/* The datasheet for the X710 and XL710 indicate that the maximum value for * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec * resolution. 8160 is 0x1FE0 when written out in hex. So instead of storing * the register value which is divided by 2 lets use the actual values and * avoid an excessive amount of translation.
*/ #define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ #define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ #define I40E_ITR_20K 50 #define I40E_ITR_8K 122 #define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ #define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) #define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) #define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC))
/* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero
*/ #define INTRL_ENA BIT(6) #define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2)
/** * i40e_intrl_usec_to_reg - convert interrupt rate limit to register * @intrl: interrupt rate limit to convert * * This function converts a decimal interrupt rate limit to the appropriate * register format expected by the firmware when setting interrupt rate limit.
*/ staticinline u16 i40e_intrl_usec_to_reg(int intrl)
{ if (intrl >> 2) return ((intrl >> 2) | INTRL_ENA); else return 0;
}
#define I40E_QUEUE_END_OF_LIST 0x7FF
/* this enum matches hardware bits and is meant to be used by DYN_CTLN * registers and QINT registers or more generally anywhere in the manual * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any * register but instead is a special value meaning "don't update" ITR0/1/2.
*/ enum i40e_dyn_idx {
I40E_IDX_ITR0 = 0,
I40E_IDX_ITR1 = 1,
I40E_IDX_ITR2 = 2,
I40E_ITR_NONE = 3 /* ITR_NONE must not be used as an index */
};
/* these are indexes into ITRN registers */ #define I40E_RX_ITR I40E_IDX_ITR0 #define I40E_TX_ITR I40E_IDX_ITR1 #define I40E_SW_ITR I40E_IDX_ITR2
/* Supported Rx Buffer Sizes (a multiple of 128) */ #define I40E_RXBUFFER_256 256 #define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ #define I40E_RXBUFFER_2048 2048 #define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ #define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */
/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, * this adds up to 512 bytes of extra data meaning the smallest allocation * we could have is 1K. * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab)
*/ #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) #define i40e_rx_desc i40e_16byte_rx_desc
/* Attempt to maximize the headroom available for incoming frames. We * use a 2K buffer for receives and need 1536/1534 to store the data for * the frame. This leaves us with 512 bytes of room. From that we need * to deduct the space needed for the shared info and the padding needed * to IP align the frame. * * Note: For cache line sizes 256 or larger this value is going to end * up negative. In these cases we should fall back to the legacy * receive path.
*/ #if (PAGE_SIZE < 8192) #define I40E_2K_TOO_SMALL_WITH_PADDING \
((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048))
staticinlineint i40e_compute_pad(int rx_buf_len)
{ int page_size, pad_size;
staticinlineint i40e_skb_pad(void)
{ int rx_buf_len;
/* If a 2K buffer cannot handle a standard Ethernet frame then * optimize padding for a 3K buffer instead of a 1.5K buffer. * * For a 3K buffer we need to add enough padding to allow for * tailroom due to NET_IP_ALIGN possibly shifting us out of * cache-line alignment.
*/ if (I40E_2K_TOO_SMALL_WITH_PADDING)
rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); else
rx_buf_len = I40E_RXBUFFER_1536;
/* if needed make room for NET_IP_ALIGN */
rx_buf_len -= NET_IP_ALIGN;
/** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) * @stat_err_bits: value to mask * * This function does some fast chicanery in order to return the * value of the mask which is really only used for boolean tests. * The status_error_len doesn't need to be shifted because it begins * at offset zero.
*/ staticinlinebool i40e_test_staterr(union i40e_rx_desc *rx_desc, const u64 stat_err_bits)
{ return !!(rx_desc->wb.qword1.status_error_len &
cpu_to_le64(stat_err_bits));
}
/* How many Rx Buffers do we bundle into one write to the hardware ? */ #define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */
#define I40E_RX_NEXT_DESC(r, i, n) \ do { \
(i)++; \ if ((i) == (r)->count) \
i = 0; \
(n) = I40E_RX_DESC((r), (i)); \
} while (0)
/* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to * the nearest 4K which represents our maximum read request size.
*/ #define I40E_MAX_READ_REQ_SIZE 4096 #define I40E_MAX_DATA_PER_TXD (16 * 1024 - 1) #define I40E_MAX_DATA_PER_TXD_ALIGNED \
(I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1))
/** * i40e_txd_use_count - estimate the number of descriptors needed for Tx * @size: transmit request size in bytes * * Due to hardware alignment restrictions (4K alignment), we need to * assume that we can have no more than 12K of data per descriptor, even * though each descriptor can take up to 16K - 1 bytes of aligned memory. * Thus, we need to divide by 12K. But division is slow! Instead, * we decompose the operation into shifts and one relatively cheap * multiply operation. * * To divide by 12K, we first divide by 4K, then divide by 3: * To divide by 4K, shift right by 12 bits * To divide by 3, multiply by 85, then divide by 256 * (Divide by 256 is done by shifting right by 8 bits) * Finally, we add one to round up. Because 256 isn't an exact multiple of * 3, we'll underestimate near each multiple of 12K. This is actually more * accurate as we have 4K - 1 of wiggle room that we can fit into the last * segment. For our purposes this is accurate out to 1M which is orders of * magnitude greater than our largest possible GSO size. * * This would then be implemented as: * return (((size >> 12) * 85) >> 8) + 1; * * Since multiplication and division are commutative, we can reorder * operations into: * return ((size * 85) >> 20) + 1;
*/ staticinlineunsignedint i40e_txd_use_count(unsignedint size)
{ return ((size * 85) >> 20) + 1;
}
enum i40e_ring_state {
__I40E_TX_FDIR_INIT_DONE,
__I40E_TX_XPS_INIT_DONE,
__I40E_RING_STATE_NBITS /* must be last */
};
/* some useful defines for virtchannel interface, which * is the only remaining user of header split
*/ #define I40E_RX_DTYPE_HEADER_SPLIT 1 #define I40E_RX_SPLIT_L2 0x1 #define I40E_RX_SPLIT_IP 0x2 #define I40E_RX_SPLIT_TCP_UDP 0x4 #define I40E_RX_SPLIT_SCTP 0x8
/* struct that defines a descriptor ring, associated with a VSI */ struct i40e_ring { struct i40e_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ struct bpf_prog *xdp_prog; union { struct i40e_tx_buffer *tx_bi; struct i40e_rx_buffer *rx_bi; struct xdp_buff **rx_bi_zc;
};
DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS);
u16 queue_index; /* Queue number of ring */
u8 dcb_tc; /* Traffic class of ring */
u8 __iomem *tail;
/* Storing xdp_buff on ring helps in saving the state of partially built * packet when i40e_clean_rx_ring_irq() must return before it sees EOP * and to resume packet building for this ring in the next call to * i40e_clean_rx_ring_irq().
*/ struct xdp_buff xdp;
/* Next descriptor to be processed; next_to_clean is updated only on * processing EOP descriptor
*/
u16 next_to_process; /* high bit set means dynamic, use accessor routines to read/write. * hardware only supports 2us resolution for the ITR registers. * these values always store the USER setting, and must be converted * before programming to a register.
*/
u16 itr_setting;
u16 count; /* Number of descriptors */
u16 reg_idx; /* HW register index of the ring */
u16 rx_buf_len;
/* used in interrupt processing */
u16 next_to_use;
u16 next_to_clean;
u16 xdp_tx_active;
u8 atr_sample_rate;
u8 atr_count;
bool ring_active; /* is ring online or not */ bool arm_wb; /* do something to arm write back */
u8 packet_stride;
struct i40e_ring_container { struct i40e_ring *ring; /* pointer to linked list of ring(s) */ unsignedlong next_update; /* jiffies value of next update */ unsignedint total_bytes; /* total bytes processed this int */ unsignedint total_packets; /* total packets processed this int */
u16 count;
u16 target_itr; /* target ITR setting for ring(s) */
u16 current_itr; /* current ITR setting for ring(s) */
};
/* iterator for handling rings in ring container */ #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next)
bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
u16 i40e_lan_select_queue(struct net_device *netdev, struct sk_buff *skb, struct net_device *sb_dev); void i40e_clean_tx_ring(struct i40e_ring *tx_ring); void i40e_clean_rx_ring(struct i40e_ring *rx_ring); int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring); int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring); void i40e_free_tx_resources(struct i40e_ring *tx_ring); void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector);
u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); void i40e_detect_recover_hung(struct i40e_pf *pf); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
u32 flags); bool i40e_is_non_eop(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc);
/** * i40e_get_head - Retrieve head from head writeback * @tx_ring: tx ring to fetch head of * * Returns value of Tx ring head based on value stored * in head write-back location
**/ staticinline u32 i40e_get_head(struct i40e_ring *tx_ring)
{ void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count;
return le32_to_cpu(*(volatile __le32 *)head);
}
/** * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed * @skb: send buffer * * Returns number of data descriptors needed for this skb. Returns 0 to indicate * there is not enough descriptors available in this ring since we need at least * one descriptor.
**/ staticinlineint i40e_xmit_descriptor_count(struct sk_buff *skb)
{ const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsignedint nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb);
for (;;) {
count += i40e_txd_use_count(size);
if (!nr_frags--) break;
size = skb_frag_size(frag++);
}
return count;
}
/** * i40e_maybe_stop_tx - 1st level check for Tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * * Returns 0 if stop is not needed
**/ staticinlineint i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
{ if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) return 0; return __i40e_maybe_stop_tx(tx_ring, size);
}
/** * i40e_chk_linearize - Check if there are more than 8 fragments per packet * @skb: send buffer * @count: number of buffers used * * Note: Our HW can't scatter-gather more than 8 fragments to build * a packet on the wire and so we need to figure out the cases where we * need to linearize the skb.
**/ staticinlinebool i40e_chk_linearize(struct sk_buff *skb, int count)
{ /* Both TSO and single send will work if count is less than 8 */ if (likely(count < I40E_MAX_BUFFER_TXD)) returnfalse;
if (skb_is_gso(skb)) return __i40e_chk_linearize(skb);
/* we can support up to 8 data buffers for a single send */ return count != I40E_MAX_BUFFER_TXD;
}
/** * txring_txq - Find the netdev Tx ring based on the i40e Tx ring * @ring: Tx ring to find the netdev equivalent of
**/ staticinlinestruct netdev_queue *txring_txq(conststruct i40e_ring *ring)
{ return netdev_get_tx_queue(ring->netdev, ring->queue_index);
} #endif/* _I40E_TXRX_H_ */
Messung V0.5
¤ Dauer der Verarbeitung: 0.16 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.