dax: add tracepoint infrastructure, PMD tracing

Tracepoints are the standard way to capture debugging and tracing
information in many parts of the kernel, including the XFS and ext4
filesystems.  Create a tracepoint header for FS DAX and add the first DAX
tracepoints to the PMD fault handler.  This allows the tracing for DAX to
be done in the same way as the filesystem tracing so that developers can
look at them together and get a coherent idea of what the system is doing.

I added both an entry and exit tracepoint because future patches will add
tracepoints to child functions of dax_iomap_pmd_fault() like
dax_pmd_load_hole() and dax_pmd_insert_mapping().  We want those messages
to be wrapped by the parent function tracepoints so the code flow is more
easily understood.  Having entry and exit tracepoints for faults also
allows us to easily see what filesystems functions were called during the
fault.  These filesystem functions get executed via iomap_begin() and
iomap_end() calls, for example, and will have their own tracepoints.

For PMD faults we primarily want to understand the type of mapping, the
fault flags, the faulting address and whether it fell back to 4k faults.
If it fell back to 4k faults the tracepoints should let us understand why.

I named the new tracepoint header file "fs_dax.h" to allow for device DAX
to have its own separate tracing header in the same directory at some
point.

Here is an example output for these events from a successful PMD fault:

  big-1441  [005] ....    32.582758: xfs_filemap_pmd_fault: dev 259:0 ino 0x1003

  big-1441  [005] ....    32.582776: dax_pmd_fault: dev 259:0 ino 0x1003
  shared WRITE|ALLOW_RETRY|KILLABLE|USER address 0x10505000 vm_start 0x10200000 vm_end 0x10700000 pgoff 0x200 max_pgoff 0x1400

  big-1441  [005] ....    32.583292: dax_pmd_fault_done: dev 259:0 ino 0x1003
  shared WRITE|ALLOW_RETRY|KILLABLE|USER address 0x10505000 vm_start 0x10200000 vm_end 0x10700000 pgoff 0x200 max_pgoff 0x1400 NOPAGE

Link: http://lkml.kernel.org/r/1484085142-2297-3-git-send-email-ross.zwisler@linux.intel.com
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 93 insertions, 0 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6ff66d6fe8e2..d22f7837ad90 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,6 +285,17 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
 #define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */
 
+#define FAULT_FLAG_TRACE \
+	{ FAULT_FLAG_WRITE,		"WRITE" }, \
+	{ FAULT_FLAG_MKWRITE,		"MKWRITE" }, \
+	{ FAULT_FLAG_ALLOW_RETRY,	"ALLOW_RETRY" }, \
+	{ FAULT_FLAG_RETRY_NOWAIT,	"RETRY_NOWAIT" }, \
+	{ FAULT_FLAG_KILLABLE,		"KILLABLE" }, \
+	{ FAULT_FLAG_TRIED,		"TRIED" }, \
+	{ FAULT_FLAG_USER,		"USER" }, \
+	{ FAULT_FLAG_REMOTE,		"REMOTE" }, \
+	{ FAULT_FLAG_INSTRUCTION,	"INSTRUCTION" }
+
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
@@ -1111,6 +1122,20 @@ static inline void clear_page_pfmemalloc(struct page *page)
 			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
 			 VM_FAULT_FALLBACK)
 
+#define VM_FAULT_RESULT_TRACE \
+	{ VM_FAULT_OOM,			"OOM" }, \
+	{ VM_FAULT_SIGBUS,		"SIGBUS" }, \
+	{ VM_FAULT_MAJOR,		"MAJOR" }, \
+	{ VM_FAULT_WRITE,		"WRITE" }, \
+	{ VM_FAULT_HWPOISON,		"HWPOISON" }, \
+	{ VM_FAULT_HWPOISON_LARGE,	"HWPOISON_LARGE" }, \
+	{ VM_FAULT_SIGSEGV,		"SIGSEGV" }, \
+	{ VM_FAULT_NOPAGE,		"NOPAGE" }, \
+	{ VM_FAULT_LOCKED,		"LOCKED" }, \
+	{ VM_FAULT_RETRY,		"RETRY" }, \
+	{ VM_FAULT_FALLBACK,		"FALLBACK" }, \
+	{ VM_FAULT_DONE_COW,		"DONE_COW" }
+
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
 #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
new file mode 100644
index 000000000000..58b0b5612683
--- /dev/null
+++ b/include/trace/events/fs_dax.h
@@ -0,0 +1,68 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM fs_dax
+
+#if !defined(_TRACE_FS_DAX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FS_DAX_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(dax_pmd_fault_class,
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma,
+		unsigned long address, unsigned int flags, pgoff_t pgoff,
+		pgoff_t max_pgoff, int result),
+	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result),
+	TP_STRUCT__entry(
+		__field(unsigned long, ino)
+		__field(unsigned long, vm_start)
+		__field(unsigned long, vm_end)
+		__field(unsigned long, vm_flags)
+		__field(unsigned long, address)
+		__field(pgoff_t, pgoff)
+		__field(pgoff_t, max_pgoff)
+		__field(dev_t, dev)
+		__field(unsigned int, flags)
+		__field(int, result)
+	),
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->vm_start = vma->vm_start;
+		__entry->vm_end = vma->vm_end;
+		__entry->vm_flags = vma->vm_flags;
+		__entry->address = address;
+		__entry->flags = flags;
+		__entry->pgoff = pgoff;
+		__entry->max_pgoff = max_pgoff;
+		__entry->result = result;
+	),
+	TP_printk("dev %d:%d ino %#lx %s %s address %#lx vm_start "
+			"%#lx vm_end %#lx pgoff %#lx max_pgoff %#lx %s",
+		MAJOR(__entry->dev),
+		MINOR(__entry->dev),
+		__entry->ino,
+		__entry->vm_flags & VM_SHARED ? "shared" : "private",
+		__print_flags(__entry->flags, "|", FAULT_FLAG_TRACE),
+		__entry->address,
+		__entry->vm_start,
+		__entry->vm_end,
+		__entry->pgoff,
+		__entry->max_pgoff,
+		__print_flags(__entry->result, "|", VM_FAULT_RESULT_TRACE)
+	)
+)
+
+#define DEFINE_PMD_FAULT_EVENT(name) \
+DEFINE_EVENT(dax_pmd_fault_class, name, \
+	TP_PROTO(struct inode *inode, struct vm_area_struct *vma, \
+		unsigned long address, unsigned int flags, pgoff_t pgoff, \
+		pgoff_t max_pgoff, int result), \
+	TP_ARGS(inode, vma, address, flags, pgoff, max_pgoff, result))
+
+DEFINE_PMD_FAULT_EVENT(dax_pmd_fault);
+DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done);
+
+
+#endif /* _TRACE_FS_DAX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>