summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace.c
diff options
context:
space:
mode:
authorSteven Rostedt <srostedt@redhat.com>2011-09-22 11:50:27 -0400
committerSteven Rostedt <rostedt@goodmis.org>2011-10-11 09:13:53 -0400
commitd696b58ca2c3ca76e784ef89a7e0453d9b7ab187 (patch)
treee5f02a13dc8fdec22e9223189122e5938e9ce77e /kernel/trace/trace.c
parente0a413f619ef8bc366dafc6f8221674993b8d85f (diff)
downloadop-kernel-dev-d696b58ca2c3ca76e784ef89a7e0453d9b7ab187.zip
op-kernel-dev-d696b58ca2c3ca76e784ef89a7e0453d9b7ab187.tar.gz
tracing: Do not allocate buffer for trace_marker
When doing intense tracing, the kmalloc inside trace_marker can introduce side effects to what is being traced. As trace_marker() is used by userspace to inject data into the kernel ring buffer, it needs to do so with the least amount of intrusion to the operations of the kernel or the user space application. As the ring buffer is designed to write directly into the buffer without the need to make a temporary buffer, and userspace already went through the hassle of knowing how big the write will be, we can simply pin the userspace pages and write the data directly into the buffer. This improves the impact of tracing via trace_marker tremendously! Thanks to Peter Zijlstra and Thomas Gleixner for pointing out the use of get_user_pages_fast() and kmap_atomic(). Suggested-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Diffstat (limited to 'kernel/trace/trace.c')
-rw-r--r--kernel/trace/trace.c111
1 files changed, 83 insertions, 28 deletions
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 13f2b84..f86efe9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3628,22 +3628,24 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
return 0;
}
-static int mark_printk(const char *fmt, ...)
-{
- int ret;
- va_list args;
- va_start(args, fmt);
- ret = trace_vprintk(0, fmt, args);
- va_end(args);
- return ret;
-}
-
static ssize_t
tracing_mark_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *fpos)
{
- char *buf;
- size_t written;
+ unsigned long addr = (unsigned long)ubuf;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ struct print_entry *entry;
+ unsigned long irq_flags;
+ struct page *pages[2];
+ int nr_pages = 1;
+ ssize_t written;
+ void *page1;
+ void *page2;
+ int offset;
+ int size;
+ int len;
+ int ret;
if (tracing_disabled)
return -EINVAL;
@@ -3651,28 +3653,81 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
if (cnt > TRACE_BUF_SIZE)
cnt = TRACE_BUF_SIZE;
- buf = kmalloc(cnt + 2, GFP_KERNEL);
- if (buf == NULL)
- return -ENOMEM;
+ /*
+ * Userspace is injecting traces into the kernel trace buffer.
+ * We want to be as non intrusive as possible.
+ * To do so, we do not want to allocate any special buffers
+ * or take any locks, but instead write the userspace data
+ * straight into the ring buffer.
+ *
+ * First we need to pin the userspace buffer into memory,
+ * which, most likely it is, because it just referenced it.
+ * But there's no guarantee that it is. By using get_user_pages_fast()
+ * and kmap_atomic/kunmap_atomic() we can get access to the
+ * pages directly. We then write the data directly into the
+ * ring buffer.
+ */
+ BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
- if (copy_from_user(buf, ubuf, cnt)) {
- kfree(buf);
- return -EFAULT;
+ /* check if we cross pages */
+ if ((addr & PAGE_MASK) != ((addr + cnt) & PAGE_MASK))
+ nr_pages = 2;
+
+ offset = addr & (PAGE_SIZE - 1);
+ addr &= PAGE_MASK;
+
+ ret = get_user_pages_fast(addr, nr_pages, 0, pages);
+ if (ret < nr_pages) {
+ while (--ret >= 0)
+ put_page(pages[ret]);
+ written = -EFAULT;
+ goto out;
}
- if (buf[cnt-1] != '\n') {
- buf[cnt] = '\n';
- buf[cnt+1] = '\0';
+
+ page1 = kmap_atomic(pages[0]);
+ if (nr_pages == 2)
+ page2 = kmap_atomic(pages[1]);
+
+ local_save_flags(irq_flags);
+ size = sizeof(*entry) + cnt + 2; /* possible \n added */
+ buffer = global_trace.buffer;
+ event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+ irq_flags, preempt_count());
+ if (!event) {
+ /* Ring buffer disabled, return as if not open for write */
+ written = -EBADF;
+ goto out_unlock;
+ }
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = _THIS_IP_;
+
+ if (nr_pages == 2) {
+ len = PAGE_SIZE - offset;
+ memcpy(&entry->buf, page1 + offset, len);
+ memcpy(&entry->buf[len], page2, cnt - len);
} else
- buf[cnt] = '\0';
+ memcpy(&entry->buf, page1 + offset, cnt);
- written = mark_printk("%s", buf);
- kfree(buf);
- *fpos += written;
+ if (entry->buf[cnt - 1] != '\n') {
+ entry->buf[cnt] = '\n';
+ entry->buf[cnt + 1] = '\0';
+ } else
+ entry->buf[cnt] = '\0';
+
+ ring_buffer_unlock_commit(buffer, event);
- /* don't tell userspace we wrote more - it might confuse them */
- if (written > cnt)
- written = cnt;
+ written = cnt;
+ *fpos += written;
+
+ out_unlock:
+ if (nr_pages == 2)
+ kunmap_atomic(page2);
+ kunmap_atomic(page1);
+ while (nr_pages > 0)
+ put_page(pages[--nr_pages]);
+ out:
return written;
}
OpenPOWER on IntegriCloud