Currently, is_shmem is not being captured. Capturing is_shmem is useful 
as it can indicate if tmpfs is being used as a backing store instead of 
persistent storage. Add the tracepoint in collapse_file() named 
"mm_khugepaged_collapse_file" for capturing is_shmem.

Signed-off-by: Gautam Menghani <gautammenghani201@gmail.com>
---
changes in v2:
1. Move filename dereference out of calling path (Steven Rostedt).
2. Capture is_shmem and index (Zach O'Keefe)

changes in v3:
1. Initialize the variables to resolve clang warning.
2. Add more info in changelog.

changes in v4:
1. Swap is_shmem and addr to save space (Steven Rostedt)

 include/trace/events/huge_memory.h | 38 ++++++++++++++++++++++++++++++
 mm/khugepaged.c                    |  7 +++---
 2 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 935af4947917..f06a255d7ec8 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -203,5 +203,43 @@ TRACE_EVENT(mm_khugepaged_scan_file,
 		__print_symbolic(__entry->result, SCAN_STATUS))
 );
 
+TRACE_EVENT(mm_khugepaged_collapse_file,
+	TP_PROTO(struct mm_struct *mm, struct page *hpage, pgoff_t index,
+			bool is_shmem, unsigned long addr, struct file *file,
+			int nr, int result),
+	TP_ARGS(mm, hpage, index, addr, is_shmem, file, nr, result),
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(unsigned long, hpfn)
+		__field(pgoff_t, index)
+		__field(unsigned long, addr)
+		__field(bool, is_shmem)
+		__string(filename, file->f_path.dentry->d_iname)
+		__field(int, nr)
+		__field(int, result)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->hpfn = hpage ? page_to_pfn(hpage) : -1;
+		__entry->index = index;
+		__entry->addr = addr;
+		__entry->is_shmem = is_shmem;
+		__assign_str(filename, file->f_path.dentry->d_iname);
+		__entry->nr = nr;
+		__entry->result = result;
+	),
+
+	TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s",
+		__entry->mm,
+		__entry->hpfn,
+		__entry->index,
+		__entry->addr,
+		__entry->is_shmem,
+		__get_str(filename),
+		__entry->nr,
+		__print_symbolic(__entry->result, SCAN_STATUS))
+);
+
 #endif /* __HUGE_MEMORY_H */
 #include <trace/define_trace.h>
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 4734315f7940..921407e2006d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1702,12 +1702,12 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
 {
 	struct address_space *mapping = file->f_mapping;
 	struct page *hpage;
-	pgoff_t index, end = start + HPAGE_PMD_NR;
+	pgoff_t index = 0, end = start + HPAGE_PMD_NR;
 	LIST_HEAD(pagelist);
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
 	int nr_none = 0, result = SCAN_SUCCEED;
 	bool is_shmem = shmem_file(file);
-	int nr;
+	int nr = 0;
 
 	VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
 	VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
@@ -2059,7 +2059,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
 		mem_cgroup_uncharge(page_folio(hpage));
 		put_page(hpage);
 	}
-	/* TODO: tracepoints */
+
+	trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result);
 	return result;
 }
 
-- 
2.34.1

On Sat,  3 Dec 2022 01:48:07 +0530
Gautam Menghani <gautammenghani201@gmail.com> wrote:

> Currently, is_shmem is not being captured. Capturing is_shmem is useful 
> as it can indicate if tmpfs is being used as a backing store instead of 
> persistent storage. Add the tracepoint in collapse_file() named 
> "mm_khugepaged_collapse_file" for capturing is_shmem.
> 
> Signed-off-by: Gautam Menghani <gautammenghani201@gmail.com>
> ---

From a tracing point of view:

Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>

-- Steve