Merge commit 'v2.6.30-rc3' into tracing/hw-branch-tracing

Conflicts:
	arch/x86/kernel/ptrace.c

Merge reason: fix the conflict above, and also pick up the CONFIG_BROKEN
              dependency change from upstream so that we can remove it
	      here.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

14 files changed, 97 insertions, 45 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2246141bda4d..417d1985e299 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -312,7 +312,7 @@ config KMEMTRACE
           and profile kernel code.
 
           This requires an userspace application to use. See
-          Documentation/vm/kmemtrace.txt for more information.
+          Documentation/trace/kmemtrace.txt for more information.
 
           Saying Y will make the kernel somewhat larger and slower. However,
           if you disable kmemtrace at run-time or boot-time, the performance
@@ -403,7 +403,7 @@ config MMIOTRACE
           implementation and works via page faults. Tracing is disabled by
           default and can be enabled at run-time.
 
-          See Documentation/tracers/mmiotrace.txt.
+          See Documentation/trace/mmiotrace.txt.
           If you are not helping to develop drivers, say N.
 
 config MMIOTRACE_TEST
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 947c5b3f90c4..921ef5d1f0ba 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -327,10 +327,10 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
         char *msg;
         struct blk_trace *bt;
 
-        if (count > BLK_TN_MAX_MSG)
+        if (count >= BLK_TN_MAX_MSG)
                 return -EINVAL;
 
-        msg = kmalloc(count, GFP_KERNEL);
+        msg = kmalloc(count + 1, GFP_KERNEL);
         if (msg == NULL)
                 return -ENOMEM;
 
@@ -339,6 +339,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
                 return -EFAULT;
         }
 
+        msg[count] = '\0';
         bt = filp->private_data;
         __trace_note_message(bt, "%s", msg);
         kfree(msg);
@@ -642,7 +643,7 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
         if (blk_pc_request(rq)) {
                 what |= BLK_TC_ACT(BLK_TC_PC);
                 __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
-                                sizeof(rq->cmd), rq->cmd);
+                                rq->cmd_len, rq->cmd);
         } else  {
                 what |= BLK_TC_ACT(BLK_TC_FS);
                 __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
@@ -1376,12 +1377,12 @@ static int blk_trace_str2mask(const char *str)
 {
         int i;
         int mask = 0;
-        char *s, *token;
+        char *buf, *s, *token;
 
-        s = kstrdup(str, GFP_KERNEL);
-        if (s == NULL)
+        buf = kstrdup(str, GFP_KERNEL);
+        if (buf == NULL)
                 return -ENOMEM;
-        s = strstrip(s);
+        s = strstrip(buf);
 
         while (1) {
                 token = strsep(&s, ",");
@@ -1402,7 +1403,7 @@ static int blk_trace_str2mask(const char *str)
                         break;
                 }
         }
-        kfree(s);
+        kfree(buf);
 
         return mask;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a0174a40c563..1ce5dc6372b8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,6 +30,7 @@
 #include <linux/percpu.h>
 #include <linux/splice.h>
 #include <linux/kdebug.h>
+#include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
@@ -147,8 +148,7 @@ static int __init set_ftrace_dump_on_oops(char *str)
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
-long
-ns2usecs(cycle_t nsec)
+unsigned long long ns2usecs(cycle_t nsec)
 {
         nsec += 500;
         do_div(nsec, 1000);
@@ -1632,7 +1632,11 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
                 return;
 
         cpumask_set_cpu(iter->cpu, iter->started);
-        trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
+
+        /* Don't print started cpu buffer for the first entry of the trace */
+        if (iter->idx > 1)
+                trace_seq_printf(s, "##### CPU %u buffer started ####\n",
+                                iter->cpu);
 }
 
 static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
@@ -1867,6 +1871,11 @@ __tracing_open(struct inode *inode, struct file *file)
         if (current_trace)
                 *iter->trace = *current_trace;
 
+        if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+                goto fail;
+
+        cpumask_clear(iter->started);
+
         if (current_trace && current_trace->print_max)
                 iter->tr = &max_tr;
         else
@@ -1917,6 +1926,7 @@ __tracing_open(struct inode *inode, struct file *file)
                 if (iter->buffer_iter[cpu])
                         ring_buffer_read_finish(iter->buffer_iter[cpu]);
         }
+        free_cpumask_var(iter->started);
  fail:
         mutex_unlock(&trace_types_lock);
         kfree(iter->trace);
@@ -1960,6 +1970,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
         seq_release(inode, file);
         mutex_destroy(&iter->mutex);
+        free_cpumask_var(iter->started);
         kfree(iter->trace);
         kfree(iter);
         return 0;
@@ -2358,9 +2369,9 @@ static const char readme_msg[] =
         "# mkdir /debug\n"
         "# mount -t debugfs nodev /debug\n\n"
         "# cat /debug/tracing/available_tracers\n"
-        "wakeup preemptirqsoff preemptoff irqsoff ftrace sched_switch none\n\n"
+        "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
         "# cat /debug/tracing/current_tracer\n"
-        "none\n"
+        "nop\n"
         "# echo sched_switch > /debug/tracing/current_tracer\n"
         "# cat /debug/tracing/current_tracer\n"
         "sched_switch\n"
@@ -3266,19 +3277,13 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
         info->tr        = &global_trace;
         info->cpu       = cpu;
-        info->spare     = ring_buffer_alloc_read_page(info->tr->buffer);
+        info->spare     = NULL;
         /* Force reading ring buffer for first read */
         info->read      = (unsigned int)-1;
-        if (!info->spare)
-                goto out;
 
         filp->private_data = info;
 
-        return 0;
-
- out:
-        kfree(info);
-        return -ENOMEM;
+        return nonseekable_open(inode, filp);
 }
 
 static ssize_t
@@ -3293,6 +3298,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
         if (!count)
                 return 0;
 
+        if (!info->spare)
+                info->spare = ring_buffer_alloc_read_page(info->tr->buffer);
+        if (!info->spare)
+                return -ENOMEM;
+
         /* Do we have previous read data to read? */
         if (info->read < PAGE_SIZE)
                 goto read;
@@ -3331,7 +3341,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 {
         struct ftrace_buffer_info *info = file->private_data;
 
-        ring_buffer_free_read_page(info->tr->buffer, info->spare);
+        if (info->spare)
+                ring_buffer_free_read_page(info->tr->buffer, info->spare);
         kfree(info);
 
         return 0;
@@ -3417,14 +3428,19 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
         int size, i;
         size_t ret;
 
-        /*
-         * We can't seek on a buffer input
-         */
-        if (unlikely(*ppos))
-                return -ESPIPE;
+        if (*ppos & (PAGE_SIZE - 1)) {
+                WARN_ONCE(1, "Ftrace: previous read must page-align\n");
+                return -EINVAL;
+        }
 
+        if (len & (PAGE_SIZE - 1)) {
+                WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
+                if (len < PAGE_SIZE)
+                        return -EINVAL;
+                len &= PAGE_MASK;
+        }
 
-        for (i = 0; i < PIPE_BUFFERS && len; i++, len -= size) {
+        for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) {
                 struct page *page;
                 int r;
 
@@ -3463,6 +3479,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 spd.partial[i].offset = 0;
                 spd.partial[i].private = (unsigned long)ref;
                 spd.nr_pages++;
+                *ppos += PAGE_SIZE;
         }
 
         spd.nr_pages = i;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9e15802cca9f..7c3f49aad6e2 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -604,7 +604,7 @@ extern int trace_selftest_startup_hw_branches(struct tracer *trace,
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
-extern long ns2usecs(cycle_t nsec);
+extern unsigned long long ns2usecs(cycle_t nsec);
 extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index ad8c22efff41..8333715e4066 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -155,6 +155,13 @@ static enum print_line_t trace_branch_print(struct trace_iterator *iter,
         return TRACE_TYPE_HANDLED;
 }
 
+static void branch_print_header(struct seq_file *s)
+{
+        seq_puts(s, "#           TASK-PID    CPU#    TIMESTAMP  CORRECT"
+                "  FUNC:FILE:LINE\n");
+        seq_puts(s, "#              | |       |          |         |   "
+                "    |\n");
+}
 
 static struct trace_event trace_branch_event = {
         .type           = TRACE_BRANCH,
@@ -169,6 +176,7 @@ static struct tracer branch_trace __read_mostly =
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest       = trace_selftest_startup_branch,
 #endif /* CONFIG_FTRACE_SELFTEST */
+        .print_header   = branch_print_header,
 };
 
 __init static int init_branch_tracer(void)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 64ec4d278ffb..576f4fa2af0d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -503,6 +503,7 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
         if (copy_from_user(&buf, ubuf, cnt))
                 return -EFAULT;
+        buf[cnt] = '\0';
 
         pred = kzalloc(sizeof(*pred), GFP_KERNEL);
         if (!pred)
@@ -520,9 +521,10 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
                 return cnt;
         }
 
-        if (filter_add_pred(call, pred)) {
+        err = filter_add_pred(call, pred);
+        if (err < 0) {
                 filter_free_pred(pred);
-                return -EINVAL;
+                return err;
         }
 
         *ppos += cnt;
@@ -569,6 +571,7 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
         if (copy_from_user(&buf, ubuf, cnt))
                 return -EFAULT;
+        buf[cnt] = '\0';
 
         pred = kzalloc(sizeof(*pred), GFP_KERNEL);
         if (!pred)
@@ -586,10 +589,11 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
                 return cnt;
         }
 
-        if (filter_add_subsystem_pred(system, pred)) {
+        err = filter_add_subsystem_pred(system, pred);
+        if (err < 0) {
                 filter_free_subsystem_preds(system);
                 filter_free_pred(pred);
-                return -EINVAL;
+                return err;
         }
 
         *ppos += cnt;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 026be412f356..e03cbf1e38f3 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -215,7 +215,7 @@ static int __filter_add_pred(struct ftrace_event_call *call,
                 }
         }
 
-        return -ENOMEM;
+        return -ENOSPC;
 }
 
 static int is_string_field(const char *type)
@@ -319,7 +319,7 @@ int filter_add_subsystem_pred(struct event_subsystem *system,
         }
 
         if (i == MAX_FILTER_PRED)
-                return -EINVAL;
+                return -ENOSPC;
 
         events_for_each(call) {
                 int err;
@@ -410,16 +410,22 @@ int filter_parse(char **pbuf, struct filter_pred *pred)
                 }
         }
 
+        if (!val_str) {
+                pred->field_name = NULL;
+                return -EINVAL;
+        }
+
         pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
         if (!pred->field_name)
                 return -ENOMEM;
 
-        pred->val = simple_strtoull(val_str, &tmp, 10);
+        pred->val = simple_strtoull(val_str, &tmp, 0);
         if (tmp == val_str) {
                 pred->str_val = kstrdup(val_str, GFP_KERNEL);
                 if (!pred->str_val)
                         return -ENOMEM;
-        }
+        } else if (*tmp != '\0')
+                return -EINVAL;
 
         return 0;
 }
diff --git a/kernel/trace/trace_events_stage_2.h b/kernel/trace/trace_events_stage_2.h
index 30743f7d4110..d363c6672c6c 100644
--- a/kernel/trace/trace_events_stage_2.h
+++ b/kernel/trace/trace_events_stage_2.h
@@ -105,10 +105,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
                 return 0;
 
 #undef __entry
-#define __entry "REC"
+#define __entry REC
 
 #undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, #args
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
 
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4d9952d3df50..07a22c33ebf3 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -40,7 +40,7 @@
 
 #undef TRACE_FIELD_ZERO_CHAR
 #define TRACE_FIELD_ZERO_CHAR(item)                                     \
-        ret = trace_seq_printf(s, "\tfield: char " #item ";\t"          \
+        ret = trace_seq_printf(s, "\tfield:char " #item ";\t"           \
                                "offset:%u;\tsize:0;\n",                 \
                                (unsigned int)offsetof(typeof(field), item)); \
         if (!ret)                                                       \
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index d72b9a63b247..64b54a59c55b 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -423,7 +423,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 
                 trace_find_cmdline(entry->pid, comm);
 
-                ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08lx]"
+                ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]"
                                        " %ld.%03ldms (+%ld.%03ldms): ", comm,
                                        entry->pid, iter->cpu, entry->flags,
                                        entry->preempt_count, iter->idx,
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index bae791ebcc51..118439709fb7 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -186,6 +186,12 @@ static enum print_line_t power_print_line(struct trace_iterator *iter)
         return TRACE_TYPE_UNHANDLED;
 }
 
+static void power_print_header(struct seq_file *s)
+{
+        seq_puts(s, "#   TIMESTAMP      STATE  EVENT\n");
+        seq_puts(s, "#       |            |      |\n");
+}
+
 static struct tracer power_tracer __read_mostly =
 {
         .name           = "power",
@@ -194,6 +200,7 @@ static struct tracer power_tracer __read_mostly =
         .stop           = stop_power_trace,
         .reset          = power_trace_reset,
         .print_line     = power_print_line,
+        .print_header   = power_print_header,
 };
 
 static int init_power_trace(void)
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index de35f200abd3..9117cea6f1ae 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -62,6 +62,9 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
         pc = preempt_count();
         tracing_record_cmdline(current);
 
+        if (sched_stopped)
+                return;
+
         local_irq_save(flags);
         cpu = raw_smp_processor_id();
         data = ctx_trace->data[cpu];
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3c5ad6b2ec84..5bc00e8f153e 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -154,7 +154,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
         if (unlikely(!tracer_enabled || next != wakeup_task))
                 goto out_unlock;
 
-        trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+        trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
         tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
         /*
@@ -257,6 +257,12 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
         data = wakeup_trace->data[wakeup_cpu];
         data->preempt_timestamp = ftrace_now(cpu);
         tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
+
+        /*
+         * We must be careful in using CALLER_ADDR2. But since wake_up
+         * is not called by an assembly function  (where as schedule is)
+         * it should be safe to use it here.
+         */
         trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked:
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a2a3af29c943..5e579645ac86 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,5 @@
+#include <trace/syscall.h>
 #include <linux/kernel.h>
-#include <linux/ftrace.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"