| Message ID | 1479300041-3436-1-git-send-email-zyjzyj2000@gmail.com |
|---|---|
| State | Awaiting Upstream, archived |
| Delegated to: | David Miller |
| Headers | show |
Hi, > > Sometimes vfta registers can not be written successfully in dcb mode. > This is very occassional. When the ixgbe nic runs for a very long time, > sometimes this bug occurs. But after IXGBE_WRITE_FLUSH is executed, > this bug never occurs. > > Signed-off-by: Zhu Yanjun <zyjzyj2000@gmail.com> > --- > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ++++- > 1 file changed, 4 insertions(+), 1 deletion(-) > > diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c > index bd93d82..1221cfb 100644 > --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c > +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c > @@ -4138,8 +4138,10 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) > } > > /* Set all bits in the VLAN filter table array */ > - for (i = hw->mac.vft_size; i--;) > + for (i = hw->mac.vft_size; i--;) { > IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U); > + IXGBE_WRITE_FLUSH(hw); > + } Should it not be sufficient to do the flush only once, at the end of the function? Regards, Lino
Sure. From the following. " VLAN Filter. Each bit ‘i’ in register ‘n’ affects packets with VLAN tags equal to 32*n+i. 128 VLAN Filter registers compose a table of 4096 bits that cover all possible VLAN tags. Each bit when set, enables packets with the associated VLAN tags to pass. Each bit when cleared, blocks packets with this VLAN tag. " Your suggestions seems reasonable. Please wait. I will make tests to vefiry your suggestions. I will keep you update. On Wed, Nov 16, 2016 at 10:05 PM, Lino Sanfilippo <LinoSanfilippo@gmx.de> wrote: > > > Hi, > >> >> Sometimes vfta registers can not be written successfully in dcb mode. >> This is very occassional. When the ixgbe nic runs for a very long time, >> sometimes this bug occurs. But after IXGBE_WRITE_FLUSH is executed, >> this bug never occurs. >> >> Signed-off-by: Zhu Yanjun <zyjzyj2000@gmail.com> >> --- >> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ++++- >> 1 file changed, 4 insertions(+), 1 deletion(-) >> >> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c >> index bd93d82..1221cfb 100644 >> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c >> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c >> @@ -4138,8 +4138,10 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) >> } >> >> /* Set all bits in the VLAN filter table array */ >> - for (i = hw->mac.vft_size; i--;) >> + for (i = hw->mac.vft_size; i--;) { >> IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U); >> + IXGBE_WRITE_FLUSH(hw); >> + } > > Should it not be sufficient to do the flush only once, at the end of the function? > > Regards, > Lino
After several week tests, your advice still make this bug appear. But my patch make this bug disappear. Zhu Yanjun On Thu, Nov 17, 2016 at 5:33 PM, zhuyj <zyjzyj2000@gmail.com> wrote: > Sure. From the following. > " > VLAN Filter. Each bit ‘i’ in register ‘n’ affects packets with VLAN > tags equal to 32*n+i. > 128 VLAN Filter registers compose a table of 4096 bits that cover all > possible VLAN > tags. > Each bit when set, enables packets with the associated VLAN tags to > pass. Each bit > when cleared, blocks packets with this VLAN tag. > " > Your suggestions seems reasonable. Please wait. I will make tests to > vefiry your suggestions. > > I will keep you update. > > On Wed, Nov 16, 2016 at 10:05 PM, Lino Sanfilippo <LinoSanfilippo@gmx.de> wrote: >> >> >> Hi, >> >>> >>> Sometimes vfta registers can not be written successfully in dcb mode. >>> This is very occassional. When the ixgbe nic runs for a very long time, >>> sometimes this bug occurs. But after IXGBE_WRITE_FLUSH is executed, >>> this bug never occurs. >>> >>> Signed-off-by: Zhu Yanjun <zyjzyj2000@gmail.com> >>> --- >>> drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ++++- >>> 1 file changed, 4 insertions(+), 1 deletion(-) >>> >>> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c >>> index bd93d82..1221cfb 100644 >>> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c >>> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c >>> @@ -4138,8 +4138,10 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) >>> } >>> >>> /* Set all bits in the VLAN filter table array */ >>> - for (i = hw->mac.vft_size; i--;) >>> + for (i = hw->mac.vft_size; i--;) { >>> IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U); >>> + IXGBE_WRITE_FLUSH(hw); >>> + } >> >> Should it not be sufficient to do the flush only once, at the end of the function? >> >> Regards, >> Lino
Hi Zhu, On 07.12.2016 04:05, zhuyj wrote: > After several week tests, your advice still make this bug appear. But > my patch make this bug disappear. > > Zhu Yanjun > In your commit message you wrote "Sometimes vfta registers can not be written successfully in dcb mode." Do you mean that the writes to the registers dont seem to have any effect at all? Or is the effect only delayed? What exactly is your test case? (BTW: please dont top-post). Regards, Lino
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bd93d82..1221cfb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4138,8 +4138,10 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) } /* Set all bits in the VLAN filter table array */ - for (i = hw->mac.vft_size; i--;) + for (i = hw->mac.vft_size; i--;) { IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U); + IXGBE_WRITE_FLUSH(hw); + } } #define VFTA_BLOCK_SIZE 8 @@ -4186,6 +4188,7 @@ static void ixgbe_scrub_vfta(struct ixgbe_adapter *adapter, u32 vfta_offset) vfta[i] |= adapter->active_vlans[word] >> bits; IXGBE_WRITE_REG(hw, IXGBE_VFTA(vfta_offset + i), vfta[i]); + IXGBE_WRITE_FLUSH(hw); } }