| Message ID | 20170410183329.28847-1-niklass@axis.com |
|---|---|
| State | Accepted, archived |
| Delegated to: | David Miller |
| Headers | show |
Hi Niklas patch looks ok for me, Alex any feedback? peppe On 4/10/2017 8:33 PM, Niklas Cassel wrote: > From: Niklas Cassel <niklas.cassel@axis.com> > > Field FL/TPL in register TDES3 is not correctly set on GMAC4. > TX appears to be functional on GMAC 4.10a even if this field is not set, > however, to avoid relying on undefined behavior, set the length in TDES3. > > The field has a different meaning depending on if the TSE bit in TDES3 > is set or not (TSO). However, regardless of the TSE bit, the field is > not optional. The field is already set correctly when the TSE bit is set. > > Since there is no limit for the number of descriptors that can be > used for a single packet, the field should be set to the sum of > the buffers contained in: > [<desc with First Descriptor bit set> ... <desc n> ... > <desc with Last Descriptor bit set>], which should be equal to skb->len. > > Signed-off-by: Niklas Cassel <niklas.cassel@axis.com> > --- > drivers/net/ethernet/stmicro/stmmac/chain_mode.c | 6 +++--- > drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- > drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 3 ++- > drivers/net/ethernet/stmicro/stmmac/enh_desc.c | 2 +- > drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 2 +- > drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 9 ++++++--- > drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++-- > 7 files changed, 17 insertions(+), 12 deletions(-) > > diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c > index 37881f81319e..e93c40b4631e 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c > +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c > @@ -52,7 +52,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > tx_q->tx_skbuff_dma[entry].len = bmax; > /* do not close the descriptor and do not set own bit */ > priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE, > - 0, false); > + 0, false, skb->len); > > while (len != 0) { > tx_q->tx_skbuff[entry] = NULL; > @@ -70,7 +70,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > tx_q->tx_skbuff_dma[entry].len = bmax; > priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, > STMMAC_CHAIN_MODE, 1, > - false); > + false, skb->len); > len -= bmax; > i++; > } else { > @@ -85,7 +85,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > /* last descriptor can be set now */ > priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, > STMMAC_CHAIN_MODE, 1, > - true); > + true, skb->len); > len = 0; > } > } > diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h > index 90d28bcad880..b7ce3fbb5375 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/common.h > +++ b/drivers/net/ethernet/stmicro/stmmac/common.h > @@ -373,7 +373,7 @@ struct stmmac_desc_ops { > /* Invoked by the xmit function to prepare the tx descriptor */ > void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls); > + bool ls, unsigned int tot_pkt_len); > void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1, > int len2, bool tx_own, bool ls, > unsigned int tcphdrlen, > diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c > index 843ec69222ea..aa6476439aee 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c > +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c > @@ -304,12 +304,13 @@ static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end) > > static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls) > + bool ls, unsigned int tot_pkt_len) > { > unsigned int tdes3 = le32_to_cpu(p->des3); > > p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK); > > + tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK; > if (is_fs) > tdes3 |= TDES3_FIRST_DESCRIPTOR; > else > diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c > index 323b59ec74a3..7546b3664113 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c > +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c > @@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(struct dma_desc *p, int mode) > > static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls) > + bool ls, unsigned int tot_pkt_len) > { > unsigned int tdes0 = le32_to_cpu(p->des0); > > diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c > index efb818ebd55e..f817f8f36569 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c > +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c > @@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct dma_desc *p, int mode) > > static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls) > + bool ls, unsigned int tot_pkt_len) > { > unsigned int tdes1 = le32_to_cpu(p->des1); > > diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c > index 31213e64513d..28e4b5d50ce6 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c > +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c > @@ -59,7 +59,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > > desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); > priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, > - STMMAC_RING_MODE, 0, false); > + STMMAC_RING_MODE, 0, > + false, skb->len); > tx_q->tx_skbuff[entry] = NULL; > entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); > > @@ -79,7 +80,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > > desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); > priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, > - STMMAC_RING_MODE, 1, true); > + STMMAC_RING_MODE, 1, > + true, skb->len); > } else { > des2 = dma_map_single(priv->device, skb->data, > nopaged_len, DMA_TO_DEVICE); > @@ -91,7 +93,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > tx_q->tx_skbuff_dma[entry].is_jumbo = true; > desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); > priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, > - STMMAC_RING_MODE, 0, true); > + STMMAC_RING_MODE, 0, > + true, skb->len); > } > > tx_q->cur_tx = entry; > diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > index a89f76b27ea2..5c1ebc70bebd 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > @@ -3033,7 +3033,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) > > /* Prepare the descriptor and set the own bit too */ > priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, > - priv->mode, 1, last_segment); > + priv->mode, 1, last_segment, > + skb->len); > } > > entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); > @@ -3116,7 +3117,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) > /* Prepare the first descriptor setting the OWN bit too */ > priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len, > csum_insertion, priv->mode, 1, > - last_segment); > + last_segment, skb->len); > > /* The own bit must be the latest setting done when prepare the > * descriptor and then barrier is needed to make sure that
Hi, On 04/11/2017 07:40 AM, Giuseppe CAVALLARO wrote: > Hi Niklas > > patch looks ok for me, Alex any feedback? It sounds good for me to. > > peppe > > On 4/10/2017 8:33 PM, Niklas Cassel wrote: >> From: Niklas Cassel <niklas.cassel@axis.com> >> >> Field FL/TPL in register TDES3 is not correctly set on GMAC4. >> TX appears to be functional on GMAC 4.10a even if this field is not set, >> however, to avoid relying on undefined behavior, set the length in TDES3. >> >> The field has a different meaning depending on if the TSE bit in TDES3 >> is set or not (TSO). However, regardless of the TSE bit, the field is >> not optional. The field is already set correctly when the TSE bit is set. >> >> Since there is no limit for the number of descriptors that can be >> used for a single packet, the field should be set to the sum of >> the buffers contained in: >> [<desc with First Descriptor bit set> ... <desc n> ... >> <desc with Last Descriptor bit set>], which should be equal to skb->len. >> >> Signed-off-by: Niklas Cassel <niklas.cassel@axis.com> >> --- >> drivers/net/ethernet/stmicro/stmmac/chain_mode.c | 6 +++--- >> drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- >> drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 3 ++- >> drivers/net/ethernet/stmicro/stmmac/enh_desc.c | 2 +- >> drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 2 +- >> drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 9 ++++++--- >> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++-- >> 7 files changed, 17 insertions(+), 12 deletions(-) >> >> diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c >> b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c >> index 37881f81319e..e93c40b4631e 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c >> +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c >> @@ -52,7 +52,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff >> *skb, int csum) >> tx_q->tx_skbuff_dma[entry].len = bmax; >> /* do not close the descriptor and do not set own bit */ >> priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, >> STMMAC_CHAIN_MODE, >> - 0, false); >> + 0, false, skb->len); >> while (len != 0) { >> tx_q->tx_skbuff[entry] = NULL; >> @@ -70,7 +70,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff >> *skb, int csum) >> tx_q->tx_skbuff_dma[entry].len = bmax; >> priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, >> STMMAC_CHAIN_MODE, 1, >> - false); >> + false, skb->len); >> len -= bmax; >> i++; >> } else { >> @@ -85,7 +85,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff >> *skb, int csum) >> /* last descriptor can be set now */ >> priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, >> STMMAC_CHAIN_MODE, 1, >> - true); >> + true, skb->len); >> len = 0; >> } >> } >> diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h >> b/drivers/net/ethernet/stmicro/stmmac/common.h >> index 90d28bcad880..b7ce3fbb5375 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/common.h >> +++ b/drivers/net/ethernet/stmicro/stmmac/common.h >> @@ -373,7 +373,7 @@ struct stmmac_desc_ops { >> /* Invoked by the xmit function to prepare the tx descriptor */ >> void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len, >> bool csum_flag, int mode, bool tx_own, >> - bool ls); >> + bool ls, unsigned int tot_pkt_len); >> void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int >> len1, >> int len2, bool tx_own, bool ls, >> unsigned int tcphdrlen, >> diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c >> b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c >> index 843ec69222ea..aa6476439aee 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c >> +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c >> @@ -304,12 +304,13 @@ static void dwmac4_rd_init_tx_desc(struct >> dma_desc *p, int mode, int end) >> static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int >> is_fs, int len, >> bool csum_flag, int mode, bool tx_own, >> - bool ls) >> + bool ls, unsigned int tot_pkt_len) >> { >> unsigned int tdes3 = le32_to_cpu(p->des3); >> p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK); >> + tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK; >> if (is_fs) >> tdes3 |= TDES3_FIRST_DESCRIPTOR; >> else >> diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c >> b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c >> index 323b59ec74a3..7546b3664113 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c >> +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c >> @@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(struct >> dma_desc *p, int mode) >> static void enh_desc_prepare_tx_desc(struct dma_desc *p, int >> is_fs, int len, >> bool csum_flag, int mode, bool tx_own, >> - bool ls) >> + bool ls, unsigned int tot_pkt_len) >> { >> unsigned int tdes0 = le32_to_cpu(p->des0); >> diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c >> b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c >> index efb818ebd55e..f817f8f36569 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c >> +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c >> @@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct dma_desc >> *p, int mode) >> static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, >> int len, >> bool csum_flag, int mode, bool tx_own, >> - bool ls) >> + bool ls, unsigned int tot_pkt_len) >> { >> unsigned int tdes1 = le32_to_cpu(p->des1); >> diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c >> b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c >> index 31213e64513d..28e4b5d50ce6 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c >> +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c >> @@ -59,7 +59,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff >> *skb, int csum) >> desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); >> priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, >> - STMMAC_RING_MODE, 0, false); >> + STMMAC_RING_MODE, 0, >> + false, skb->len); >> tx_q->tx_skbuff[entry] = NULL; >> entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); >> @@ -79,7 +80,8 @@ static int stmmac_jumbo_frm(void *p, struct >> sk_buff *skb, int csum) >> desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); >> priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, >> - STMMAC_RING_MODE, 1, true); >> + STMMAC_RING_MODE, 1, >> + true, skb->len); >> } else { >> des2 = dma_map_single(priv->device, skb->data, >> nopaged_len, DMA_TO_DEVICE); >> @@ -91,7 +93,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff >> *skb, int csum) >> tx_q->tx_skbuff_dma[entry].is_jumbo = true; >> desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); >> priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, >> - STMMAC_RING_MODE, 0, true); >> + STMMAC_RING_MODE, 0, >> + true, skb->len); >> } >> tx_q->cur_tx = entry; >> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c >> b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c >> index a89f76b27ea2..5c1ebc70bebd 100644 >> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c >> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c >> @@ -3033,7 +3033,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff >> *skb, struct net_device *dev) >> /* Prepare the descriptor and set the own bit too */ >> priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, >> - priv->mode, 1, last_segment); >> + priv->mode, 1, last_segment, >> + skb->len); >> } >> entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); >> @@ -3116,7 +3117,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff >> *skb, struct net_device *dev) >> /* Prepare the first descriptor setting the OWN bit too */ >> priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len, >> csum_insertion, priv->mode, 1, >> - last_segment); >> + last_segment, skb->len); >> /* The own bit must be the latest setting done when >> prepare the >> * descriptor and then barrier is needed to make sure that > >
Hi Niklas, Às 7:33 PM de 4/10/2017, Niklas Cassel escreveu: > From: Niklas Cassel <niklas.cassel@axis.com> > > Field FL/TPL in register TDES3 is not correctly set on GMAC4. > TX appears to be functional on GMAC 4.10a even if this field is not set, > however, to avoid relying on undefined behavior, set the length in TDES3. > > The field has a different meaning depending on if the TSE bit in TDES3 > is set or not (TSO). However, regardless of the TSE bit, the field is > not optional. The field is already set correctly when the TSE bit is set. > > Since there is no limit for the number of descriptors that can be > used for a single packet, the field should be set to the sum of > the buffers contained in: > [<desc with First Descriptor bit set> ... <desc n> ... > <desc with Last Descriptor bit set>], which should be equal to skb->len. > > Signed-off-by: Niklas Cassel <niklas.cassel@axis.com> Sounds fine to me. Did you check for performance improvement? Thanks. Joao
On 04/11/2017 10:48 AM, Joao Pinto wrote: > > Hi Niklas, > > Às 7:33 PM de 4/10/2017, Niklas Cassel escreveu: >> From: Niklas Cassel <niklas.cassel@axis.com> >> >> Field FL/TPL in register TDES3 is not correctly set on GMAC4. >> TX appears to be functional on GMAC 4.10a even if this field is not set, >> however, to avoid relying on undefined behavior, set the length in TDES3. >> >> The field has a different meaning depending on if the TSE bit in TDES3 >> is set or not (TSO). However, regardless of the TSE bit, the field is >> not optional. The field is already set correctly when the TSE bit is set. >> >> Since there is no limit for the number of descriptors that can be >> used for a single packet, the field should be set to the sum of >> the buffers contained in: >> [<desc with First Descriptor bit set> ... <desc n> ... >> <desc with Last Descriptor bit set>], which should be equal to skb->len. >> >> Signed-off-by: Niklas Cassel <niklas.cassel@axis.com> > > Sounds fine to me. Did you check for performance improvement? Thanks. > Hello Joao, I could not see any difference with 1 TCP stream in iperf3 Without the patch: # ./iperf3-armhf -c 192.168.0.1 Connecting to host 192.168.0.1, port 5201 [ 4] local 192.168.0.105 port 51878 connected to 192.168.0.1 port 5201 [ 23.486426] random: fast init done [ ID] Interval Transfer Bandwidth Retr Cwnd [ 4] 0.00-1.00 sec 61.7 MBytes 517 Mbits/sec 0 294 KBytes [ 4] 1.00-2.00 sec 61.3 MBytes 515 Mbits/sec 0 294 KBytes [ 26.043850] random: crng init done [ 4] 2.00-3.00 sec 61.4 MBytes 515 Mbits/sec 0 294 KBytes [ 4] 3.00-4.00 sec 61.0 MBytes 512 Mbits/sec 0 294 KBytes [ 4] 4.00-5.00 sec 61.5 MBytes 516 Mbits/sec 0 294 KBytes [ 4] 5.00-6.00 sec 61.2 MBytes 514 Mbits/sec 0 294 KBytes [ 4] 6.00-7.00 sec 61.5 MBytes 516 Mbits/sec 0 294 KBytes [ 4] 7.00-8.00 sec 61.4 MBytes 515 Mbits/sec 0 294 KBytes [ 4] 8.00-9.00 sec 61.2 MBytes 514 Mbits/sec 0 294 KBytes [ 4] 9.00-10.00 sec 61.3 MBytes 514 Mbits/sec 0 294 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bandwidth Retr [ 4] 0.00-10.00 sec 614 MBytes 515 Mbits/sec 0 sender [ 4] 0.00-10.00 sec 613 MBytes 514 Mbits/sec receiver With the patch: # ./iperf3-armhf -c 192.168.0.1 Connecting to host 192.168.0.1, port 5201 [ 4] local 192.168.0.105 port 37696 connected to 192.168.0.1 port 5201 [ 85.266262] random: fast init done [ ID] Interval Transfer Bandwidth Retr Cwnd [ 4] 0.00-1.00 sec 62.1 MBytes 520 Mbits/sec 0 288 KBytes [ 4] 1.00-2.00 sec 61.0 MBytes 512 Mbits/sec 0 288 KBytes [ 87.782547] random: crng init done [ 4] 2.00-3.00 sec 61.3 MBytes 515 Mbits/sec 0 300 KBytes [ 4] 3.00-4.00 sec 61.1 MBytes 512 Mbits/sec 0 300 KBytes [ 4] 4.00-5.00 sec 61.4 MBytes 515 Mbits/sec 0 300 KBytes [ 4] 5.00-6.00 sec 61.1 MBytes 513 Mbits/sec 0 300 KBytes [ 4] 6.00-7.00 sec 61.1 MBytes 513 Mbits/sec 0 300 KBytes [ 4] 7.00-8.00 sec 61.6 MBytes 517 Mbits/sec 0 300 KBytes [ 4] 8.00-9.00 sec 61.3 MBytes 515 Mbits/sec 0 300 KBytes [ 4] 9.00-10.00 sec 61.6 MBytes 517 Mbits/sec 0 300 KBytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID] Interval Transfer Bandwidth Retr [ 4] 0.00-10.00 sec 614 MBytes 515 Mbits/sec 0 sender [ 4] 0.00-10.00 sec 613 MBytes 514 Mbits/sec receiver Note that the results above are with TSO off. With TSO on, I get 921 Mbps. However, the patch should not affect the case where TSO is on. Regards, Niklas
On 4/10/2017 8:33 PM, Niklas Cassel wrote: > From: Niklas Cassel <niklas.cassel@axis.com> > > Field FL/TPL in register TDES3 is not correctly set on GMAC4. > TX appears to be functional on GMAC 4.10a even if this field is not set, > however, to avoid relying on undefined behavior, set the length in TDES3. > > The field has a different meaning depending on if the TSE bit in TDES3 > is set or not (TSO). However, regardless of the TSE bit, the field is > not optional. The field is already set correctly when the TSE bit is set. > > Since there is no limit for the number of descriptors that can be > used for a single packet, the field should be set to the sum of > the buffers contained in: > [<desc with First Descriptor bit set> ... <desc n> ... > <desc with Last Descriptor bit set>], which should be equal to skb->len. > > Signed-off-by: Niklas Cassel <niklas.cassel@axis.com> Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com> > --- > drivers/net/ethernet/stmicro/stmmac/chain_mode.c | 6 +++--- > drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- > drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 3 ++- > drivers/net/ethernet/stmicro/stmmac/enh_desc.c | 2 +- > drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 2 +- > drivers/net/ethernet/stmicro/stmmac/ring_mode.c | 9 ++++++--- > drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++-- > 7 files changed, 17 insertions(+), 12 deletions(-) > > diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c > index 37881f81319e..e93c40b4631e 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c > +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c > @@ -52,7 +52,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > tx_q->tx_skbuff_dma[entry].len = bmax; > /* do not close the descriptor and do not set own bit */ > priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE, > - 0, false); > + 0, false, skb->len); > > while (len != 0) { > tx_q->tx_skbuff[entry] = NULL; > @@ -70,7 +70,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > tx_q->tx_skbuff_dma[entry].len = bmax; > priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, > STMMAC_CHAIN_MODE, 1, > - false); > + false, skb->len); > len -= bmax; > i++; > } else { > @@ -85,7 +85,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > /* last descriptor can be set now */ > priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, > STMMAC_CHAIN_MODE, 1, > - true); > + true, skb->len); > len = 0; > } > } > diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h > index 90d28bcad880..b7ce3fbb5375 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/common.h > +++ b/drivers/net/ethernet/stmicro/stmmac/common.h > @@ -373,7 +373,7 @@ struct stmmac_desc_ops { > /* Invoked by the xmit function to prepare the tx descriptor */ > void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls); > + bool ls, unsigned int tot_pkt_len); > void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1, > int len2, bool tx_own, bool ls, > unsigned int tcphdrlen, > diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c > index 843ec69222ea..aa6476439aee 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c > +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c > @@ -304,12 +304,13 @@ static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end) > > static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls) > + bool ls, unsigned int tot_pkt_len) > { > unsigned int tdes3 = le32_to_cpu(p->des3); > > p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK); > > + tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK; > if (is_fs) > tdes3 |= TDES3_FIRST_DESCRIPTOR; > else > diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c > index 323b59ec74a3..7546b3664113 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c > +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c > @@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(struct dma_desc *p, int mode) > > static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls) > + bool ls, unsigned int tot_pkt_len) > { > unsigned int tdes0 = le32_to_cpu(p->des0); > > diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c > index efb818ebd55e..f817f8f36569 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c > +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c > @@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct dma_desc *p, int mode) > > static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, > bool csum_flag, int mode, bool tx_own, > - bool ls) > + bool ls, unsigned int tot_pkt_len) > { > unsigned int tdes1 = le32_to_cpu(p->des1); > > diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c > index 31213e64513d..28e4b5d50ce6 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c > +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c > @@ -59,7 +59,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > > desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); > priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, > - STMMAC_RING_MODE, 0, false); > + STMMAC_RING_MODE, 0, > + false, skb->len); > tx_q->tx_skbuff[entry] = NULL; > entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); > > @@ -79,7 +80,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > > desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); > priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, > - STMMAC_RING_MODE, 1, true); > + STMMAC_RING_MODE, 1, > + true, skb->len); > } else { > des2 = dma_map_single(priv->device, skb->data, > nopaged_len, DMA_TO_DEVICE); > @@ -91,7 +93,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) > tx_q->tx_skbuff_dma[entry].is_jumbo = true; > desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); > priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, > - STMMAC_RING_MODE, 0, true); > + STMMAC_RING_MODE, 0, > + true, skb->len); > } > > tx_q->cur_tx = entry; > diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > index a89f76b27ea2..5c1ebc70bebd 100644 > --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > @@ -3033,7 +3033,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) > > /* Prepare the descriptor and set the own bit too */ > priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, > - priv->mode, 1, last_segment); > + priv->mode, 1, last_segment, > + skb->len); > } > > entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); > @@ -3116,7 +3117,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) > /* Prepare the first descriptor setting the OWN bit too */ > priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len, > csum_insertion, priv->mode, 1, > - last_segment); > + last_segment, skb->len); > > /* The own bit must be the latest setting done when prepare the > * descriptor and then barrier is needed to make sure that
From: Niklas Cassel <niklas.cassel@axis.com> Date: Mon, 10 Apr 2017 20:33:29 +0200 > From: Niklas Cassel <niklas.cassel@axis.com> > > Field FL/TPL in register TDES3 is not correctly set on GMAC4. > TX appears to be functional on GMAC 4.10a even if this field is not set, > however, to avoid relying on undefined behavior, set the length in TDES3. > > The field has a different meaning depending on if the TSE bit in TDES3 > is set or not (TSO). However, regardless of the TSE bit, the field is > not optional. The field is already set correctly when the TSE bit is set. > > Since there is no limit for the number of descriptors that can be > used for a single packet, the field should be set to the sum of > the buffers contained in: > [<desc with First Descriptor bit set> ... <desc n> ... > <desc with Last Descriptor bit set>], which should be equal to skb->len. > > Signed-off-by: Niklas Cassel <niklas.cassel@axis.com> Applied, thanks.
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index 37881f81319e..e93c40b4631e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -52,7 +52,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].len = bmax; /* do not close the descriptor and do not set own bit */ priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE, - 0, false); + 0, false, skb->len); while (len != 0) { tx_q->tx_skbuff[entry] = NULL; @@ -70,7 +70,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].len = bmax; priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, STMMAC_CHAIN_MODE, 1, - false); + false, skb->len); len -= bmax; i++; } else { @@ -85,7 +85,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) /* last descriptor can be set now */ priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, STMMAC_CHAIN_MODE, 1, - true); + true, skb->len); len = 0; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 90d28bcad880..b7ce3fbb5375 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -373,7 +373,7 @@ struct stmmac_desc_ops { /* Invoked by the xmit function to prepare the tx descriptor */ void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls); + bool ls, unsigned int tot_pkt_len); void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1, int len2, bool tx_own, bool ls, unsigned int tcphdrlen, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 843ec69222ea..aa6476439aee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -304,12 +304,13 @@ static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end) static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls) + bool ls, unsigned int tot_pkt_len) { unsigned int tdes3 = le32_to_cpu(p->des3); p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK); + tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK; if (is_fs) tdes3 |= TDES3_FIRST_DESCRIPTOR; else diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 323b59ec74a3..7546b3664113 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(struct dma_desc *p, int mode) static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls) + bool ls, unsigned int tot_pkt_len) { unsigned int tdes0 = le32_to_cpu(p->des0); diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index efb818ebd55e..f817f8f36569 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct dma_desc *p, int mode) static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, bool csum_flag, int mode, bool tx_own, - bool ls) + bool ls, unsigned int tot_pkt_len) { unsigned int tdes1 = le32_to_cpu(p->des1); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index 31213e64513d..28e4b5d50ce6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -59,7 +59,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, - STMMAC_RING_MODE, 0, false); + STMMAC_RING_MODE, 0, + false, skb->len); tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); @@ -79,7 +80,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, - STMMAC_RING_MODE, 1, true); + STMMAC_RING_MODE, 1, + true, skb->len); } else { des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); @@ -91,7 +93,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, - STMMAC_RING_MODE, 0, true); + STMMAC_RING_MODE, 0, + true, skb->len); } tx_q->cur_tx = entry; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a89f76b27ea2..5c1ebc70bebd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3033,7 +3033,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Prepare the descriptor and set the own bit too */ priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, - priv->mode, 1, last_segment); + priv->mode, 1, last_segment, + skb->len); } entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); @@ -3116,7 +3117,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Prepare the first descriptor setting the OWN bit too */ priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len, csum_insertion, priv->mode, 1, - last_segment); + last_segment, skb->len); /* The own bit must be the latest setting done when prepare the * descriptor and then barrier is needed to make sure that