Merge branch 'master' of git://1984.lsi.us.es/net-next-2.6

Conflicts:
	net/ipv4/route.c

Signed-off-by: Patrick McHardy <kaber@trash.net>

9 files changed, 103 insertions, 15 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bcdef88..14674dce77a6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -69,6 +69,21 @@ config EVENT_TRACING
         select CONTEXT_SWITCH_TRACER
         bool
 
+config EVENT_POWER_TRACING_DEPRECATED
+        depends on EVENT_TRACING
+        bool "Deprecated power event trace API, to be removed"
+        default y
+        help
+          Provides old power event types:
+          C-state/idle accounting events:
+          power:power_start
+          power:power_end
+          and old cpufreq accounting event:
+          power:power_frequency
+          This is for userspace compatibility
+          and will vanish after 5 kernel iterations,
+          namely 2.6.41.
+
 config CONTEXT_SWITCH_TRACER
         bool
 
@@ -126,7 +141,7 @@ 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
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index bc251ed66724..7b8ec0281548 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -168,7 +168,6 @@ static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
 static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
                                  BLK_TC_ACT(BLK_TC_WRITE) };
 
-#define BLK_TC_HARDBARRIER      BLK_TC_BARRIER
 #define BLK_TC_RAHEAD           BLK_TC_AHEAD
 
 /* The ilog2() calls fall out because they're constant */
@@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
                 return;
 
         what |= ddir_act[rw & WRITE];
-        what |= MASK_TC_BIT(rw, HARDBARRIER);
         what |= MASK_TC_BIT(rw, SYNC);
         what |= MASK_TC_BIT(rw, RAHEAD);
         what |= MASK_TC_BIT(rw, META);
@@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 
         if (rw & REQ_RAHEAD)
                 rwbs[i++] = 'A';
-        if (rw & REQ_HARDBARRIER)
-                rwbs[i++] = 'B';
         if (rw & REQ_SYNC)
                 rwbs[i++] = 'S';
         if (rw & REQ_META)
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index a22582a06161..f55fcf61b223 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -13,5 +13,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/power.h>
 
-EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+#ifdef EVENT_POWER_TRACING_DEPRECATED
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9ed509a015d8..bd1c35a4fbcc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3853,6 +3853,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 
                 /* Need to copy one event at a time */
                 do {
+                        /* We need the size of one event, because
+                         * rb_advance_reader only advances by one event,
+                         * whereas rb_event_ts_length may include the size of
+                         * one or two events.
+                         * We have already ensured there's enough space if this
+                         * is a time extend. */
+                        size = rb_event_length(event);
                         memcpy(bpage->data + pos, rpage->data + rpos, size);
 
                         len -= size;
@@ -3867,7 +3874,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                         event = rb_reader_event(cpu_buffer);
                         /* Always keep the time extend and data together */
                         size = rb_event_ts_length(event);
-                } while (len > size);
+                } while (len >= size);
 
                 /* update bpage */
                 local_set(&bpage->commit, pos);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b8106cd0..f8cf959bad45 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
@@ -1284,6 +1283,8 @@ void trace_dump_stack(void)
         __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
 }
 
+static DEFINE_PER_CPU(int, user_stack_count);
+
 void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
@@ -1302,6 +1303,18 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
         if (unlikely(in_nmi()))
                 return;
 
+        /*
+         * prevent recursion, since the user stack tracing may
+         * trigger other kernel events.
+         */
+        preempt_disable();
+        if (__this_cpu_read(user_stack_count))
+                goto out;
+
+        __this_cpu_inc(user_stack_count);
+
+
+
         event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
                                           sizeof(*entry), flags, pc);
         if (!event)
@@ -1319,6 +1332,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
         save_stack_trace_user(&trace);
         if (!filter_check_discard(call, entry, buffer, event))
                 ring_buffer_unlock_commit(buffer, event);
+
+        __this_cpu_dec(user_stack_count);
+
+ out:
+        preempt_enable();
 }
 
 #ifdef UNUSED
@@ -2320,11 +2338,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
         return count;
 }
 
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+        if (file->f_mode & FMODE_READ)
+                return seq_lseek(file, offset, origin);
+        else
+                return 0;
+}
+
 static const struct file_operations tracing_fops = {
         .open           = tracing_open,
         .read           = seq_read,
         .write          = tracing_write_stub,
-        .llseek         = seq_lseek,
+        .llseek         = tracing_seek,
         .release        = tracing_release,
 };
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 39c059ca670e..19a359d5e6d5 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 /* Count the events in use (per event id, not per instance) */
 static int      total_ref_count;
 
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+                                 struct perf_event *p_event)
+{
+        /* No tracing, just counting, so no obvious leak */
+        if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+                return 0;
+
+        /* Some events are ok to be traced by non-root users... */
+        if (p_event->attach_state == PERF_ATTACH_TASK) {
+                if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+                        return 0;
+        }
+
+        /*
+         * ...otherwise raw tracepoint data can be a severe data leak,
+         * only allow root to have these.
+         */
+        if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        return 0;
+}
+
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
                                  struct perf_event *p_event)
 {
         struct hlist_head __percpu *list;
-        int ret = -ENOMEM;
+        int ret;
         int cpu;
 
+        ret = perf_trace_event_perm(tp_event, p_event);
+        if (ret)
+                return ret;
+
         p_event->tp_event = tp_event;
         if (tp_event->perf_refcount++ > 0)
                 return 0;
 
+        ret = -ENOMEM;
+
         list = alloc_percpu(struct hlist_head);
         if (!list)
                 goto fail;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0725eeab1937..35fde09b81de 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,6 +27,12 @@
 
 DEFINE_MUTEX(event_mutex);
 
+DEFINE_MUTEX(event_storage_mutex);
+EXPORT_SYMBOL_GPL(event_storage_mutex);
+
+char event_storage[EVENT_STORAGE_SIZE];
+EXPORT_SYMBOL_GPL(event_storage);
+
 LIST_HEAD(ftrace_events);
 LIST_HEAD(ftrace_common_fields);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4ba44deaac25..4b74d71705c0 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -83,13 +83,19 @@ static void __always_unused ____ftrace_check_##name(void)	\
 
 #undef __array
 #define __array(type, item, len)                                        \
-        BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                         \
-        ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+        do {                                                            \
+                BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                 \
+                mutex_lock(&event_storage_mutex);                       \
+                snprintf(event_storage, sizeof(event_storage),          \
+                         "%s[%d]", #type, len);                         \
+                ret = trace_define_field(event_call, event_storage, #item, \
                                  offsetof(typeof(field), item),         \
                                  sizeof(field.item),                    \
                                  is_signed_type(type), FILTER_OTHER);   \
-        if (ret)                                                        \
-                return ret;
+                mutex_unlock(&event_storage_mutex);                     \
+                if (ret)                                                \
+                        return ret;                                     \
+        } while (0);
 
 #undef __array_desc
 #define __array_desc(type, container, item, len)                        \
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 155a415b3209..659732eba07c 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -558,7 +558,7 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 static int trace_wakeup_test_thread(void *data)
 {
         /* Make this a RT thread, doesn't need to be too high */
-        struct sched_param param = { .sched_priority = 5 };
+        static const struct sched_param param = { .sched_priority = 5 };
         struct completion *x = data;
 
         sched_setscheduler(current, SCHED_FIFO, &param);