Merge tag 'batman-adv-for-davem' of git://git.open-mesh.org/linux-merge
Included changes:
- update emails for A. Quartulli and M. Lindner in MAINTAINERS
- switch to the next on-the-wire protocol version
- introduce the T(ype) V(ersion) L(ength) V(alue) framework
- adjust the existing components to make them use the new TVLV code
- make the TT component use CRC32 instead of CRC16
- totally remove the VIS functionality (has been moved to userspace)
- reorder packet types and flags
- add static checks on packet format
- remove __packed from batadv_ogm_packet
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index add6d7a..1bce77f 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -34,7 +34,7 @@
#include "be_hw.h"
#include "be_roce.h"
-#define DRV_VER "4.9.134.0u"
+#define DRV_VER "4.9.224.0u"
#define DRV_NAME "be2net"
#define BE_NAME "Emulex BladeEngine2"
#define BE3_NAME "Emulex BladeEngine3"
@@ -325,6 +325,11 @@
u32 rx_input_fifo_overflow_drop;
u32 pmem_fifo_overflow_drop;
u32 jabber_events;
+ u32 rx_roce_bytes_lsd;
+ u32 rx_roce_bytes_msd;
+ u32 rx_roce_frames;
+ u32 roce_drops_payload_len;
+ u32 roce_drops_crc;
};
struct be_vf_cfg {
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 787bce8..2d55436 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1436,8 +1436,12 @@
OPCODE_ETH_GET_STATISTICS, nonemb_cmd->size, wrb, nonemb_cmd);
/* version 1 of the cmd is not supported only by BE2 */
- if (!BE2_chip(adapter))
+ if (BE2_chip(adapter))
+ hdr->version = 0;
+ if (BE3_chip(adapter) || lancer_chip(adapter))
hdr->version = 1;
+ else
+ hdr->version = 2;
be_mcc_notify(adapter);
adapter->stats_cmd_sent = true;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 337ef1f..8870837 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1662,6 +1662,67 @@
u32 rsvd[4];
};
+struct be_port_rxf_stats_v2 {
+ u32 rsvd0[10];
+ u32 roce_bytes_received_lsd;
+ u32 roce_bytes_received_msd;
+ u32 rsvd1[5];
+ u32 roce_frames_received;
+ u32 rx_crc_errors;
+ u32 rx_alignment_symbol_errors;
+ u32 rx_pause_frames;
+ u32 rx_priority_pause_frames;
+ u32 rx_control_frames;
+ u32 rx_in_range_errors;
+ u32 rx_out_range_errors;
+ u32 rx_frame_too_long;
+ u32 rx_address_filtered;
+ u32 rx_dropped_too_small;
+ u32 rx_dropped_too_short;
+ u32 rx_dropped_header_too_small;
+ u32 rx_dropped_tcp_length;
+ u32 rx_dropped_runt;
+ u32 rsvd2[10];
+ u32 rx_ip_checksum_errs;
+ u32 rx_tcp_checksum_errs;
+ u32 rx_udp_checksum_errs;
+ u32 rsvd3[7];
+ u32 rx_switched_unicast_packets;
+ u32 rx_switched_multicast_packets;
+ u32 rx_switched_broadcast_packets;
+ u32 rsvd4[3];
+ u32 tx_pauseframes;
+ u32 tx_priority_pauseframes;
+ u32 tx_controlframes;
+ u32 rsvd5[10];
+ u32 rxpp_fifo_overflow_drop;
+ u32 rx_input_fifo_overflow_drop;
+ u32 pmem_fifo_overflow_drop;
+ u32 jabber_events;
+ u32 rsvd6[3];
+ u32 rx_drops_payload_size;
+ u32 rx_drops_clipped_header;
+ u32 rx_drops_crc;
+ u32 roce_drops_payload_len;
+ u32 roce_drops_crc;
+ u32 rsvd7[19];
+};
+
+struct be_rxf_stats_v2 {
+ struct be_port_rxf_stats_v2 port[4];
+ u32 rsvd0[2];
+ u32 rx_drops_no_pbuf;
+ u32 rx_drops_no_txpb;
+ u32 rx_drops_no_erx_descr;
+ u32 rx_drops_no_tpre_descr;
+ u32 rsvd1[6];
+ u32 rx_drops_too_many_frags;
+ u32 rx_drops_invalid_ring;
+ u32 forwarded_packets;
+ u32 rx_drops_mtu;
+ u32 rsvd2[35];
+};
+
struct be_hw_stats_v1 {
struct be_rxf_stats_v1 rxf;
u32 rsvd0[BE_TXP_SW_SZ];
@@ -1680,6 +1741,29 @@
struct be_hw_stats_v1 hw_stats;
};
+struct be_erx_stats_v2 {
+ u32 rx_drops_no_fragments[136]; /* dwordS 0 to 135*/
+ u32 rsvd[3];
+};
+
+struct be_hw_stats_v2 {
+ struct be_rxf_stats_v2 rxf;
+ u32 rsvd0[BE_TXP_SW_SZ];
+ struct be_erx_stats_v2 erx;
+ struct be_pmem_stats pmem;
+ u32 rsvd1[18];
+};
+
+struct be_cmd_req_get_stats_v2 {
+ struct be_cmd_req_hdr hdr;
+ u8 rsvd[sizeof(struct be_hw_stats_v2)];
+};
+
+struct be_cmd_resp_get_stats_v2 {
+ struct be_cmd_resp_hdr hdr;
+ struct be_hw_stats_v2 hw_stats;
+};
+
/************** get fat capabilites *******************/
#define MAX_MODULES 27
#define MAX_MODES 4
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 3dcf817..0833003 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -116,7 +116,12 @@
{DRVSTAT_INFO(rx_drops_mtu)},
/* Number of packets dropped due to random early drop function */
{DRVSTAT_INFO(eth_red_drops)},
- {DRVSTAT_INFO(be_on_die_temperature)}
+ {DRVSTAT_INFO(be_on_die_temperature)},
+ {DRVSTAT_INFO(rx_roce_bytes_lsd)},
+ {DRVSTAT_INFO(rx_roce_bytes_msd)},
+ {DRVSTAT_INFO(rx_roce_frames)},
+ {DRVSTAT_INFO(roce_drops_payload_len)},
+ {DRVSTAT_INFO(roce_drops_crc)}
};
#define ETHTOOL_STATS_NUM ARRAY_SIZE(et_stats)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 9daee2e..2d6115c 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -306,10 +306,14 @@
struct be_cmd_resp_get_stats_v0 *cmd = adapter->stats_cmd.va;
return &cmd->hw_stats;
- } else {
+ } else if (BE3_chip(adapter)) {
struct be_cmd_resp_get_stats_v1 *cmd = adapter->stats_cmd.va;
return &cmd->hw_stats;
+ } else {
+ struct be_cmd_resp_get_stats_v2 *cmd = adapter->stats_cmd.va;
+
+ return &cmd->hw_stats;
}
}
@@ -320,10 +324,14 @@
struct be_hw_stats_v0 *hw_stats = hw_stats_from_cmd(adapter);
return &hw_stats->erx;
- } else {
+ } else if (BE3_chip(adapter)) {
struct be_hw_stats_v1 *hw_stats = hw_stats_from_cmd(adapter);
return &hw_stats->erx;
+ } else {
+ struct be_hw_stats_v2 *hw_stats = hw_stats_from_cmd(adapter);
+
+ return &hw_stats->erx;
}
}
@@ -422,6 +430,60 @@
adapter->drv_stats.eth_red_drops = pmem_sts->eth_red_drops;
}
+static void populate_be_v2_stats(struct be_adapter *adapter)
+{
+ struct be_hw_stats_v2 *hw_stats = hw_stats_from_cmd(adapter);
+ struct be_pmem_stats *pmem_sts = &hw_stats->pmem;
+ struct be_rxf_stats_v2 *rxf_stats = &hw_stats->rxf;
+ struct be_port_rxf_stats_v2 *port_stats =
+ &rxf_stats->port[adapter->port_num];
+ struct be_drv_stats *drvs = &adapter->drv_stats;
+
+ be_dws_le_to_cpu(hw_stats, sizeof(*hw_stats));
+ drvs->pmem_fifo_overflow_drop = port_stats->pmem_fifo_overflow_drop;
+ drvs->rx_priority_pause_frames = port_stats->rx_priority_pause_frames;
+ drvs->rx_pause_frames = port_stats->rx_pause_frames;
+ drvs->rx_crc_errors = port_stats->rx_crc_errors;
+ drvs->rx_control_frames = port_stats->rx_control_frames;
+ drvs->rx_in_range_errors = port_stats->rx_in_range_errors;
+ drvs->rx_frame_too_long = port_stats->rx_frame_too_long;
+ drvs->rx_dropped_runt = port_stats->rx_dropped_runt;
+ drvs->rx_ip_checksum_errs = port_stats->rx_ip_checksum_errs;
+ drvs->rx_tcp_checksum_errs = port_stats->rx_tcp_checksum_errs;
+ drvs->rx_udp_checksum_errs = port_stats->rx_udp_checksum_errs;
+ drvs->rx_dropped_tcp_length = port_stats->rx_dropped_tcp_length;
+ drvs->rx_dropped_too_small = port_stats->rx_dropped_too_small;
+ drvs->rx_dropped_too_short = port_stats->rx_dropped_too_short;
+ drvs->rx_out_range_errors = port_stats->rx_out_range_errors;
+ drvs->rx_dropped_header_too_small =
+ port_stats->rx_dropped_header_too_small;
+ drvs->rx_input_fifo_overflow_drop =
+ port_stats->rx_input_fifo_overflow_drop;
+ drvs->rx_address_filtered = port_stats->rx_address_filtered;
+ drvs->rx_alignment_symbol_errors =
+ port_stats->rx_alignment_symbol_errors;
+ drvs->rxpp_fifo_overflow_drop = port_stats->rxpp_fifo_overflow_drop;
+ drvs->tx_pauseframes = port_stats->tx_pauseframes;
+ drvs->tx_controlframes = port_stats->tx_controlframes;
+ drvs->tx_priority_pauseframes = port_stats->tx_priority_pauseframes;
+ drvs->jabber_events = port_stats->jabber_events;
+ drvs->rx_drops_no_pbuf = rxf_stats->rx_drops_no_pbuf;
+ drvs->rx_drops_no_erx_descr = rxf_stats->rx_drops_no_erx_descr;
+ drvs->forwarded_packets = rxf_stats->forwarded_packets;
+ drvs->rx_drops_mtu = rxf_stats->rx_drops_mtu;
+ drvs->rx_drops_no_tpre_descr = rxf_stats->rx_drops_no_tpre_descr;
+ drvs->rx_drops_too_many_frags = rxf_stats->rx_drops_too_many_frags;
+ adapter->drv_stats.eth_red_drops = pmem_sts->eth_red_drops;
+ if (be_roce_supported(adapter)) {
+ drvs->rx_roce_bytes_lsd = port_stats->roce_bytes_received_lsd;
+ drvs->rx_roce_bytes_msd = port_stats->roce_bytes_received_msd;
+ drvs->rx_roce_frames = port_stats->roce_frames_received;
+ drvs->roce_drops_crc = port_stats->roce_drops_crc;
+ drvs->roce_drops_payload_len =
+ port_stats->roce_drops_payload_len;
+ }
+}
+
static void populate_lancer_stats(struct be_adapter *adapter)
{
@@ -489,7 +551,7 @@
void be_parse_stats(struct be_adapter *adapter)
{
- struct be_erx_stats_v1 *erx = be_erx_stats_from_cmd(adapter);
+ struct be_erx_stats_v2 *erx = be_erx_stats_from_cmd(adapter);
struct be_rx_obj *rxo;
int i;
u32 erx_stat;
@@ -499,11 +561,13 @@
} else {
if (BE2_chip(adapter))
populate_be_v0_stats(adapter);
- else
- /* for BE3 and Skyhawk */
+ else if (BE3_chip(adapter))
+ /* for BE3 */
populate_be_v1_stats(adapter);
+ else
+ populate_be_v2_stats(adapter);
- /* as erx_v1 is longer than v0, ok to use v1 for v0 access */
+ /* erx_v2 is longer than v0, v1. use v2 for v0, v1 access */
for_all_rx_queues(adapter, rxo, i) {
erx_stat = erx->rx_drops_no_fragments[rxo->q.id];
populate_erx_stats(adapter, rxo, erx_stat);
@@ -4102,9 +4166,11 @@
cmd->size = sizeof(struct lancer_cmd_req_pport_stats);
else if (BE2_chip(adapter))
cmd->size = sizeof(struct be_cmd_req_get_stats_v0);
- else
- /* BE3 and Skyhawk */
+ else if (BE3_chip(adapter))
cmd->size = sizeof(struct be_cmd_req_get_stats_v1);
+ else
+ /* ALL non-BE ASICs */
+ cmd->size = sizeof(struct be_cmd_req_get_stats_v2);
cmd->va = dma_zalloc_coherent(&adapter->pdev->dev, cmd->size, &cmd->dma,
GFP_KERNEL);
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index b5252eb..c06a76c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -347,9 +347,9 @@
u32 rx_buf_failed;
u32 rx_page_failed;
- /* These are arrays of rings, allocated at run-time */
- struct i40e_ring *rx_rings;
- struct i40e_ring *tx_rings;
+ /* These are containers of ring pointers, allocated at run-time */
+ struct i40e_ring **rx_rings;
+ struct i40e_ring **tx_rings;
u16 work_limit;
/* high bit set means dynamic, use accessor routines to read/write.
@@ -366,7 +366,7 @@
u8 dtype;
/* List of q_vectors allocated to this VSI */
- struct i40e_q_vector *q_vectors;
+ struct i40e_q_vector **q_vectors;
int num_q_vectors;
int base_vector;
@@ -422,8 +422,9 @@
u8 num_ringpairs; /* total number of ring pairs in vector */
- char name[IFNAMSIZ + 9];
cpumask_t affinity_mask;
+ struct rcu_head rcu; /* to avoid race with update stats on free */
+ char name[IFNAMSIZ + 9];
} ____cacheline_internodealigned_in_smp;
/* lan device */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 8dbd91f..19e248f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -258,12 +258,12 @@
for (i = 0; i < vsi->num_queue_pairs; i++) {
len = sizeof(struct i40e_tx_buffer);
- memcpy(p, vsi->tx_rings[i].tx_bi, len);
+ memcpy(p, vsi->tx_rings[i]->tx_bi, len);
p += len;
}
for (i = 0; i < vsi->num_queue_pairs; i++) {
len = sizeof(struct i40e_rx_buffer);
- memcpy(p, vsi->rx_rings[i].rx_bi, len);
+ memcpy(p, vsi->rx_rings[i]->rx_bi, len);
p += len;
}
@@ -484,100 +484,104 @@
" tx_restart = %d, tx_busy = %d, rx_buf_failed = %d, rx_page_failed = %d\n",
vsi->tx_restart, vsi->tx_busy,
vsi->rx_buf_failed, vsi->rx_page_failed);
- if (vsi->rx_rings) {
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: desc = %p\n",
- i, vsi->rx_rings[i].desc);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: dev = %p, netdev = %p, rx_bi = %p\n",
- i, vsi->rx_rings[i].dev,
- vsi->rx_rings[i].netdev,
- vsi->rx_rings[i].rx_bi);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
- i, vsi->rx_rings[i].state,
- vsi->rx_rings[i].queue_index,
- vsi->rx_rings[i].reg_idx);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: rx_hdr_len = %d, rx_buf_len = %d, dtype = %d\n",
- i, vsi->rx_rings[i].rx_hdr_len,
- vsi->rx_rings[i].rx_buf_len,
- vsi->rx_rings[i].dtype);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
- i, vsi->rx_rings[i].hsplit,
- vsi->rx_rings[i].next_to_use,
- vsi->rx_rings[i].next_to_clean,
- vsi->rx_rings[i].ring_active);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: rx_stats: packets = %lld, bytes = %lld, non_eop_descs = %lld\n",
- i, vsi->rx_rings[i].rx_stats.packets,
- vsi->rx_rings[i].rx_stats.bytes,
- vsi->rx_rings[i].rx_stats.non_eop_descs);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: rx_stats: alloc_rx_page_failed = %lld, alloc_rx_buff_failed = %lld\n",
- i,
- vsi->rx_rings[i].rx_stats.alloc_rx_page_failed,
- vsi->rx_rings[i].rx_stats.alloc_rx_buff_failed);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: size = %i, dma = 0x%08lx\n",
- i, vsi->rx_rings[i].size,
- (long unsigned int)vsi->rx_rings[i].dma);
- dev_info(&pf->pdev->dev,
- " rx_rings[%i]: vsi = %p, q_vector = %p\n",
- i, vsi->rx_rings[i].vsi,
- vsi->rx_rings[i].q_vector);
- }
+ rcu_read_lock();
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ struct i40e_ring *rx_ring = ACCESS_ONCE(vsi->rx_rings[i]);
+ if (!rx_ring)
+ continue;
+
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: desc = %p\n",
+ i, rx_ring->desc);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: dev = %p, netdev = %p, rx_bi = %p\n",
+ i, rx_ring->dev,
+ rx_ring->netdev,
+ rx_ring->rx_bi);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
+ i, rx_ring->state,
+ rx_ring->queue_index,
+ rx_ring->reg_idx);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: rx_hdr_len = %d, rx_buf_len = %d, dtype = %d\n",
+ i, rx_ring->rx_hdr_len,
+ rx_ring->rx_buf_len,
+ rx_ring->dtype);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
+ i, rx_ring->hsplit,
+ rx_ring->next_to_use,
+ rx_ring->next_to_clean,
+ rx_ring->ring_active);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: rx_stats: packets = %lld, bytes = %lld, non_eop_descs = %lld\n",
+ i, rx_ring->stats.packets,
+ rx_ring->stats.bytes,
+ rx_ring->rx_stats.non_eop_descs);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: rx_stats: alloc_rx_page_failed = %lld, alloc_rx_buff_failed = %lld\n",
+ i,
+ rx_ring->rx_stats.alloc_rx_page_failed,
+ rx_ring->rx_stats.alloc_rx_buff_failed);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: size = %i, dma = 0x%08lx\n",
+ i, rx_ring->size,
+ (long unsigned int)rx_ring->dma);
+ dev_info(&pf->pdev->dev,
+ " rx_rings[%i]: vsi = %p, q_vector = %p\n",
+ i, rx_ring->vsi,
+ rx_ring->q_vector);
}
- if (vsi->tx_rings) {
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: desc = %p\n",
- i, vsi->tx_rings[i].desc);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: dev = %p, netdev = %p, tx_bi = %p\n",
- i, vsi->tx_rings[i].dev,
- vsi->tx_rings[i].netdev,
- vsi->tx_rings[i].tx_bi);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
- i, vsi->tx_rings[i].state,
- vsi->tx_rings[i].queue_index,
- vsi->tx_rings[i].reg_idx);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: dtype = %d\n",
- i, vsi->tx_rings[i].dtype);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
- i, vsi->tx_rings[i].hsplit,
- vsi->tx_rings[i].next_to_use,
- vsi->tx_rings[i].next_to_clean,
- vsi->tx_rings[i].ring_active);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: tx_stats: packets = %lld, bytes = %lld, restart_queue = %lld\n",
- i, vsi->tx_rings[i].tx_stats.packets,
- vsi->tx_rings[i].tx_stats.bytes,
- vsi->tx_rings[i].tx_stats.restart_queue);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: tx_stats: tx_busy = %lld, completed = %lld, tx_done_old = %lld\n",
- i,
- vsi->tx_rings[i].tx_stats.tx_busy,
- vsi->tx_rings[i].tx_stats.completed,
- vsi->tx_rings[i].tx_stats.tx_done_old);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: size = %i, dma = 0x%08lx\n",
- i, vsi->tx_rings[i].size,
- (long unsigned int)vsi->tx_rings[i].dma);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: vsi = %p, q_vector = %p\n",
- i, vsi->tx_rings[i].vsi,
- vsi->tx_rings[i].q_vector);
- dev_info(&pf->pdev->dev,
- " tx_rings[%i]: DCB tc = %d\n",
- i, vsi->tx_rings[i].dcb_tc);
- }
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ struct i40e_ring *tx_ring = ACCESS_ONCE(vsi->tx_rings[i]);
+ if (!tx_ring)
+ continue;
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: desc = %p\n",
+ i, tx_ring->desc);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: dev = %p, netdev = %p, tx_bi = %p\n",
+ i, tx_ring->dev,
+ tx_ring->netdev,
+ tx_ring->tx_bi);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: state = %li, queue_index = %d, reg_idx = %d\n",
+ i, tx_ring->state,
+ tx_ring->queue_index,
+ tx_ring->reg_idx);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: dtype = %d\n",
+ i, tx_ring->dtype);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: hsplit = %d, next_to_use = %d, next_to_clean = %d, ring_active = %i\n",
+ i, tx_ring->hsplit,
+ tx_ring->next_to_use,
+ tx_ring->next_to_clean,
+ tx_ring->ring_active);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: tx_stats: packets = %lld, bytes = %lld, restart_queue = %lld\n",
+ i, tx_ring->stats.packets,
+ tx_ring->stats.bytes,
+ tx_ring->tx_stats.restart_queue);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: tx_stats: tx_busy = %lld, tx_done_old = %lld\n",
+ i,
+ tx_ring->tx_stats.tx_busy,
+ tx_ring->tx_stats.tx_done_old);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: size = %i, dma = 0x%08lx\n",
+ i, tx_ring->size,
+ (long unsigned int)tx_ring->dma);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: vsi = %p, q_vector = %p\n",
+ i, tx_ring->vsi,
+ tx_ring->q_vector);
+ dev_info(&pf->pdev->dev,
+ " tx_rings[%i]: DCB tc = %d\n",
+ i, tx_ring->dcb_tc);
}
+ rcu_read_unlock();
dev_info(&pf->pdev->dev,
" work_limit = %d, rx_itr_setting = %d (%s), tx_itr_setting = %d (%s)\n",
vsi->work_limit, vsi->rx_itr_setting,
@@ -587,15 +591,6 @@
dev_info(&pf->pdev->dev,
" max_frame = %d, rx_hdr_len = %d, rx_buf_len = %d dtype = %d\n",
vsi->max_frame, vsi->rx_hdr_len, vsi->rx_buf_len, vsi->dtype);
- if (vsi->q_vectors) {
- for (i = 0; i < vsi->num_q_vectors; i++) {
- dev_info(&pf->pdev->dev,
- " q_vectors[%i]: base index = %ld\n",
- i, ((long int)*vsi->q_vectors[i].rx.ring-
- (long int)*vsi->q_vectors[0].rx.ring)/
- sizeof(struct i40e_ring));
- }
- }
dev_info(&pf->pdev->dev,
" num_q_vectors = %i, base_vector = %i\n",
vsi->num_q_vectors, vsi->base_vector);
@@ -792,9 +787,9 @@
return;
}
if (is_rx_ring)
- ring = vsi->rx_rings[ring_id];
+ ring = *vsi->rx_rings[ring_id];
else
- ring = vsi->tx_rings[ring_id];
+ ring = *vsi->tx_rings[ring_id];
if (cnt == 2) {
dev_info(&pf->pdev->dev, "vsi = %02i %s ring = %02i\n",
vsi_seid, is_rx_ring ? "rx" : "tx", ring_id);
@@ -1996,7 +1991,7 @@
goto netdev_ops_write_done;
}
for (i = 0; i < vsi->num_q_vectors; i++)
- napi_schedule(&vsi->q_vectors[i].napi);
+ napi_schedule(&vsi->q_vectors[i]->napi);
dev_info(&pf->pdev->dev, "napi called\n");
} else {
dev_info(&pf->pdev->dev, "unknown command '%s'\n",
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 9a76b8c..1b86138 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -399,8 +399,8 @@
ring->tx_max_pending = I40E_MAX_NUM_DESCRIPTORS;
ring->rx_mini_max_pending = 0;
ring->rx_jumbo_max_pending = 0;
- ring->rx_pending = vsi->rx_rings[0].count;
- ring->tx_pending = vsi->tx_rings[0].count;
+ ring->rx_pending = vsi->rx_rings[0]->count;
+ ring->tx_pending = vsi->tx_rings[0]->count;
ring->rx_mini_pending = 0;
ring->rx_jumbo_pending = 0;
}
@@ -429,8 +429,8 @@
new_rx_count = ALIGN(new_rx_count, I40E_REQ_DESCRIPTOR_MULTIPLE);
/* if nothing to do return success */
- if ((new_tx_count == vsi->tx_rings[0].count) &&
- (new_rx_count == vsi->rx_rings[0].count))
+ if ((new_tx_count == vsi->tx_rings[0]->count) &&
+ (new_rx_count == vsi->rx_rings[0]->count))
return 0;
while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state))
@@ -439,8 +439,8 @@
if (!netif_running(vsi->netdev)) {
/* simple case - set for the next time the netdev is started */
for (i = 0; i < vsi->num_queue_pairs; i++) {
- vsi->tx_rings[i].count = new_tx_count;
- vsi->rx_rings[i].count = new_rx_count;
+ vsi->tx_rings[i]->count = new_tx_count;
+ vsi->rx_rings[i]->count = new_rx_count;
}
goto done;
}
@@ -451,10 +451,10 @@
*/
/* alloc updated Tx resources */
- if (new_tx_count != vsi->tx_rings[0].count) {
+ if (new_tx_count != vsi->tx_rings[0]->count) {
netdev_info(netdev,
"Changing Tx descriptor count from %d to %d.\n",
- vsi->tx_rings[0].count, new_tx_count);
+ vsi->tx_rings[0]->count, new_tx_count);
tx_rings = kcalloc(vsi->alloc_queue_pairs,
sizeof(struct i40e_ring), GFP_KERNEL);
if (!tx_rings) {
@@ -464,7 +464,7 @@
for (i = 0; i < vsi->num_queue_pairs; i++) {
/* clone ring and setup updated count */
- tx_rings[i] = vsi->tx_rings[i];
+ tx_rings[i] = *vsi->tx_rings[i];
tx_rings[i].count = new_tx_count;
err = i40e_setup_tx_descriptors(&tx_rings[i]);
if (err) {
@@ -481,10 +481,10 @@
}
/* alloc updated Rx resources */
- if (new_rx_count != vsi->rx_rings[0].count) {
+ if (new_rx_count != vsi->rx_rings[0]->count) {
netdev_info(netdev,
"Changing Rx descriptor count from %d to %d\n",
- vsi->rx_rings[0].count, new_rx_count);
+ vsi->rx_rings[0]->count, new_rx_count);
rx_rings = kcalloc(vsi->alloc_queue_pairs,
sizeof(struct i40e_ring), GFP_KERNEL);
if (!rx_rings) {
@@ -494,7 +494,7 @@
for (i = 0; i < vsi->num_queue_pairs; i++) {
/* clone ring and setup updated count */
- rx_rings[i] = vsi->rx_rings[i];
+ rx_rings[i] = *vsi->rx_rings[i];
rx_rings[i].count = new_rx_count;
err = i40e_setup_rx_descriptors(&rx_rings[i]);
if (err) {
@@ -517,8 +517,8 @@
if (tx_rings) {
for (i = 0; i < vsi->num_queue_pairs; i++) {
- i40e_free_tx_resources(&vsi->tx_rings[i]);
- vsi->tx_rings[i] = tx_rings[i];
+ i40e_free_tx_resources(vsi->tx_rings[i]);
+ *vsi->tx_rings[i] = tx_rings[i];
}
kfree(tx_rings);
tx_rings = NULL;
@@ -526,8 +526,8 @@
if (rx_rings) {
for (i = 0; i < vsi->num_queue_pairs; i++) {
- i40e_free_rx_resources(&vsi->rx_rings[i]);
- vsi->rx_rings[i] = rx_rings[i];
+ i40e_free_rx_resources(vsi->rx_rings[i]);
+ *vsi->rx_rings[i] = rx_rings[i];
}
kfree(rx_rings);
rx_rings = NULL;
@@ -579,6 +579,7 @@
char *p;
int j;
struct rtnl_link_stats64 *net_stats = i40e_get_vsi_stats_struct(vsi);
+ unsigned int start;
i40e_update_stats(vsi);
@@ -587,14 +588,30 @@
data[i++] = (i40e_gstrings_net_stats[j].sizeof_stat ==
sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
}
- for (j = 0; j < vsi->num_queue_pairs; j++) {
- data[i++] = vsi->tx_rings[j].tx_stats.packets;
- data[i++] = vsi->tx_rings[j].tx_stats.bytes;
+ rcu_read_lock();
+ for (j = 0; j < vsi->num_queue_pairs; j++, i += 4) {
+ struct i40e_ring *tx_ring = ACCESS_ONCE(vsi->tx_rings[j]);
+ struct i40e_ring *rx_ring;
+
+ if (!tx_ring)
+ continue;
+
+ /* process Tx ring statistics */
+ do {
+ start = u64_stats_fetch_begin_bh(&tx_ring->syncp);
+ data[i] = tx_ring->stats.packets;
+ data[i + 1] = tx_ring->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&tx_ring->syncp, start));
+
+ /* Rx ring is the 2nd half of the queue pair */
+ rx_ring = &tx_ring[1];
+ do {
+ start = u64_stats_fetch_begin_bh(&rx_ring->syncp);
+ data[i + 2] = rx_ring->stats.packets;
+ data[i + 3] = rx_ring->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&rx_ring->syncp, start));
}
- for (j = 0; j < vsi->num_queue_pairs; j++) {
- data[i++] = vsi->rx_rings[j].rx_stats.packets;
- data[i++] = vsi->rx_rings[j].rx_stats.bytes;
- }
+ rcu_read_unlock();
if (vsi == pf->vsi[pf->lan_vsi]) {
for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) {
p = (char *)pf + i40e_gstrings_stats[j].stat_offset;
@@ -641,8 +658,6 @@
p += ETH_GSTRING_LEN;
snprintf(p, ETH_GSTRING_LEN, "tx-%u.tx_bytes", i);
p += ETH_GSTRING_LEN;
- }
- for (i = 0; i < vsi->num_queue_pairs; i++) {
snprintf(p, ETH_GSTRING_LEN, "rx-%u.rx_packets", i);
p += ETH_GSTRING_LEN;
snprintf(p, ETH_GSTRING_LEN, "rx-%u.rx_bytes", i);
@@ -910,8 +925,8 @@
}
vector = vsi->base_vector;
- q_vector = vsi->q_vectors;
- for (i = 0; i < vsi->num_q_vectors; i++, vector++, q_vector++) {
+ for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+ q_vector = vsi->q_vectors[i];
q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
wr32(hw, I40E_PFINT_ITRN(0, vector - 1), q_vector->rx.itr);
q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 221aa47..fbe7fe2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -36,7 +36,7 @@
#define DRV_VERSION_MAJOR 0
#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 9
+#define DRV_VERSION_BUILD 10
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
@@ -347,14 +347,53 @@
**/
static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
struct net_device *netdev,
- struct rtnl_link_stats64 *storage)
+ struct rtnl_link_stats64 *stats)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
+ struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi);
+ int i;
- *storage = *i40e_get_vsi_stats_struct(vsi);
+ rcu_read_lock();
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ struct i40e_ring *tx_ring, *rx_ring;
+ u64 bytes, packets;
+ unsigned int start;
- return storage;
+ tx_ring = ACCESS_ONCE(vsi->tx_rings[i]);
+ if (!tx_ring)
+ continue;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&tx_ring->syncp);
+ packets = tx_ring->stats.packets;
+ bytes = tx_ring->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&tx_ring->syncp, start));
+
+ stats->tx_packets += packets;
+ stats->tx_bytes += bytes;
+ rx_ring = &tx_ring[1];
+
+ do {
+ start = u64_stats_fetch_begin_bh(&rx_ring->syncp);
+ packets = rx_ring->stats.packets;
+ bytes = rx_ring->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&rx_ring->syncp, start));
+
+ stats->rx_packets += packets;
+ stats->rx_bytes += bytes;
+ }
+ rcu_read_unlock();
+
+ /* following stats updated by ixgbe_watchdog_task() */
+ stats->multicast = vsi_stats->multicast;
+ stats->tx_errors = vsi_stats->tx_errors;
+ stats->tx_dropped = vsi_stats->tx_dropped;
+ stats->rx_errors = vsi_stats->rx_errors;
+ stats->rx_crc_errors = vsi_stats->rx_crc_errors;
+ stats->rx_length_errors = vsi_stats->rx_length_errors;
+
+ return stats;
}
/**
@@ -376,10 +415,14 @@
memset(&vsi->eth_stats_offsets, 0, sizeof(vsi->eth_stats_offsets));
if (vsi->rx_rings)
for (i = 0; i < vsi->num_queue_pairs; i++) {
- memset(&vsi->rx_rings[i].rx_stats, 0 ,
- sizeof(vsi->rx_rings[i].rx_stats));
- memset(&vsi->tx_rings[i].tx_stats, 0,
- sizeof(vsi->tx_rings[i].tx_stats));
+ memset(&vsi->rx_rings[i]->stats, 0 ,
+ sizeof(vsi->rx_rings[i]->stats));
+ memset(&vsi->rx_rings[i]->rx_stats, 0 ,
+ sizeof(vsi->rx_rings[i]->rx_stats));
+ memset(&vsi->tx_rings[i]->stats, 0 ,
+ sizeof(vsi->tx_rings[i]->stats));
+ memset(&vsi->tx_rings[i]->tx_stats, 0,
+ sizeof(vsi->tx_rings[i]->tx_stats));
}
vsi->stat_offsets_loaded = false;
}
@@ -598,7 +641,7 @@
continue;
for (i = 0; i < vsi->num_queue_pairs; i++) {
- struct i40e_ring *ring = &vsi->tx_rings[i];
+ struct i40e_ring *ring = vsi->tx_rings[i];
clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state);
}
}
@@ -652,7 +695,7 @@
continue;
for (i = 0; i < vsi->num_queue_pairs; i++) {
- struct i40e_ring *ring = &vsi->tx_rings[i];
+ struct i40e_ring *ring = vsi->tx_rings[i];
tc = ring->dcb_tc;
if (xoff[tc])
@@ -704,21 +747,38 @@
tx_restart = tx_busy = 0;
rx_page = 0;
rx_buf = 0;
+ rcu_read_lock();
for (q = 0; q < vsi->num_queue_pairs; q++) {
struct i40e_ring *p;
+ u64 bytes, packets;
+ unsigned int start;
- p = &vsi->rx_rings[q];
- rx_b += p->rx_stats.bytes;
- rx_p += p->rx_stats.packets;
- rx_buf += p->rx_stats.alloc_rx_buff_failed;
- rx_page += p->rx_stats.alloc_rx_page_failed;
+ /* locate Tx ring */
+ p = ACCESS_ONCE(vsi->tx_rings[q]);
- p = &vsi->tx_rings[q];
- tx_b += p->tx_stats.bytes;
- tx_p += p->tx_stats.packets;
+ do {
+ start = u64_stats_fetch_begin_bh(&p->syncp);
+ packets = p->stats.packets;
+ bytes = p->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ tx_b += bytes;
+ tx_p += packets;
tx_restart += p->tx_stats.restart_queue;
tx_busy += p->tx_stats.tx_busy;
+
+ /* Rx queue is part of the same block as Tx queue */
+ p = &p[1];
+ do {
+ start = u64_stats_fetch_begin_bh(&p->syncp);
+ packets = p->stats.packets;
+ bytes = p->stats.bytes;
+ } while (u64_stats_fetch_retry_bh(&p->syncp, start));
+ rx_b += bytes;
+ rx_p += packets;
+ rx_buf += p->rx_stats.alloc_rx_buff_failed;
+ rx_page += p->rx_stats.alloc_rx_page_failed;
}
+ rcu_read_unlock();
vsi->tx_restart = tx_restart;
vsi->tx_busy = tx_busy;
vsi->rx_page_failed = rx_page;
@@ -1988,7 +2048,7 @@
int i, err = 0;
for (i = 0; i < vsi->num_queue_pairs && !err; i++)
- err = i40e_setup_tx_descriptors(&vsi->tx_rings[i]);
+ err = i40e_setup_tx_descriptors(vsi->tx_rings[i]);
return err;
}
@@ -2004,8 +2064,8 @@
int i;
for (i = 0; i < vsi->num_queue_pairs; i++)
- if (vsi->tx_rings[i].desc)
- i40e_free_tx_resources(&vsi->tx_rings[i]);
+ if (vsi->tx_rings[i]->desc)
+ i40e_free_tx_resources(vsi->tx_rings[i]);
}
/**
@@ -2023,7 +2083,7 @@
int i, err = 0;
for (i = 0; i < vsi->num_queue_pairs && !err; i++)
- err = i40e_setup_rx_descriptors(&vsi->rx_rings[i]);
+ err = i40e_setup_rx_descriptors(vsi->rx_rings[i]);
return err;
}
@@ -2038,8 +2098,8 @@
int i;
for (i = 0; i < vsi->num_queue_pairs; i++)
- if (vsi->rx_rings[i].desc)
- i40e_free_rx_resources(&vsi->rx_rings[i]);
+ if (vsi->rx_rings[i]->desc)
+ i40e_free_rx_resources(vsi->rx_rings[i]);
}
/**
@@ -2223,8 +2283,8 @@
int err = 0;
u16 i;
- for (i = 0; (i < vsi->num_queue_pairs) && (!err); i++)
- err = i40e_configure_tx_ring(&vsi->tx_rings[i]);
+ for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
+ err = i40e_configure_tx_ring(vsi->tx_rings[i]);
return err;
}
@@ -2274,7 +2334,7 @@
/* set up individual rings */
for (i = 0; i < vsi->num_queue_pairs && !err; i++)
- err = i40e_configure_rx_ring(&vsi->rx_rings[i]);
+ err = i40e_configure_rx_ring(vsi->rx_rings[i]);
return err;
}
@@ -2298,8 +2358,8 @@
qoffset = vsi->tc_config.tc_info[n].qoffset;
qcount = vsi->tc_config.tc_info[n].qcount;
for (i = qoffset; i < (qoffset + qcount); i++) {
- struct i40e_ring *rx_ring = &vsi->rx_rings[i];
- struct i40e_ring *tx_ring = &vsi->tx_rings[i];
+ struct i40e_ring *rx_ring = vsi->rx_rings[i];
+ struct i40e_ring *tx_ring = vsi->tx_rings[i];
rx_ring->dcb_tc = n;
tx_ring->dcb_tc = n;
}
@@ -2354,8 +2414,8 @@
*/
qp = vsi->base_queue;
vector = vsi->base_vector;
- q_vector = vsi->q_vectors;
- for (i = 0; i < vsi->num_q_vectors; i++, q_vector++, vector++) {
+ for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+ q_vector = vsi->q_vectors[i];
q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
q_vector->rx.latency_range = I40E_LOW_LATENCY;
wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1),
@@ -2435,7 +2495,7 @@
**/
static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
{
- struct i40e_q_vector *q_vector = vsi->q_vectors;
+ struct i40e_q_vector *q_vector = vsi->q_vectors[0];
struct i40e_pf *pf = vsi->back;
struct i40e_hw *hw = &pf->hw;
u32 val;
@@ -2512,7 +2572,7 @@
{
struct i40e_q_vector *q_vector = data;
- if (!q_vector->tx.ring[0] && !q_vector->rx.ring[0])
+ if (!q_vector->tx.ring && !q_vector->rx.ring)
return IRQ_HANDLED;
napi_schedule(&q_vector->napi);
@@ -2529,7 +2589,7 @@
{
struct i40e_q_vector *q_vector = data;
- if (!q_vector->tx.ring[0] && !q_vector->rx.ring[0])
+ if (!q_vector->tx.ring && !q_vector->rx.ring)
return IRQ_HANDLED;
pr_info("fdir ring cleaning needed\n");
@@ -2554,16 +2614,16 @@
int vector, err;
for (vector = 0; vector < q_vectors; vector++) {
- struct i40e_q_vector *q_vector = &(vsi->q_vectors[vector]);
+ struct i40e_q_vector *q_vector = vsi->q_vectors[vector];
- if (q_vector->tx.ring[0] && q_vector->rx.ring[0]) {
+ if (q_vector->tx.ring && q_vector->rx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
"%s-%s-%d", basename, "TxRx", rx_int_idx++);
tx_int_idx++;
- } else if (q_vector->rx.ring[0]) {
+ } else if (q_vector->rx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
"%s-%s-%d", basename, "rx", rx_int_idx++);
- } else if (q_vector->tx.ring[0]) {
+ } else if (q_vector->tx.ring) {
snprintf(q_vector->name, sizeof(q_vector->name) - 1,
"%s-%s-%d", basename, "tx", tx_int_idx++);
} else {
@@ -2611,8 +2671,8 @@
int i;
for (i = 0; i < vsi->num_queue_pairs; i++) {
- wr32(hw, I40E_QINT_TQCTL(vsi->tx_rings[i].reg_idx), 0);
- wr32(hw, I40E_QINT_RQCTL(vsi->rx_rings[i].reg_idx), 0);
+ wr32(hw, I40E_QINT_TQCTL(vsi->tx_rings[i]->reg_idx), 0);
+ wr32(hw, I40E_QINT_RQCTL(vsi->rx_rings[i]->reg_idx), 0);
}
if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
@@ -2705,7 +2765,7 @@
i40e_flush(hw);
if (!test_bit(__I40E_DOWN, &pf->state))
- napi_schedule(&pf->vsi[pf->lan_vsi]->q_vectors[0].napi);
+ napi_schedule(&pf->vsi[pf->lan_vsi]->q_vectors[0]->napi);
}
if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) {
@@ -2774,40 +2834,26 @@
}
/**
- * i40e_map_vector_to_rxq - Assigns the Rx queue to the vector
+ * i40e_map_vector_to_qp - Assigns the queue pair to the vector
* @vsi: the VSI being configured
* @v_idx: vector index
- * @r_idx: rx queue index
+ * @qp_idx: queue pair index
**/
-static void map_vector_to_rxq(struct i40e_vsi *vsi, int v_idx, int r_idx)
+static void map_vector_to_qp(struct i40e_vsi *vsi, int v_idx, int qp_idx)
{
- struct i40e_q_vector *q_vector = &(vsi->q_vectors[v_idx]);
- struct i40e_ring *rx_ring = &(vsi->rx_rings[r_idx]);
-
- rx_ring->q_vector = q_vector;
- q_vector->rx.ring[q_vector->rx.count] = rx_ring;
- q_vector->rx.count++;
- q_vector->rx.latency_range = I40E_LOW_LATENCY;
- q_vector->vsi = vsi;
-}
-
-/**
- * i40e_map_vector_to_txq - Assigns the Tx queue to the vector
- * @vsi: the VSI being configured
- * @v_idx: vector index
- * @t_idx: tx queue index
- **/
-static void map_vector_to_txq(struct i40e_vsi *vsi, int v_idx, int t_idx)
-{
- struct i40e_q_vector *q_vector = &(vsi->q_vectors[v_idx]);
- struct i40e_ring *tx_ring = &(vsi->tx_rings[t_idx]);
+ struct i40e_q_vector *q_vector = vsi->q_vectors[v_idx];
+ struct i40e_ring *tx_ring = vsi->tx_rings[qp_idx];
+ struct i40e_ring *rx_ring = vsi->rx_rings[qp_idx];
tx_ring->q_vector = q_vector;
- q_vector->tx.ring[q_vector->tx.count] = tx_ring;
+ tx_ring->next = q_vector->tx.ring;
+ q_vector->tx.ring = tx_ring;
q_vector->tx.count++;
- q_vector->tx.latency_range = I40E_LOW_LATENCY;
- q_vector->num_ringpairs++;
- q_vector->vsi = vsi;
+
+ rx_ring->q_vector = q_vector;
+ rx_ring->next = q_vector->rx.ring;
+ q_vector->rx.ring = rx_ring;
+ q_vector->rx.count++;
}
/**
@@ -2823,7 +2869,7 @@
{
int qp_remaining = vsi->num_queue_pairs;
int q_vectors = vsi->num_q_vectors;
- int qp_per_vector;
+ int num_ringpairs;
int v_start = 0;
int qp_idx = 0;
@@ -2831,11 +2877,21 @@
* group them so there are multiple queues per vector.
*/
for (; v_start < q_vectors && qp_remaining; v_start++) {
- qp_per_vector = DIV_ROUND_UP(qp_remaining, q_vectors - v_start);
- for (; qp_per_vector;
- qp_per_vector--, qp_idx++, qp_remaining--) {
- map_vector_to_rxq(vsi, v_start, qp_idx);
- map_vector_to_txq(vsi, v_start, qp_idx);
+ struct i40e_q_vector *q_vector = vsi->q_vectors[v_start];
+
+ num_ringpairs = DIV_ROUND_UP(qp_remaining, q_vectors - v_start);
+
+ q_vector->num_ringpairs = num_ringpairs;
+
+ q_vector->rx.count = 0;
+ q_vector->tx.count = 0;
+ q_vector->rx.ring = NULL;
+ q_vector->tx.ring = NULL;
+
+ while (num_ringpairs--) {
+ map_vector_to_qp(vsi, v_start, qp_idx);
+ qp_idx++;
+ qp_remaining--;
}
}
}
@@ -2887,7 +2943,7 @@
pf->flags |= I40E_FLAG_IN_NETPOLL;
if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
for (i = 0; i < vsi->num_q_vectors; i++)
- i40e_msix_clean_rings(0, &vsi->q_vectors[i]);
+ i40e_msix_clean_rings(0, vsi->q_vectors[i]);
} else {
i40e_intr(pf->pdev->irq, netdev);
}
@@ -3073,14 +3129,14 @@
u16 vector = i + base;
/* free only the irqs that were actually requested */
- if (vsi->q_vectors[i].num_ringpairs == 0)
+ if (vsi->q_vectors[i]->num_ringpairs == 0)
continue;
/* clear the affinity_mask in the IRQ descriptor */
irq_set_affinity_hint(pf->msix_entries[vector].vector,
NULL);
free_irq(pf->msix_entries[vector].vector,
- &vsi->q_vectors[i]);
+ vsi->q_vectors[i]);
/* Tear down the interrupt queue link list
*
@@ -3164,6 +3220,39 @@
}
/**
+ * i40e_free_q_vector - Free memory allocated for specific interrupt vector
+ * @vsi: the VSI being configured
+ * @v_idx: Index of vector to be freed
+ *
+ * This function frees the memory allocated to the q_vector. In addition if
+ * NAPI is enabled it will delete any references to the NAPI struct prior
+ * to freeing the q_vector.
+ **/
+static void i40e_free_q_vector(struct i40e_vsi *vsi, int v_idx)
+{
+ struct i40e_q_vector *q_vector = vsi->q_vectors[v_idx];
+ struct i40e_ring *ring;
+
+ if (!q_vector)
+ return;
+
+ /* disassociate q_vector from rings */
+ i40e_for_each_ring(ring, q_vector->tx)
+ ring->q_vector = NULL;
+
+ i40e_for_each_ring(ring, q_vector->rx)
+ ring->q_vector = NULL;
+
+ /* only VSI w/ an associated netdev is set up w/ NAPI */
+ if (vsi->netdev)
+ netif_napi_del(&q_vector->napi);
+
+ vsi->q_vectors[v_idx] = NULL;
+
+ kfree_rcu(q_vector, rcu);
+}
+
+/**
* i40e_vsi_free_q_vectors - Free memory allocated for interrupt vectors
* @vsi: the VSI being un-configured
*
@@ -3174,24 +3263,8 @@
{
int v_idx;
- for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++) {
- struct i40e_q_vector *q_vector = &vsi->q_vectors[v_idx];
- int r_idx;
-
- if (!q_vector)
- continue;
-
- /* disassociate q_vector from rings */
- for (r_idx = 0; r_idx < q_vector->tx.count; r_idx++)
- q_vector->tx.ring[r_idx]->q_vector = NULL;
- for (r_idx = 0; r_idx < q_vector->rx.count; r_idx++)
- q_vector->rx.ring[r_idx]->q_vector = NULL;
-
- /* only VSI w/ an associated netdev is set up w/ NAPI */
- if (vsi->netdev)
- netif_napi_del(&q_vector->napi);
- }
- kfree(vsi->q_vectors);
+ for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
+ i40e_free_q_vector(vsi, v_idx);
}
/**
@@ -3241,7 +3314,7 @@
return;
for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_enable(&vsi->q_vectors[q_idx].napi);
+ napi_enable(&vsi->q_vectors[q_idx]->napi);
}
/**
@@ -3256,7 +3329,7 @@
return;
for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_disable(&vsi->q_vectors[q_idx].napi);
+ napi_disable(&vsi->q_vectors[q_idx]->napi);
}
/**
@@ -3703,8 +3776,11 @@
if ((pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP) &&
(vsi->netdev)) {
+ netdev_info(vsi->netdev, "NIC Link is Up\n");
netif_tx_start_all_queues(vsi->netdev);
netif_carrier_on(vsi->netdev);
+ } else if (vsi->netdev) {
+ netdev_info(vsi->netdev, "NIC Link is Down\n");
}
i40e_service_event_schedule(pf);
@@ -3772,8 +3848,8 @@
i40e_napi_disable_all(vsi);
for (i = 0; i < vsi->num_queue_pairs; i++) {
- i40e_clean_tx_ring(&vsi->tx_rings[i]);
- i40e_clean_rx_ring(&vsi->rx_rings[i]);
+ i40e_clean_tx_ring(vsi->tx_rings[i]);
+ i40e_clean_rx_ring(vsi->rx_rings[i]);
}
}
@@ -4153,8 +4229,9 @@
if (new_link == old_link)
return;
- netdev_info(pf->vsi[pf->lan_vsi]->netdev,
- "NIC Link is %s\n", (new_link ? "Up" : "Down"));
+ if (!test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
+ netdev_info(pf->vsi[pf->lan_vsi]->netdev,
+ "NIC Link is %s\n", (new_link ? "Up" : "Down"));
/* Notify the base of the switch tree connected to
* the link. Floating VEBs are not notified.
@@ -4199,9 +4276,9 @@
continue;
for (i = 0; i < vsi->num_queue_pairs; i++) {
- set_check_for_tx_hang(&vsi->tx_rings[i]);
+ set_check_for_tx_hang(vsi->tx_rings[i]);
if (test_bit(__I40E_HANG_CHECK_ARMED,
- &vsi->tx_rings[i].state))
+ &vsi->tx_rings[i]->state))
armed++;
}
@@ -4937,6 +5014,8 @@
{
int ret = -ENODEV;
struct i40e_vsi *vsi;
+ int sz_vectors;
+ int sz_rings;
int vsi_idx;
int i;
@@ -4962,14 +5041,14 @@
vsi_idx = i; /* Found one! */
} else {
ret = -ENODEV;
- goto err_alloc_vsi; /* out of VSI slots! */
+ goto unlock_pf; /* out of VSI slots! */
}
pf->next_vsi = ++i;
vsi = kzalloc(sizeof(*vsi), GFP_KERNEL);
if (!vsi) {
ret = -ENOMEM;
- goto err_alloc_vsi;
+ goto unlock_pf;
}
vsi->type = type;
vsi->back = pf;
@@ -4982,14 +5061,40 @@
vsi->work_limit = I40E_DEFAULT_IRQ_WORK;
INIT_LIST_HEAD(&vsi->mac_filter_list);
- i40e_set_num_rings_in_vsi(vsi);
+ ret = i40e_set_num_rings_in_vsi(vsi);
+ if (ret)
+ goto err_rings;
+
+ /* allocate memory for ring pointers */
+ sz_rings = sizeof(struct i40e_ring *) * vsi->alloc_queue_pairs * 2;
+ vsi->tx_rings = kzalloc(sz_rings, GFP_KERNEL);
+ if (!vsi->tx_rings) {
+ ret = -ENOMEM;
+ goto err_rings;
+ }
+ vsi->rx_rings = &vsi->tx_rings[vsi->alloc_queue_pairs];
+
+ /* allocate memory for q_vector pointers */
+ sz_vectors = sizeof(struct i40e_q_vectors *) * vsi->num_q_vectors;
+ vsi->q_vectors = kzalloc(sz_vectors, GFP_KERNEL);
+ if (!vsi->q_vectors) {
+ ret = -ENOMEM;
+ goto err_vectors;
+ }
/* Setup default MSIX irq handler for VSI */
i40e_vsi_setup_irqhandler(vsi, i40e_msix_clean_rings);
pf->vsi[vsi_idx] = vsi;
ret = vsi_idx;
-err_alloc_vsi:
+ goto unlock_pf;
+
+err_vectors:
+ kfree(vsi->tx_rings);
+err_rings:
+ pf->next_vsi = i - 1;
+ kfree(vsi);
+unlock_pf:
mutex_unlock(&pf->switch_mutex);
return ret;
}
@@ -5030,6 +5135,10 @@
i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
+ /* free the ring and vector containers */
+ kfree(vsi->q_vectors);
+ kfree(vsi->tx_rings);
+
pf->vsi[vsi->idx] = NULL;
if (vsi->idx < pf->next_vsi)
pf->next_vsi = vsi->idx;
@@ -5043,34 +5152,39 @@
}
/**
+ * i40e_vsi_clear_rings - Deallocates the Rx and Tx rings for the provided VSI
+ * @vsi: the VSI being cleaned
+ **/
+static s32 i40e_vsi_clear_rings(struct i40e_vsi *vsi)
+{
+ int i;
+
+ for (i = 0; i < vsi->alloc_queue_pairs; i++) {
+ kfree_rcu(vsi->tx_rings[i], rcu);
+ vsi->tx_rings[i] = NULL;
+ vsi->rx_rings[i] = NULL;
+ }
+
+ return 0;
+}
+
+/**
* i40e_alloc_rings - Allocates the Rx and Tx rings for the provided VSI
* @vsi: the VSI being configured
**/
static int i40e_alloc_rings(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
- int ret = 0;
int i;
- vsi->rx_rings = kcalloc(vsi->alloc_queue_pairs,
- sizeof(struct i40e_ring), GFP_KERNEL);
- if (!vsi->rx_rings) {
- ret = -ENOMEM;
- goto err_alloc_rings;
- }
-
- vsi->tx_rings = kcalloc(vsi->alloc_queue_pairs,
- sizeof(struct i40e_ring), GFP_KERNEL);
- if (!vsi->tx_rings) {
- ret = -ENOMEM;
- kfree(vsi->rx_rings);
- goto err_alloc_rings;
- }
-
/* Set basic values in the rings to be used later during open() */
for (i = 0; i < vsi->alloc_queue_pairs; i++) {
- struct i40e_ring *rx_ring = &vsi->rx_rings[i];
- struct i40e_ring *tx_ring = &vsi->tx_rings[i];
+ struct i40e_ring *tx_ring;
+ struct i40e_ring *rx_ring;
+
+ tx_ring = kzalloc(sizeof(struct i40e_ring) * 2, GFP_KERNEL);
+ if (!tx_ring)
+ goto err_out;
tx_ring->queue_index = i;
tx_ring->reg_idx = vsi->base_queue + i;
@@ -5081,7 +5195,9 @@
tx_ring->count = vsi->num_desc;
tx_ring->size = 0;
tx_ring->dcb_tc = 0;
+ vsi->tx_rings[i] = tx_ring;
+ rx_ring = &tx_ring[1];
rx_ring->queue_index = i;
rx_ring->reg_idx = vsi->base_queue + i;
rx_ring->ring_active = false;
@@ -5095,24 +5211,14 @@
set_ring_16byte_desc_enabled(rx_ring);
else
clear_ring_16byte_desc_enabled(rx_ring);
- }
-
-err_alloc_rings:
- return ret;
-}
-
-/**
- * i40e_vsi_clear_rings - Deallocates the Rx and Tx rings for the provided VSI
- * @vsi: the VSI being cleaned
- **/
-static int i40e_vsi_clear_rings(struct i40e_vsi *vsi)
-{
- if (vsi) {
- kfree(vsi->rx_rings);
- kfree(vsi->tx_rings);
+ vsi->rx_rings[i] = rx_ring;
}
return 0;
+
+err_out:
+ i40e_vsi_clear_rings(vsi);
+ return -ENOMEM;
}
/**
@@ -5249,6 +5355,38 @@
}
/**
+ * i40e_alloc_q_vector - Allocate memory for a single interrupt vector
+ * @vsi: the VSI being configured
+ * @v_idx: index of the vector in the vsi struct
+ *
+ * We allocate one q_vector. If allocation fails we return -ENOMEM.
+ **/
+static int i40e_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
+{
+ struct i40e_q_vector *q_vector;
+
+ /* allocate q_vector */
+ q_vector = kzalloc(sizeof(struct i40e_q_vector), GFP_KERNEL);
+ if (!q_vector)
+ return -ENOMEM;
+
+ q_vector->vsi = vsi;
+ q_vector->v_idx = v_idx;
+ cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
+ if (vsi->netdev)
+ netif_napi_add(vsi->netdev, &q_vector->napi,
+ i40e_napi_poll, vsi->work_limit);
+
+ q_vector->rx.latency_range = I40E_LOW_LATENCY;
+ q_vector->tx.latency_range = I40E_LOW_LATENCY;
+
+ /* tie q_vector and vsi together */
+ vsi->q_vectors[v_idx] = q_vector;
+
+ return 0;
+}
+
+/**
* i40e_alloc_q_vectors - Allocate memory for interrupt vectors
* @vsi: the VSI being configured
*
@@ -5259,6 +5397,7 @@
{
struct i40e_pf *pf = vsi->back;
int v_idx, num_q_vectors;
+ int err;
/* if not MSIX, give the one vector only to the LAN VSI */
if (pf->flags & I40E_FLAG_MSIX_ENABLED)
@@ -5268,22 +5407,19 @@
else
return -EINVAL;
- vsi->q_vectors = kcalloc(num_q_vectors,
- sizeof(struct i40e_q_vector),
- GFP_KERNEL);
- if (!vsi->q_vectors)
- return -ENOMEM;
-
for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
- vsi->q_vectors[v_idx].vsi = vsi;
- vsi->q_vectors[v_idx].v_idx = v_idx;
- cpumask_set_cpu(v_idx, &vsi->q_vectors[v_idx].affinity_mask);
- if (vsi->netdev)
- netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx].napi,
- i40e_napi_poll, vsi->work_limit);
+ err = i40e_alloc_q_vector(vsi, v_idx);
+ if (err)
+ goto err_out;
}
return 0;
+
+err_out:
+ while (v_idx--)
+ i40e_free_q_vector(vsi, v_idx);
+
+ return err;
}
/**
@@ -5950,7 +6086,7 @@
int ret = -ENOENT;
struct i40e_pf *pf = vsi->back;
- if (vsi->q_vectors) {
+ if (vsi->q_vectors[0]) {
dev_info(&pf->pdev->dev, "VSI %d has existing q_vectors\n",
vsi->seid);
return -EEXIST;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 49d2cfa..dc89e72 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -64,7 +64,7 @@
if (!vsi)
return -ENOENT;
- tx_ring = &vsi->tx_rings[0];
+ tx_ring = vsi->tx_rings[0];
dev = tx_ring->dev;
dma = dma_map_single(dev, fdir_data->raw_packet,
@@ -73,11 +73,12 @@
goto dma_fail;
/* grab the next descriptor */
- fdir_desc = I40E_TX_FDIRDESC(tx_ring, tx_ring->next_to_use);
- tx_buf = &tx_ring->tx_bi[tx_ring->next_to_use];
- tx_ring->next_to_use++;
- if (tx_ring->next_to_use == tx_ring->count)
- tx_ring->next_to_use = 0;
+ i = tx_ring->next_to_use;
+ fdir_desc = I40E_TX_FDIRDESC(tx_ring, i);
+ tx_buf = &tx_ring->tx_bi[i];
+
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32((fdir_data->q_index
<< I40E_TXD_FLTR_QW0_QINDEX_SHIFT)
@@ -134,11 +135,11 @@
fdir_desc->fd_id = cpu_to_le32(fdir_data->fd_id);
/* Now program a dummy descriptor */
- tx_desc = I40E_TX_DESC(tx_ring, tx_ring->next_to_use);
- tx_buf = &tx_ring->tx_bi[tx_ring->next_to_use];
- tx_ring->next_to_use++;
- if (tx_ring->next_to_use == tx_ring->count)
- tx_ring->next_to_use = 0;
+ i = tx_ring->next_to_use;
+ tx_desc = I40E_TX_DESC(tx_ring, i);
+
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
tx_desc->buffer_addr = cpu_to_le64(dma);
td_cmd = I40E_TX_DESC_CMD_EOP |
@@ -148,9 +149,6 @@
tx_desc->cmd_type_offset_bsz =
build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_LOOKUP, 0);
- /* Mark the data descriptor to be watched */
- tx_buf->next_to_watch = tx_desc;
-
/* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch. (Only
* applicable for weak-ordered memory model archs,
@@ -158,6 +156,9 @@
*/
wmb();
+ /* Mark the data descriptor to be watched */
+ tx_buf->next_to_watch = tx_desc;
+
writel(tx_ring->next_to_use, tx_ring->tail);
return 0;
@@ -188,27 +189,30 @@
}
/**
- * i40e_unmap_tx_resource - Release a Tx buffer
+ * i40e_unmap_and_free_tx_resource - Release a Tx buffer
* @ring: the ring that owns the buffer
* @tx_buffer: the buffer to free
**/
-static inline void i40e_unmap_tx_resource(struct i40e_ring *ring,
- struct i40e_tx_buffer *tx_buffer)
+static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring,
+ struct i40e_tx_buffer *tx_buffer)
{
- if (tx_buffer->dma) {
- if (tx_buffer->tx_flags & I40E_TX_FLAGS_MAPPED_AS_PAGE)
- dma_unmap_page(ring->dev,
- tx_buffer->dma,
- tx_buffer->length,
- DMA_TO_DEVICE);
- else
+ if (tx_buffer->skb) {
+ dev_kfree_skb_any(tx_buffer->skb);
+ if (dma_unmap_len(tx_buffer, len))
dma_unmap_single(ring->dev,
- tx_buffer->dma,
- tx_buffer->length,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
DMA_TO_DEVICE);
+ } else if (dma_unmap_len(tx_buffer, len)) {
+ dma_unmap_page(ring->dev,
+ dma_unmap_addr(tx_buffer, dma),
+ dma_unmap_len(tx_buffer, len),
+ DMA_TO_DEVICE);
}
- tx_buffer->dma = 0;
- tx_buffer->time_stamp = 0;
+ tx_buffer->next_to_watch = NULL;
+ tx_buffer->skb = NULL;
+ dma_unmap_len_set(tx_buffer, len, 0);
+ /* tx_buffer must be completely set up in the transmit path */
}
/**
@@ -217,7 +221,6 @@
**/
void i40e_clean_tx_ring(struct i40e_ring *tx_ring)
{
- struct i40e_tx_buffer *tx_buffer;
unsigned long bi_size;
u16 i;
@@ -226,13 +229,8 @@
return;
/* Free all the Tx ring sk_buffs */
- for (i = 0; i < tx_ring->count; i++) {
- tx_buffer = &tx_ring->tx_bi[i];
- i40e_unmap_tx_resource(tx_ring, tx_buffer);
- if (tx_buffer->skb)
- dev_kfree_skb_any(tx_buffer->skb);
- tx_buffer->skb = NULL;
- }
+ for (i = 0; i < tx_ring->count; i++)
+ i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]);
bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count;
memset(tx_ring->tx_bi, 0, bi_size);
@@ -242,6 +240,13 @@
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
+
+ if (!tx_ring->netdev)
+ return;
+
+ /* cleanup Tx queue statistics */
+ netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev,
+ tx_ring->queue_index));
}
/**
@@ -300,14 +305,14 @@
* run the check_tx_hang logic with a transmit completion
* pending but without time to complete it yet.
*/
- if ((tx_ring->tx_stats.tx_done_old == tx_ring->tx_stats.packets) &&
+ if ((tx_ring->tx_stats.tx_done_old == tx_ring->stats.packets) &&
tx_pending) {
/* make sure it is true for two checks in a row */
ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED,
&tx_ring->state);
} else {
/* update completed stats and disarm the hang check */
- tx_ring->tx_stats.tx_done_old = tx_ring->tx_stats.packets;
+ tx_ring->tx_stats.tx_done_old = tx_ring->stats.packets;
clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state);
}
@@ -331,62 +336,88 @@
tx_buf = &tx_ring->tx_bi[i];
tx_desc = I40E_TX_DESC(tx_ring, i);
+ i -= tx_ring->count;
- for (; budget; budget--) {
- struct i40e_tx_desc *eop_desc;
-
- eop_desc = tx_buf->next_to_watch;
+ do {
+ struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
/* if next_to_watch is not set then there is no work pending */
if (!eop_desc)
break;
+ /* prevent any other reads prior to eop_desc */
+ read_barrier_depends();
+
/* if the descriptor isn't done, no work yet to do */
if (!(eop_desc->cmd_type_offset_bsz &
cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
break;
- /* count the packet as being completed */
- tx_ring->tx_stats.completed++;
+ /* clear next_to_watch to prevent false hangs */
tx_buf->next_to_watch = NULL;
- tx_buf->time_stamp = 0;
- /* set memory barrier before eop_desc is verified */
- rmb();
+ /* update the statistics for this packet */
+ total_bytes += tx_buf->bytecount;
+ total_packets += tx_buf->gso_segs;
- do {
- i40e_unmap_tx_resource(tx_ring, tx_buf);
+ /* free the skb */
+ dev_kfree_skb_any(tx_buf->skb);
- /* clear dtype status */
- tx_desc->cmd_type_offset_bsz &=
- ~cpu_to_le64(I40E_TXD_QW1_DTYPE_MASK);
+ /* unmap skb header data */
+ dma_unmap_single(tx_ring->dev,
+ dma_unmap_addr(tx_buf, dma),
+ dma_unmap_len(tx_buf, len),
+ DMA_TO_DEVICE);
- if (likely(tx_desc == eop_desc)) {
- eop_desc = NULL;
+ /* clear tx_buffer data */
+ tx_buf->skb = NULL;
+ dma_unmap_len_set(tx_buf, len, 0);
- dev_kfree_skb_any(tx_buf->skb);
- tx_buf->skb = NULL;
-
- total_bytes += tx_buf->bytecount;
- total_packets += tx_buf->gso_segs;
- }
+ /* unmap remaining buffers */
+ while (tx_desc != eop_desc) {
tx_buf++;
tx_desc++;
i++;
- if (unlikely(i == tx_ring->count)) {
- i = 0;
+ if (unlikely(!i)) {
+ i -= tx_ring->count;
tx_buf = tx_ring->tx_bi;
tx_desc = I40E_TX_DESC(tx_ring, 0);
}
- } while (eop_desc);
- }
+ /* unmap any remaining paged data */
+ if (dma_unmap_len(tx_buf, len)) {
+ dma_unmap_page(tx_ring->dev,
+ dma_unmap_addr(tx_buf, dma),
+ dma_unmap_len(tx_buf, len),
+ DMA_TO_DEVICE);
+ dma_unmap_len_set(tx_buf, len, 0);
+ }
+ }
+
+ /* move us one more past the eop_desc for start of next pkt */
+ tx_buf++;
+ tx_desc++;
+ i++;
+ if (unlikely(!i)) {
+ i -= tx_ring->count;
+ tx_buf = tx_ring->tx_bi;
+ tx_desc = I40E_TX_DESC(tx_ring, 0);
+ }
+
+ /* update budget accounting */
+ budget--;
+ } while (likely(budget));
+
+ i += tx_ring->count;
tx_ring->next_to_clean = i;
- tx_ring->tx_stats.bytes += total_bytes;
- tx_ring->tx_stats.packets += total_packets;
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->stats.bytes += total_bytes;
+ tx_ring->stats.packets += total_packets;
+ u64_stats_update_end(&tx_ring->syncp);
tx_ring->q_vector->tx.total_bytes += total_bytes;
tx_ring->q_vector->tx.total_packets += total_packets;
+
if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) {
/* schedule immediate reset if we believe we hung */
dev_info(tx_ring->dev, "Detected Tx Unit Hang\n"
@@ -414,6 +445,10 @@
return true;
}
+ netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
+ tx_ring->queue_index),
+ total_packets, total_bytes);
+
#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) &&
(I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) {
@@ -1042,8 +1077,10 @@
}
rx_ring->next_to_clean = i;
- rx_ring->rx_stats.packets += total_rx_packets;
- rx_ring->rx_stats.bytes += total_rx_bytes;
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->stats.packets += total_rx_packets;
+ rx_ring->stats.bytes += total_rx_bytes;
+ u64_stats_update_end(&rx_ring->syncp);
rx_ring->q_vector->rx.total_packets += total_rx_packets;
rx_ring->q_vector->rx.total_bytes += total_rx_bytes;
@@ -1067,27 +1104,28 @@
struct i40e_q_vector *q_vector =
container_of(napi, struct i40e_q_vector, napi);
struct i40e_vsi *vsi = q_vector->vsi;
+ struct i40e_ring *ring;
bool clean_complete = true;
int budget_per_ring;
- int i;
if (test_bit(__I40E_DOWN, &vsi->state)) {
napi_complete(napi);
return 0;
}
- /* We attempt to distribute budget to each Rx queue fairly, but don't
- * allow the budget to go below 1 because that would exit polling early.
- * Since the actual Tx work is minimal, we can give the Tx a larger
+ /* Since the actual Tx work is minimal, we can give the Tx a larger
* budget and be more aggressive about cleaning up the Tx descriptors.
*/
+ i40e_for_each_ring(ring, q_vector->tx)
+ clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit);
+
+ /* We attempt to distribute budget to each Rx queue fairly, but don't
+ * allow the budget to go below 1 because that would exit polling early.
+ */
budget_per_ring = max(budget/q_vector->num_ringpairs, 1);
- for (i = 0; i < q_vector->num_ringpairs; i++) {
- clean_complete &= i40e_clean_tx_irq(q_vector->tx.ring[i],
- vsi->work_limit);
- clean_complete &= i40e_clean_rx_irq(q_vector->rx.ring[i],
- budget_per_ring);
- }
+
+ i40e_for_each_ring(ring, q_vector->rx)
+ clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring);
/* If work not completed, return budget and polling will return */
if (!clean_complete)
@@ -1144,6 +1182,7 @@
struct tcphdr *th;
unsigned int hlen;
u32 flex_ptype, dtype_cmd;
+ u16 i;
/* make sure ATR is enabled */
if (!(pf->flags & I40E_FLAG_FDIR_ATR_ENABLED))
@@ -1183,10 +1222,11 @@
tx_ring->atr_count = 0;
/* grab the next descriptor */
- fdir_desc = I40E_TX_FDIRDESC(tx_ring, tx_ring->next_to_use);
- tx_ring->next_to_use++;
- if (tx_ring->next_to_use == tx_ring->count)
- tx_ring->next_to_use = 0;
+ i = tx_ring->next_to_use;
+ fdir_desc = I40E_TX_FDIRDESC(tx_ring, i);
+
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
flex_ptype = (tx_ring->queue_index << I40E_TXD_FLTR_QW0_QINDEX_SHIFT) &
I40E_TXD_FLTR_QW0_QINDEX_MASK;
@@ -1276,27 +1316,6 @@
}
/**
- * i40e_tx_csum - is checksum offload requested
- * @tx_ring: ptr to the ring to send
- * @skb: ptr to the skb we're sending
- * @tx_flags: the collected send information
- * @protocol: the send protocol
- *
- * Returns true if checksum offload is requested
- **/
-static bool i40e_tx_csum(struct i40e_ring *tx_ring, struct sk_buff *skb,
- u32 tx_flags, __be16 protocol)
-{
- if ((skb->ip_summed != CHECKSUM_PARTIAL) &&
- !(tx_flags & I40E_TX_FLAGS_TXSW)) {
- if (!(tx_flags & I40E_TX_FLAGS_HW_VLAN))
- return false;
- }
-
- return skb->ip_summed == CHECKSUM_PARTIAL;
-}
-
-/**
* i40e_tso - set up the tso context descriptor
* @tx_ring: ptr to the ring to send
* @skb: ptr to the skb we're sending
@@ -1482,15 +1501,16 @@
const u32 cd_tunneling, const u32 cd_l2tag2)
{
struct i40e_tx_context_desc *context_desc;
+ int i = tx_ring->next_to_use;
if (!cd_type_cmd_tso_mss && !cd_tunneling && !cd_l2tag2)
return;
/* grab the next descriptor */
- context_desc = I40E_TX_CTXTDESC(tx_ring, tx_ring->next_to_use);
- tx_ring->next_to_use++;
- if (tx_ring->next_to_use == tx_ring->count)
- tx_ring->next_to_use = 0;
+ context_desc = I40E_TX_CTXTDESC(tx_ring, i);
+
+ i++;
+ tx_ring->next_to_use = (i < tx_ring->count) ? i : 0;
/* cpu_to_le32 and assign to struct fields */
context_desc->tunneling_params = cpu_to_le32(cd_tunneling);
@@ -1512,68 +1532,71 @@
struct i40e_tx_buffer *first, u32 tx_flags,
const u8 hdr_len, u32 td_cmd, u32 td_offset)
{
- struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
unsigned int data_len = skb->data_len;
unsigned int size = skb_headlen(skb);
- struct device *dev = tx_ring->dev;
- u32 paylen = skb->len - hdr_len;
- u16 i = tx_ring->next_to_use;
+ struct skb_frag_struct *frag;
struct i40e_tx_buffer *tx_bi;
struct i40e_tx_desc *tx_desc;
- u32 buf_offset = 0;
+ u16 i = tx_ring->next_to_use;
u32 td_tag = 0;
dma_addr_t dma;
u16 gso_segs;
- dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE);
- if (dma_mapping_error(dev, dma))
- goto dma_error;
-
if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >>
I40E_TX_FLAGS_VLAN_SHIFT;
}
+ if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO))
+ gso_segs = skb_shinfo(skb)->gso_segs;
+ else
+ gso_segs = 1;
+
+ /* multiply data chunks by size of headers */
+ first->bytecount = skb->len - hdr_len + (gso_segs * hdr_len);
+ first->gso_segs = gso_segs;
+ first->skb = skb;
+ first->tx_flags = tx_flags;
+
+ dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE);
+
tx_desc = I40E_TX_DESC(tx_ring, i);
- for (;;) {
- while (size > I40E_MAX_DATA_PER_TXD) {
- tx_desc->buffer_addr = cpu_to_le64(dma + buf_offset);
+ tx_bi = first;
+
+ for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+ if (dma_mapping_error(tx_ring->dev, dma))
+ goto dma_error;
+
+ /* record length, and DMA address */
+ dma_unmap_len_set(tx_bi, len, size);
+ dma_unmap_addr_set(tx_bi, dma, dma);
+
+ tx_desc->buffer_addr = cpu_to_le64(dma);
+
+ while (unlikely(size > I40E_MAX_DATA_PER_TXD)) {
tx_desc->cmd_type_offset_bsz =
build_ctob(td_cmd, td_offset,
I40E_MAX_DATA_PER_TXD, td_tag);
- buf_offset += I40E_MAX_DATA_PER_TXD;
- size -= I40E_MAX_DATA_PER_TXD;
-
tx_desc++;
i++;
if (i == tx_ring->count) {
tx_desc = I40E_TX_DESC(tx_ring, 0);
i = 0;
}
+
+ dma += I40E_MAX_DATA_PER_TXD;
+ size -= I40E_MAX_DATA_PER_TXD;
+
+ tx_desc->buffer_addr = cpu_to_le64(dma);
}
- tx_bi = &tx_ring->tx_bi[i];
- tx_bi->length = buf_offset + size;
- tx_bi->tx_flags = tx_flags;
- tx_bi->dma = dma;
-
- tx_desc->buffer_addr = cpu_to_le64(dma + buf_offset);
- tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset,
- size, td_tag);
-
if (likely(!data_len))
break;
- size = skb_frag_size(frag);
- data_len -= size;
- buf_offset = 0;
- tx_flags |= I40E_TX_FLAGS_MAPPED_AS_PAGE;
-
- dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
- if (dma_mapping_error(dev, dma))
- goto dma_error;
+ tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset,
+ size, td_tag);
tx_desc++;
i++;
@@ -1582,31 +1605,25 @@
i = 0;
}
- frag++;
+ size = skb_frag_size(frag);
+ data_len -= size;
+
+ dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size,
+ DMA_TO_DEVICE);
+
+ tx_bi = &tx_ring->tx_bi[i];
}
- tx_desc->cmd_type_offset_bsz |=
- cpu_to_le64((u64)I40E_TXD_CMD << I40E_TXD_QW1_CMD_SHIFT);
+ tx_desc->cmd_type_offset_bsz =
+ build_ctob(td_cmd, td_offset, size, td_tag) |
+ cpu_to_le64((u64)I40E_TXD_CMD << I40E_TXD_QW1_CMD_SHIFT);
- i++;
- if (i == tx_ring->count)
- i = 0;
+ netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev,
+ tx_ring->queue_index),
+ first->bytecount);
- tx_ring->next_to_use = i;
-
- if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO))
- gso_segs = skb_shinfo(skb)->gso_segs;
- else
- gso_segs = 1;
-
- /* multiply data chunks by size of headers */
- tx_bi->bytecount = paylen + (gso_segs * hdr_len);
- tx_bi->gso_segs = gso_segs;
- tx_bi->skb = skb;
-
- /* set the timestamp and next to watch values */
+ /* set the timestamp */
first->time_stamp = jiffies;
- first->next_to_watch = tx_desc;
/* Force memory writes to complete before letting h/w
* know there are new descriptors to fetch. (Only
@@ -1615,16 +1632,27 @@
*/
wmb();
+ /* set next_to_watch value indicating a packet is present */
+ first->next_to_watch = tx_desc;
+
+ i++;
+ if (i == tx_ring->count)
+ i = 0;
+
+ tx_ring->next_to_use = i;
+
+ /* notify HW of packet */
writel(i, tx_ring->tail);
+
return;
dma_error:
- dev_info(dev, "TX DMA map failed\n");
+ dev_info(tx_ring->dev, "TX DMA map failed\n");
/* clear dma mappings for failed tx_bi map */
for (;;) {
tx_bi = &tx_ring->tx_bi[i];
- i40e_unmap_tx_resource(tx_ring, tx_bi);
+ i40e_unmap_and_free_tx_resource(tx_ring, tx_bi);
if (tx_bi == first)
break;
if (i == 0)
@@ -1632,8 +1660,6 @@
i--;
}
- dev_kfree_skb_any(skb);
-
tx_ring->next_to_use = i;
}
@@ -1758,16 +1784,16 @@
skb_tx_timestamp(skb);
- /* Always offload the checksum, since it's in the data descriptor */
- if (i40e_tx_csum(tx_ring, skb, tx_flags, protocol))
- tx_flags |= I40E_TX_FLAGS_CSUM;
-
- /* always enable offload insertion */
+ /* always enable CRC insertion offload */
td_cmd |= I40E_TX_DESC_CMD_ICRC;
- if (tx_flags & I40E_TX_FLAGS_CSUM)
+ /* Always offload the checksum, since it's in the data descriptor */
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ tx_flags |= I40E_TX_FLAGS_CSUM;
+
i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset,
tx_ring, &cd_tunneling);
+ }
i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
cd_tunneling, cd_l2tag2);
@@ -1801,7 +1827,7 @@
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
- struct i40e_ring *tx_ring = &vsi->tx_rings[skb->queue_mapping];
+ struct i40e_ring *tx_ring = vsi->tx_rings[skb->queue_mapping];
/* hardware can't handle really short frames, hardware padding works
* beyond this point
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index b1d7722..db55d99 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -102,23 +102,20 @@
#define I40E_TX_FLAGS_IPV6 (u32)(1 << 5)
#define I40E_TX_FLAGS_FCCRC (u32)(1 << 6)
#define I40E_TX_FLAGS_FSO (u32)(1 << 7)
-#define I40E_TX_FLAGS_TXSW (u32)(1 << 8)
-#define I40E_TX_FLAGS_MAPPED_AS_PAGE (u32)(1 << 9)
#define I40E_TX_FLAGS_VLAN_MASK 0xffff0000
#define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000
#define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29
#define I40E_TX_FLAGS_VLAN_SHIFT 16
struct i40e_tx_buffer {
- struct sk_buff *skb;
- dma_addr_t dma;
- unsigned long time_stamp;
- u16 length;
- u32 tx_flags;
struct i40e_tx_desc *next_to_watch;
+ unsigned long time_stamp;
+ struct sk_buff *skb;
unsigned int bytecount;
- u16 gso_segs;
- u8 mapped_as_page;
+ unsigned short gso_segs;
+ DEFINE_DMA_UNMAP_ADDR(dma);
+ DEFINE_DMA_UNMAP_LEN(len);
+ u32 tx_flags;
};
struct i40e_rx_buffer {
@@ -129,18 +126,18 @@
unsigned int page_offset;
};
-struct i40e_tx_queue_stats {
+struct i40e_queue_stats {
u64 packets;
u64 bytes;
+};
+
+struct i40e_tx_queue_stats {
u64 restart_queue;
u64 tx_busy;
- u64 completed;
u64 tx_done_old;
};
struct i40e_rx_queue_stats {
- u64 packets;
- u64 bytes;
u64 non_eop_descs;
u64 alloc_rx_page_failed;
u64 alloc_rx_buff_failed;
@@ -183,6 +180,7 @@
/* 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 */
@@ -219,6 +217,8 @@
bool ring_active; /* is ring online or not */
/* stats structs */
+ struct i40e_queue_stats stats;
+ struct u64_stats_sync syncp;
union {
struct i40e_tx_queue_stats tx_stats;
struct i40e_rx_queue_stats rx_stats;
@@ -229,6 +229,8 @@
struct i40e_vsi *vsi; /* Backreference to associated VSI */
struct i40e_q_vector *q_vector; /* Backreference to associated vector */
+
+ struct rcu_head rcu; /* to avoid race on free */
} ____cacheline_internodealigned_in_smp;
enum i40e_latency_range {
@@ -238,9 +240,8 @@
};
struct i40e_ring_container {
-#define I40E_MAX_RINGPAIR_PER_VECTOR 8
/* array of pointers to rings */
- struct i40e_ring *ring[I40E_MAX_RINGPAIR_PER_VECTOR];
+ struct i40e_ring *ring;
unsigned int total_bytes; /* total bytes processed this int */
unsigned int total_packets; /* total packets processed this int */
u16 count;
@@ -248,6 +249,10 @@
u16 itr;
};
+/* iterator for handling rings in ring container */
+#define i40e_for_each_ring(pos, head) \
+ for (pos = (head).ring; pos != NULL; pos = pos->next)
+
void 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);
void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index eee1f19..b2d0347 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -188,6 +188,11 @@
return tot;
}
+/* fake multicast ability */
+static void veth_set_multicast_list(struct net_device *dev)
+{
+}
+
static int veth_open(struct net_device *dev)
{
struct veth_priv *priv = netdev_priv(dev);
@@ -250,6 +255,7 @@
.ndo_start_xmit = veth_xmit,
.ndo_change_mtu = veth_change_mtu,
.ndo_get_stats64 = veth_get_stats64,
+ .ndo_set_rx_mode = veth_set_multicast_list,
.ndo_set_mac_address = eth_mac_addr,
};
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 35f6c1b..a80a63c 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -115,16 +115,8 @@
return IP6CB(skb)->iif;
}
-struct inet6_request_sock {
- struct in6_addr loc_addr;
- struct in6_addr rmt_addr;
- struct sk_buff *pktopts;
- int iif;
-};
-
struct tcp6_request_sock {
struct tcp_request_sock tcp6rsk_tcp;
- struct inet6_request_sock tcp6rsk_inet6;
};
struct ipv6_mc_socklist;
@@ -264,26 +256,12 @@
return inet_sk(__sk)->pinet6;
}
-static inline struct inet6_request_sock *
- inet6_rsk(const struct request_sock *rsk)
-{
- return (struct inet6_request_sock *)(((u8 *)rsk) +
- inet_rsk(rsk)->inet6_rsk_offset);
-}
-
-static inline u32 inet6_rsk_offset(struct request_sock *rsk)
-{
- return rsk->rsk_ops->obj_size - sizeof(struct inet6_request_sock);
-}
-
static inline struct request_sock *inet6_reqsk_alloc(struct request_sock_ops *ops)
{
struct request_sock *req = reqsk_alloc(ops);
- if (req != NULL) {
- inet_rsk(req)->inet6_rsk_offset = inet6_rsk_offset(req);
- inet6_rsk(req)->pktopts = NULL;
- }
+ if (req)
+ inet_rsk(req)->pktopts = NULL;
return req;
}
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 6d9a7e6..06da91e 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -70,13 +70,14 @@
struct inet_request_sock {
struct request_sock req;
-#if IS_ENABLED(CONFIG_IPV6)
- u16 inet6_rsk_offset;
-#endif
- __be16 loc_port;
- __be32 loc_addr;
- __be32 rmt_addr;
- __be16 rmt_port;
+#define ir_loc_addr req.__req_common.skc_rcv_saddr
+#define ir_rmt_addr req.__req_common.skc_daddr
+#define ir_num req.__req_common.skc_num
+#define ir_rmt_port req.__req_common.skc_dport
+#define ir_v6_rmt_addr req.__req_common.skc_v6_daddr
+#define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr
+#define ir_iif req.__req_common.skc_bound_dev_if
+
kmemcheck_bitfield_begin(flags);
u16 snd_wscale : 4,
rcv_wscale : 4,
@@ -88,6 +89,7 @@
no_srccheck: 1;
kmemcheck_bitfield_end(flags);
struct ip_options_rcu *opt;
+ struct sk_buff *pktopts;
};
static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 65c3e516..7f830ff 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -48,6 +48,7 @@
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
+ struct sock_common __req_common;
struct request_sock *dl_next;
u16 mss;
u8 num_retrans; /* number of retransmits */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 39bbfa1..1db3a01 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1109,8 +1109,8 @@
ireq->wscale_ok = rx_opt->wscale_ok;
ireq->acked = 0;
ireq->ecn_ok = 0;
- ireq->rmt_port = tcp_hdr(skb)->source;
- ireq->loc_port = tcp_hdr(skb)->dest;
+ ireq->ir_rmt_port = tcp_hdr(skb)->source;
+ ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
}
void tcp_enter_memory_pressure(struct sock *sk);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d81cff1..8ead744 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2936,32 +2936,30 @@
int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
- struct sk_buff *p = *head;
- struct sk_buff *nskb;
- struct skb_shared_info *skbinfo = skb_shinfo(skb);
- struct skb_shared_info *pinfo = skb_shinfo(p);
- unsigned int headroom;
- unsigned int len = skb_gro_len(skb);
+ struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
unsigned int offset = skb_gro_offset(skb);
unsigned int headlen = skb_headlen(skb);
+ struct sk_buff *nskb, *lp, *p = *head;
+ unsigned int len = skb_gro_len(skb);
unsigned int delta_truesize;
+ unsigned int headroom;
- if (p->len + len >= 65536)
+ if (unlikely(p->len + len >= 65536))
return -E2BIG;
- if (pinfo->frag_list)
- goto merge;
- else if (headlen <= offset) {
+ lp = NAPI_GRO_CB(p)->last ?: p;
+ pinfo = skb_shinfo(lp);
+
+ if (headlen <= offset) {
skb_frag_t *frag;
skb_frag_t *frag2;
int i = skbinfo->nr_frags;
int nr_frags = pinfo->nr_frags + i;
- offset -= headlen;
-
if (nr_frags > MAX_SKB_FRAGS)
- return -E2BIG;
+ goto merge;
+ offset -= headlen;
pinfo->nr_frags = nr_frags;
skbinfo->nr_frags = 0;
@@ -2992,7 +2990,7 @@
unsigned int first_offset;
if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS)
- return -E2BIG;
+ goto merge;
first_offset = skb->data -
(unsigned char *)page_address(page) +
@@ -3010,7 +3008,10 @@
delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
goto done;
- } else if (skb_gro_len(p) != pinfo->gso_size)
+ }
+ if (pinfo->frag_list)
+ goto merge;
+ if (skb_gro_len(p) != pinfo->gso_size)
return -E2BIG;
headroom = skb_headroom(p);
@@ -3062,16 +3063,24 @@
__skb_pull(skb, offset);
- NAPI_GRO_CB(p)->last->next = skb;
+ if (!NAPI_GRO_CB(p)->last)
+ skb_shinfo(p)->frag_list = skb;
+ else
+ NAPI_GRO_CB(p)->last->next = skb;
NAPI_GRO_CB(p)->last = skb;
skb_header_release(skb);
+ lp = p;
done:
NAPI_GRO_CB(p)->count++;
p->data_len += len;
p->truesize += delta_truesize;
p->len += len;
-
+ if (lp != p) {
+ lp->data_len += len;
+ lp->truesize += delta_truesize;
+ lp->len += len;
+ }
NAPI_GRO_CB(skb)->same_flow = 1;
return 0;
}
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ebc54fe..720c362 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -409,9 +409,9 @@
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
- newinet->inet_daddr = ireq->rmt_addr;
- newinet->inet_rcv_saddr = ireq->loc_addr;
- newinet->inet_saddr = ireq->loc_addr;
+ newinet->inet_daddr = ireq->ir_rmt_addr;
+ newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+ newinet->inet_saddr = ireq->ir_loc_addr;
newinet->inet_opt = ireq->opt;
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
@@ -516,10 +516,10 @@
const struct inet_request_sock *ireq = inet_rsk(req);
struct dccp_hdr *dh = dccp_hdr(skb);
- dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->loc_addr,
- ireq->rmt_addr);
- err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
- ireq->rmt_addr,
+ dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
+ ireq->ir_rmt_addr);
+ err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
+ ireq->ir_rmt_addr,
ireq->opt);
err = net_xmit_eval(err);
}
@@ -641,8 +641,8 @@
goto drop_and_free;
ireq = inet_rsk(req);
- ireq->loc_addr = ip_hdr(skb)->daddr;
- ireq->rmt_addr = ip_hdr(skb)->saddr;
+ ireq->ir_loc_addr = ip_hdr(skb)->daddr;
+ ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
/*
* Step 3: Process LISTEN state
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 7f075b8..4ac71ff 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -216,7 +216,7 @@
static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
{
- struct inet6_request_sock *ireq6 = inet6_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct in6_addr *final_p, final;
@@ -226,12 +226,12 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
- fl6.daddr = ireq6->rmt_addr;
- fl6.saddr = ireq6->loc_addr;
+ fl6.daddr = ireq->ir_v6_rmt_addr;
+ fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowlabel = 0;
- fl6.flowi6_oif = ireq6->iif;
- fl6.fl6_dport = inet_rsk(req)->rmt_port;
- fl6.fl6_sport = inet_rsk(req)->loc_port;
+ fl6.flowi6_oif = ireq->ir_iif;
+ fl6.fl6_dport = ireq->ir_rmt_port;
+ fl6.fl6_sport = htons(ireq->ir_num);
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
@@ -249,9 +249,9 @@
struct dccp_hdr *dh = dccp_hdr(skb);
dh->dccph_checksum = dccp_v6_csum_finish(skb,
- &ireq6->loc_addr,
- &ireq6->rmt_addr);
- fl6.daddr = ireq6->rmt_addr;
+ &ireq->ir_v6_loc_addr,
+ &ireq->ir_v6_rmt_addr);
+ fl6.daddr = ireq->ir_v6_rmt_addr;
err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
err = net_xmit_eval(err);
}
@@ -264,8 +264,7 @@
static void dccp_v6_reqsk_destructor(struct request_sock *req)
{
dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
- if (inet6_rsk(req)->pktopts != NULL)
- kfree_skb(inet6_rsk(req)->pktopts);
+ kfree_skb(inet_rsk(req)->pktopts);
}
static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
@@ -359,7 +358,7 @@
{
struct request_sock *req;
struct dccp_request_sock *dreq;
- struct inet6_request_sock *ireq6;
+ struct inet_request_sock *ireq;
struct ipv6_pinfo *np = inet6_sk(sk);
const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
@@ -398,22 +397,22 @@
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
- ireq6 = inet6_rsk(req);
- ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
- ireq6->loc_addr = ipv6_hdr(skb)->daddr;
+ ireq = inet_rsk(req);
+ ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
- ireq6->pktopts = skb;
+ ireq->pktopts = skb;
}
- ireq6->iif = sk->sk_bound_dev_if;
+ ireq->ir_iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
- ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
- ireq6->iif = inet6_iif(skb);
+ ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ ireq->ir_iif = inet6_iif(skb);
/*
* Step 3: Process LISTEN state
@@ -446,7 +445,7 @@
struct request_sock *req,
struct dst_entry *dst)
{
- struct inet6_request_sock *ireq6 = inet6_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
@@ -505,12 +504,12 @@
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
- fl6.daddr = ireq6->rmt_addr;
+ fl6.daddr = ireq->ir_v6_rmt_addr;
final_p = fl6_update_dst(&fl6, np->opt, &final);
- fl6.saddr = ireq6->loc_addr;
+ fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
- fl6.fl6_dport = inet_rsk(req)->rmt_port;
- fl6.fl6_sport = inet_rsk(req)->loc_port;
+ fl6.fl6_dport = ireq->ir_rmt_port;
+ fl6.fl6_sport = htons(ireq->ir_num);
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
@@ -538,10 +537,10 @@
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
- newsk->sk_v6_daddr = ireq6->rmt_addr;
- newnp->saddr = ireq6->loc_addr;
- newsk->sk_v6_rcv_saddr = ireq6->loc_addr;
- newsk->sk_bound_dev_if = ireq6->iif;
+ newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
+ newnp->saddr = ireq->ir_v6_loc_addr;
+ newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
+ newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
@@ -554,10 +553,10 @@
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
- if (ireq6->pktopts != NULL) {
- newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
- consume_skb(ireq6->pktopts);
- ireq6->pktopts = NULL;
+ if (ireq->pktopts != NULL) {
+ newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
+ consume_skb(ireq->pktopts);
+ ireq->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h
index 6604fc3..af259e1 100644
--- a/net/dccp/ipv6.h
+++ b/net/dccp/ipv6.h
@@ -25,7 +25,6 @@
struct dccp6_request_sock {
struct dccp_request_sock dccp;
- struct inet6_request_sock inet6;
};
struct dccp6_timewait_sock {
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 32e80d9..9e2f78b 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -266,10 +266,10 @@
{
struct dccp_request_sock *dreq = dccp_rsk(req);
- inet_rsk(req)->rmt_port = dccp_hdr(skb)->dccph_sport;
- inet_rsk(req)->loc_port = dccp_hdr(skb)->dccph_dport;
- inet_rsk(req)->acked = 0;
- dreq->dreq_timestamp_echo = 0;
+ inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport;
+ inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport);
+ inet_rsk(req)->acked = 0;
+ dreq->dreq_timestamp_echo = 0;
/* inherit feature negotiation options from listening socket */
return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
diff --git a/net/dccp/output.c b/net/dccp/output.c
index d17fc90..8876078 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -424,8 +424,8 @@
/* Build and checksum header */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
- dh->dccph_sport = inet_rsk(req)->loc_port;
- dh->dccph_dport = inet_rsk(req)->rmt_port;
+ dh->dccph_sport = htons(inet_rsk(req)->ir_num);
+ dh->dccph_dport = inet_rsk(req)->ir_rmt_port;
dh->dccph_doff = (dccp_header_size +
DCCP_SKB_CB(skb)->dccpd_opt_len) / 4;
dh->dccph_type = DCCP_PKT_RESPONSE;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 45c74ba..ec9a9ef 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1117,12 +1117,8 @@
* first tnode need some special handling
*/
- if (tp)
- pos = tp->pos+tp->bits;
- else
- pos = 0;
-
if (n) {
+ pos = tp ? tp->pos+tp->bits : 0;
newpos = tkey_mismatch(key, pos, n->key);
tn = tnode_new(n->key, newpos, 1);
} else {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 56e82a4..fc0e649 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -412,8 +412,8 @@
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol,
flags,
- (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
- ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+ (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
+ ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -448,8 +448,8 @@
flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol, inet_sk_flowi_flags(sk),
- (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
- ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
+ (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
+ ireq->ir_loc_addr, ireq->ir_rmt_port, inet_sk(sk)->inet_sport);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -495,9 +495,9 @@
prev = &req->dl_next) {
const struct inet_request_sock *ireq = inet_rsk(req);
- if (ireq->rmt_port == rport &&
- ireq->rmt_addr == raddr &&
- ireq->loc_addr == laddr &&
+ if (ireq->ir_rmt_port == rport &&
+ ireq->ir_rmt_addr == raddr &&
+ ireq->ir_loc_addr == laddr &&
AF_INET_FAMILY(req->rsk_ops->family)) {
WARN_ON(req->sk);
*prevp = prev;
@@ -514,7 +514,8 @@
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
- const u32 h = inet_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port,
+ const u32 h = inet_synq_hash(inet_rsk(req)->ir_rmt_addr,
+ inet_rsk(req)->ir_rmt_port,
lopt->hash_rnd, lopt->nr_table_entries);
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
@@ -674,9 +675,9 @@
newsk->sk_state = TCP_SYN_RECV;
newicsk->icsk_bind_hash = NULL;
- inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port;
- inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port);
- inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port;
+ inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
+ inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
+ inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
newsk->sk_write_space = sk_stream_write_space;
newicsk->icsk_retransmits = 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index ecc179d..41e1c3e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -679,12 +679,12 @@
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6) {
if (req->rsk_ops->family == AF_INET6) {
- entry->saddr = inet6_rsk(req)->loc_addr.s6_addr32;
- entry->daddr = inet6_rsk(req)->rmt_addr.s6_addr32;
+ entry->saddr = ireq->ir_v6_loc_addr.s6_addr32;
+ entry->daddr = ireq->ir_v6_rmt_addr.s6_addr32;
} else if (req->rsk_ops->family == AF_INET) {
- ipv6_addr_set_v4mapped(ireq->loc_addr,
+ ipv6_addr_set_v4mapped(ireq->ir_loc_addr,
&entry->saddr_storage);
- ipv6_addr_set_v4mapped(ireq->rmt_addr,
+ ipv6_addr_set_v4mapped(ireq->ir_rmt_addr,
&entry->daddr_storage);
entry->saddr = entry->saddr_storage.s6_addr32;
entry->daddr = entry->daddr_storage.s6_addr32;
@@ -692,8 +692,8 @@
} else
#endif
{
- entry->saddr = &ireq->loc_addr;
- entry->daddr = &ireq->rmt_addr;
+ entry->saddr = &ireq->ir_loc_addr;
+ entry->daddr = &ireq->ir_rmt_addr;
}
}
@@ -728,9 +728,9 @@
tmo = 0;
r->id.idiag_sport = inet->inet_sport;
- r->id.idiag_dport = ireq->rmt_port;
- r->id.idiag_src[0] = ireq->loc_addr;
- r->id.idiag_dst[0] = ireq->rmt_addr;
+ r->id.idiag_dport = ireq->ir_rmt_port;
+ r->id.idiag_src[0] = ireq->ir_loc_addr;
+ r->id.idiag_dst[0] = ireq->ir_rmt_addr;
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
@@ -789,13 +789,13 @@
if (reqnum < s_reqnum)
continue;
- if (r->id.idiag_dport != ireq->rmt_port &&
+ if (r->id.idiag_dport != ireq->ir_rmt_port &&
r->id.idiag_dport)
continue;
if (bc) {
inet_diag_req_addrs(sk, req, &entry);
- entry.dport = ntohs(ireq->rmt_port);
+ entry.dport = ntohs(ireq->ir_rmt_port);
if (!inet_diag_bc_run(bc, &entry))
continue;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 15e0241..3b64c59 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -304,10 +304,10 @@
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
req->mss = mss;
- ireq->loc_port = th->dest;
- ireq->rmt_port = th->source;
- ireq->loc_addr = ip_hdr(skb)->daddr;
- ireq->rmt_addr = ip_hdr(skb)->saddr;
+ ireq->ir_num = ntohs(th->dest);
+ ireq->ir_rmt_port = th->source;
+ ireq->ir_loc_addr = ip_hdr(skb)->daddr;
+ ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
ireq->ecn_ok = ecn_ok;
ireq->snd_wscale = tcp_opt.snd_wscale;
ireq->sack_ok = tcp_opt.sack_ok;
@@ -347,8 +347,8 @@
flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
- (opt && opt->srr) ? opt->faddr : ireq->rmt_addr,
- ireq->loc_addr, th->source, th->dest);
+ (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
+ ireq->ir_loc_addr, th->source, th->dest);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 47b8ab7..eb651a0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -755,7 +755,12 @@
if (tp->srtt > 8 + 2)
do_div(rate, tp->srtt);
- sk->sk_pacing_rate = min_t(u64, rate, sk->sk_max_pacing_rate);
+ /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate
+ * without any lock. We want to make sure compiler wont store
+ * intermediate values in this location.
+ */
+ ACCESS_ONCE(sk->sk_pacing_rate) = min_t(u64, rate,
+ sk->sk_max_pacing_rate);
}
/* Calculate rto without backoff. This is the second half of Van Jacobson's
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e4695dd..114d1b74 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -835,11 +835,11 @@
skb = tcp_make_synack(sk, dst, req, NULL);
if (skb) {
- __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
+ __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
skb_set_queue_mapping(skb, queue_mapping);
- err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
- ireq->rmt_addr,
+ err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
+ ireq->ir_rmt_addr,
ireq->opt);
err = net_xmit_eval(err);
if (!tcp_rsk(req)->snt_synack && !err)
@@ -972,7 +972,7 @@
{
union tcp_md5_addr *addr;
- addr = (union tcp_md5_addr *)&inet_rsk(req)->rmt_addr;
+ addr = (union tcp_md5_addr *)&inet_rsk(req)->ir_rmt_addr;
return tcp_md5_do_lookup(sk, addr, AF_INET);
}
@@ -1149,8 +1149,8 @@
saddr = inet_sk(sk)->inet_saddr;
daddr = inet_sk(sk)->inet_daddr;
} else if (req) {
- saddr = inet_rsk(req)->loc_addr;
- daddr = inet_rsk(req)->rmt_addr;
+ saddr = inet_rsk(req)->ir_loc_addr;
+ daddr = inet_rsk(req)->ir_rmt_addr;
} else {
const struct iphdr *iph = ip_hdr(skb);
saddr = iph->saddr;
@@ -1366,8 +1366,8 @@
kfree_skb(skb_synack);
return -1;
}
- err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr,
- ireq->rmt_addr, ireq->opt);
+ err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
+ ireq->ir_rmt_addr, ireq->opt);
err = net_xmit_eval(err);
if (!err)
tcp_rsk(req)->snt_synack = tcp_time_stamp;
@@ -1502,8 +1502,8 @@
tcp_openreq_init(req, &tmp_opt, skb);
ireq = inet_rsk(req);
- ireq->loc_addr = daddr;
- ireq->rmt_addr = saddr;
+ ireq->ir_loc_addr = daddr;
+ ireq->ir_rmt_addr = saddr;
ireq->no_srccheck = inet_sk(sk)->transparent;
ireq->opt = tcp_v4_save_options(skb);
@@ -1578,15 +1578,15 @@
fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
if (skb_synack) {
- __tcp_v4_send_check(skb_synack, ireq->loc_addr, ireq->rmt_addr);
+ __tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_rmt_addr);
skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb));
} else
goto drop_and_free;
if (likely(!do_fastopen)) {
int err;
- err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr,
- ireq->rmt_addr, ireq->opt);
+ err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
+ ireq->ir_rmt_addr, ireq->opt);
err = net_xmit_eval(err);
if (err || want_cookie)
goto drop_and_free;
@@ -1644,9 +1644,9 @@
newtp = tcp_sk(newsk);
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
- newinet->inet_daddr = ireq->rmt_addr;
- newinet->inet_rcv_saddr = ireq->loc_addr;
- newinet->inet_saddr = ireq->loc_addr;
+ newinet->inet_daddr = ireq->ir_rmt_addr;
+ newinet->inet_rcv_saddr = ireq->ir_loc_addr;
+ newinet->inet_saddr = ireq->ir_loc_addr;
inet_opt = ireq->opt;
rcu_assign_pointer(newinet->inet_opt, inet_opt);
ireq->opt = NULL;
@@ -2548,10 +2548,10 @@
seq_printf(f, "%4d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK%n",
i,
- ireq->loc_addr,
+ ireq->ir_loc_addr,
ntohs(inet_sk(sk)->inet_sport),
- ireq->rmt_addr,
- ntohs(ireq->rmt_port),
+ ireq->ir_rmt_addr,
+ ntohs(ireq->ir_rmt_port),
TCP_SYN_RECV,
0, 0, /* could print option size, but that is af dependent. */
1, /* timers active (only the expire timer) */
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 8fcc2cb..4a2a841 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -215,13 +215,15 @@
addr.family = req->rsk_ops->family;
switch (addr.family) {
case AF_INET:
- addr.addr.a4 = inet_rsk(req)->rmt_addr;
+ addr.addr.a4 = inet_rsk(req)->ir_rmt_addr;
hash = (__force unsigned int) addr.addr.a4;
break;
+#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
- *(struct in6_addr *)addr.addr.a6 = inet6_rsk(req)->rmt_addr;
- hash = ipv6_addr_hash(&inet6_rsk(req)->rmt_addr);
+ *(struct in6_addr *)addr.addr.a6 = inet_rsk(req)->ir_v6_rmt_addr;
+ hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr);
break;
+#endif
default:
return NULL;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c6f01f2..2822ad0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2734,8 +2734,8 @@
th->syn = 1;
th->ack = 1;
TCP_ECN_make_synack(req, th);
- th->source = ireq->loc_port;
- th->dest = ireq->rmt_port;
+ th->source = htons(ireq->ir_num);
+ th->dest = ireq->ir_rmt_port;
/* Setting of flags are superfluous here for callers (and ECE is
* not even correctly set)
*/
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index b7400b4..77bb8af 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -70,20 +70,20 @@
struct flowi6 *fl6,
const struct request_sock *req)
{
- struct inet6_request_sock *treq = inet6_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *final_p, final;
struct dst_entry *dst;
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = IPPROTO_TCP;
- fl6->daddr = treq->rmt_addr;
+ fl6->daddr = ireq->ir_v6_rmt_addr;
final_p = fl6_update_dst(fl6, np->opt, &final);
- fl6->saddr = treq->loc_addr;
- fl6->flowi6_oif = treq->iif;
+ fl6->saddr = ireq->ir_v6_loc_addr;
+ fl6->flowi6_oif = ireq->ir_iif;
fl6->flowi6_mark = sk->sk_mark;
- fl6->fl6_dport = inet_rsk(req)->rmt_port;
- fl6->fl6_sport = inet_rsk(req)->loc_port;
+ fl6->fl6_dport = ireq->ir_rmt_port;
+ fl6->fl6_sport = htons(ireq->ir_num);
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
@@ -129,13 +129,13 @@
lopt->nr_table_entries)];
(req = *prev) != NULL;
prev = &req->dl_next) {
- const struct inet6_request_sock *treq = inet6_rsk(req);
+ const struct inet_request_sock *ireq = inet_rsk(req);
- if (inet_rsk(req)->rmt_port == rport &&
+ if (ireq->ir_rmt_port == rport &&
req->rsk_ops->family == AF_INET6 &&
- ipv6_addr_equal(&treq->rmt_addr, raddr) &&
- ipv6_addr_equal(&treq->loc_addr, laddr) &&
- (!treq->iif || treq->iif == iif)) {
+ ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) &&
+ ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) &&
+ (!ireq->ir_iif || ireq->ir_iif == iif)) {
WARN_ON(req->sk != NULL);
*prevp = prev;
return req;
@@ -153,8 +153,8 @@
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
- const u32 h = inet6_synq_hash(&inet6_rsk(req)->rmt_addr,
- inet_rsk(req)->rmt_port,
+ const u32 h = inet6_synq_hash(&inet_rsk(req)->ir_v6_rmt_addr,
+ inet_rsk(req)->ir_rmt_port,
lopt->hash_rnd, lopt->nr_table_entries);
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index d703218..d04d3f1 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -150,7 +150,6 @@
{
struct tcp_options_received tcp_opt;
struct inet_request_sock *ireq;
- struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
@@ -187,7 +186,6 @@
goto out;
ireq = inet_rsk(req);
- ireq6 = inet6_rsk(req);
treq = tcp_rsk(req);
treq->listener = NULL;
@@ -195,22 +193,22 @@
goto out_free;
req->mss = mss;
- ireq->rmt_port = th->source;
- ireq->loc_port = th->dest;
- ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
- ireq6->loc_addr = ipv6_hdr(skb)->daddr;
+ ireq->ir_rmt_port = th->source;
+ ireq->ir_num = ntohs(th->dest);
+ ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
- ireq6->pktopts = skb;
+ ireq->pktopts = skb;
}
- ireq6->iif = sk->sk_bound_dev_if;
+ ireq->ir_iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
- ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
- ireq6->iif = inet6_iif(skb);
+ ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ ireq->ir_iif = inet6_iif(skb);
req->expires = 0UL;
req->num_retrans = 0;
@@ -234,12 +232,12 @@
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
- fl6.daddr = ireq6->rmt_addr;
+ fl6.daddr = ireq->ir_v6_rmt_addr;
final_p = fl6_update_dst(&fl6, np->opt, &final);
- fl6.saddr = ireq6->loc_addr;
+ fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
- fl6.fl6_dport = inet_rsk(req)->rmt_port;
+ fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = inet_sk(sk)->inet_sport;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 541dfc4..b996ee2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -465,7 +465,7 @@
struct request_sock *req,
u16 queue_mapping)
{
- struct inet6_request_sock *treq = inet6_rsk(req);
+ struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff * skb;
int err = -ENOMEM;
@@ -477,9 +477,10 @@
skb = tcp_make_synack(sk, dst, req, NULL);
if (skb) {
- __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
+ __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
+ &ireq->ir_v6_rmt_addr);
- fl6->daddr = treq->rmt_addr;
+ fl6->daddr = ireq->ir_v6_rmt_addr;
skb_set_queue_mapping(skb, queue_mapping);
err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
err = net_xmit_eval(err);
@@ -502,7 +503,7 @@
static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
- kfree_skb(inet6_rsk(req)->pktopts);
+ kfree_skb(inet_rsk(req)->pktopts);
}
#ifdef CONFIG_TCP_MD5SIG
@@ -521,7 +522,7 @@
static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk,
struct request_sock *req)
{
- return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr);
+ return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr);
}
static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
@@ -623,8 +624,8 @@
saddr = &inet6_sk(sk)->saddr;
daddr = &sk->sk_v6_daddr;
} else if (req) {
- saddr = &inet6_rsk(req)->loc_addr;
- daddr = &inet6_rsk(req)->rmt_addr;
+ saddr = &inet_rsk(req)->ir_v6_loc_addr;
+ daddr = &inet_rsk(req)->ir_v6_rmt_addr;
} else {
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
saddr = &ip6h->saddr;
@@ -949,7 +950,7 @@
{
struct tcp_options_received tmp_opt;
struct request_sock *req;
- struct inet6_request_sock *treq;
+ struct inet_request_sock *ireq;
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
__u32 isn = TCP_SKB_CB(skb)->when;
@@ -994,25 +995,25 @@
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
tcp_openreq_init(req, &tmp_opt, skb);
- treq = inet6_rsk(req);
- treq->rmt_addr = ipv6_hdr(skb)->saddr;
- treq->loc_addr = ipv6_hdr(skb)->daddr;
+ ireq = inet_rsk(req);
+ ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
+ ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
if (!want_cookie || tmp_opt.tstamp_ok)
TCP_ECN_create_request(req, skb, sock_net(sk));
- treq->iif = sk->sk_bound_dev_if;
+ ireq->ir_iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
- ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
- treq->iif = inet6_iif(skb);
+ ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
+ ireq->ir_iif = inet6_iif(skb);
if (!isn) {
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
- treq->pktopts = skb;
+ ireq->pktopts = skb;
}
if (want_cookie) {
@@ -1051,7 +1052,7 @@
* to the moment of synflood.
*/
LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI6/%u\n",
- &treq->rmt_addr, ntohs(tcp_hdr(skb)->source));
+ &ireq->ir_v6_rmt_addr, ntohs(tcp_hdr(skb)->source));
goto drop_and_release;
}
@@ -1086,7 +1087,7 @@
struct request_sock *req,
struct dst_entry *dst)
{
- struct inet6_request_sock *treq;
+ struct inet_request_sock *ireq;
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct tcp6_sock *newtcp6sk;
struct inet_sock *newinet;
@@ -1151,7 +1152,7 @@
return newsk;
}
- treq = inet6_rsk(req);
+ ireq = inet_rsk(req);
if (sk_acceptq_is_full(sk))
goto out_overflow;
@@ -1185,10 +1186,10 @@
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
- newsk->sk_v6_daddr = treq->rmt_addr;
- newnp->saddr = treq->loc_addr;
- newsk->sk_v6_rcv_saddr = treq->loc_addr;
- newsk->sk_bound_dev_if = treq->iif;
+ newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
+ newnp->saddr = ireq->ir_v6_loc_addr;
+ newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
+ newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
@@ -1203,11 +1204,11 @@
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
- if (treq->pktopts != NULL) {
- newnp->pktoptions = skb_clone(treq->pktopts,
+ if (ireq->pktopts != NULL) {
+ newnp->pktoptions = skb_clone(ireq->pktopts,
sk_gfp_atomic(sk, GFP_ATOMIC));
- consume_skb(treq->pktopts);
- treq->pktopts = NULL;
+ consume_skb(ireq->pktopts);
+ ireq->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
@@ -1722,8 +1723,8 @@
const struct sock *sk, struct request_sock *req, int i, kuid_t uid)
{
int ttd = req->expires - jiffies;
- const struct in6_addr *src = &inet6_rsk(req)->loc_addr;
- const struct in6_addr *dest = &inet6_rsk(req)->rmt_addr;
+ const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
+ const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr;
if (ttd < 0)
ttd = 0;
@@ -1734,10 +1735,10 @@
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3],
- ntohs(inet_rsk(req)->loc_port),
+ inet_rsk(req)->ir_num,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3],
- ntohs(inet_rsk(req)->rmt_port),
+ ntohs(inet_rsk(req)->ir_rmt_port),
TCP_SYN_RECV,
0,0, /* could print option size, but that is af dependent. */
1, /* timers active (only the expire timer) */
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 96a458e..dce1beb 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -817,7 +817,7 @@
switch (req->rsk_ops->family) {
case AF_INET:
entry = netlbl_domhsh_getentry_af4(secattr->domain,
- inet_rsk(req)->rmt_addr);
+ inet_rsk(req)->ir_rmt_addr);
if (entry == NULL) {
ret_val = -ENOENT;
goto req_setattr_return;