diff options
| author | Lennert Buytenhek <buytenh@wantstofly.org> | 2009-04-29 11:58:18 +0000 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@suse.de> | 2009-05-08 14:54:36 -0700 |
| commit | a239571a953830dbf73f2fcdee6731b5483c77d6 (patch) | |
| tree | bcc15c4b51f49a73db0489b1f7a9e472370c1bff | |
| parent | 0d8f4f2015d4f9ea3057e2d521084944306e91df (diff) | |
mv643xx_eth: 64bit mib counter read fix
commit 93af7aca44f0e82e67bda10a0fb73d383edcc8bd upstream.
On several mv643xx_eth hardware versions, the two 64bit mib counters
for 'good octets received' and 'good octets sent' are actually 32bit
counters, and reading from the upper half of the register has the same
effect as reading from the lower half of the register: an atomic
read-and-clear of the entire 32bit counter value. This can under heavy
traffic occasionally lead to small numbers being added to the upper
half of the 64bit mib counter even though no 32bit wrap has occured.
Since we poll the mib counters at least every 30 seconds anyway, we
might as well just skip the reads of the upper halves of the hardware
counters without breaking the stats, which this patch does.
Signed-off-by: Lennert Buytenhek <buytenh@marvell.com>
Cc: stable@kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
| -rw-r--r-- | drivers/net/mv643xx_eth.c | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index 0a18b9e96da1..abd5a89a876d 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -1060,7 +1060,6 @@ static void mib_counters_update(struct mv643xx_eth_private *mp) struct mib_counters *p = &mp->mib_counters; p->good_octets_received += mib_read(mp, 0x00); - p->good_octets_received += (u64)mib_read(mp, 0x04) << 32; p->bad_octets_received += mib_read(mp, 0x08); p->internal_mac_transmit_err += mib_read(mp, 0x0c); p->good_frames_received += mib_read(mp, 0x10); @@ -1074,7 +1073,6 @@ static void mib_counters_update(struct mv643xx_eth_private *mp) p->frames_512_to_1023_octets += mib_read(mp, 0x30); p->frames_1024_to_max_octets += mib_read(mp, 0x34); p->good_octets_sent += mib_read(mp, 0x38); - p->good_octets_sent += (u64)mib_read(mp, 0x3c) << 32; p->good_frames_sent += mib_read(mp, 0x40); p->excessive_collision += mib_read(mp, 0x44); p->multicast_frames_sent += mib_read(mp, 0x48); |