On Fri, 2015-08-28 at 11:24 -0700, David Miller wrote:

From: Raghavendra K T <redacted>
Date: Fri, 28 Aug 2015 12:09:52 +0530

quoted

On 08/28/2015 12:08 AM, David Miller wrote:

quoted

From: Raghavendra K T <redacted>
Date: Wed, 26 Aug 2015 23:07:33 +0530

quoted

@@ -4641,10 +4647,12 @@ static inline void __snmp6_fill_stats64(u64

*stats, void __percpu *mib,
  static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int
  attrtype,
  			     int bytes)
  {
+	u64 buff[IPSTATS_MIB_MAX] = {0,};
+

 ...

quoted

hope you wanted to know the overhead than to change the current
patch. please let me know..

I want you to change that variable initializer to an explicit memset().

The compiler is emitting a memset() or similar _anyways_.

Not because it will have any impact at all upon performance, but because
of how it looks to people trying to read and understand the code.

I don't read it as particularly different.

There are > 100 uses of the not quite a memset initialization
style using "= { <0,> }" in net/

$ git grep -E "=\s*\{\s*0?\s*,?\s*\}" net | wc -l
138

There is a difference though if a struct is copied to
user-space as a {} initialization only guarantees that
struct members are initialized to 0 where memset also
zeros any alignment padding.

Maybe a checkpatch rule like this?
---
 scripts/checkpatch.pl | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index e14dcdb..f79e5c9 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl

@@ -3237,6 +3237,13 @@ sub process {
 			next;
 		}
 
+# check for non-global initializations that could be memset
+		if ($realfile =~ m@^(drivers/net/|net/)@ &&
+		    $sline =~ /^.\s+$Declare\s*$Ident\s*=\s*\{\s*0?\s*,?\s*\}/) {
+			CHK("BRACE_INITIALIZATION",
+			    "Prefer an explicit memset to a declaration initialization\n" . $herecurr);
+		}
+
 # check for initialisation to aggregates open brace on the next line
 		if ($line =~ /^.\s*{/ &&
 		    $prevline =~ /(?:^|[^=])=\s*$/) {