond.sptk.many.clr rel<<4 (qp=0) */
+        brl->quad1.slot2 = BRL_INST(rel >> 59, rel & 0xfffff);
+}
+
 /*
  * In this function we check to see if the instruction
  * is IP relative instruction and update the kprobe
@@ -496,6 +510,77 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
         regs->b0 = ((struct fnptr *)kretprobe_trampoline)->ip;
 }
 
+/* Check the instruction in the slot is break */
+static int __kprobes __is_ia64_break_inst(bundle_t *bundle, uint slot)
+{
+        unsigned int major_opcode;
+        unsigned int template = bundle->quad0.template;
+        unsigned long kprobe_inst;
+
+        /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */
+        if (slot == 1 && bundle_encoding[template][1] == L)
+                slot++;
+
+        /* Get Kprobe probe instruction at given slot*/
+        get_kprobe_inst(bundle, slot, &kprobe_inst, &major_opcode);
+
+        /* For break instruction,
+         * Bits 37:40 Major opcode to be zero
+         * Bits 27:32 X6 to be zero
+         * Bits 32:35 X3 to be zero
+         */
+        if (major_opcode || ((kprobe_inst >> 27) & 0x1FF)) {
+                /* Not a break instruction */
+                return 0;
+        }
+
+        /* Is a break instruction */
+        return 1;
+}
+
+/*
+ * In this function, we check whether the target bundle modifies IP or
+ * it triggers an exception. If so, it cannot be boostable.
+ */
+static int __kprobes can_boost(bundle_t *bundle, uint slot,
+                               unsigned long bundle_addr)
+{
+        unsigned int template = bundle->quad0.template;
+
+        do {
+                if (search_exception_tables(bundle_addr + slot) ||
+                    __is_ia64_break_inst(bundle, slot))
+                        return 0;       /* exception may occur in this bundle*/
+        } while ((++slot) < 3);
+        template &= 0x1e;
+        if (template >= 0x10 /* including B unit */ ||
+            template == 0x04 /* including X unit */ ||
+            template == 0x06) /* undefined */
+                return 0;
+
+        return 1;
+}
+
+/* Prepare long jump bundle and disables other boosters if need */
+static void __kprobes prepare_booster(struct kprobe *p)
+{
+        unsigned long addr = (unsigned long)p->addr & ~0xFULL;
+        unsigned int slot = (unsigned long)p->addr & 0xf;
+        struct kprobe *other_kp;
+
+        if (can_boost(&p->ainsn.insn[0].bundle, slot, addr)) {
+                set_brl_inst(&p->ainsn.insn[1].bundle, (bundle_t *)addr + 1);
+                p->ainsn.inst_flag |= INST_FLAG_BOOSTABLE;
+        }
+
+        /* disables boosters in previous slots */
+        for (; addr < (unsigned long)p->addr; addr++) {
+                other_kp = get_kprobe((void *)addr);
+                if (other_kp)
+                        other_kp->ainsn.inst_flag &= ~INST_FLAG_BOOSTABLE;
+        }
+}
+
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
         unsigned long addr = (unsigned long) p->addr;
@@ -530,6 +615,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 
         prepare_break_inst(template, slot, major_opcode, kprobe_inst, p, qp);
 
+        prepare_booster(p);
+
         return 0;
 }
 
@@ -543,7 +630,9 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
         src = &p->opcode.bundle;
 
         flush_icache_range((unsigned long)p->ainsn.insn,
-                        (unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
+                           (unsigned long)p->ainsn.insn +
+                           sizeof(kprobe_opcode_t) * MAX_INSN_SIZE);
+
         switch (p->ainsn.slot) {
                 case 0:
                         dest->quad0.slot0 = src->quad0.slot0;
@@ -584,13 +673,13 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
         mutex_lock(&kprobe_mutex);
-        free_insn_slot(p->ainsn.insn, 0);
+        free_insn_slot(p->ainsn.insn, p->ainsn.inst_flag & INST_FLAG_BOOSTABLE);
         mutex_unlock(&kprobe_mutex);
 }
 /*
  * We are resuming execution after a single step fault, so the pt_regs
  * structure reflects the register state after we executed the instruction
- * located in the kprobe (p->ainsn.insn.bundle).  We still need to adjust
+ * located in the kprobe (p->ainsn.insn->bundle).  We still need to adjust
  * the ip to point back to the original stack address. To set the IP address
  * to original stack address, handle the case where we need to fixup the
  * relative IP address and/or fixup branch register.
@@ -607,7 +696,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
         if (slot == 1 && bundle_encoding[template][1] == L)
                 slot = 2;
 
-        if (p->ainsn.inst_flag) {
+        if (p->ainsn.inst_flag & ~INST_FLAG_BOOSTABLE) {
 
                 if (p->ainsn.inst_flag & INST_FLAG_FIX_RELATIVE_IP_ADDR) {
                         /* Fix relative IP address */
@@ -686,33 +775,12 @@ static void __kprobes prepare_ss(struct kprobe *p, struct pt_regs *regs)
 static int __kprobes is_ia64_break_inst(struct pt_regs *regs)
 {
         unsigned int slot = ia64_psr(regs)->ri;
-        unsigned int template, major_opcode;
-        unsigned long kprobe_inst;
         unsigned long *kprobe_addr = (unsigned long *)regs->cr_iip;
         bundle_t bundle;
 
         memcpy(&bundle, kprobe_addr, sizeof(bundle_t));
-        template = bundle.quad0.template;
-
-        /* Move to slot 2, if bundle is MLX type and kprobe slot is 1 */
-        if (slot == 1 && bundle_encoding[template][1] == L)
-                slot++;
 
-        /* Get Kprobe probe instruction at given slot*/
-        get_kprobe_inst(&bundle, slot, &kprobe_inst, &major_opcode);
-
-        /* For break instruction,
-         * Bits 37:40 Major opcode to be zero
-         * Bits 27:32 X6 to be zero
-         * Bits 32:35 X3 to be zero
-         */
-        if (major_opcode || ((kprobe_inst >> 27) & 0x1FF) ) {
-                /* Not a break instruction */
-                return 0;
-        }
-
-        /* Is a break instruction */
-        return 1;
+        return __is_ia64_break_inst(&bundle, slot);
 }
 
 static int __kprobes pre_kprobes_handler(struct die_args *args)
@@ -802,6 +870,19 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
                 return 1;
 
 ss_probe:
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM)
+        if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
+                /* Boost up -- we can execute copied instructions directly */
+                ia64_psr(regs)->ri = p->ainsn.slot;
+                regs->cr_iip = (unsigned long)&p->ainsn.insn->bundle & ~0xFULL;
+                /* turn single stepping off */
+                ia64_psr(regs)->ss = 0;
+
+                reset_current_kprobe();
+                preempt_enable_no_resched();
+                return 1;
+        }
+#endif
         prepare_ss(p, regs);
         kcb->kprobe_status = KPROBE_HIT_SS;
         return 1;
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 607006a6a976..e51bced3b0fa 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -69,6 +69,7 @@
  * 2007-04-27 Russ Anderson <rja@sgi.com>
  *            Support multiple cpus going through OS_MCA in the same event.
  */
+#include <linux/jiffies.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -295,7 +296,8 @@ static void ia64_mlogbuf_dump_from_init(void)
         if (mlogbuf_finished)
                 return;
 
-        if (mlogbuf_timestamp && (mlogbuf_timestamp + 30*HZ > jiffies)) {
+        if (mlogbuf_timestamp &&
+                        time_before(jiffies, mlogbuf_timestamp + 30 * HZ)) {
                 printk(KERN_ERR "INIT: mlogbuf_dump is interrupted by INIT "
                         " and the system seems to be messed up.\n");
                 ia64_mlogbuf_finish(0);
@@ -1311,20 +1313,17 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
         } else {
                 /* Dump buffered message to console */
                 ia64_mlogbuf_finish(1);
-#ifdef CONFIG_KEXEC
-                atomic_set(&kdump_in_progress, 1);
-                monarch_cpu = -1;
-#endif
         }
+
         if (__get_cpu_var(ia64_mca_tr_reload)) {
                 mca_insert_tr(0x1); /*Reload dynamic itrs*/
                 mca_insert_tr(0x2); /*Reload dynamic itrs*/
         }
+
         if (notify_die(DIE_MCA_MONARCH_LEAVE, "MCA", regs, (long)&nd, 0, recover)
                         == NOTIFY_STOP)
                 ia64_mca_spin(__func__);
 
-
         if (atomic_dec_return(&mca_count) > 0) {
                 int i;
 
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index a2aabfdc80d9..d1d24f4598da 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -4204,10 +4204,10 @@ pfm_check_task_exist(pfm_context_t *ctx)
         do_each_thread (g, t) {
                 if (t->thread.pfm_context == ctx) {
                         ret = 0;
-                        break;
+                        goto out;
                 }
         } while_each_thread (g, t);
-
+out:
         read_unlock(&tasklist_lock);
 
         DPRINT(("pfm_check_task_exist: ret=%d ctx=%p\n", ret, ctx));
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index b86a072418a2..5015ca1275ca 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -177,6 +177,29 @@ filter_rsvd_memory (unsigned long start, unsigned long end, void *arg)
         return 0;
 }
 
+/*
+ * Similar to "filter_rsvd_memory()", but the reserved memory ranges
+ * are not filtered out.
+ */
+int __init
+filter_memory(unsigned long start, unsigned long end, void *arg)
+{
+        void (*func)(unsigned long, unsigned long, int);
+
+#if IGNORE_PFN0
+        if (start == PAGE_OFFSET) {
+                printk(KERN_WARNING "warning: skipping physical page 0\n");
+                start += PAGE_SIZE;
+                if (start >= end)
+                        return 0;
+        }
+#endif
+        func = arg;
+        if (start < end)
+                call_pernode_memory(__pa(start), end - start, func);
+        return 0;
+}
+
 static void __init
 sort_regions (struct rsvd_region *rsvd_region, int max)
 {
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 32ee5979a042..16483be18c0b 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -400,9 +400,9 @@ smp_callin (void)
         /* Setup the per cpu irq handling data structures */
         __setup_vector_irq(cpuid);
         cpu_set(cpuid, cpu_online_map);
-        unlock_ipi_calllock();
         per_cpu(cpu_state, cpuid) = CPU_ONLINE;
         spin_unlock(&vector_lock);
+        unlock_ipi_calllock();
 
         smp_setup_percpu_timer();
 
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 6903361d11a5..ff0e7c10faa7 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -13,6 +13,7 @@
  * 2001/08/13   Correct size of extended floats (float_fsz) from 16 to 10 bytes.
  * 2001/01/17   Add support emulation of unaligned kernel accesses.
  */
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/tty.h>
@@ -1290,7 +1291,7 @@ within_logging_rate_limit (void)
 {
         static unsigned long count, last_time;
 
-        if (jiffies - last_time > 5*HZ)
+        if (time_after(jiffies, last_time + 5 * HZ))
                 count = 0;
         if (count < 5) {
                 last_time = jiffies;