* [PATCH net-next 01/12] net: hns3: Fix ets validate issue
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
There is a defect in hclge_ets_validate(). If each member of tc_tsa is
not IEEE_8021QAZ_TSA_ETS, the variable total_ets_bw won't be updated.
In this case, the check for value of total_ets_bw will fail. This patch
fixes it by checking total_ets_bw only after it has been updated.
Fixes: cacde272dd00 ("net: hns3: Add hclge_dcb module for the support of DCB feature")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index f08ebb7..92f1938 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -73,6 +73,7 @@ static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets)
static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
u8 *tc, bool *changed)
{
+ bool has_ets_tc = false;
u32 total_ets_bw = 0;
u8 max_tc = 0;
u8 i;
@@ -100,13 +101,14 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
*changed = true;
total_ets_bw += ets->tc_tx_bw[i];
- break;
+ has_ets_tc = true;
+ break;
default:
return -EINVAL;
}
}
- if (total_ets_bw != BW_PERCENT)
+ if (has_ets_tc && total_ets_bw != BW_PERCENT)
return -EINVAL;
*tc = max_tc + 1;
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 02/12] net: hns3: Unify the type convert for desc.data
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
For desc.data is already point to the address of struct member "data[6]",
it's unnecessary to use '&' to get its address. This patch unifies all
the type convert for dest.data, using "req = (struct name *)dest.data".
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++--
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 6 +++---
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index cf365d4..e9625ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3387,7 +3387,7 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en)
struct hclge_desc desc;
int ret, i = 0;
- req = (struct hclge_serdes_lb_cmd *)&desc.data[0];
+ req = (struct hclge_serdes_lb_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK, false);
if (en) {
@@ -4634,7 +4634,7 @@ static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev)
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_INSERT, false);
- tx_req = (struct hclge_tx_vlan_type_cfg_cmd *)&desc.data;
+ tx_req = (struct hclge_tx_vlan_type_cfg_cmd *)desc.data;
tx_req->ot_vlan_type = cpu_to_le16(hdev->vlan_type_cfg.tx_ot_vlan_type);
tx_req->in_vlan_type = cpu_to_le16(hdev->vlan_type_cfg.tx_in_vlan_type);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 0282067..00bb394 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -172,7 +172,7 @@ static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap,
u8 pfc_bitmap)
{
struct hclge_desc desc;
- struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)&desc.data;
+ struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PFC_PAUSE_EN, false);
@@ -188,7 +188,7 @@ static int hclge_pause_param_cfg(struct hclge_dev *hdev, const u8 *addr,
struct hclge_cfg_pause_param_cmd *pause_param;
struct hclge_desc desc;
- pause_param = (struct hclge_cfg_pause_param_cmd *)&desc.data;
+ pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, false);
@@ -207,7 +207,7 @@ int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr)
u8 trans_gap;
int ret;
- pause_param = (struct hclge_cfg_pause_param_cmd *)&desc.data;
+ pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true);
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 03/12] net: hns3: Adjust prefix of tx/rx statistic names
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
Some prefix of tx/rx statistic names are redundant, this patch modifies
these names.
The new prefix looks like below:
rxq#1_ -> rxq1_
txq#1_ -> txq1_
tx_dropped -> dropped
tx_wake -> wake
tx_busy -> busy
rx_dropped -> dropped
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 10 +++++-----
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++--
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++--
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 3cfb6b8..ce2e6ea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -22,13 +22,13 @@ struct hns3_stats {
static const struct hns3_stats hns3_txq_stats[] = {
/* Tx per-queue statistics */
HNS3_TQP_STAT("io_err_cnt", io_err_cnt),
- HNS3_TQP_STAT("tx_dropped", sw_err_cnt),
+ HNS3_TQP_STAT("dropped", sw_err_cnt),
HNS3_TQP_STAT("seg_pkt_cnt", seg_pkt_cnt),
HNS3_TQP_STAT("packets", tx_pkts),
HNS3_TQP_STAT("bytes", tx_bytes),
HNS3_TQP_STAT("errors", tx_err_cnt),
- HNS3_TQP_STAT("tx_wake", restart_queue),
- HNS3_TQP_STAT("tx_busy", tx_busy),
+ HNS3_TQP_STAT("wake", restart_queue),
+ HNS3_TQP_STAT("busy", tx_busy),
};
#define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)
@@ -36,7 +36,7 @@ static const struct hns3_stats hns3_txq_stats[] = {
static const struct hns3_stats hns3_rxq_stats[] = {
/* Rx per-queue statistics */
HNS3_TQP_STAT("io_err_cnt", io_err_cnt),
- HNS3_TQP_STAT("rx_dropped", sw_err_cnt),
+ HNS3_TQP_STAT("dropped", sw_err_cnt),
HNS3_TQP_STAT("seg_pkt_cnt", seg_pkt_cnt),
HNS3_TQP_STAT("packets", rx_pkts),
HNS3_TQP_STAT("bytes", rx_bytes),
@@ -369,7 +369,7 @@ static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats,
data[ETH_GSTRING_LEN - 1] = '\0';
/* first, prepend the prefix string */
- n1 = snprintf(data, MAX_PREFIX_SIZE, "%s#%d_",
+ n1 = snprintf(data, MAX_PREFIX_SIZE, "%s%d_",
prefix, i);
n1 = min_t(uint, n1, MAX_PREFIX_SIZE - 1);
size_left = (ETH_GSTRING_LEN - 1) - n1;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e9625ce..86d3d8b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -354,7 +354,7 @@ static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
for (i = 0; i < kinfo->num_tqps; i++) {
struct hclge_tqp *tqp = container_of(handle->kinfo.tqp[i],
struct hclge_tqp, q);
- snprintf(buff, ETH_GSTRING_LEN, "txq#%d_pktnum_rcd",
+ snprintf(buff, ETH_GSTRING_LEN, "txq%d_pktnum_rcd",
tqp->index);
buff = buff + ETH_GSTRING_LEN;
}
@@ -362,7 +362,7 @@ static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
for (i = 0; i < kinfo->num_tqps; i++) {
struct hclge_tqp *tqp = container_of(kinfo->tqp[i],
struct hclge_tqp, q);
- snprintf(buff, ETH_GSTRING_LEN, "rxq#%d_pktnum_rcd",
+ snprintf(buff, ETH_GSTRING_LEN, "rxq%d_pktnum_rcd",
tqp->index);
buff = buff + ETH_GSTRING_LEN;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 166a2cf..c220d9b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -110,7 +110,7 @@ static u8 *hclgevf_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
for (i = 0; i < hdev->num_tqps; i++) {
struct hclgevf_tqp *tqp = container_of(handle->kinfo.tqp[i],
struct hclgevf_tqp, q);
- snprintf(buff, ETH_GSTRING_LEN, "txq#%d_pktnum_rcd",
+ snprintf(buff, ETH_GSTRING_LEN, "txq%d_pktnum_rcd",
tqp->index);
buff += ETH_GSTRING_LEN;
}
@@ -118,7 +118,7 @@ static u8 *hclgevf_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
for (i = 0; i < hdev->num_tqps; i++) {
struct hclgevf_tqp *tqp = container_of(handle->kinfo.tqp[i],
struct hclgevf_tqp, q);
- snprintf(buff, ETH_GSTRING_LEN, "rxq#%d_pktnum_rcd",
+ snprintf(buff, ETH_GSTRING_LEN, "rxq%d_pktnum_rcd",
tqp->index);
buff += ETH_GSTRING_LEN;
}
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 04/12] net: hns3: Fix tqp array traversal condition for vf
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
There are two tqp_num variables "hdev->tqp_num" and "kinfo->tqp_num"
used in VF. "hdev->tqp_num" is the total tqp number allocated to the
VF, and "kinfo->tqp_num" indicates the tqp number being used by the
VF. Usually the two variables are equal. But for the case hdev->tqp_num
larger than rss_size_max, and num_tc is 1, "kinfo->tqp_num" will be
less than "hdev->tqp_num".
In original codes, "hdev->tqp_num" is always used to traverse the
tqp array of kinfo. It may cause null pointer error when "hdev->tqp_num"
is larger than "kinfo->tqp_num"
Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
.../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 50 +++++++++++-----------
1 file changed, 24 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index c220d9b..f7ab2eb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -31,16 +31,15 @@ static inline struct hclgevf_dev *hclgevf_ae_get_hdev(
static int hclgevf_tqps_update_stats(struct hnae3_handle *handle)
{
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
- struct hnae3_queue *queue;
struct hclgevf_desc desc;
struct hclgevf_tqp *tqp;
int status;
int i;
- for (i = 0; i < hdev->num_tqps; i++) {
- queue = handle->kinfo.tqp[i];
- tqp = container_of(queue, struct hclgevf_tqp, q);
+ for (i = 0; i < kinfo->num_tqps; i++) {
+ tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q);
hclgevf_cmd_setup_basic_desc(&desc,
HCLGEVF_OPC_QUERY_RX_STATUS,
true);
@@ -77,17 +76,16 @@ static int hclgevf_tqps_update_stats(struct hnae3_handle *handle)
static u64 *hclgevf_tqps_get_stats(struct hnae3_handle *handle, u64 *data)
{
struct hnae3_knic_private_info *kinfo = &handle->kinfo;
- struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
struct hclgevf_tqp *tqp;
u64 *buff = data;
int i;
- for (i = 0; i < hdev->num_tqps; i++) {
- tqp = container_of(handle->kinfo.tqp[i], struct hclgevf_tqp, q);
+ for (i = 0; i < kinfo->num_tqps; i++) {
+ tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q);
*buff++ = tqp->tqp_stats.rcb_tx_ring_pktnum_rcd;
}
for (i = 0; i < kinfo->num_tqps; i++) {
- tqp = container_of(handle->kinfo.tqp[i], struct hclgevf_tqp, q);
+ tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q);
*buff++ = tqp->tqp_stats.rcb_rx_ring_pktnum_rcd;
}
@@ -96,28 +94,28 @@ static u64 *hclgevf_tqps_get_stats(struct hnae3_handle *handle, u64 *data)
static int hclgevf_tqps_get_sset_count(struct hnae3_handle *handle, int strset)
{
- struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
- return hdev->num_tqps * 2;
+ return kinfo->num_tqps * 2;
}
static u8 *hclgevf_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
{
- struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
u8 *buff = data;
int i = 0;
- for (i = 0; i < hdev->num_tqps; i++) {
- struct hclgevf_tqp *tqp = container_of(handle->kinfo.tqp[i],
- struct hclgevf_tqp, q);
+ for (i = 0; i < kinfo->num_tqps; i++) {
+ struct hclgevf_tqp *tqp = container_of(kinfo->tqp[i],
+ struct hclgevf_tqp, q);
snprintf(buff, ETH_GSTRING_LEN, "txq%d_pktnum_rcd",
tqp->index);
buff += ETH_GSTRING_LEN;
}
- for (i = 0; i < hdev->num_tqps; i++) {
- struct hclgevf_tqp *tqp = container_of(handle->kinfo.tqp[i],
- struct hclgevf_tqp, q);
+ for (i = 0; i < kinfo->num_tqps; i++) {
+ struct hclgevf_tqp *tqp = container_of(kinfo->tqp[i],
+ struct hclgevf_tqp, q);
snprintf(buff, ETH_GSTRING_LEN, "rxq%d_pktnum_rcd",
tqp->index);
buff += ETH_GSTRING_LEN;
@@ -738,14 +736,12 @@ static int hclgevf_get_queue_id(struct hnae3_queue *queue)
static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle)
{
- struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
- struct hnae3_queue *queue;
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct hclgevf_tqp *tqp;
int i;
- for (i = 0; i < hdev->num_tqps; i++) {
- queue = handle->kinfo.tqp[i];
- tqp = container_of(queue, struct hclgevf_tqp, q);
+ for (i = 0; i < kinfo->num_tqps; i++) {
+ tqp = container_of(kinfo->tqp[i], struct hclgevf_tqp, q);
memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats));
}
}
@@ -1420,12 +1416,13 @@ static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
static int hclgevf_ae_start(struct hnae3_handle *handle)
{
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
int i, queue_id;
- for (i = 0; i < handle->kinfo.num_tqps; i++) {
+ for (i = 0; i < kinfo->num_tqps; i++) {
/* ring enable */
- queue_id = hclgevf_get_queue_id(handle->kinfo.tqp[i]);
+ queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
if (queue_id < 0) {
dev_warn(&hdev->pdev->dev,
"Get invalid queue id, ignore it\n");
@@ -1448,14 +1445,15 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
static void hclgevf_ae_stop(struct hnae3_handle *handle)
{
+ struct hnae3_knic_private_info *kinfo = &handle->kinfo;
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
int i, queue_id;
set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
- for (i = 0; i < hdev->num_tqps; i++) {
+ for (i = 0; i < kinfo->num_tqps; i++) {
/* Ring disable */
- queue_id = hclgevf_get_queue_id(handle->kinfo.tqp[i]);
+ queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
if (queue_id < 0) {
dev_warn(&hdev->pdev->dev,
"Get invalid queue id, ignore it\n");
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 05/12] net: hns3: Unify the prefix of vf functions
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
The prefix of most functions for vf are hclgevf. This patch renames the
function with inconsistent prefix.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index f7ab2eb..84129c5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -180,7 +180,7 @@ static int hclgevf_get_tc_info(struct hclgevf_dev *hdev)
return 0;
}
-static int hclge_get_queue_info(struct hclgevf_dev *hdev)
+static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
{
#define HCLGEVF_TQPS_RSS_INFO_LEN 8
u8 resp_msg[HCLGEVF_TQPS_RSS_INFO_LEN];
@@ -1341,7 +1341,7 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
int ret;
/* get queue configuration from PF */
- ret = hclge_get_queue_info(hdev);
+ ret = hclgevf_get_queue_info(hdev);
if (ret)
return ret;
/* get tc configuration from PF */
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 06/12] net: hns3: Add handle for default case
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
There are a few "switch-case" codes missed handle for default case. For
some abnormal case, it should return error code instead of return 0.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 ++
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 7 +++++--
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 ++++++
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 8 ++++----
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 +++
5 files changed, 20 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index e404130..fc27f3f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2176,6 +2176,8 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
l4_type == HNS3_L4_TYPE_SCTP))
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
+ default:
+ break;
}
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index ce2e6ea..46701cf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -351,9 +351,10 @@ static int hns3_get_sset_count(struct net_device *netdev, int stringset)
case ETH_SS_TEST:
return ops->get_sset_count(h, stringset);
- }
- return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
}
static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats,
@@ -417,6 +418,8 @@ static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
case ETH_SS_TEST:
ops->get_strings(h, stringset, data);
break;
+ default:
+ break;
}
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 86d3d8b..73d9d0d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2224,6 +2224,8 @@ static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type,
case HCLGE_VECTOR0_EVENT_MBX:
hclge_write_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG, regclr);
break;
+ default:
+ break;
}
}
@@ -5218,6 +5220,10 @@ static int hclge_init_client_instance(struct hnae3_client *client,
hnae3_set_client_init_flag(client, ae_dev, 1);
}
+
+ break;
+ default:
+ return -EINVAL;
}
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index d8c0cc8..0d3b445 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -134,7 +134,7 @@ static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
- break;
+ return 0;
case HCLGEVF_TYPE_CRQ:
reg_val = (u32)ring->desc_dma_addr;
hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
@@ -147,10 +147,10 @@ static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
- break;
+ return 0;
+ default:
+ return -EINVAL;
}
-
- return 0;
}
void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 84129c5..b644187 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1667,6 +1667,9 @@ static int hclgevf_init_client_instance(struct hnae3_client *client,
}
hnae3_set_client_init_flag(client, ae_dev, 1);
+ break;
+ default:
+ return -EINVAL;
}
return 0;
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 07/12] net: hns3: Add nic state check before calling netif_tx_wake_queue
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
When nic down, it firstly calls netif_tx_stop_all_queues(), then calls
napi_disable(). But napi_disable() will wait current napi_poll finish,
it may call netif_tx_wake_queue(). This patch fixes it by add nic state
checking.
Fixes: 424eb834a9be ("net: hns3: Unified HNS3 {VF|PF} Ethernet Driver for hip08 SoC")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index fc27f3f..73b42d3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1973,6 +1973,7 @@ static int is_valid_clean_head(struct hns3_enet_ring *ring, int h)
void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
{
struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
struct netdev_queue *dev_queue;
int bytes, pkts;
int head;
@@ -2018,7 +2019,8 @@ void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
* sees the new next_to_clean.
*/
smp_mb();
- if (netif_tx_queue_stopped(dev_queue)) {
+ if (netif_tx_queue_stopped(dev_queue) &&
+ !test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) {
netif_tx_wake_queue(dev_queue);
ring->stats.restart_queue++;
}
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 08/12] net: hns3: Add unlikely for dma_mapping_error check
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
For dma_mapping_error is unlikely happened, this patch adds unlikely for
dma_mapping_error check.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 73b42d3..8b63707 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1807,7 +1807,7 @@ static int hns3_map_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb)
cb->dma = dma_map_page(ring_to_dev(ring), cb->priv, 0,
cb->length, ring_to_dma_dir(ring));
- if (dma_mapping_error(ring_to_dev(ring), cb->dma))
+ if (unlikely(dma_mapping_error(ring_to_dev(ring), cb->dma)))
return -EIO;
return 0;
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 09/12] net: hns3: Remove print messages for error packet
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Jian Shen
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Jian Shen <shenjian15@huawei.com>
There are already multiple types packets statistics for error packets,
it's unnecessary to print them, which may affect the rx performance if
print too many.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 8b63707..5a4773a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2149,7 +2149,6 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
hnae3_get_bit(l234info, HNS3_RXD_L4E_B) ||
hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) ||
hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) {
- netdev_err(netdev, "L3/L4 error pkt\n");
u64_stats_update_begin(&ring->syncp);
ring->stats.l3l4_csum_err++;
u64_stats_update_end(&ring->syncp);
@@ -2328,8 +2327,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
}
if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
- netdev_err(netdev, "no valid bd,%016llx,%016llx\n",
- ((u64 *)desc)[0], ((u64 *)desc)[1]);
u64_stats_update_begin(&ring->syncp);
ring->stats.non_vld_descs++;
u64_stats_update_end(&ring->syncp);
@@ -2340,7 +2337,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
if (unlikely((!desc->rx.pkt_len) ||
hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
- netdev_err(netdev, "truncated pkt\n");
u64_stats_update_begin(&ring->syncp);
ring->stats.err_pkt_len++;
u64_stats_update_end(&ring->syncp);
@@ -2350,7 +2346,6 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
}
if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) {
- netdev_err(netdev, "L2 error pkt\n");
u64_stats_update_begin(&ring->syncp);
ring->stats.l2_err++;
u64_stats_update_end(&ring->syncp);
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 10/12] net: hns3: Add get_media_type ops support for VF
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Fuyun Liang
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Peng Li <lipeng321@huawei.com>
This patch adds the ops of get_media_type support for VF.
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 +
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 11 +++++++++++
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 1 +
3 files changed, 13 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 17db631..fc87e1b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -107,6 +107,7 @@ enum hnae3_media_type {
HNAE3_MEDIA_TYPE_FIBER,
HNAE3_MEDIA_TYPE_COPPER,
HNAE3_MEDIA_TYPE_BACKPLANE,
+ HNAE3_MEDIA_TYPE_NONE,
};
enum hnae3_reset_notify_type {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index b644187..9781931 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1340,6 +1340,8 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
{
int ret;
+ hdev->hw.mac.media_type = HNAE3_MEDIA_TYPE_NONE;
+
/* get queue configuration from PF */
ret = hclgevf_get_queue_info(hdev);
if (ret)
@@ -2009,6 +2011,14 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
hdev->hw.mac.duplex = duplex;
}
+static void hclgevf_get_media_type(struct hnae3_handle *handle,
+ u8 *media_type)
+{
+ struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ if (media_type)
+ *media_type = hdev->hw.mac.media_type;
+}
+
static const struct hnae3_ae_ops hclgevf_ops = {
.init_ae_dev = hclgevf_init_ae_dev,
.uninit_ae_dev = hclgevf_uninit_ae_dev,
@@ -2046,6 +2056,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
.get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info,
.get_status = hclgevf_get_status,
.get_ksettings_an_result = hclgevf_get_ksettings_an_result,
+ .get_media_type = hclgevf_get_media_type,
};
static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index b23ba17..2af01f1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -66,6 +66,7 @@ enum hclgevf_states {
#define HCLGEVF_MPF_ENBALE 1
struct hclgevf_mac {
+ u8 media_type;
u8 mac_addr[ETH_ALEN];
int link;
u8 duplex;
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 11/12] net: hns3: Fix speed/duplex information loss problem when executing ethtool ethx cmd of VF
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Fuyun Liang
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Fuyun Liang <liangfuyun1@huawei.com>
Our VF has not implemented the ops for get_port_type. So when we executing
ethtool ethx cmd of VF, hns3_get_link_ksettings will return directly. And
we can not query anything.
To support get_link_ksettings for VF, this patch replaces get_port_type
with get_media_type. If the media type is HNAE3_MEDIA_TYPE_NONE,
hns3_get_link_ksettings will return link information of VF.
Fixes: 12f46bc1d447 ("net: hns3: Refine hns3_get_link_ksettings()")
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 66 +++++++++++++---------
1 file changed, 39 insertions(+), 27 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 46701cf..8803a87 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -545,55 +545,67 @@ static int hns3_set_pauseparam(struct net_device *netdev,
return -EOPNOTSUPP;
}
+static void hns3_get_ksettings(struct hnae3_handle *h,
+ struct ethtool_link_ksettings *cmd)
+{
+ const struct hnae3_ae_ops *ops = h->ae_algo->ops;
+
+ /* 1.auto_neg & speed & duplex from cmd */
+ if (ops->get_ksettings_an_result)
+ ops->get_ksettings_an_result(h,
+ &cmd->base.autoneg,
+ &cmd->base.speed,
+ &cmd->base.duplex);
+
+ /* 2.get link mode*/
+ if (ops->get_link_mode)
+ ops->get_link_mode(h,
+ cmd->link_modes.supported,
+ cmd->link_modes.advertising);
+
+ /* 3.mdix_ctrl&mdix get from phy reg */
+ if (ops->get_mdix_mode)
+ ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl,
+ &cmd->base.eth_tp_mdix);
+}
+
static int hns3_get_link_ksettings(struct net_device *netdev,
struct ethtool_link_ksettings *cmd)
{
struct hnae3_handle *h = hns3_get_handle(netdev);
const struct hnae3_ae_ops *ops;
+ u8 media_type;
u8 link_stat;
if (!h->ae_algo || !h->ae_algo->ops)
return -EOPNOTSUPP;
ops = h->ae_algo->ops;
- if (ops->get_port_type)
- ops->get_port_type(h, &cmd->base.port);
+ if (ops->get_media_type)
+ ops->get_media_type(h, &media_type);
else
return -EOPNOTSUPP;
- switch (cmd->base.port) {
- case PORT_FIBRE:
- /* 1.auto_neg & speed & duplex from cmd */
- if (ops->get_ksettings_an_result)
- ops->get_ksettings_an_result(h,
- &cmd->base.autoneg,
- &cmd->base.speed,
- &cmd->base.duplex);
- else
- return -EOPNOTSUPP;
-
- /* 2.get link mode*/
- if (ops->get_link_mode)
- ops->get_link_mode(h,
- cmd->link_modes.supported,
- cmd->link_modes.advertising);
-
- /* 3.mdix_ctrl&mdix get from phy reg */
- if (ops->get_mdix_mode)
- ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl,
- &cmd->base.eth_tp_mdix);
-
+ switch (media_type) {
+ case HNAE3_MEDIA_TYPE_NONE:
+ cmd->base.port = PORT_NONE;
+ hns3_get_ksettings(h, cmd);
+ break;
+ case HNAE3_MEDIA_TYPE_FIBER:
+ cmd->base.port = PORT_FIBRE;
+ hns3_get_ksettings(h, cmd);
break;
- case PORT_TP:
+ case HNAE3_MEDIA_TYPE_COPPER:
if (!netdev->phydev)
return -EOPNOTSUPP;
+ cmd->base.port = PORT_TP;
phy_ethtool_ksettings_get(netdev->phydev, cmd);
break;
default:
- netdev_warn(netdev,
- "Unknown port type, neither Fibre/Copper detected");
+
+ netdev_warn(netdev, "Unknown media type");
return 0;
}
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 12/12] net: hns3: Remove redundant hclge_get_port_type()
From: Salil Mehta @ 2018-09-21 15:41 UTC (permalink / raw)
To: davem
Cc: salil.mehta, yisen.zhuang, lipeng321, mehta.salil, netdev,
linux-kernel, linuxarm, Fuyun Liang
In-Reply-To: <20180921154148.26756-1-salil.mehta@huawei.com>
From: Peng Li <lipeng321@huawei.com>
This patch removes hclge_get_port_type which is redundant.
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 -
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 22 ----------------------
2 files changed, 23 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index fc87e1b..564afd4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -411,7 +411,6 @@ struct hnae3_ae_ops {
void (*get_link_mode)(struct hnae3_handle *handle,
unsigned long *supported,
unsigned long *advertising);
- void (*get_port_type)(struct hnae3_handle *handle, u8 *port_type);
};
struct hnae3_dcb_ops {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 73d9d0d..2de5a00 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5970,27 +5970,6 @@ static void hclge_get_link_mode(struct hnae3_handle *handle,
}
}
-static void hclge_get_port_type(struct hnae3_handle *handle,
- u8 *port_type)
-{
- struct hclge_vport *vport = hclge_get_vport(handle);
- struct hclge_dev *hdev = vport->back;
- u8 media_type = hdev->hw.mac.media_type;
-
- switch (media_type) {
- case HNAE3_MEDIA_TYPE_FIBER:
- *port_type = PORT_FIBRE;
- break;
- case HNAE3_MEDIA_TYPE_COPPER:
- *port_type = PORT_TP;
- break;
- case HNAE3_MEDIA_TYPE_UNKNOWN:
- default:
- *port_type = PORT_OTHER;
- break;
- }
-}
-
static const struct hnae3_ae_ops hclge_ops = {
.init_ae_dev = hclge_init_ae_dev,
.uninit_ae_dev = hclge_uninit_ae_dev,
@@ -6048,7 +6027,6 @@ static const struct hnae3_ae_ops hclge_ops = {
.get_regs = hclge_get_regs,
.set_led_id = hclge_set_led_id,
.get_link_mode = hclge_get_link_mode,
- .get_port_type = hclge_get_port_type,
};
static struct hnae3_ae_algo ae_algo = {
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net] ixgbe: check return value of napi_complete_done()
From: Eric Dumazet @ 2018-09-21 15:43 UTC (permalink / raw)
To: Alexei Starovoitov, Eric Dumazet, Song Liu
Cc: Jeff Kirsher, netdev, intel-wired-lan@lists.osuosl.org,
Kernel Team, stable@vger.kernel.org, Alexei Starovoitov
In-Reply-To: <d15e9eec-6236-af26-0eb5-84e7dc27b4d7@fb.com>
On 09/21/2018 08:14 AM, Alexei Starovoitov wrote:
> On 9/21/18 7:59 AM, Eric Dumazet wrote:
>>
>>
>> On 09/21/2018 07:55 AM, Alexei Starovoitov wrote:
>>
>>>
>>> should we remove ndo_poll_controller then?
>>> My understanding that the patch helps by not letting
>>> drivers do napi_schedule() for all queues into this_cpu, right?
>>> But most of the drivers do exactly that in their ndo_poll_controller
>>> implementations. Means most of the drivers will experience
>>> this nasty behavior.
>>>
>>
>> Some legacy drivers do not use NAPI yet, but provide ndo_poll_controller()
>>
>> I believe users caring about system behavior with multi queue NIC are
>> all using NAPI enabled drivers, so this should be fine.
>
> I'm not following.
> All modern napi enabled drivers need to _remove_ ndo_poll_controller
> from the driver. This is a lot of churn.
netpoll could skip calling ndo_poll_controller() if at least one NAPI
has been registered on the device.
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 57557a6a950cc9cdff959391576a03381d328c1a..149474c1ad71dde295d3a2b085ef51eb50278d81 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -189,7 +189,6 @@ static void poll_napi(struct net_device *dev)
static void netpoll_poll_dev(struct net_device *dev)
{
- const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
/* Don't do any rx activity if the dev_lock mutex is held
@@ -204,14 +203,12 @@ static void netpoll_poll_dev(struct net_device *dev)
return;
}
- ops = dev->netdev_ops;
- if (!ops->ndo_poll_controller) {
- up(&ni->dev_lock);
- return;
- }
+ if (list_empty(&dev->napi_list)) {
+ const struct net_device_ops *ops = dev->netdev_ops;
- /* Process pending work on NIC */
- ops->ndo_poll_controller(dev);
+ if (ops->ndo_poll_controller)
+ ops->ndo_poll_controller(dev);
+ }
poll_napi(dev);
But this looks a bit risky, I know some drivers use NAPI only for RX,
and conventional hard IRQ handler for TX completions.
Better be safe, and apply a small patch series, I can handle that, do not worry.
> Isn't it cleaner (less error prone) to introduce new ndo
> for legacy drivers without napi?
Not really, this is basically not doable, since no one of us can test this.
^ permalink raw reply related
* [PATCH ipsec] net: xfrm: pass constant family to nf_hook function
From: Florian Westphal @ 2018-09-21 10:35 UTC (permalink / raw)
To: netdev; +Cc: dsahern, Florian Westphal
Unfortunately some versions of gcc emit following warning:
linux/compiler.h:252:20: warning: array subscript is above array bounds [-Warray-bounds]
hook_head = rcu_dereference(net->nf.hooks_arp[hook]);
^~~~~~~~~~~~~~~~~~~~~
xfrm_output_resume passes non-const 'pf' argument so compiler can't know
that the affected statement above will never be executed (we only
pass either NFPROTO_IPV4 or NFPROTO_IPV6), this change makes this
explicit.
Another solution would be to increase hooks_arp[] size, but that
increases struct net size needlesly.
Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
David, i hope this will silence the warning, would be nice
if you could test it.
I don't really like this patch, but I see no better solution
expect needless increase of hooks_arp[].
Any other idea?
net/xfrm/xfrm_output.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 45ba07ab3e4f..199c0e782ac7 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -152,11 +152,24 @@ int xfrm_output_resume(struct sk_buff *skb, int err)
if (!skb_dst(skb)->xfrm)
return dst_output(net, skb->sk, skb);
- err = nf_hook(skb_dst(skb)->ops->family,
- NF_INET_POST_ROUTING, net, skb->sk, skb,
- NULL, skb_dst(skb)->dev, xfrm_output2);
- if (unlikely(err != 1))
- goto out;
+ switch (skb_dst(skb)->ops->family) {
+ case AF_INET:
+ err = nf_hook(NFPROTO_IPV4,
+ NF_INET_POST_ROUTING, net, skb->sk, skb,
+ NULL, skb_dst(skb)->dev, xfrm_output2);
+ if (unlikely(err != 1))
+ goto out;
+ break;
+ case AF_INET6:
+ err = nf_hook(NFPROTO_IPV6,
+ NF_INET_POST_ROUTING, net, skb->sk, skb,
+ NULL, skb_dst(skb)->dev, xfrm_output2);
+ if (unlikely(err != 1))
+ goto out;
+ break;
+ default:
+ break;
+ }
}
if (err == -EINPROGRESS)
--
2.16.4
^ permalink raw reply related
* [PATCH 2/2] net: if_arp: use define instead of hard-coded value
From: Håkon Bugge @ 2018-09-21 10:39 UTC (permalink / raw)
To: David S . Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI
Cc: linux-kernel, netdev
In-Reply-To: <20180921103930.1420679-1-Haakon.Bugge@oracle.com>
uapi/linux/if_arp.h includes linux/netdevice.h, which uses
IFNAMSIZ. Hence, use it instead of hard-coded value.
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
---
include/uapi/linux/if_arp.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h
index b68b4b3d9172..c3cc5a9e5eaf 100644
--- a/include/uapi/linux/if_arp.h
+++ b/include/uapi/linux/if_arp.h
@@ -118,7 +118,7 @@ struct arpreq {
struct sockaddr arp_ha; /* hardware address */
int arp_flags; /* flags */
struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
- char arp_dev[16];
+ char arp_dev[IFNAMSIZ];
};
struct arpreq_old {
--
2.14.3
^ permalink raw reply related
* [PATCH 1/2] net: if_arp: Fix incorrect indents
From: Håkon Bugge @ 2018-09-21 10:39 UTC (permalink / raw)
To: David S . Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI
Cc: linux-kernel, netdev
In-Reply-To: <20180921103930.1420679-1-Haakon.Bugge@oracle.com>
Fixing incorrect indents and align comments.
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
---
include/uapi/linux/if_arp.h | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h
index 4605527ca41b..b68b4b3d9172 100644
--- a/include/uapi/linux/if_arp.h
+++ b/include/uapi/linux/if_arp.h
@@ -114,18 +114,18 @@
/* ARP ioctl request. */
struct arpreq {
- struct sockaddr arp_pa; /* protocol address */
- struct sockaddr arp_ha; /* hardware address */
- int arp_flags; /* flags */
- struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
- char arp_dev[16];
+ struct sockaddr arp_pa; /* protocol address */
+ struct sockaddr arp_ha; /* hardware address */
+ int arp_flags; /* flags */
+ struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
+ char arp_dev[16];
};
struct arpreq_old {
- struct sockaddr arp_pa; /* protocol address */
- struct sockaddr arp_ha; /* hardware address */
- int arp_flags; /* flags */
- struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
+ struct sockaddr arp_pa; /* protocol address */
+ struct sockaddr arp_ha; /* hardware address */
+ int arp_flags; /* flags */
+ struct sockaddr arp_netmask; /* netmask (only for proxy arps) */
};
/* ARP Flag values. */
--
2.14.3
^ permalink raw reply related
* Re: [PATCH net] net: diag: Fix swapped src/dst in udp_dump_one.
From: Lorenzo Colitti @ 2018-09-21 10:46 UTC (permalink / raw)
To: David Miller
Cc: netdev, Maciej Żenczykowski, David Ahern,
Jeffrey Vander Stoep
In-Reply-To: <20180914.083038.452831271321088318.davem@davemloft.net>
On Fri, Sep 14, 2018 at 11:30 PM David Miller <davem@davemloft.net> wrote:
> Unfortunately I think we are stuck with how things are now.
>
> Indisputably, your patch breaks userland components that have
> workarounds in order to work with existing kernels. [...]
> I cannot apply this, sorry.
Understood. We're about to start using this UDP codepath on Android,
so I wanted to see if this would be fixed before we commit to the
current behaviour in our conformance tests, at which point we won't
ever be able to change it either.
Would you take a patch to add a one-line comment saying that this is
the way it is for backwards compatibility? If that comment were there
anyone else who finds this will not spend time debugging it and
immediately know what's going on. The fact that the ports are inverted
is not easy to spot on casual inspection.
^ permalink raw reply
* Re: [PATCH net-next] cxgb4vf: Add ethtool private flags for changing force_link_up
From: Arjun Vynipadath @ 2018-09-21 10:46 UTC (permalink / raw)
To: Jakub Kicinski
Cc: netdev, davem, dt, nirranjan, indranil, Casey Leedom,
Ganesh Goudar
In-Reply-To: <20180918113914.58811ecf@cakuba.netronome.com>
On Tuesday, September 09/18/18, 2018 at 11:39:14 -0700, Jakub Kicinski wrote:
> On Tue, 18 Sep 2018 18:37:23 +0530, Arjun Vynipadath wrote:
> > Forcing link up of virtual interfaces even when physical link is down
> > causes packet drops and ping failures during bonding failover. Hence
> > adding a ethtool private flag to toggle force_link_up whenever required.
> >
> > Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
> > Signed-off-by: Casey Leedom <leedom@chelsio.com>
> > Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
>
> Could you describe how this mechanism relates to the existing
> ndo_set_vf_link_state, which you seem to not make use of:
>
> $ git grep ndo_set_vf_link_state -- drivers/net/ethernet/chelsio/
> $
>
> I understand you're configuring the setting from the VF side, but the
> question, as always, is: why ;)
Hi Jakub,
ndo_set_vf_link_state can't be presently used in our case.
We dont have firmware support to communicate the link flags set through
ndo_set_vf_link_state from pf (cxgb4) driver to vf (cxgb4vf) driver.
Thanks,
Arjun.
^ permalink raw reply
* [PATCH net-next V2 0/2] net/sched: Add hardware specific counters to TC actions
From: Eelco Chaudron @ 2018-09-21 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, jiri, xiyou.wangcong, jhs, jakub.kicinski
Add hardware specific counters to TC actions which will be exported
through the netlink API. This makes troubleshooting TC flower offload
easier, as it possible to differentiate the packets being offloaded.
Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
v2 - Rebased on latest net-next
Eelco Chaudron (2):
net/core: Add new basic hardware counter
net/sched: Add hardware specific counters to TC actions
include/net/act_api.h | 8 +++-
include/net/gen_stats.h | 4 ++
include/net/pkt_cls.h | 2 +
include/uapi/linux/gen_stats.h | 1 +
net/core/gen_stats.c | 73 ++++++++++++++++++++++++++++++----------
net/sched/act_api.c | 14 ++++++--
net/sched/act_gact.c | 6 +++
net/sched/act_mirred.c | 5 ++-
8 files changed, 85 insertions(+), 28 deletions(-)
^ permalink raw reply
* [PATCH net-next V2 1/2] net/core: Add new basic hardware counter
From: Eelco Chaudron @ 2018-09-21 11:13 UTC (permalink / raw)
To: netdev; +Cc: davem, jiri, xiyou.wangcong, jhs, jakub.kicinski
In-Reply-To: <20180921111330.3532.29886.stgit@wsfd-netdev20.ntdv.lab.eng.bos.redhat.com>
Add a new hardware specific basic counter, TCA_STATS_BASIC_HW. This can
be used to count packets/bytes processed by hardware offload.
Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
---
include/net/gen_stats.h | 4 ++
include/uapi/linux/gen_stats.h | 1 +
net/core/gen_stats.c | 73 ++++++++++++++++++++++++++++++----------
3 files changed, 59 insertions(+), 19 deletions(-)
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 883bb90..946bd53 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -44,6 +44,10 @@ void __gnet_stats_copy_basic(const seqcount_t *running,
struct gnet_stats_basic_packed *bstats,
struct gnet_stats_basic_cpu __percpu *cpu,
struct gnet_stats_basic_packed *b);
+int gnet_stats_copy_basic_hw(const seqcount_t *running,
+ struct gnet_dump *d,
+ struct gnet_stats_basic_cpu __percpu *cpu,
+ struct gnet_stats_basic_packed *b);
int gnet_stats_copy_rate_est(struct gnet_dump *d,
struct net_rate_estimator __rcu **ptr);
int gnet_stats_copy_queue(struct gnet_dump *d,
diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h
index 24a861c..065408e 100644
--- a/include/uapi/linux/gen_stats.h
+++ b/include/uapi/linux/gen_stats.h
@@ -12,6 +12,7 @@ enum {
TCA_STATS_APP,
TCA_STATS_RATE_EST64,
TCA_STATS_PAD,
+ TCA_STATS_BASIC_HW,
__TCA_STATS_MAX,
};
#define TCA_STATS_MAX (__TCA_STATS_MAX - 1)
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 188d693..65a2e82 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -162,30 +162,18 @@
}
EXPORT_SYMBOL(__gnet_stats_copy_basic);
-/**
- * gnet_stats_copy_basic - copy basic statistics into statistic TLV
- * @running: seqcount_t pointer
- * @d: dumping handle
- * @cpu: copy statistic per cpu
- * @b: basic statistics
- *
- * Appends the basic statistics to the top level TLV created by
- * gnet_stats_start_copy().
- *
- * Returns 0 on success or -1 with the statistic lock released
- * if the room in the socket buffer was not sufficient.
- */
int
-gnet_stats_copy_basic(const seqcount_t *running,
- struct gnet_dump *d,
- struct gnet_stats_basic_cpu __percpu *cpu,
- struct gnet_stats_basic_packed *b)
+___gnet_stats_copy_basic(const seqcount_t *running,
+ struct gnet_dump *d,
+ struct gnet_stats_basic_cpu __percpu *cpu,
+ struct gnet_stats_basic_packed *b,
+ int type)
{
struct gnet_stats_basic_packed bstats = {0};
__gnet_stats_copy_basic(running, &bstats, cpu, b);
- if (d->compat_tc_stats) {
+ if (d->compat_tc_stats && type == TCA_STATS_BASIC) {
d->tc_stats.bytes = bstats.bytes;
d->tc_stats.packets = bstats.packets;
}
@@ -196,14 +184,61 @@
memset(&sb, 0, sizeof(sb));
sb.bytes = bstats.bytes;
sb.packets = bstats.packets;
- return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb),
+ return gnet_stats_copy(d, type, &sb, sizeof(sb),
TCA_STATS_PAD);
}
return 0;
}
+
+/**
+ * gnet_stats_copy_basic - copy basic statistics into statistic TLV
+ * @running: seqcount_t pointer
+ * @d: dumping handle
+ * @cpu: copy statistic per cpu
+ * @b: basic statistics
+ *
+ * Appends the basic statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_basic(const seqcount_t *running,
+ struct gnet_dump *d,
+ struct gnet_stats_basic_cpu __percpu *cpu,
+ struct gnet_stats_basic_packed *b)
+{
+ return ___gnet_stats_copy_basic(running, d, cpu, b,
+ TCA_STATS_BASIC);
+}
EXPORT_SYMBOL(gnet_stats_copy_basic);
/**
+ * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV
+ * @running: seqcount_t pointer
+ * @d: dumping handle
+ * @cpu: copy statistic per cpu
+ * @b: basic statistics
+ *
+ * Appends the basic statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_basic_hw(const seqcount_t *running,
+ struct gnet_dump *d,
+ struct gnet_stats_basic_cpu __percpu *cpu,
+ struct gnet_stats_basic_packed *b)
+{
+ return ___gnet_stats_copy_basic(running, d, cpu, b,
+ TCA_STATS_BASIC_HW);
+}
+EXPORT_SYMBOL(gnet_stats_copy_basic_hw);
+
+/**
* gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
* @d: dumping handle
* @rate_est: rate estimator
^ permalink raw reply related
* [PATCH net-next V2 2/2] net/sched: Add hardware specific counters to TC actions
From: Eelco Chaudron @ 2018-09-21 11:14 UTC (permalink / raw)
To: netdev; +Cc: davem, jiri, xiyou.wangcong, jhs, jakub.kicinski
In-Reply-To: <20180921111330.3532.29886.stgit@wsfd-netdev20.ntdv.lab.eng.bos.redhat.com>
Add additional counters that will store the bytes/packets processed by
hardware. These will be exported through the netlink interface for
displaying by the iproute2 tc tool
Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
---
include/net/act_api.h | 8 +++++---
include/net/pkt_cls.h | 2 +-
net/sched/act_api.c | 14 +++++++++++---
net/sched/act_gact.c | 6 +++++-
net/sched/act_mirred.c | 5 ++++-
5 files changed, 26 insertions(+), 9 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index c6f195b..1ddff33 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -31,10 +31,12 @@ struct tc_action {
int tcfa_action;
struct tcf_t tcfa_tm;
struct gnet_stats_basic_packed tcfa_bstats;
+ struct gnet_stats_basic_packed tcfa_bstats_hw;
struct gnet_stats_queue tcfa_qstats;
struct net_rate_estimator __rcu *tcfa_rate_est;
spinlock_t tcfa_lock;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+ struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw;
struct gnet_stats_queue __percpu *cpu_qstats;
struct tc_cookie __rcu *act_cookie;
struct tcf_chain *goto_chain;
@@ -94,7 +96,7 @@ struct tc_action_ops {
struct netlink_callback *, int,
const struct tc_action_ops *,
struct netlink_ext_ack *);
- void (*stats_update)(struct tc_action *, u64, u32, u64);
+ void (*stats_update)(struct tc_action *, u64, u32, u64, bool);
size_t (*get_fill_size)(const struct tc_action *act);
struct net_device *(*get_dev)(const struct tc_action *a);
void (*put_dev)(struct net_device *dev);
@@ -182,13 +184,13 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
- u64 packets, u64 lastuse)
+ u64 packets, u64 lastuse, bool hw)
{
#ifdef CONFIG_NET_CLS_ACT
if (!a->ops->stats_update)
return;
- a->ops->stats_update(a, bytes, packets, lastuse);
+ a->ops->stats_update(a, bytes, packets, lastuse, hw);
#endif
}
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 75a3f3f..bbfe27f 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -318,7 +318,7 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts)
for (i = 0; i < exts->nr_actions; i++) {
struct tc_action *a = exts->actions[i];
- tcf_action_stats_update(a, bytes, packets, lastuse);
+ tcf_action_stats_update(a, bytes, packets, lastuse, true);
}
preempt_enable();
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 6f118d6..1acd3a8 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -81,6 +81,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
static void free_tcf(struct tc_action *p)
{
free_percpu(p->cpu_bstats);
+ free_percpu(p->cpu_bstats_hw);
free_percpu(p->cpu_qstats);
tcf_set_action_cookie(&p->act_cookie, NULL);
@@ -372,9 +373,12 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
if (!p->cpu_bstats)
goto err1;
+ p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
+ if (!p->cpu_bstats_hw)
+ goto err2;
p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
if (!p->cpu_qstats)
- goto err2;
+ goto err3;
}
spin_lock_init(&p->tcfa_lock);
p->tcfa_index = index;
@@ -386,15 +390,17 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
&p->tcfa_rate_est,
&p->tcfa_lock, NULL, est);
if (err)
- goto err3;
+ goto err4;
}
p->idrinfo = idrinfo;
p->ops = ops;
*a = p;
return 0;
-err3:
+err4:
free_percpu(p->cpu_qstats);
+err3:
+ free_percpu(p->cpu_bstats_hw);
err2:
free_percpu(p->cpu_bstats);
err1:
@@ -979,6 +985,8 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
goto errout;
if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 ||
+ gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw,
+ &p->tcfa_bstats_hw) < 0 ||
gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 ||
gnet_stats_copy_queue(&d, p->cpu_qstats,
&p->tcfa_qstats,
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index aa44d14..c89a7fa 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -157,7 +157,7 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
}
static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
- u64 lastuse)
+ u64 lastuse, bool hw)
{
struct tcf_gact *gact = to_gact(a);
int action = READ_ONCE(gact->tcf_action);
@@ -168,6 +168,10 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
if (action == TC_ACT_SHOT)
this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;
+ if (hw)
+ _bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats_hw),
+ bytes, packets);
+
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a9d64bf..1dae5f2 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -283,12 +283,15 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
}
static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
- u64 lastuse)
+ u64 lastuse, bool hw)
{
struct tcf_mirred *m = to_mirred(a);
struct tcf_t *tm = &m->tcf_tm;
_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+ if (hw)
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+ bytes, packets);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
^ permalink raw reply related
* Re: [PATCH 0/2] net/sched: Add hardware specific counters to TC actions
From: Eelco Chaudron @ 2018-09-21 11:14 UTC (permalink / raw)
To: Jakub Kicinski
Cc: David Miller, netdev, jhs, xiyou.wangcong, jiri, simon.horman,
Marcelo Ricardo Leitner, louis.peens, Paolo, Davide Caratti
In-Reply-To: <20180920071415.6ff73da6@cakuba.netronome.com>
On 20 Sep 2018, at 16:14, Jakub Kicinski wrote:
> On Thu, 20 Sep 2018 09:14:08 +0200, Eelco Chaudron wrote:
>> Is there anything else blocking from getting this into net-next?
>>
>> I still think this patch is beneficial for the full user experience, and
>> I’ve got requests from QA and others for this.
>
> Not from my perspective, the numbers look okay, feel free to repost!
Thanks, I sent out a v2 re-based on the latest net-next.
^ permalink raw reply
* Re: Regression caused by commit 7bb05b85bc2d ("r8169: don't use MSI-X on RTL8106e")
From: Andy Shevchenko @ 2018-09-21 17:08 UTC (permalink / raw)
To: Jian-Hong Pan
Cc: Kai-Heng Feng, Heiner Kallweit, Thomas Gleixner, netdev,
Linux Kernel Mailing List, Linux Upstreaming Team, Daniel Drake,
steved424
In-Reply-To: <CAPpJ_edB_G5QPj-by9Y6Zjj36Xm9dmKXy8Kv5gXMf4YfybvuwA@mail.gmail.com>
On Thu, Sep 13, 2018 at 8:53 AM Jian-Hong Pan <jian-hong@endlessm.com> wrote:
>
> 2018-09-12 16:19 GMT+08:00 Kai-Heng Feng <kai.heng.feng@canonical.com>:
> > at 14:32, Thomas Gleixner <tglx@linutronix.de> wrote:
> >
> >> On Wed, 12 Sep 2018, Kai-Heng Feng wrote:
> >>
> >>> There's a Dell machine with RTL8106e stops to work after S3 since the
> >>> commit introduced. So I am wondering if it's possible to revert the
> >>> commit and use DMI/subsystem id based quirk table?
> >>
> >>
> >> Probably.
Have you seen this thread:
https://patchwork.ozlabs.org/cover/968924/
and this one:
https://patchwork.kernel.org/patch/10583229/
?
> >
> >
> > Hopefully Jian-Hong can cook up a quirk table for the issue.
>
> Module r8169 gets nothing in the PCI BAR after system resumes which
> makes MSI-X fail on some ASUS laptops equipped with RTL8106e chip.
> https://www.spinics.net/lists/linux-pci/msg75598.html
>
> Actually, I am waiting for the patch "PCI: Reprogram bridge prefetch
> registers on resume" being merged.
> https://marc.info/?l=linux-pm&m=153680987814299&w=2
>
> It resolves the drivers which get nothing in PCI BAR after system resumes.
>
> After that, I can remove the falling back code of RTL8106e.
>
> Heiner, any comment?
>
> Regards,
> Jian-Hong Pan
>
> >>
> >>> It's because of commit bc976233a872 ("genirq/msi, x86/vector: Prevent
> >>> reservation mode for non maskable MSI") cleared the reservation mode, and
> >>> I
> >>> can see this after S3:
> >>>
> >>> [ 94.872838] do_IRQ: 3.33 No irq handler for vector
> >>
> >>
> >> It's not because of that commit, really. There is a interrupt sent after
> >> resume to the wrong vector for whatever reason. The MSI vector cannot be
> >> masked it seems in the device, but the driver should quiescen the device
> >> to
> >> a point where it does not send interrupts.
> >
> >
> > Understood.
> >
> >>
> >>> If the device uses MSI-X instead of MSI, the issue doesn't happen because
> >>> of
> >>> reservation mode.
> >>
> >>
> >> Reservation mode has absolutely nothing to do with that. What prevents the
> >> issue is the fact that MSI-X can be masked by the IRQ core.
> >
> >
> > So in this case I think keep the device using MSI-X is a better route, it's
> > MSI-X capable anyway.
> >
> >>
> >>> Is it something should be handled by x86 BIOS? Because I don't see this
> >>> issue
> >>> when I use Suspend-to-Idle, which doesn't use BIOS to do suspend.
> >>
> >>
> >> Suspend to idle works completely different and I don't see the BIOS at
> >> fault here. it's more an issue of MSI not being maskable on that device,
> >> which can't be fixed in BIOS or it's some half quiescened state which is
> >> used when suspending and that's a pure driver issue.
> >
> >
> > Understood.
> > Thanks for all the info!
> >
> > Kai-Heng
> >
> >>
> >> Thanks,
> >>
> >> tglx
> >
> >
> >
--
With Best Regards,
Andy Shevchenko
^ permalink raw reply
* [PATCH bpf-next 2/9] bpf: rework cgroup storage pointer passing
From: Roman Gushchin @ 2018-09-21 17:14 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Kernel Team, Roman Gushchin,
Daniel Borkmann, Alexei Starovoitov
In-Reply-To: <20180921171353.11050-1-guro@fb.com>
To simplify the following introduction of per-cpu cgroup storage,
let's rework a bit a mechanism of passing a pointer to a cgroup
storage into the bpf_get_local_storage(). Let's save a pointer
to the corresponding bpf_cgroup_storage structure, instead of
a pointer to the actual buffer.
It will help us to handle per-cpu storage later, which has
a different way of accessing to the actual data.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf-cgroup.h | 13 ++++---------
kernel/bpf/helpers.c | 8 ++++++--
kernel/bpf/local_storage.c | 3 ++-
3 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index e9871b012dac..7e0c9a1d48b7 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -23,7 +23,8 @@ struct bpf_cgroup_storage;
extern struct static_key_false cgroup_bpf_enabled_key;
#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
-DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
+DECLARE_PER_CPU(struct bpf_cgroup_storage*,
+ bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
#define for_each_cgroup_storage_type(stype) \
for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++)
@@ -115,15 +116,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage
*storage[MAX_BPF_CGROUP_STORAGE_TYPE])
{
enum bpf_cgroup_storage_type stype;
- struct bpf_storage_buffer *buf;
-
- for_each_cgroup_storage_type(stype) {
- if (!storage[stype])
- continue;
- buf = READ_ONCE(storage[stype]->buf);
- this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]);
- }
+ for_each_cgroup_storage_type(stype)
+ this_cpu_write(bpf_cgroup_storage[stype], storage[stype]);
}
struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9070b2ace6aa..e42f8789b7ea 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -195,7 +195,8 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
};
#ifdef CONFIG_CGROUP_BPF
-DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
+DECLARE_PER_CPU(struct bpf_cgroup_storage*,
+ bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
{
@@ -204,8 +205,11 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
* verifier checks that its value is correct.
*/
enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
+ struct bpf_cgroup_storage *storage;
- return (unsigned long) this_cpu_read(bpf_cgroup_storage[stype]);
+ storage = this_cpu_read(bpf_cgroup_storage[stype]);
+
+ return (unsigned long)&READ_ONCE(storage->buf)->data[0];
}
const struct bpf_func_proto bpf_get_local_storage_proto = {
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 0bd9f19fc557..6742292fb39e 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -7,7 +7,8 @@
#include <linux/rbtree.h>
#include <linux/slab.h>
-DEFINE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
+DEFINE_PER_CPU(struct bpf_cgroup_storage*,
+ bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
#ifdef CONFIG_CGROUP_BPF
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next 3/9] bpf: introduce per-cpu cgroup local storage
From: Roman Gushchin @ 2018-09-21 17:14 UTC (permalink / raw)
To: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Kernel Team, Roman Gushchin,
Daniel Borkmann, Alexei Starovoitov
In-Reply-To: <20180921171353.11050-1-guro@fb.com>
This commit introduced per-cpu cgroup local storage.
Per-cpu cgroup local storage is very similar to simple cgroup storage
(let's call it shared), except all the data is per-cpu.
The main goal of per-cpu variant is to implement super fast
counters (e.g. packet counters), which don't require neither
lookups, neither atomic operations.
>From userspace's point of view, accessing a per-cpu cgroup storage
is similar to other per-cpu map types (e.g. per-cpu hashmaps and
arrays).
Writing to a per-cpu cgroup storage is not atomic, but is performed
by copying longs, so some minimal atomicity is here, exactly
as with other per-cpu maps.
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf-cgroup.h | 20 ++++-
include/linux/bpf.h | 1 +
include/linux/bpf_types.h | 1 +
include/uapi/linux/bpf.h | 1 +
kernel/bpf/helpers.c | 8 +-
kernel/bpf/local_storage.c | 148 ++++++++++++++++++++++++++++++++-----
kernel/bpf/syscall.c | 11 ++-
kernel/bpf/verifier.c | 15 +++-
8 files changed, 177 insertions(+), 28 deletions(-)
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 7e0c9a1d48b7..9bd907657f9b 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -37,7 +37,10 @@ struct bpf_storage_buffer {
};
struct bpf_cgroup_storage {
- struct bpf_storage_buffer *buf;
+ union {
+ struct bpf_storage_buffer *buf;
+ char __percpu *percpu_buf;
+ };
struct bpf_cgroup_storage_map *map;
struct bpf_cgroup_storage_key key;
struct list_head list;
@@ -109,6 +112,9 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
static inline enum bpf_cgroup_storage_type cgroup_storage_type(
struct bpf_map *map)
{
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
+ return BPF_CGROUP_STORAGE_PERCPU;
+
return BPF_CGROUP_STORAGE_SHARED;
}
@@ -131,6 +137,10 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map);
void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map);
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
+ void *value, u64 flags);
+
/* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
#define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \
({ \
@@ -285,6 +295,14 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; }
static inline void bpf_cgroup_storage_free(
struct bpf_cgroup_storage *storage) {}
+static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key,
+ void *value) {
+ return 0;
+}
+static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
+ void *key, void *value, u64 flags) {
+ return 0;
+}
#define cgroup_bpf_enabled (0)
#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b457fbe7b70b..018299a595c8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -274,6 +274,7 @@ struct bpf_prog_offload {
enum bpf_cgroup_storage_type {
BPF_CGROUP_STORAGE_SHARED,
+ BPF_CGROUP_STORAGE_PERCPU,
__BPF_CGROUP_STORAGE_MAX
};
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index c9bd6fb765b0..5432f4c9f50e 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -43,6 +43,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
#endif
#ifdef CONFIG_CGROUP_BPF
BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, cgroup_storage_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index aa5ccd2385ed..e2070d819e04 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -127,6 +127,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_SOCKHASH,
BPF_MAP_TYPE_CGROUP_STORAGE,
BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
};
enum bpf_prog_type {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index e42f8789b7ea..1f21ef1c4ad3 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -206,10 +206,16 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
*/
enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
struct bpf_cgroup_storage *storage;
+ void *ptr = NULL;
storage = this_cpu_read(bpf_cgroup_storage[stype]);
- return (unsigned long)&READ_ONCE(storage->buf)->data[0];
+ if (stype == BPF_CGROUP_STORAGE_SHARED)
+ ptr = &READ_ONCE(storage->buf)->data[0];
+ else
+ ptr = this_cpu_ptr(storage->percpu_buf);
+
+ return (unsigned long)ptr;
}
const struct bpf_func_proto bpf_get_local_storage_proto = {
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 6742292fb39e..d991355b5b46 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -152,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return 0;
}
+int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
+ void *value)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ int cpu, off = 0;
+ u32 size;
+
+ rcu_read_lock();
+ storage = cgroup_storage_lookup(map, key, false);
+ if (!storage) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
+
+ /* per_cpu areas are zero-filled and bpf programs can only
+ * access 'value_size' of them, so copying rounded areas
+ * will not leak any kernel data
+ */
+ size = round_up(_map->value_size, 8);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off,
+ per_cpu_ptr(storage->percpu_buf, cpu), size);
+ off += size;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
+int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
+ void *value, u64 map_flags)
+{
+ struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ int cpu, off = 0;
+ u32 size;
+
+ if (unlikely(map_flags & BPF_EXIST))
+ return -EINVAL;
+
+ rcu_read_lock();
+ storage = cgroup_storage_lookup(map, key, false);
+ if (!storage) {
+ rcu_read_unlock();
+ return -ENOENT;
+ }
+
+ /* the user space will provide round_up(value_size, 8) bytes that
+ * will be copied into per-cpu area. bpf programs can only access
+ * value_size of it. During lookup the same extra bytes will be
+ * returned or zeros which were zero-filled by percpu_alloc,
+ * so no kernel data leaks possible
+ */
+ size = round_up(_map->value_size, 8);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
+ value + off, size);
+ off += size;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
void *_next_key)
{
@@ -292,55 +357,98 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
{
struct bpf_cgroup_storage *storage;
struct bpf_map *map;
+ gfp_t flags;
+ size_t size;
u32 pages;
map = prog->aux->cgroup_storage[stype];
if (!map)
return NULL;
- pages = round_up(sizeof(struct bpf_cgroup_storage) +
- sizeof(struct bpf_storage_buffer) +
- map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ if (stype == BPF_CGROUP_STORAGE_SHARED) {
+ size = sizeof(struct bpf_storage_buffer) + map->value_size;
+ pages = round_up(sizeof(struct bpf_cgroup_storage) + size,
+ PAGE_SIZE) >> PAGE_SHIFT;
+ } else {
+ size = map->value_size;
+ pages = round_up(round_up(size, 8) * num_possible_cpus(),
+ PAGE_SIZE) >> PAGE_SHIFT;
+ }
+
if (bpf_map_charge_memlock(map, pages))
return ERR_PTR(-EPERM);
storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
__GFP_ZERO | GFP_USER, map->numa_node);
- if (!storage) {
- bpf_map_uncharge_memlock(map, pages);
- return ERR_PTR(-ENOMEM);
- }
+ if (!storage)
+ goto enomem;
- storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
- map->value_size, __GFP_ZERO | GFP_USER,
- map->numa_node);
- if (!storage->buf) {
- bpf_map_uncharge_memlock(map, pages);
- kfree(storage);
- return ERR_PTR(-ENOMEM);
+ flags = __GFP_ZERO | GFP_USER;
+
+ if (stype == BPF_CGROUP_STORAGE_SHARED) {
+ storage->buf = kmalloc_node(size, flags, map->numa_node);
+ if (!storage->buf)
+ goto enomem;
+ } else {
+ storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags);
+ if (!storage->percpu_buf)
+ goto enomem;
}
storage->map = (struct bpf_cgroup_storage_map *)map;
return storage;
+
+enomem:
+ bpf_map_uncharge_memlock(map, pages);
+ kfree(storage);
+ return ERR_PTR(-ENOMEM);
+}
+
+static void free_cgroup_storage_rcu(struct rcu_head *rcu)
+{
+ struct bpf_cgroup_storage *storage =
+ container_of(rcu, struct bpf_cgroup_storage, rcu);
+
+ kfree(storage->buf);
+ kfree(storage);
+}
+
+static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu)
+{
+ struct bpf_cgroup_storage *storage =
+ container_of(rcu, struct bpf_cgroup_storage, rcu);
+
+ free_percpu(storage->percpu_buf);
+ kfree(storage);
}
void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
{
- u32 pages;
+ enum bpf_cgroup_storage_type stype;
struct bpf_map *map;
+ u32 pages;
if (!storage)
return;
map = &storage->map->map;
- pages = round_up(sizeof(struct bpf_cgroup_storage) +
- sizeof(struct bpf_storage_buffer) +
- map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ stype = cgroup_storage_type(map);
+ if (stype == BPF_CGROUP_STORAGE_SHARED)
+ pages = round_up(sizeof(struct bpf_cgroup_storage) +
+ sizeof(struct bpf_storage_buffer) +
+ map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+ else
+ pages = round_up(round_up(map->value_size, 8) *
+ num_possible_cpus(),
+ PAGE_SIZE) >> PAGE_SHIFT;
+
bpf_map_uncharge_memlock(map, pages);
- kfree_rcu(storage->buf, rcu);
- kfree_rcu(storage, rcu);
+ if (stype == BPF_CGROUP_STORAGE_SHARED)
+ call_rcu(&storage->rcu, free_cgroup_storage_rcu);
+ else
+ call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu);
}
void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8c91d2b41b1e..5742df21598c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -686,7 +686,8 @@ static int map_lookup_elem(union bpf_attr *attr)
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
value_size = sizeof(u32);
@@ -705,6 +706,8 @@ static int map_lookup_elem(union bpf_attr *attr)
err = bpf_percpu_hash_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
err = bpf_stackmap_copy(map, key, value);
} else if (IS_FD_ARRAY(map)) {
@@ -774,7 +777,8 @@ static int map_update_elem(union bpf_attr *attr)
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
- map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else
value_size = map->value_size;
@@ -809,6 +813,9 @@ static int map_update_elem(union bpf_attr *attr)
err = bpf_percpu_hash_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, attr->flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
+ err = bpf_percpu_cgroup_storage_update(map, key, value,
+ attr->flags);
} else if (IS_FD_ARRAY(map)) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e75f36de91d6..d94073deb68a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2074,6 +2074,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
goto error;
break;
case BPF_MAP_TYPE_CGROUP_STORAGE:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
if (func_id != BPF_FUNC_get_local_storage)
goto error;
break;
@@ -2164,7 +2165,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
goto error;
break;
case BPF_FUNC_get_local_storage:
- if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
goto error;
break;
case BPF_FUNC_sk_select_reuseport:
@@ -5049,6 +5051,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
return 0;
}
+static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
+{
+ return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+}
+
/* look for pseudo eBPF instructions that access map FDs and
* replace them with actual map pointers
*/
@@ -5139,10 +5147,9 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
}
env->used_maps[env->used_map_cnt++] = map;
- if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
+ if (bpf_map_is_cgroup_storage(map) &&
bpf_cgroup_storage_assign(env->prog, map)) {
- verbose(env,
- "only one cgroup storage is allowed\n");
+ verbose(env, "only one cgroup storage of each type is allowed\n");
fdput(f);
return -EBUSY;
}
--
2.17.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox