[PATCH net-next v2] net: stmmac: TSO: Simplify the code flow of DMA descriptor allocations
Furong Xu
0x1207 at gmail.com
Fri Dec 20 00:07:26 PST 2024
The TCP Segmentation Offload (TSO) engine is an optional function in
DWMAC cores, it is implemented for dwmac4 and dwxgmac2 only, ancient
dwmac100 and dwmac1000 are not supported by hardware. Current driver
code checks priv->dma_cap.tsoen which is read from MAC_HW_Feature1
register to determine if TSO is enabled in hardware configurations,
if (!priv->dma_cap.tsoen) driver never sets NETIF_F_TSO for net_device.
This patch never affects dwmac100/dwmac1000 and their stmmac_desc_ops:
ndesc_ops/enh_desc_ops, since TSO is never supported by them two.
The DMA AXI address width of DWMAC cores can be configured to
32-bit/40-bit/48-bit, then the format of DMA transmit descriptors
get a little different between 32-bit and 40-bit/48-bit.
Current driver code checks priv->dma_cap.addr64 to use certain format
with certain configuration.
This patch converts the format of DMA transmit descriptors on dwmac4
and dwxgmac2 that the DMA AXI address width is configured to 32-bit (as
described by function comments of stmmac_tso_xmit() in current code) to
a more generic format (see updated function comments after this patch)
which is actually already used on 40-bit/48-bit platforms to provide
better compatibility and make code flow cleaner in TSO TX routine.
Another interesting finding, struct stmmac_desc_ops is a common abstract
interface to maintain descriptors, we should avoid the direct assignment
of descriptor members (e.g. desc->des0), stmmac_set_desc_addr() is the
proper method yet. This patch tries to improve this by the way.
Tested and verified on:
DWMAC CORE 5.00a with 32-bit DMA AXI address width
DWMAC CORE 5.10a with 32-bit DMA AXI address width
DWXGMAC CORE 3.20a with 40-bit DMA AXI address width
Signed-off-by: Furong Xu <0x1207 at gmail.com>
---
V1 -> V2: Update commit message
V1: https://lore.kernel.org/r/20241213030006.337695-1-0x1207@gmail.com
---
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 60 ++++++++-----------
1 file changed, 24 insertions(+), 36 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6bc10ffe7a2b..99eaec8bac4a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4116,11 +4116,7 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des,
desc = &tx_q->dma_tx[tx_q->cur_tx];
curr_addr = des + (total_len - tmp_len);
- if (priv->dma_cap.addr64 <= 32)
- desc->des0 = cpu_to_le32(curr_addr);
- else
- stmmac_set_desc_addr(priv, desc, curr_addr);
-
+ stmmac_set_desc_addr(priv, desc, curr_addr);
buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
TSO_MAX_BUFF_SIZE : tmp_len;
@@ -4166,17 +4162,27 @@ static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue)
* First Descriptor
* --------
* | DES0 |---> buffer1 = L2/L3/L4 header
- * | DES1 |---> TCP Payload (can continue on next descr...)
- * | DES2 |---> buffer 1 and 2 len
+ * | DES1 |---> can be used as buffer2 for TCP Payload if the DMA AXI address
+ * | | width is 32-bit, but we never use it.
+ * | | Also can be used as the most-significant 8-bits or 16-bits of
+ * | | buffer1 address pointer if the DMA AXI address width is 40-bit
+ * | | or 48-bit, and we always use it.
+ * | DES2 |---> buffer1 len
* | DES3 |---> must set TSE, TCP hdr len-> [22:19]. TCP payload len [17:0]
* --------
+ * --------
+ * | DES0 |---> buffer1 = TCP Payload (can continue on next descr...)
+ * | DES1 |---> same as the First Descriptor
+ * | DES2 |---> buffer1 len
+ * | DES3 |
+ * --------
* |
* ...
* |
* --------
- * | DES0 | --| Split TCP Payload on Buffers 1 and 2
- * | DES1 | --|
- * | DES2 | --> buffer 1 and 2 len
+ * | DES0 |---> buffer1 = Split TCP Payload
+ * | DES1 |---> same as the First Descriptor
+ * | DES2 |---> buffer1 len
* | DES3 |
* --------
*
@@ -4186,15 +4192,14 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dma_desc *desc, *first, *mss_desc = NULL;
struct stmmac_priv *priv = netdev_priv(dev);
- int tmp_pay_len = 0, first_tx, nfrags;
unsigned int first_entry, tx_packets;
struct stmmac_txq_stats *txq_stats;
struct stmmac_tx_queue *tx_q;
u32 pay_len, mss, queue;
- dma_addr_t tso_des, des;
+ int i, first_tx, nfrags;
u8 proto_hdr_len, hdr;
+ dma_addr_t des;
bool set_ic;
- int i;
/* Always insert VLAN tag to SKB payload for TSO frames.
*
@@ -4279,24 +4284,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
if (dma_mapping_error(priv->device, des))
goto dma_map_err;
- if (priv->dma_cap.addr64 <= 32) {
- first->des0 = cpu_to_le32(des);
-
- /* Fill start of payload in buff2 of first descriptor */
- if (pay_len)
- first->des1 = cpu_to_le32(des + proto_hdr_len);
-
- /* If needed take extra descriptors to fill the remaining payload */
- tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
- tso_des = des;
- } else {
- stmmac_set_desc_addr(priv, first, des);
- tmp_pay_len = pay_len;
- tso_des = des + proto_hdr_len;
- pay_len = 0;
- }
-
- stmmac_tso_allocator(priv, tso_des, tmp_pay_len, (nfrags == 0), queue);
+ stmmac_set_desc_addr(priv, first, des);
+ stmmac_tso_allocator(priv, des + proto_hdr_len, pay_len,
+ (nfrags == 0), queue);
/* In case two or more DMA transmit descriptors are allocated for this
* non-paged SKB data, the DMA buffer address should be saved to
@@ -4400,11 +4390,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
}
/* Complete the first descriptor before granting the DMA */
- stmmac_prepare_tso_tx_desc(priv, first, 1,
- proto_hdr_len,
- pay_len,
- 1, tx_q->tx_skbuff_dma[first_entry].last_segment,
- hdr / 4, (skb->len - proto_hdr_len));
+ stmmac_prepare_tso_tx_desc(priv, first, 1, proto_hdr_len, 0, 1,
+ tx_q->tx_skbuff_dma[first_entry].last_segment,
+ hdr / 4, (skb->len - proto_hdr_len));
/* If context desc is used to change MSS */
if (mss_desc) {
--
2.34.1
More information about the linux-arm-kernel
mailing list