1 files changed, 133 insertions, 71 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3ec2ee6f6560..086d36316805 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -33,10 +33,10 @@
 #include <linux/kdebug.h>
 #include <linux/string.h>
 #include <linux/rwsem.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
-#include <linux/gfp.h>
 #include <linux/fs.h>
 
 #include "trace.h"
@@ -117,9 +117,12 @@ static cpumask_var_t __read_mostly	tracing_buffer_mask;
  *
  * It is default off, but you can enable it with either specifying
  * "ftrace_dump_on_oops" in the kernel command line, or setting
- * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ * /proc/sys/kernel/ftrace_dump_on_oops
+ * Set 1 if you want to dump buffers of all CPUs
+ * Set 2 if you want to dump the buffer of the CPU that triggered oops
  */
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
 
 static int tracing_set_tracer(const char *buf);
 
@@ -139,8 +142,17 @@ __setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {
-        ftrace_dump_on_oops = 1;
-        return 1;
+        if (*str++ != '=' || !*str) {
+                ftrace_dump_on_oops = DUMP_ALL;
+                return 1;
+        }
+
+        if (!strcmp("orig_cpu", str)) {
+                ftrace_dump_on_oops = DUMP_ORIG;
+                return 1;
+        }
+
+        return 0;
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
@@ -1545,7 +1557,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+                unsigned long *lost_events)
 {
         struct ring_buffer_event *event;
         struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1556,7 +1569,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
         if (buf_iter)
                 event = ring_buffer_iter_peek(buf_iter, ts);
         else
-                event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+                event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+                                         lost_events);
 
         ftrace_enable_cpu();
 
@@ -1564,10 +1578,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+                  unsigned long *missing_events, u64 *ent_ts)
 {
         struct ring_buffer *buffer = iter->tr->buffer;
         struct trace_entry *ent, *next = NULL;
+        unsigned long lost_events = 0, next_lost = 0;
         int cpu_file = iter->cpu_file;
         u64 next_ts = 0, ts;
         int next_cpu = -1;
@@ -1580,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
         if (cpu_file > TRACE_PIPE_ALL_CPU) {
                 if (ring_buffer_empty_cpu(buffer, cpu_file))
                         return NULL;
-                ent = peek_next_entry(iter, cpu_file, ent_ts);
+                ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
                 if (ent_cpu)
                         *ent_cpu = cpu_file;
 
@@ -1592,7 +1608,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
                 if (ring_buffer_empty_cpu(buffer, cpu))
                         continue;
 
-                ent = peek_next_entry(iter, cpu, &ts);
+                ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
                 /*
                  * Pick the entry with the smallest timestamp:
@@ -1601,6 +1617,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
                         next = ent;
                         next_cpu = cpu;
                         next_ts = ts;
+                        next_lost = lost_events;
                 }
         }
 
@@ -1610,6 +1627,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
         if (ent_ts)
                 *ent_ts = next_ts;
 
+        if (missing_events)
+                *missing_events = next_lost;
+
         return next;
 }
 
@@ -1617,13 +1637,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
                                           int *ent_cpu, u64 *ent_ts)
 {
-        return __find_next_entry(iter, ent_cpu, ent_ts);
+        return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-        iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+        iter->ent = __find_next_entry(iter, &iter->cpu,
+                                      &iter->lost_events, &iter->ts);
 
         if (iter->ent)
                 trace_iterator_increment(iter);
@@ -1635,7 +1656,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
         /* Don't allow ftrace to trace into the ring buffers */
         ftrace_disable_cpu();
-        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+                            &iter->lost_events);
         ftrace_enable_cpu();
 }
 
@@ -1786,7 +1808,7 @@ static void print_func_help_header(struct seq_file *m)
 }
 
 
-static void
+void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1914,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
         }
 
         if (event)
-                return event->trace(iter, sym_flags);
+                return event->funcs->trace(iter, sym_flags, event);
 
         if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
                 goto partial;
@@ -1940,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
         event = ftrace_find_event(entry->type);
         if (event)
-                return event->raw(iter, 0);
+                return event->funcs->raw(iter, 0, event);
 
         if (!trace_seq_printf(s, "%d ?\n", entry->type))
                 goto partial;
@@ -1967,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
         event = ftrace_find_event(entry->type);
         if (event) {
-                enum print_line_t ret = event->hex(iter, 0);
+                enum print_line_t ret = event->funcs->hex(iter, 0, event);
                 if (ret != TRACE_TYPE_HANDLED)
                         return ret;
         }
@@ -1992,10 +2014,11 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
         }
 
         event = ftrace_find_event(entry->type);
-        return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+        return event ? event->funcs->binary(iter, 0, event) :
+                TRACE_TYPE_HANDLED;
 }
 
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
 {
         int cpu;
 
@@ -2030,6 +2053,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
         enum print_line_t ret;
 
+        if (iter->lost_events)
+                trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+                                 iter->cpu, iter->lost_events);
+
         if (iter->trace && iter->trace->print_line) {
                 ret = iter->trace->print_line(iter);
                 if (ret != TRACE_TYPE_UNHANDLED)
@@ -2058,6 +2085,23 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
         return print_trace_fmt(iter);
 }
 
+void trace_default_header(struct seq_file *m)
+{
+        struct trace_iterator *iter = m->private;
+
+        if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+                /* print nothing if the buffers are empty */
+                if (trace_empty(iter))
+                        return;
+                print_trace_header(m, iter);
+                if (!(trace_flags & TRACE_ITER_VERBOSE))
+                        print_lat_help_header(m);
+        } else {
+                if (!(trace_flags & TRACE_ITER_VERBOSE))
+                        print_func_help_header(m);
+        }
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
         struct trace_iterator *iter = v;
@@ -2070,17 +2114,9 @@ static int s_show(struct seq_file *m, void *v)
                 }
                 if (iter->trace && iter->trace->print_header)
                         iter->trace->print_header(m);
-                else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
-                        /* print nothing if the buffers are empty */
-                        if (trace_empty(iter))
-                                return 0;
-                        print_trace_header(m, iter);
-                        if (!(trace_flags & TRACE_ITER_VERBOSE))
-                                print_lat_help_header(m);
-                } else {
-                        if (!(trace_flags & TRACE_ITER_VERBOSE))
-                                print_func_help_header(m);
-                }
+                else
+                        trace_default_header(m);
+
         } else if (iter->leftover) {
                 /*
                  * If we filled the seq_file buffer earlier, we
@@ -2166,15 +2202,20 @@ __tracing_open(struct inode *inode, struct file *file)
 
         if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
                 for_each_tracing_cpu(cpu) {
-
                         iter->buffer_iter[cpu] =
-                                ring_buffer_read_start(iter->tr->buffer, cpu);
+                                ring_buffer_read_prepare(iter->tr->buffer, cpu);
+                }
+                ring_buffer_read_prepare_sync();
+                for_each_tracing_cpu(cpu) {
+                        ring_buffer_read_start(iter->buffer_iter[cpu]);
                         tracing_iter_reset(iter, cpu);
                 }
         } else {
                 cpu = iter->cpu_file;
                 iter->buffer_iter[cpu] =
-                                ring_buffer_read_start(iter->tr->buffer, cpu);
+                        ring_buffer_read_prepare(iter->tr->buffer, cpu);
+                ring_buffer_read_prepare_sync();
+                ring_buffer_read_start(iter->buffer_iter[cpu]);
                 tracing_iter_reset(iter, cpu);
         }
 
@@ -3269,12 +3310,12 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
                                         size_t len,
                                         unsigned int flags)
 {
-        struct page *pages[PIPE_BUFFERS];
-        struct partial_page partial[PIPE_BUFFERS];
+        struct page *pages_def[PIPE_DEF_BUFFERS];
+        struct partial_page partial_def[PIPE_DEF_BUFFERS];
         struct trace_iterator *iter = filp->private_data;
         struct splice_pipe_desc spd = {
-                .pages          = pages,
-                .partial        = partial,
+                .pages          = pages_def,
+                .partial        = partial_def,
                 .nr_pages       = 0, /* This gets updated below. */
                 .flags          = flags,
                 .ops            = &tracing_pipe_buf_ops,
@@ -3285,6 +3326,9 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
         size_t rem;
         unsigned int i;
 
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
         /* copy the tracer to avoid using a global lock all around */
         mutex_lock(&trace_types_lock);
         if (unlikely(old_tracer != current_trace && current_trace)) {
@@ -3315,23 +3359,23 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
         trace_access_lock(iter->cpu_file);
 
         /* Fill as many pages as possible. */
-        for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
-                pages[i] = alloc_page(GFP_KERNEL);
-                if (!pages[i])
+        for (i = 0, rem = len; i < pipe->buffers && rem; i++) {
+                spd.pages[i] = alloc_page(GFP_KERNEL);
+                if (!spd.pages[i])
                         break;
 
                 rem = tracing_fill_pipe_page(rem, iter);
 
                 /* Copy the data into the page, so we can start over. */
                 ret = trace_seq_to_buffer(&iter->seq,
-                                          page_address(pages[i]),
+                                          page_address(spd.pages[i]),
                                           iter->seq.len);
                 if (ret < 0) {
-                        __free_page(pages[i]);
+                        __free_page(spd.pages[i]);
                         break;
                 }
-                partial[i].offset = 0;
-                partial[i].len = iter->seq.len;
+                spd.partial[i].offset = 0;
+                spd.partial[i].len = iter->seq.len;
 
                 trace_seq_init(&iter->seq);
         }
@@ -3342,12 +3386,14 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
         spd.nr_pages = i;
 
-        return splice_to_pipe(pipe, &spd);
+        ret = splice_to_pipe(pipe, &spd);
+out:
+        splice_shrink_spd(pipe, &spd);
+        return ret;
 
 out_err:
         mutex_unlock(&iter->mutex);
-
-        return ret;
+        goto out;
 }
 
 static ssize_t
@@ -3620,7 +3666,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
                      size_t count, loff_t *ppos)
 {
         struct ftrace_buffer_info *info = filp->private_data;
-        unsigned int pos;
         ssize_t ret;
         size_t size;
 
@@ -3647,11 +3692,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
         if (ret < 0)
                 return 0;
 
-        pos = ring_buffer_page_len(info->spare);
-
-        if (pos < PAGE_SIZE)
-                memset(info->spare + pos, 0, PAGE_SIZE - pos);
-
 read:
         size = PAGE_SIZE - info->read;
         if (size > count)
@@ -3746,11 +3786,11 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                             unsigned int flags)
 {
         struct ftrace_buffer_info *info = file->private_data;
-        struct partial_page partial[PIPE_BUFFERS];
-        struct page *pages[PIPE_BUFFERS];
+        struct partial_page partial_def[PIPE_DEF_BUFFERS];
+        struct page *pages_def[PIPE_DEF_BUFFERS];
         struct splice_pipe_desc spd = {
-                .pages          = pages,
-                .partial        = partial,
+                .pages          = pages_def,
+                .partial        = partial_def,
                 .flags          = flags,
                 .ops            = &buffer_pipe_buf_ops,
                 .spd_release    = buffer_spd_release,
@@ -3759,22 +3799,28 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
         int entries, size, i;
         size_t ret;
 
+        if (splice_grow_spd(pipe, &spd))
+                return -ENOMEM;
+
         if (*ppos & (PAGE_SIZE - 1)) {
                 WARN_ONCE(1, "Ftrace: previous read must page-align\n");
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out;
         }
 
         if (len & (PAGE_SIZE - 1)) {
                 WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
-                if (len < PAGE_SIZE)
-                        return -EINVAL;
+                if (len < PAGE_SIZE) {
+                        ret = -EINVAL;
+                        goto out;
+                }
                 len &= PAGE_MASK;
         }
 
         trace_access_lock(info->cpu);
         entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 
-        for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
+        for (i = 0; i < pipe->buffers && len && entries; i++, len -= PAGE_SIZE) {
                 struct page *page;
                 int r;
 
@@ -3829,11 +3875,12 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
                 else
                         ret = 0;
                 /* TODO: block */
-                return ret;
+                goto out;
         }
 
         ret = splice_to_pipe(pipe, &spd);
-
+        splice_shrink_spd(pipe, &spd);
+out:
         return ret;
 }
 
@@ -4324,7 +4371,7 @@ static int trace_panic_handler(struct notifier_block *this,
                                unsigned long event, void *unused)
 {
         if (ftrace_dump_on_oops)
-                ftrace_dump();
+                ftrace_dump(ftrace_dump_on_oops);
         return NOTIFY_OK;
 }
 
@@ -4341,7 +4388,7 @@ static int trace_die_handler(struct notifier_block *self,
         switch (val) {
         case DIE_OOPS:
                 if (ftrace_dump_on_oops)
-                        ftrace_dump();
+                        ftrace_dump(ftrace_dump_on_oops);
                 break;
         default:
                 break;
@@ -4382,7 +4429,8 @@ trace_printk_seq(struct trace_seq *s)
         trace_seq_init(s);
 }
 
-static void __ftrace_dump(bool disable_tracing)
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 {
         static arch_spinlock_t ftrace_dump_lock =
                 (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -4415,12 +4463,25 @@ static void __ftrace_dump(bool disable_tracing)
         /* don't look at user memory in panic mode */
         trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-        printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
         /* Simulate the iterator */
         iter.tr = &global_trace;
         iter.trace = current_trace;
-        iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+        switch (oops_dump_mode) {
+        case DUMP_ALL:
+                iter.cpu_file = TRACE_PIPE_ALL_CPU;
+                break;
+        case DUMP_ORIG:
+                iter.cpu_file = raw_smp_processor_id();
+                break;
+        case DUMP_NONE:
+                goto out_enable;
+        default:
+                printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+                iter.cpu_file = TRACE_PIPE_ALL_CPU;
+        }
+
+        printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
         /*
          * We need to stop all tracing on all CPUS to read the
@@ -4459,6 +4520,7 @@ static void __ftrace_dump(bool disable_tracing)
         else
                 printk(KERN_TRACE "---------------------------------\n");
 
+ out_enable:
         /* Re-enable tracing if requested */
         if (!disable_tracing) {
                 trace_flags |= old_userobj;
@@ -4475,9 +4537,9 @@ static void __ftrace_dump(bool disable_tracing)
 }
 
 /* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-        __ftrace_dump(true);
+        __ftrace_dump(true, oops_dump_mode);
 }
 
 __init static int tracer_alloc_buffers(void)