merge-upstream/v5.4.68 from branch/tag: upstream/v5.4.68 into branch: cos-5.4
Changelog:
-------------------------------------------------------------
Cong Wang (1):
act_ife: load meta modules before tcf_idr_check_alloc()
Dan Carpenter (1):
hdlc_ppp: add range checks in ppp_cp_parse_cr()
David Ahern (2):
ipv4: Initialize flowi4_multipath_hash in data path
ipv4: Update exception handling for multipath routes via same device
Edwin Peer (1):
bnxt_en: return proper error codes in bnxt_show_temp
Eric Dumazet (3):
ipv6: avoid lockdep issue in fib6_del()
net: qrtr: check skb_put_padto() return value
net: add __must_check to skb_put_padto()
Florian Fainelli (2):
net: phy: Avoid NPD upon phy_detach() when driver is unbound
net: phy: Do not warn in phy_stop() on PHY_DOWN
Ganji Aravind (1):
cxgb4: Fix offset when clearing filter byte counters
Greg Kroah-Hartman (1):
Linux 5.4.68
Hauke Mehrtens (4):
net: lantiq: Wake TX queue again
net: lantiq: use netif_tx_napi_add() for TX NAPI
net: lantiq: Use napi_complete_done()
net: lantiq: Disable IRQs only if NAPI gets scheduled
Henry Ptasinski (1):
net: sctp: Fix IPv6 ancestor_size calc in sctp_copy_descendant
Ido Schimmel (1):
net: Fix bridge enslavement failure
Jakub Kicinski (2):
ibmvnic: add missing parenthesis in do_reset()
nfp: use correct define to return NONE fec
Linus Walleij (1):
net: dsa: rtl8366: Properly clear member config
Maor Dickman (1):
net/mlx5e: Enable adding peer miss rules only if merged eswitch is supported
Maor Gottlieb (1):
net/mlx5: Fix FTE cleanup
Mark Gray (1):
geneve: add transport ports in route lookup for geneve
Mark Salyzyn (1):
af_key: pfkey_dump needs parameter validation
Michael Chan (1):
bnxt_en: Protect bnxt_set_eee() and bnxt_set_pauseparam() with mutex.
Mingming Cao (1):
ibmvnic fix NULL tx_pools and rx_tools issue at do_reset
Muchun Song (1):
kprobes: fix kill kprobe which has been marked as gone
Necip Fazil Yildiran (1):
net: ipv6: fix kconfig dependency warning for IPV6_SEG6_HMAC
Peilin Ye (1):
tipc: Fix memory leak in tipc_group_create_member()
Petr Machata (1):
net: DCB: Validate DCB_ATTR_DCB_BUFFER argument
Raju Rangoju (1):
cxgb4: fix memory leak during module unload
Ralph Campbell (1):
mm/thp: fix __split_huge_pmd_locked() for migration PMD
Suravee Suthikulpanit (1):
iommu/amd: Use cmpxchg_double() when updating 128-bit IRTE
Tariq Toukan (1):
net/mlx5e: TLS, Do not expose FPGA TLS counter if not supported
Tetsuo Handa (1):
tipc: fix shutdown() of connection oriented socket
Vasundhara Volam (2):
bnxt_en: Avoid sending firmware messages when AER error is detected.
bnxt_en: Fix NULL ptr dereference crash in bnxt_fw_reset_task()
Vinicius Costa Gomes (1):
taprio: Fix allowing too small intervals
Vladimir Oltean (1):
net: bridge: br_vlan_get_pvid_rcu() should dereference the VLAN group under RCU
Wei Wang (1):
ip: fix tos reflection in ack and reset packets
Xin Long (1):
tipc: use skb_unshare() instead in tipc_buf_append()
Xunlei Pang (1):
mm: memcg: fix memcg reclaim soft lockup
Yunsheng Lin (1):
net: sch_generic: aviod concurrent reset and enqueue op for lockless qdisc
BUG=b/169503032
TEST=tryjob, validation and K8s e2e
RELEASE_NOTE=Updated the Linux kernel to upstream/v5.4.68.
Signed-off-by: COS Kernel Merge Bot <cloud-image-merge-automation@prod.google.com>
Change-Id: I55ffedd714fef8cfc824efca51403d51b77b1276
diff --git a/Makefile b/Makefile
index d2e46ca..acb2499 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 5
PATCHLEVEL = 4
-SUBLEVEL = 67
+SUBLEVEL = 68
EXTRAVERSION =
NAME = Kleptomaniac Octopus
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 390568a..fc0160e 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -138,7 +138,7 @@
select PCI_PASID
select IOMMU_API
select IOMMU_IOVA
- depends on X86_64 && PCI && ACPI
+ depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
---help---
With this option you can enable support for AMD IOMMU hardware in
your system. An IOMMU is a hardware component which provides
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index fa91d85..7b724f7 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3873,6 +3873,7 @@
static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
struct amd_ir_data *data)
{
+ bool ret;
struct irq_remap_table *table;
struct amd_iommu *iommu;
unsigned long flags;
@@ -3890,10 +3891,18 @@
entry = (struct irte_ga *)table->table;
entry = &entry[index];
- entry->lo.fields_remap.valid = 0;
- entry->hi.val = irte->hi.val;
- entry->lo.val = irte->lo.val;
- entry->lo.fields_remap.valid = 1;
+
+ ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+ entry->lo.val, entry->hi.val,
+ irte->lo.val, irte->hi.val);
+ /*
+ * We use cmpxchg16 to atomically update the 128-bit IRTE,
+ * and it cannot be updated by the hardware or other processors
+ * behind us, so the return value of cmpxchg16 should be the
+ * same as the old value.
+ */
+ WARN_ON(!ret);
+
if (data)
data->ref = entry;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 135ae52..31d7e2d 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1522,7 +1522,14 @@
iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
else
iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
- if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+
+ /*
+ * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+ * GAM also requires GA mode. Therefore, we need to
+ * check cmpxchg16b support before enabling it.
+ */
+ if (!boot_cpu_has(X86_FEATURE_CX16) ||
+ ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
break;
case 0x11:
@@ -1531,8 +1538,18 @@
iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
else
iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
- if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+
+ /*
+ * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+ * XT, GAM also requires GA mode. Therefore, we need to
+ * check cmpxchg16b support before enabling them.
+ */
+ if (!boot_cpu_has(X86_FEATURE_CX16) ||
+ ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+ break;
+ }
+
/*
* Note: Since iommu_update_intcapxt() leverages
* the IOMMU MMIO access to MSI capability block registers
diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 1368816..99cdb2f 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -452,13 +452,19 @@
return ret;
if (vid == vlanmc.vid) {
- /* clear VLAN member configurations */
- vlanmc.vid = 0;
- vlanmc.priority = 0;
- vlanmc.member = 0;
- vlanmc.untag = 0;
- vlanmc.fid = 0;
-
+ /* Remove this port from the VLAN */
+ vlanmc.member &= ~BIT(port);
+ vlanmc.untag &= ~BIT(port);
+ /*
+ * If no ports are members of this VLAN
+ * anymore then clear the whole member
+ * config so it can be reused.
+ */
+ if (!vlanmc.member && vlanmc.untag) {
+ vlanmc.vid = 0;
+ vlanmc.priority = 0;
+ vlanmc.fid = 0;
+ }
ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
if (ret) {
dev_err(smi->dev,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4030020..4f4fd80 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4204,7 +4204,7 @@
u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
u16 dst = BNXT_HWRM_CHNL_CHIMP;
- if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+ if (BNXT_NO_FW_ACCESS(bp))
return -EBUSY;
if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
@@ -5539,7 +5539,7 @@
struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr;
u16 error_code;
- if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+ if (BNXT_NO_FW_ACCESS(bp))
return 0;
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1);
@@ -7454,7 +7454,7 @@
if (set_tpa)
tpa_flags = bp->flags & BNXT_FLAG_TPA;
- else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+ else if (BNXT_NO_FW_ACCESS(bp))
return 0;
for (i = 0; i < bp->nr_vnics; i++) {
rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
@@ -8939,18 +8939,16 @@
struct hwrm_temp_monitor_query_output *resp;
struct bnxt *bp = dev_get_drvdata(dev);
u32 len = 0;
+ int rc;
resp = bp->hwrm_cmd_resp_addr;
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
mutex_lock(&bp->hwrm_cmd_lock);
- if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+ rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (!rc)
len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */
mutex_unlock(&bp->hwrm_cmd_lock);
-
- if (len)
- return len;
-
- return sprintf(buf, "unknown\n");
+ return rc ?: len;
}
static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
@@ -8970,7 +8968,16 @@
static void bnxt_hwmon_open(struct bnxt *bp)
{
+ struct hwrm_temp_monitor_query_input req = {0};
struct pci_dev *pdev = bp->pdev;
+ int rc;
+
+ bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
+ rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+ if (rc == -EACCES || rc == -EOPNOTSUPP) {
+ bnxt_hwmon_close(bp);
+ return;
+ }
if (bp->hwmon_dev)
return;
@@ -11385,14 +11392,15 @@
if (BNXT_PF(bp))
bnxt_sriov_disable(bp);
+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+ bnxt_cancel_sp_work(bp);
+ bp->sp_event = 0;
+
bnxt_dl_fw_reporters_destroy(bp, true);
pci_disable_pcie_error_reporting(pdev);
unregister_netdev(dev);
bnxt_dl_unregister(bp);
bnxt_shutdown_tc(bp);
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- bnxt_cancel_sp_work(bp);
- bp->sp_event = 0;
bnxt_clear_int_mode(bp);
bnxt_hwrm_func_drv_unrgtr(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a61a587..d2dd852 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1628,6 +1628,10 @@
#define BNXT_STATE_ABORT_ERR 5
#define BNXT_STATE_FW_FATAL_COND 6
+#define BNXT_NO_FW_ACCESS(bp) \
+ (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \
+ pci_channel_offline((bp)->pdev))
+
struct bnxt_irq *irq_tbl;
int total_irqs;
u8 mac_addr[ETH_ALEN];
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index fd01bcc..1d15ff0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1665,9 +1665,12 @@
if (!BNXT_SINGLE_PF(bp))
return -EOPNOTSUPP;
+ mutex_lock(&bp->link_lock);
if (epause->autoneg) {
- if (!(link_info->autoneg & BNXT_AUTONEG_SPEED))
- return -EINVAL;
+ if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
+ rc = -EINVAL;
+ goto pause_exit;
+ }
link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL;
if (bp->hwrm_spec_code >= 0x10201)
@@ -1688,11 +1691,11 @@
if (epause->tx_pause)
link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX;
- if (netif_running(dev)) {
- mutex_lock(&bp->link_lock);
+ if (netif_running(dev))
rc = bnxt_hwrm_set_pause(bp);
- mutex_unlock(&bp->link_lock);
- }
+
+pause_exit:
+ mutex_unlock(&bp->link_lock);
return rc;
}
@@ -2397,8 +2400,7 @@
struct bnxt *bp = netdev_priv(dev);
struct ethtool_eee *eee = &bp->eee;
struct bnxt_link_info *link_info = &bp->link_info;
- u32 advertising =
- _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
+ u32 advertising;
int rc = 0;
if (!BNXT_SINGLE_PF(bp))
@@ -2407,19 +2409,23 @@
if (!(bp->flags & BNXT_FLAG_EEE_CAP))
return -EOPNOTSUPP;
+ mutex_lock(&bp->link_lock);
+ advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0);
if (!edata->eee_enabled)
goto eee_ok;
if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) {
netdev_warn(dev, "EEE requires autoneg\n");
- return -EINVAL;
+ rc = -EINVAL;
+ goto eee_exit;
}
if (edata->tx_lpi_enabled) {
if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi ||
edata->tx_lpi_timer < bp->lpi_tmr_lo)) {
netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n",
bp->lpi_tmr_lo, bp->lpi_tmr_hi);
- return -EINVAL;
+ rc = -EINVAL;
+ goto eee_exit;
} else if (!bp->lpi_tmr_hi) {
edata->tx_lpi_timer = eee->tx_lpi_timer;
}
@@ -2429,7 +2435,8 @@
} else if (edata->advertised & ~advertising) {
netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n",
edata->advertised, advertising);
- return -EINVAL;
+ rc = -EINVAL;
+ goto eee_exit;
}
eee->advertised = edata->advertised;
@@ -2441,6 +2448,8 @@
if (netif_running(dev))
rc = bnxt_hwrm_set_link_setting(bp, false, true);
+eee_exit:
+ mutex_unlock(&bp->link_lock);
return rc;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index f459313..137ff00 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1617,13 +1617,16 @@
static int configure_filter_tcb(struct adapter *adap, unsigned int tid,
struct filter_entry *f)
{
- if (f->fs.hitcnts)
+ if (f->fs.hitcnts) {
set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W,
- TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) |
+ TCB_TIMESTAMP_V(TCB_TIMESTAMP_M),
+ TCB_TIMESTAMP_V(0ULL),
+ 1);
+ set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W,
TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M),
- TCB_TIMESTAMP_V(0ULL) |
TCB_RTT_TS_RECENT_AGE_V(0ULL),
1);
+ }
if (f->fs.newdmac)
set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
index b1a073e..a020e84 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
@@ -229,7 +229,7 @@
{
struct mps_entries_ref *mps_entry, *tmp;
- if (!list_empty(&adap->mps_ref))
+ if (list_empty(&adap->mps_ref))
return;
spin_lock(&adap->mps_ref_lock);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 2d20a48..5329af2 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -416,6 +416,9 @@
int i, j, rc;
u64 *size_array;
+ if (!adapter->rx_pool)
+ return -1;
+
size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size));
@@ -586,6 +589,9 @@
int tx_scrqs;
int i, rc;
+ if (!adapter->tx_pool)
+ return -1;
+
tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs);
for (i = 0; i < tx_scrqs; i++) {
rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]);
@@ -1918,7 +1924,10 @@
adapter->req_rx_add_entries_per_subcrq !=
old_num_rx_slots ||
adapter->req_tx_entries_per_subcrq !=
- old_num_tx_slots) {
+ old_num_tx_slots ||
+ !adapter->rx_pool ||
+ !adapter->tso_pool ||
+ !adapter->tx_pool) {
release_rx_pools(adapter);
release_tx_pools(adapter);
release_napi(adapter);
@@ -1930,12 +1939,18 @@
} else {
rc = reset_tx_pools(adapter);
- if (rc)
+ if (rc) {
+ netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n",
+ rc);
goto out;
+ }
rc = reset_rx_pools(adapter);
- if (rc)
+ if (rc) {
+ netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n",
+ rc);
goto out;
+ }
}
ibmvnic_disable_irqs(adapter);
}
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 900affb..9694827 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -230,8 +230,8 @@
}
if (rx < budget) {
- napi_complete(&ch->napi);
- ltq_dma_enable_irq(&ch->dma);
+ if (napi_complete_done(&ch->napi, rx))
+ ltq_dma_enable_irq(&ch->dma);
}
return rx;
@@ -268,9 +268,12 @@
net_dev->stats.tx_bytes += bytes;
netdev_completed_queue(ch->priv->net_dev, pkts, bytes);
+ if (netif_queue_stopped(net_dev))
+ netif_wake_queue(net_dev);
+
if (pkts < budget) {
- napi_complete(&ch->napi);
- ltq_dma_enable_irq(&ch->dma);
+ if (napi_complete_done(&ch->napi, pkts))
+ ltq_dma_enable_irq(&ch->dma);
}
return pkts;
@@ -341,10 +344,12 @@
{
struct xrx200_chan *ch = ptr;
- ltq_dma_disable_irq(&ch->dma);
- ltq_dma_ack_irq(&ch->dma);
+ if (napi_schedule_prep(&ch->napi)) {
+ __napi_schedule(&ch->napi);
+ ltq_dma_disable_irq(&ch->dma);
+ }
- napi_schedule(&ch->napi);
+ ltq_dma_ack_irq(&ch->dma);
return IRQ_HANDLED;
}
@@ -498,7 +503,7 @@
/* setup NAPI */
netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32);
- netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
+ netif_tx_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32);
platform_set_drvdata(pdev, priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 01468ec..b949b9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -35,7 +35,6 @@
#include <net/sock.h>
#include "en.h"
-#include "accel/tls.h"
#include "fpga/sdk.h"
#include "en_accel/tls.h"
@@ -51,9 +50,14 @@
#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
+static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+{
+ return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+}
+
int mlx5e_tls_get_count(struct mlx5e_priv *priv)
{
- if (!priv->tls)
+ if (!is_tls_atomic_stats(priv))
return 0;
return NUM_TLS_SW_COUNTERS;
@@ -63,7 +67,7 @@
{
unsigned int i, idx = 0;
- if (!priv->tls)
+ if (!is_tls_atomic_stats(priv))
return 0;
for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
@@ -77,7 +81,7 @@
{
int i, idx = 0;
- if (!priv->tls)
+ if (!is_tls_atomic_stats(priv))
return 0;
for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 5acfdea..7cc80dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1143,36 +1143,38 @@
}
esw->fdb_table.offloads.send_to_vport_grp = g;
- /* create peer esw miss group */
- memset(flow_group_in, 0, inlen);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+ /* create peer esw miss group */
+ memset(flow_group_in, 0, inlen);
- esw_set_flow_group_source_port(esw, flow_group_in);
+ esw_set_flow_group_source_port(esw, flow_group_in);
- if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
- match_criteria = MLX5_ADDR_OF(create_flow_group_in,
- flow_group_in,
- match_criteria);
+ if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+ match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+ flow_group_in,
+ match_criteria);
- MLX5_SET_TO_ONES(fte_match_param, match_criteria,
- misc_parameters.source_eswitch_owner_vhca_id);
+ MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+ misc_parameters.source_eswitch_owner_vhca_id);
- MLX5_SET(create_flow_group_in, flow_group_in,
- source_eswitch_owner_vhca_id_valid, 1);
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ source_eswitch_owner_vhca_id_valid, 1);
+ }
+
+ MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+ MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+ ix + esw->total_vports - 1);
+ ix += esw->total_vports;
+
+ g = mlx5_create_flow_group(fdb, flow_group_in);
+ if (IS_ERR(g)) {
+ err = PTR_ERR(g);
+ esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+ goto peer_miss_err;
+ }
+ esw->fdb_table.offloads.peer_miss_grp = g;
}
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
- ix + esw->total_vports - 1);
- ix += esw->total_vports;
-
- g = mlx5_create_flow_group(fdb, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
- goto peer_miss_err;
- }
- esw->fdb_table.offloads.peer_miss_grp = g;
-
/* create miss group */
memset(flow_group_in, 0, inlen);
MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
@@ -1206,7 +1208,8 @@
miss_rule_err:
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
miss_err:
- mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
peer_miss_err:
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
send_vport_err:
@@ -1229,7 +1232,8 @@
mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
- mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index b66e5b6..9ac2f52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -629,7 +629,7 @@
fte->action = *flow_act;
fte->flow_context = spec->flow_context;
- tree_init_node(&fte->node, NULL, del_sw_fte);
+ tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
return fte;
}
@@ -1737,7 +1737,6 @@
up_write_ref_node(&g->node, false);
rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
up_write_ref_node(&fte->node, false);
- tree_put_node(&fte->node, false);
return rule;
}
rule = ERR_PTR(-ENOENT);
@@ -1837,7 +1836,6 @@
up_write_ref_node(&g->node, false);
rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
up_write_ref_node(&fte->node, false);
- tree_put_node(&fte->node, false);
tree_put_node(&g->node, false);
return rule;
@@ -1930,7 +1928,9 @@
up_write_ref_node(&fte->node, false);
} else {
del_hw_fte(&fte->node);
- up_write(&fte->node.lock);
+ /* Avoid double call to del_hw_fte */
+ fte->node.del_hw_func = NULL;
+ up_write_ref_node(&fte->node, false);
tree_put_node(&fte->node, false);
}
kfree(handle);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 1b840ee..17b91ed 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -731,8 +731,8 @@
struct nfp_eth_table_port *eth_port;
struct nfp_port *port;
- param->active_fec = ETHTOOL_FEC_NONE_BIT;
- param->fec = ETHTOOL_FEC_NONE_BIT;
+ param->active_fec = ETHTOOL_FEC_NONE;
+ param->fec = ETHTOOL_FEC_NONE;
port = nfp_port_from_netdev(netdev);
eth_port = nfp_port_get_eth_port(port);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index adfdf62..fcb7a6b 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -773,7 +773,8 @@
struct net_device *dev,
struct geneve_sock *gs4,
struct flowi4 *fl4,
- const struct ip_tunnel_info *info)
+ const struct ip_tunnel_info *info,
+ __be16 dport, __be16 sport)
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
@@ -789,6 +790,8 @@
fl4->flowi4_proto = IPPROTO_UDP;
fl4->daddr = info->key.u.ipv4.dst;
fl4->saddr = info->key.u.ipv4.src;
+ fl4->fl4_dport = dport;
+ fl4->fl4_sport = sport;
tos = info->key.tos;
if ((tos == 1) && !geneve->collect_md) {
@@ -823,7 +826,8 @@
struct net_device *dev,
struct geneve_sock *gs6,
struct flowi6 *fl6,
- const struct ip_tunnel_info *info)
+ const struct ip_tunnel_info *info,
+ __be16 dport, __be16 sport)
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
@@ -839,6 +843,9 @@
fl6->flowi6_proto = IPPROTO_UDP;
fl6->daddr = info->key.u.ipv6.dst;
fl6->saddr = info->key.u.ipv6.src;
+ fl6->fl6_dport = dport;
+ fl6->fl6_sport = sport;
+
prio = info->key.tos;
if ((prio == 1) && !geneve->collect_md) {
prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
@@ -885,14 +892,15 @@
__be16 sport;
int err;
- rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+ sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+ rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+ geneve->info.key.tp_dst, sport);
if (IS_ERR(rt))
return PTR_ERR(rt);
skb_tunnel_check_pmtu(skb, &rt->dst,
GENEVE_IPV4_HLEN + info->options_len);
- sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
if (geneve->collect_md) {
tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
ttl = key->ttl;
@@ -947,13 +955,14 @@
__be16 sport;
int err;
- dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+ sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+ dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+ geneve->info.key.tp_dst, sport);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len);
- sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
if (geneve->collect_md) {
prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
ttl = key->ttl;
@@ -1034,13 +1043,18 @@
{
struct ip_tunnel_info *info = skb_tunnel_info(skb);
struct geneve_dev *geneve = netdev_priv(dev);
+ __be16 sport;
if (ip_tunnel_info_af(info) == AF_INET) {
struct rtable *rt;
struct flowi4 fl4;
- struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
- rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
+ struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
+ sport = udp_flow_src_port(geneve->net, skb,
+ 1, USHRT_MAX, true);
+
+ rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
+ geneve->info.key.tp_dst, sport);
if (IS_ERR(rt))
return PTR_ERR(rt);
@@ -1050,9 +1064,13 @@
} else if (ip_tunnel_info_af(info) == AF_INET6) {
struct dst_entry *dst;
struct flowi6 fl6;
- struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
- dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info);
+ struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
+ sport = udp_flow_src_port(geneve->net, skb,
+ 1, USHRT_MAX, true);
+
+ dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
+ geneve->info.key.tp_dst, sport);
if (IS_ERR(dst))
return PTR_ERR(dst);
@@ -1063,8 +1081,7 @@
return -EINVAL;
}
- info->key.tp_src = udp_flow_src_port(geneve->net, skb,
- 1, USHRT_MAX, true);
+ info->key.tp_src = sport;
info->key.tp_dst = geneve->info.key.tp_dst;
return 0;
}
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 54e5d4f..b718b11 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -834,7 +834,7 @@
*/
void phy_stop(struct phy_device *phydev)
{
- if (!phy_is_started(phydev)) {
+ if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) {
WARN(1, "called from state %s\n",
phy_state_to_str(phydev->state));
return;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 110924d..9d0a306 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1421,7 +1421,8 @@
phy_led_triggers_unregister(phydev);
- module_put(phydev->mdio.dev.driver->owner);
+ if (phydev->mdio.dev.driver)
+ module_put(phydev->mdio.dev.driver->owner);
/* If the device had no specific driver before (i.e. - it
* was using the generic driver), we unbind the device
diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c
index 48ced39..16f33d1 100644
--- a/drivers/net/wan/hdlc_ppp.c
+++ b/drivers/net/wan/hdlc_ppp.c
@@ -383,11 +383,8 @@
}
for (opt = data; len; len -= opt[1], opt += opt[1]) {
- if (len < 2 || len < opt[1]) {
- dev->stats.rx_errors++;
- kfree(out);
- return; /* bad packet, drop silently */
- }
+ if (len < 2 || opt[1] < 2 || len < opt[1])
+ goto err_out;
if (pid == PID_LCP)
switch (opt[0]) {
@@ -395,6 +392,8 @@
continue; /* MRU always OK and > 1500 bytes? */
case LCP_OPTION_ACCM: /* async control character map */
+ if (opt[1] < sizeof(valid_accm))
+ goto err_out;
if (!memcmp(opt, valid_accm,
sizeof(valid_accm)))
continue;
@@ -406,6 +405,8 @@
}
break;
case LCP_OPTION_MAGIC:
+ if (len < 6)
+ goto err_out;
if (opt[1] != 6 || (!opt[2] && !opt[3] &&
!opt[4] && !opt[5]))
break; /* reject invalid magic number */
@@ -424,6 +425,11 @@
ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data);
kfree(out);
+ return;
+
+err_out:
+ dev->stats.rx_errors++;
+ kfree(out);
}
static int ppp_rx(struct sk_buff *skb)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 955e137..a62889c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3185,8 +3185,9 @@
* is untouched. Otherwise it is extended. Returns zero on
* success. The skb is freed on error if @free_on_error is true.
*/
-static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len,
- bool free_on_error)
+static inline int __must_check __skb_put_padto(struct sk_buff *skb,
+ unsigned int len,
+ bool free_on_error)
{
unsigned int size = skb->len;
@@ -3209,7 +3210,7 @@
* is untouched. Otherwise it is extended. Returns zero on
* success. The skb is freed on error.
*/
-static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
+static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len)
{
return __skb_put_padto(skb, len, true);
}
diff --git a/include/net/flow.h b/include/net/flow.h
index a50fb77..d058e63 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -116,6 +116,7 @@
fl4->saddr = saddr;
fl4->fl4_dport = dport;
fl4->fl4_sport = sport;
+ fl4->flowi4_multipath_hash = 0;
}
/* Reset some input parameters after previous lookup */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 2b6f3f1..3e8f87a 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -224,12 +224,14 @@
data_ready_signalled:1;
atomic_t pd_mode;
+
+ /* Fields after this point will be skipped on copies, like on accept
+ * and peeloff operations
+ */
+
/* Receive to here while partial delivery is in effect. */
struct sk_buff_head pd_lobby;
- /* These must be the last fields, as they will skipped on copies,
- * like on accept and peeloff operations
- */
struct list_head auto_asconf_list;
int do_auto_asconf;
};
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index bbff4bc..5646f29 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2088,6 +2088,9 @@
{
struct kprobe *kp;
+ if (WARN_ON_ONCE(kprobe_gone(p)))
+ return;
+
p->flags |= KPROBE_FLAG_GONE;
if (kprobe_aggrprobe(p)) {
/*
@@ -2270,7 +2273,10 @@
mutex_lock(&kprobe_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
- hlist_for_each_entry_rcu(p, head, hlist)
+ hlist_for_each_entry_rcu(p, head, hlist) {
+ if (kprobe_gone(p))
+ continue;
+
if (within_module_init((unsigned long)p->addr, mod) ||
(checkcore &&
within_module_core((unsigned long)p->addr, mod))) {
@@ -2287,6 +2293,7 @@
*/
kill_kprobe(p);
}
+ }
}
mutex_unlock(&kprobe_mutex);
return NOTIFY_DONE;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da9040a..873de55 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2174,7 +2174,7 @@
put_page(page);
add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
return;
- } else if (is_huge_zero_pmd(*pmd)) {
+ } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
/*
* FIXME: Do we want to invalidate secondary mmu by calling
* mmu_notifier_invalidate_range() see comments below inside
@@ -2262,27 +2262,33 @@
pte = pte_offset_map(&_pmd, addr);
BUG_ON(!pte_none(*pte));
set_pte_at(mm, addr, pte, entry);
- atomic_inc(&page[i]._mapcount);
+ if (!pmd_migration)
+ atomic_inc(&page[i]._mapcount);
pte_unmap(pte);
}
- /*
- * Set PG_double_map before dropping compound_mapcount to avoid
- * false-negative page_mapped().
- */
- if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) {
- for (i = 0; i < HPAGE_PMD_NR; i++)
- atomic_inc(&page[i]._mapcount);
- }
-
- if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
- /* Last compound_mapcount is gone. */
- __dec_node_page_state(page, NR_ANON_THPS);
- if (TestClearPageDoubleMap(page)) {
- /* No need in mapcount reference anymore */
+ if (!pmd_migration) {
+ /*
+ * Set PG_double_map before dropping compound_mapcount to avoid
+ * false-negative page_mapped().
+ */
+ if (compound_mapcount(page) > 1 &&
+ !TestSetPageDoubleMap(page)) {
for (i = 0; i < HPAGE_PMD_NR; i++)
- atomic_dec(&page[i]._mapcount);
+ atomic_inc(&page[i]._mapcount);
}
+
+ lock_page_memcg(page);
+ if (atomic_add_negative(-1, compound_mapcount_ptr(page))) {
+ /* Last compound_mapcount is gone. */
+ __dec_lruvec_page_state(page, NR_ANON_THPS);
+ if (TestClearPageDoubleMap(page)) {
+ /* No need in mapcount reference anymore */
+ for (i = 0; i < HPAGE_PMD_NR; i++)
+ atomic_dec(&page[i]._mapcount);
+ }
+ }
+ unlock_page_memcg(page);
}
smp_wmb(); /* make pte visible before pmd */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7fde5f9..6db9176 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2775,6 +2775,14 @@
unsigned long reclaimed;
unsigned long scanned;
+ /*
+ * This loop can become CPU-bound when target memcgs
+ * aren't eligible for reclaim - either because they
+ * don't have any reclaimable pages, or because their
+ * memory is explicitly protected. Avoid soft lockups.
+ */
+ cond_resched();
+
switch (mem_cgroup_protected(root, memcg)) {
case MEMCG_PROT_MIN:
/*
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index bb98984..48413b5 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -1229,11 +1229,13 @@
}
}
-static int __br_vlan_get_pvid(const struct net_device *dev,
- struct net_bridge_port *p, u16 *p_pvid)
+int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
{
struct net_bridge_vlan_group *vg;
+ struct net_bridge_port *p;
+ ASSERT_RTNL();
+ p = br_port_get_check_rtnl(dev);
if (p)
vg = nbp_vlan_group(p);
else if (netif_is_bridge_master(dev))
@@ -1244,18 +1246,23 @@
*p_pvid = br_get_pvid(vg);
return 0;
}
-
-int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
-{
- ASSERT_RTNL();
-
- return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid);
-}
EXPORT_SYMBOL_GPL(br_vlan_get_pvid);
int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid)
{
- return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid);
+ struct net_bridge_vlan_group *vg;
+ struct net_bridge_port *p;
+
+ p = br_port_get_check_rcu(dev);
+ if (p)
+ vg = nbp_vlan_group_rcu(p);
+ else if (netif_is_bridge_master(dev))
+ vg = br_vlan_group_rcu(netdev_priv(dev));
+ else
+ return -EINVAL;
+
+ *p_pvid = br_get_pvid(vg);
+ return 0;
}
EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu);
diff --git a/net/core/dev.c b/net/core/dev.c
index cdc1c3a1..20c7fd7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8241,7 +8241,7 @@
if (!first.id_len)
first = *ppid;
else if (memcmp(&first, ppid, sizeof(*ppid)))
- return -ENODATA;
+ return -EOPNOTSUPP;
}
return err;
diff --git a/net/core/filter.c b/net/core/filter.c
index 5c490d4..cf2a685 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4650,6 +4650,7 @@
fl4.saddr = params->ipv4_src;
fl4.fl4_sport = params->sport;
fl4.fl4_dport = params->dport;
+ fl4.flowi4_multipath_hash = 0;
if (flags & BPF_FIB_LOOKUP_DIRECT) {
u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index d2a4553..0fd1c2a 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1426,6 +1426,7 @@
{
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
+ int prio;
int err;
if (!ops)
@@ -1475,6 +1476,13 @@
struct dcbnl_buffer *buffer =
nla_data(ieee[DCB_ATTR_DCB_BUFFER]);
+ for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) {
+ if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) {
+ err = -EINVAL;
+ goto err;
+ }
+ }
+
err = ops->dcbnl_setbuffer(netdev, buffer);
if (err)
goto err;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2b0521f..0a8220d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -372,6 +372,7 @@
fl4.flowi4_tun_key.tun_id = 0;
fl4.flowi4_flags = 0;
fl4.flowi4_uid = sock_net_uid(net, NULL);
+ fl4.flowi4_multipath_hash = 0;
no_addr = idev->ifa_list == NULL;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b36c4a3..079dcf9 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -74,6 +74,7 @@
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
+#include <net/inet_ecn.h>
#include <net/lwtunnel.h>
#include <linux/bpf-cgroup.h>
#include <linux/igmp.h>
@@ -1699,7 +1700,7 @@
if (IS_ERR(rt))
return;
- inet_sk(sk)->tos = arg->tos;
+ inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b3a8d32..aa77f98 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -785,8 +785,10 @@
neigh_event_send(n, NULL);
} else {
if (fib_lookup(net, fl4, &res, 0) == 0) {
- struct fib_nh_common *nhc = FIB_RES_NHC(res);
+ struct fib_nh_common *nhc;
+ fib_select_path(net, &res, fl4, skb);
+ nhc = FIB_RES_NHC(res);
update_or_create_fnhe(nhc, fl4->daddr, new_gw,
0, false,
jiffies + ip_rt_gc_timeout);
@@ -1012,6 +1014,7 @@
static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct dst_entry *dst = &rt->dst;
+ struct net *net = dev_net(dst->dev);
u32 old_mtu = ipv4_mtu(dst);
struct fib_result res;
bool lock = false;
@@ -1032,9 +1035,11 @@
return;
rcu_read_lock();
- if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
- struct fib_nh_common *nhc = FIB_RES_NHC(res);
+ if (fib_lookup(net, fl4, &res, 0) == 0) {
+ struct fib_nh_common *nhc;
+ fib_select_path(net, &res, fl4, NULL);
+ nhc = FIB_RES_NHC(res);
update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
jiffies + ip_rt_mtu_expires);
}
@@ -2104,6 +2109,7 @@
fl4.daddr = daddr;
fl4.saddr = saddr;
fl4.flowi4_uid = sock_net_uid(net, NULL);
+ fl4.flowi4_multipath_hash = 0;
if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
flkeys = &_flkeys;
@@ -2625,8 +2631,6 @@
fib_select_path(net, res, fl4, skb);
dev_out = FIB_RES_DEV(*res);
- fl4->flowi4_oif = dev_out->ifindex;
-
make_route:
rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ae1344e..dce1447 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -289,6 +289,7 @@
config IPV6_SEG6_HMAC
bool "IPv6: Segment Routing HMAC support"
depends on IPV6
+ select CRYPTO
select CRYPTO_HMAC
select CRYPTO_SHA1
select CRYPTO_SHA256
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7a0c877..96d80e5 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1896,14 +1896,19 @@
/* Need to own table->tb6_lock */
int fib6_del(struct fib6_info *rt, struct nl_info *info)
{
- struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
- lockdep_is_held(&rt->fib6_table->tb6_lock));
- struct fib6_table *table = rt->fib6_table;
struct net *net = info->nl_net;
struct fib6_info __rcu **rtp;
struct fib6_info __rcu **rtp_next;
+ struct fib6_table *table;
+ struct fib6_node *fn;
- if (!fn || rt == net->ipv6.fib6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
+ return -ENOENT;
+
+ table = rt->fib6_table;
+ fn = rcu_dereference_protected(rt->fib6_node,
+ lockdep_is_held(&table->tb6_lock));
+ if (!fn)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 979c579..a915bc8 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1849,6 +1849,13 @@
if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
+ if ((xfilter->sadb_x_filter_splen >=
+ (sizeof(xfrm_address_t) << 3)) ||
+ (xfilter->sadb_x_filter_dplen >=
+ (sizeof(xfrm_address_t) << 3))) {
+ mutex_unlock(&pfk->dump_lock);
+ return -EINVAL;
+ }
filter = kmalloc(sizeof(*filter), GFP_KERNEL);
if (filter == NULL) {
mutex_unlock(&pfk->dump_lock);
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index a699e31..d6d2736 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -178,7 +178,7 @@
{
struct qrtr_hdr_v1 *hdr;
size_t len = skb->len;
- int rc = -ENODEV;
+ int rc;
hdr = skb_push(skb, sizeof(*hdr));
hdr->version = cpu_to_le32(QRTR_PROTO_VER_1);
@@ -196,15 +196,17 @@
hdr->size = cpu_to_le32(len);
hdr->confirm_rx = 0;
- skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
+ rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr));
- mutex_lock(&node->ep_lock);
- if (node->ep)
- rc = node->ep->xmit(node->ep, skb);
- else
- kfree_skb(skb);
- mutex_unlock(&node->ep_lock);
-
+ if (!rc) {
+ mutex_lock(&node->ep_lock);
+ rc = -ENODEV;
+ if (node->ep)
+ rc = node->ep->xmit(node->ep, skb);
+ else
+ kfree_skb(skb);
+ mutex_unlock(&node->ep_lock);
+ }
return rc;
}
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index a0cfb47..778371b 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -436,6 +436,25 @@
kfree_rcu(p, rcu);
}
+static int load_metalist(struct nlattr **tb, bool rtnl_held)
+{
+ int i;
+
+ for (i = 1; i < max_metacnt; i++) {
+ if (tb[i]) {
+ void *val = nla_data(tb[i]);
+ int len = nla_len(tb[i]);
+ int rc;
+
+ rc = load_metaops_and_vet(i, val, len, rtnl_held);
+ if (rc != 0)
+ return rc;
+ }
+ }
+
+ return 0;
+}
+
static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
bool exists, bool rtnl_held)
{
@@ -449,10 +468,6 @@
val = nla_data(tb[i]);
len = nla_len(tb[i]);
- rc = load_metaops_and_vet(i, val, len, rtnl_held);
- if (rc != 0)
- return rc;
-
rc = add_metainfo(ife, i, val, len, exists);
if (rc)
return rc;
@@ -508,6 +523,21 @@
if (!p)
return -ENOMEM;
+ if (tb[TCA_IFE_METALST]) {
+ err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
+ tb[TCA_IFE_METALST], NULL,
+ NULL);
+ if (err) {
+ kfree(p);
+ return err;
+ }
+ err = load_metalist(tb2, rtnl_held);
+ if (err) {
+ kfree(p);
+ return err;
+ }
+ }
+
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0) {
@@ -569,15 +599,9 @@
}
if (tb[TCA_IFE_METALST]) {
- err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
- tb[TCA_IFE_METALST], NULL,
- NULL);
- if (err)
- goto metadata_parse_err;
err = populate_metalist(ife, tb2, exists, rtnl_held);
if (err)
goto metadata_parse_err;
-
} else {
/* if no passed metadata allow list or passed allow-all
* then here we process by adding as many supported metadatum
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 896c903..0e275e1 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1126,29 +1126,38 @@
struct netdev_queue *dev_queue,
void *_qdisc_default)
{
- struct Qdisc *qdisc_default = _qdisc_default;
- struct Qdisc *qdisc;
+ struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc);
- qdisc = rtnl_dereference(dev_queue->qdisc);
if (qdisc) {
- bool nolock = qdisc->flags & TCQ_F_NOLOCK;
-
- if (nolock)
- spin_lock_bh(&qdisc->seqlock);
- spin_lock_bh(qdisc_lock(qdisc));
-
if (!(qdisc->flags & TCQ_F_BUILTIN))
set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
-
- rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
- qdisc_reset(qdisc);
-
- spin_unlock_bh(qdisc_lock(qdisc));
- if (nolock)
- spin_unlock_bh(&qdisc->seqlock);
}
}
+static void dev_reset_queue(struct net_device *dev,
+ struct netdev_queue *dev_queue,
+ void *_unused)
+{
+ struct Qdisc *qdisc;
+ bool nolock;
+
+ qdisc = dev_queue->qdisc_sleeping;
+ if (!qdisc)
+ return;
+
+ nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+ if (nolock)
+ spin_lock_bh(&qdisc->seqlock);
+ spin_lock_bh(qdisc_lock(qdisc));
+
+ qdisc_reset(qdisc);
+
+ spin_unlock_bh(qdisc_lock(qdisc));
+ if (nolock)
+ spin_unlock_bh(&qdisc->seqlock);
+}
+
static bool some_qdisc_is_busy(struct net_device *dev)
{
unsigned int i;
@@ -1207,12 +1216,20 @@
dev_watchdog_down(dev);
}
- /* Wait for outstanding qdisc-less dev_queue_xmit calls.
+ /* Wait for outstanding qdisc-less dev_queue_xmit calls or
+ * outstanding qdisc enqueuing calls.
* This is avoided if all devices are in dismantle phase :
* Caller will call synchronize_net() for us
*/
synchronize_net();
+ list_for_each_entry(dev, head, close_list) {
+ netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);
+
+ if (dev_ingress_queue(dev))
+ dev_reset_queue(dev, dev_ingress_queue(dev), NULL);
+ }
+
/* Wait for outstanding qdisc_run calls. */
list_for_each_entry(dev, head, close_list) {
while (some_qdisc_is_busy(dev))
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 6a5086e..2b797a7 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -777,9 +777,11 @@
[TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 },
};
-static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
+static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
+ struct sched_entry *entry,
struct netlink_ext_ack *extack)
{
+ int min_duration = length_to_duration(q, ETH_ZLEN);
u32 interval = 0;
if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD])
@@ -794,7 +796,10 @@
interval = nla_get_u32(
tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]);
- if (interval == 0) {
+ /* The interval should allow at least the minimum ethernet
+ * frame to go out.
+ */
+ if (interval < min_duration) {
NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry");
return -EINVAL;
}
@@ -804,8 +809,9 @@
return 0;
}
-static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
- int index, struct netlink_ext_ack *extack)
+static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n,
+ struct sched_entry *entry, int index,
+ struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
int err;
@@ -819,10 +825,10 @@
entry->index = index;
- return fill_sched_entry(tb, entry, extack);
+ return fill_sched_entry(q, tb, entry, extack);
}
-static int parse_sched_list(struct nlattr *list,
+static int parse_sched_list(struct taprio_sched *q, struct nlattr *list,
struct sched_gate_list *sched,
struct netlink_ext_ack *extack)
{
@@ -847,7 +853,7 @@
return -ENOMEM;
}
- err = parse_sched_entry(n, entry, i, extack);
+ err = parse_sched_entry(q, n, entry, i, extack);
if (err < 0) {
kfree(entry);
return err;
@@ -862,7 +868,7 @@
return i;
}
-static int parse_taprio_schedule(struct nlattr **tb,
+static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb,
struct sched_gate_list *new,
struct netlink_ext_ack *extack)
{
@@ -883,8 +889,8 @@
new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]);
if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST])
- err = parse_sched_list(
- tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack);
+ err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST],
+ new, extack);
if (err < 0)
return err;
@@ -1474,7 +1480,7 @@
goto free_sched;
}
- err = parse_taprio_schedule(tb, new_admin, extack);
+ err = parse_taprio_schedule(q, tb, new_admin, extack);
if (err < 0)
goto free_sched;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3a11212b..1fcc13f 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9337,13 +9337,10 @@
static inline void sctp_copy_descendant(struct sock *sk_to,
const struct sock *sk_from)
{
- int ancestor_size = sizeof(struct inet_sock) +
- sizeof(struct sctp_sock) -
- offsetof(struct sctp_sock, pd_lobby);
+ size_t ancestor_size = sizeof(struct inet_sock);
- if (sk_from->sk_family == PF_INET6)
- ancestor_size += sizeof(struct ipv6_pinfo);
-
+ ancestor_size += sk_from->sk_prot->obj_size;
+ ancestor_size -= offsetof(struct sctp_sock, pd_lobby);
__inet_sk_copy_descendant(sk_to, sk_from, ancestor_size);
}
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 89257e2..f53871b 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -273,8 +273,8 @@
return NULL;
}
-static void tipc_group_add_to_tree(struct tipc_group *grp,
- struct tipc_member *m)
+static int tipc_group_add_to_tree(struct tipc_group *grp,
+ struct tipc_member *m)
{
u64 nkey, key = (u64)m->node << 32 | m->port;
struct rb_node **n, *parent = NULL;
@@ -291,10 +291,11 @@
else if (key > nkey)
n = &(*n)->rb_right;
else
- return;
+ return -EEXIST;
}
rb_link_node(&m->tree_node, parent, n);
rb_insert_color(&m->tree_node, &grp->members);
+ return 0;
}
static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
@@ -302,6 +303,7 @@
u32 instance, int state)
{
struct tipc_member *m;
+ int ret;
m = kzalloc(sizeof(*m), GFP_ATOMIC);
if (!m)
@@ -314,8 +316,12 @@
m->port = port;
m->instance = instance;
m->bc_acked = grp->bc_snd_nxt - 1;
+ ret = tipc_group_add_to_tree(grp, m);
+ if (ret < 0) {
+ kfree(m);
+ return NULL;
+ }
grp->member_cnt++;
- tipc_group_add_to_tree(grp, m);
tipc_nlist_add(&grp->dests, m->node);
m->state = state;
return m;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 922d262..ee4b226 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -140,7 +140,8 @@
if (fragid == FIRST_FRAGMENT) {
if (unlikely(head))
goto err;
- if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
+ frag = skb_unshare(frag, GFP_ATOMIC);
+ if (unlikely(!frag))
goto err;
head = *headbuf = frag;
*buf = NULL;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 5318bb6..959155c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2616,10 +2616,7 @@
trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " ");
__tipc_shutdown(sock, TIPC_CONN_SHUTDOWN);
- if (tipc_sk_type_connectionless(sk))
- sk->sk_shutdown = SHUTDOWN_MASK;
- else
- sk->sk_shutdown = SEND_SHUTDOWN;
+ sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == TIPC_DISCONNECTING) {
/* Discard any unreceived messages */
