diff options
| author | Raj Victor <victor.raj@intel.com> | 2024-04-19 04:08:50 -0400 |
|---|---|---|
| committer | Tony Nguyen <anthony.l.nguyen@intel.com> | 2024-04-22 13:05:19 -0700 |
| commit | 91427e6d9030611b27a4150ad3c59e4db3f02b8c (patch) | |
| tree | abe94b0f5c80de517597531d086278a919988f54 /drivers/net/ethernet/intel/ice/ice_ddp.c | |
| parent | 5625ca5640caa3fb797f155601d56379d260d6ba (diff) | |
| download | lwn-91427e6d9030611b27a4150ad3c59e4db3f02b8c.tar.gz lwn-91427e6d9030611b27a4150ad3c59e4db3f02b8c.zip | |
ice: Support 5 layer topology
There is a performance issue when the number of VSIs are not multiple
of 8. This is caused due to the max children limitation per node(8) in
9 layer topology. The BW credits are shared evenly among the children
by default. Assume one node has 8 children and the other has 1.
The parent of these nodes share the BW credit equally among them.
Apparently this causes a problem for the first node which has 8 children.
The 9th VM get more BW credits than the first 8 VMs.
Example:
1) With 8 VM's:
for x in 0 1 2 3 4 5 6 7;
do taskset -c ${x} netperf -P0 -H 172.68.169.125 & sleep .1 ; done
tx_queue_0_packets: 23283027
tx_queue_1_packets: 23292289
tx_queue_2_packets: 23276136
tx_queue_3_packets: 23279828
tx_queue_4_packets: 23279828
tx_queue_5_packets: 23279333
tx_queue_6_packets: 23277745
tx_queue_7_packets: 23279950
tx_queue_8_packets: 0
2) With 9 VM's:
for x in 0 1 2 3 4 5 6 7 8;
do taskset -c ${x} netperf -P0 -H 172.68.169.125 & sleep .1 ; done
tx_queue_0_packets: 24163396
tx_queue_1_packets: 24164623
tx_queue_2_packets: 24163188
tx_queue_3_packets: 24163701
tx_queue_4_packets: 24163683
tx_queue_5_packets: 24164668
tx_queue_6_packets: 23327200
tx_queue_7_packets: 24163853
tx_queue_8_packets: 91101417
So on average queue 8 statistics show that 3.7 times more packets were
send there than to the other queues.
The FW starting with version 3.20, has increased the max number of
children per node by reducing the number of layers from 9 to 5. Reflect
this on driver side.
Signed-off-by: Raj Victor <victor.raj@intel.com>
Co-developed-by: Michal Wilczynski <michal.wilczynski@intel.com>
Signed-off-by: Michal Wilczynski <michal.wilczynski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_ddp.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ice/ice_ddp.c | 209 |
1 files changed, 209 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 2ffa11fa2df1..87d86d8897ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -4,6 +4,7 @@ #include "ice_common.h" #include "ice.h" #include "ice_ddp.h" +#include "ice_sched.h" /* For supporting double VLAN mode, it is necessary to enable or disable certain * boost tcam entries. The metadata labels names that match the following @@ -2272,3 +2273,211 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, return state; } + +/** + * ice_get_set_tx_topo - get or set Tx topology + * @hw: pointer to the HW struct + * @buf: pointer to Tx topology buffer + * @buf_size: buffer size + * @cd: pointer to command details structure or NULL + * @flags: pointer to descriptor flags + * @set: 0-get, 1-set topology + * + * The function will get or set Tx topology + * + * Return: zero when set was successful, negative values otherwise. + */ +static int +ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, + struct ice_sq_cd *cd, u8 *flags, bool set) +{ + struct ice_aqc_get_set_tx_topo *cmd; + struct ice_aq_desc desc; + int status; + + cmd = &desc.params.get_set_tx_topo; + if (set) { + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo); + cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED; + /* requested to update a new topology, not a default topology */ + if (buf) + cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM | + ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW; + + if (ice_is_e825c(hw)) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } else { + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo); + cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM; + } + + if (!ice_is_e825c(hw)) + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); + if (status) + return status; + /* read the return flag values (first byte) for get operation */ + if (!set && flags) + *flags = desc.params.get_set_tx_topo.set_flags; + + return 0; +} + +/** + * ice_cfg_tx_topo - Initialize new Tx topology if available + * @hw: pointer to the HW struct + * @buf: pointer to Tx topology buffer + * @len: buffer size + * + * The function will apply the new Tx topology from the package buffer + * if available. + * + * Return: zero when update was successful, negative values otherwise. + */ +int ice_cfg_tx_topo(struct ice_hw *hw, u8 *buf, u32 len) +{ + u8 *current_topo, *new_topo = NULL; + struct ice_run_time_cfg_seg *seg; + struct ice_buf_hdr *section; + struct ice_pkg_hdr *pkg_hdr; + enum ice_ddp_state state; + u16 offset, size = 0; + u32 reg = 0; + int status; + u8 flags; + + if (!buf || !len) + return -EINVAL; + + /* Does FW support new Tx topology mode ? */ + if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) { + ice_debug(hw, ICE_DBG_INIT, "FW doesn't support compatibility mode\n"); + return -EOPNOTSUPP; + } + + current_topo = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); + if (!current_topo) + return -ENOMEM; + + /* Get the current Tx topology */ + status = ice_get_set_tx_topo(hw, current_topo, ICE_AQ_MAX_BUF_LEN, NULL, + &flags, false); + + kfree(current_topo); + + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n"); + return status; + } + + /* Is default topology already applied ? */ + if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_9_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "Default topology already applied\n"); + return -EEXIST; + } + + /* Is new topology already applied ? */ + if ((flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "New topology already applied\n"); + return -EEXIST; + } + + /* Setting topology already issued? */ + if (flags & ICE_AQC_TX_TOPO_FLAGS_ISSUED) { + ice_debug(hw, ICE_DBG_INIT, "Update Tx topology was done by another PF\n"); + /* Add a small delay before exiting */ + msleep(2000); + return -EEXIST; + } + + /* Change the topology from new to default (5 to 9) */ + if (!(flags & ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW) && + hw->num_tx_sched_layers == ICE_SCHED_5_LAYERS) { + ice_debug(hw, ICE_DBG_INIT, "Change topology from 5 to 9 layers\n"); + goto update_topo; + } + + pkg_hdr = (struct ice_pkg_hdr *)buf; + state = ice_verify_pkg(pkg_hdr, len); + if (state) { + ice_debug(hw, ICE_DBG_INIT, "Failed to verify pkg (err: %d)\n", + state); + return -EIO; + } + + /* Find runtime configuration segment */ + seg = (struct ice_run_time_cfg_seg *) + ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE_RUN_TIME_CFG, pkg_hdr); + if (!seg) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment is missing\n"); + return -EIO; + } + + if (le32_to_cpu(seg->buf_table.buf_count) < ICE_MIN_S_COUNT) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology segment count(%d) is wrong\n", + seg->buf_table.buf_count); + return -EIO; + } + + section = ice_pkg_val_buf(seg->buf_table.buf_array); + if (!section || le32_to_cpu(section->section_entry[0].type) != + ICE_SID_TX_5_LAYER_TOPO) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology section type is wrong\n"); + return -EIO; + } + + size = le16_to_cpu(section->section_entry[0].size); + offset = le16_to_cpu(section->section_entry[0].offset); + if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology section size is wrong\n"); + return -EIO; + } + + /* Make sure the section fits in the buffer */ + if (offset + size > ICE_PKG_BUF_SIZE) { + ice_debug(hw, ICE_DBG_INIT, "5 layer topology buffer > 4K\n"); + return -EIO; + } + + /* Get the new topology buffer */ + new_topo = ((u8 *)section) + offset; + +update_topo: + /* Acquire global lock to make sure that set topology issued + * by one PF. + */ + status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, ICE_RES_WRITE, + ICE_GLOBAL_CFG_LOCK_TIMEOUT); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n"); + return status; + } + + /* Check if reset was triggered already. */ + reg = rd32(hw, GLGEN_RSTAT); + if (reg & GLGEN_RSTAT_DEVSTATE_M) { + /* Reset is in progress, re-init the HW again */ + ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n"); + ice_check_reset(hw); + return 0; + } + + /* Set new topology */ + status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n"); + return status; + } + + /* New topology is updated, delay 1 second before issuing the CORER */ + msleep(1000); + ice_reset(hw, ICE_RESET_CORER); + /* CORER will clear the global lock, so no explicit call + * required for release. + */ + + return 0; +} |