hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'linus'

This commit is contained in:
Andrew Morton 2022-08-25 21:45:38 -07:00
parent e9ac503883 4c612826be
commit ec6624452e
112 changed files with 970 additions and 449 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Documentation/admin-guide/sysctl/net.rst
View File

@ -271,7 +271,7 @@ poll cycle or the number of packets processed reaches netdev_budget.
netdev_max_backlog
------------------
Maximum number of packets, queued on the INPUT side, when the interface
Maximum number of packets, queued on the INPUT side, when the interface
receives packets faster than kernel can process them.
netdev_rss_key

1
MAINTAINERS
View File

@ -3679,6 +3679,7 @@ F: Documentation/networking/bonding.rst
F: drivers/net/bonding/
F: include/net/bond*
F: include/uapi/linux/if_bonding.h
F: tools/testing/selftests/drivers/net/bonding/
BOSCH SENSORTEC BMA400 ACCELEROMETER IIO DRIVER
M: Dan Robertson <dan@dlrobertson.com>

2
drivers/firmware/dmi_scan.c
View File

@ -630,7 +630,7 @@ static int __init dmi_smbios3_present(const u8 *buf)
{
if (memcmp(buf, "_SM3_", 5) == 0 &&
buf[6] < 32 && dmi_checksum(buf, buf[6])) {
dmi_ver = get_unaligned_be32(buf + 6) & 0xFFFFFF;
dmi_ver = get_unaligned_be24(buf + 7);
dmi_num = 0; /* No longer specified */
dmi_len = get_unaligned_le32(buf + 12);
dmi_base = get_unaligned_le64(buf + 16);

41
drivers/net/bonding/bond_3ad.c
View File

@ -84,7 +84,8 @@ enum ad_link_speed_type {
static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = {
0, 0, 0, 0, 0, 0
};
static u16 ad_ticks_per_sec;
static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL;
static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000;
static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned =
@ -2001,36 +2002,24 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout)
/**
* bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures
* @bond: bonding struct to work on
* @tick_resolution: tick duration (millisecond resolution)
*
* Can be called only after the mac address of the bond is set.
*/
void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
void bond_3ad_initialize(struct bonding *bond)
{
/* check that the bond is not initialized yet */
if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr),
bond->dev->dev_addr)) {
BOND_AD_INFO(bond).aggregator_identifier = 0;
BOND_AD_INFO(bond).system.sys_priority =
bond->params.ad_actor_sys_prio;
if (is_zero_ether_addr(bond->params.ad_actor_system))
BOND_AD_INFO(bond).system.sys_mac_addr =
*((struct mac_addr *)bond->dev->dev_addr);
else
BOND_AD_INFO(bond).system.sys_mac_addr =
*((struct mac_addr *)bond->params.ad_actor_system);
BOND_AD_INFO(bond).aggregator_identifier = 0;
BOND_AD_INFO(bond).system.sys_priority =
bond->params.ad_actor_sys_prio;
if (is_zero_ether_addr(bond->params.ad_actor_system))
BOND_AD_INFO(bond).system.sys_mac_addr =
*((struct mac_addr *)bond->dev->dev_addr);
else
BOND_AD_INFO(bond).system.sys_mac_addr =
*((struct mac_addr *)bond->params.ad_actor_system);
/* initialize how many times this module is called in one
* second (should be about every 100ms)
*/
ad_ticks_per_sec = tick_resolution;
bond_3ad_initiate_agg_selection(bond,
AD_AGGREGATOR_SELECTION_TIMER *
ad_ticks_per_sec);
}
bond_3ad_initiate_agg_selection(bond,
AD_AGGREGATOR_SELECTION_TIMER *
ad_ticks_per_sec);
}
/**

2
drivers/net/bonding/bond_main.c
View File

@ -2081,7 +2081,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
/* Initialize AD with the number of times that the AD timer is called in 1 second
* can be called only after the mac address of the bond is set
*/
bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL);
bond_3ad_initialize(bond);
} else {
SLAVE_AD_INFO(new_slave)->id =
SLAVE_AD_INFO(prev_slave)->id + 1;

53
drivers/net/dsa/microchip/ksz_common.c
View File

@ -803,9 +803,15 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port,
if (dev->info->supports_rgmii[port])
phy_interface_set_rgmii(config->supported_interfaces);
if (dev->info->internal_phy[port])
if (dev->info->internal_phy[port]) {
__set_bit(PHY_INTERFACE_MODE_INTERNAL,
config->supported_interfaces);
/* Compatibility for phylib's default interface type when the
* phy-mode property is absent
*/
__set_bit(PHY_INTERFACE_MODE_GMII,
config->supported_interfaces);
}
if (dev->dev_ops->get_caps)
dev->dev_ops->get_caps(dev, port, config);
@ -962,6 +968,7 @@ static void ksz_update_port_member(struct ksz_device *dev, int port)
static int ksz_setup(struct dsa_switch *ds)
{
struct ksz_device *dev = ds->priv;
struct ksz_port *p;
const u16 *regs;
int ret;
@ -1001,6 +1008,14 @@ static int ksz_setup(struct dsa_switch *ds)
return ret;
}
/* Start with learning disabled on standalone user ports, and enabled
* on the CPU port. In lack of other finer mechanisms, learning on the
* CPU port will avoid flooding bridge local addresses on the network
* in some cases.
*/
p = &dev->ports[dev->cpu_port];
p->learning = true;
/* start switch */
regmap_update_bits(dev->regmap[0], regs[S_START_CTRL],
SW_START, SW_START);
@ -1277,6 +1292,8 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
ksz_pread8(dev, port, regs[P_STP_CTRL], &data);
data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE);
p = &dev->ports[port];
switch (state) {
case BR_STATE_DISABLED:
data |= PORT_LEARN_DISABLE;
@ -1286,9 +1303,13 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
break;
case BR_STATE_LEARNING:
data |= PORT_RX_ENABLE;
if (!p->learning)
data |= PORT_LEARN_DISABLE;
break;
case BR_STATE_FORWARDING:
data |= (PORT_TX_ENABLE | PORT_RX_ENABLE);
if (!p->learning)
data |= PORT_LEARN_DISABLE;
break;
case BR_STATE_BLOCKING:
data |= PORT_LEARN_DISABLE;
@ -1300,12 +1321,38 @@ void ksz_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
ksz_pwrite8(dev, port, regs[P_STP_CTRL], data);
p = &dev->ports[port];
p->stp_state = state;
ksz_update_port_member(dev, port);
}
static int ksz_port_pre_bridge_flags(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack)
{
if (flags.mask & ~BR_LEARNING)
return -EINVAL;
return 0;
}
static int ksz_port_bridge_flags(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack)
{
struct ksz_device *dev = ds->priv;
struct ksz_port *p = &dev->ports[port];
if (flags.mask & BR_LEARNING) {
p->learning = !!(flags.val & BR_LEARNING);
/* Make the change take effect immediately */
ksz_port_stp_state_set(ds, port, p->stp_state);
}
return 0;
}
static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
int port,
enum dsa_tag_protocol mp)
@ -1719,6 +1766,8 @@ static const struct dsa_switch_ops ksz_switch_ops = {
.port_bridge_join = ksz_port_bridge_join,
.port_bridge_leave = ksz_port_bridge_leave,
.port_stp_state_set = ksz_port_stp_state_set,
.port_pre_bridge_flags = ksz_port_pre_bridge_flags,
.port_bridge_flags = ksz_port_bridge_flags,
.port_fast_age = ksz_port_fast_age,
.port_vlan_filtering = ksz_port_vlan_filtering,
.port_vlan_add = ksz_port_vlan_add,

1
drivers/net/dsa/microchip/ksz_common.h
View File

@ -65,6 +65,7 @@ struct ksz_chip_data {
struct ksz_port {
bool remove_tag; /* Remove Tag flag set, for ksz8795 only */
bool learning;
int stp_state;
struct phy_device phydev;

5
drivers/net/ethernet/broadcom/bnxt/bnxt.c
View File

@ -11178,10 +11178,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
features &= ~NETIF_F_NTUPLE;
if (bp->flags & BNXT_FLAG_NO_AGG_RINGS)
features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
if (!(bp->flags & BNXT_FLAG_TPA))
if ((bp->flags & BNXT_FLAG_NO_AGG_RINGS) || bp->xdp_prog)
features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
if (!(features & NETIF_F_GRO))

1
drivers/net/ethernet/broadcom/bnxt/bnxt.h
View File

@ -2130,6 +2130,7 @@ struct bnxt {
#define BNXT_DUMP_CRASH 1
struct bpf_prog *xdp_prog;
u8 xdp_has_frags;
struct bnxt_ptp_cfg *ptp_cfg;
u8 ptp_all_rx_tstamp;

1
drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
View File

@ -1306,6 +1306,7 @@ int bnxt_dl_register(struct bnxt *bp)
if (rc)
goto err_dl_port_unreg;
devlink_set_features(dl, DEVLINK_F_RELOAD);
out:
devlink_register(dl);
return 0;

2
drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
View File

@ -623,7 +623,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset)
hw_resc->max_stat_ctxs -= le16_to_cpu(req->min_stat_ctx) * n;
hw_resc->max_vnics -= le16_to_cpu(req->min_vnics) * n;
if (bp->flags & BNXT_FLAG_CHIP_P5)
hw_resc->max_irqs -= vf_msix * n;
hw_resc->max_nqs -= vf_msix;
rc = pf->active_vfs;
}

10
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
View File

@ -181,6 +181,7 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
struct xdp_buff *xdp)
{
struct bnxt_sw_rx_bd *rx_buf;
u32 buflen = PAGE_SIZE;
struct pci_dev *pdev;
dma_addr_t mapping;
u32 offset;
@ -192,7 +193,10 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
mapping = rx_buf->mapping - bp->rx_dma_offset;
dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
xdp_init_buff(xdp, BNXT_PAGE_MODE_BUF_SIZE + offset, &rxr->xdp_rxq);
if (bp->xdp_has_frags)
buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
}
@ -397,8 +401,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
return -EOPNOTSUPP;
}
if (prog)
if (prog) {
tx_xdp = bp->rx_nr_rings;
bp->xdp_has_frags = prog->aux->xdp_has_frags;
}
tc = netdev_get_num_tc(dev);
if (!tc)

6
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
View File

@ -2886,6 +2886,7 @@ static void dpaa_adjust_link(struct net_device *net_dev)
/* The Aquantia PHYs are capable of performing rate adaptation */
#define PHY_VEND_AQUANTIA 0x03a1b400
#define PHY_VEND_AQUANTIA2 0x31c31c00
static int dpaa_phy_init(struct net_device *net_dev)
{
@ -2893,6 +2894,7 @@ static int dpaa_phy_init(struct net_device *net_dev)
struct mac_device *mac_dev;
struct phy_device *phy_dev;
struct dpaa_priv *priv;
u32 phy_vendor;
priv = netdev_priv(net_dev);
mac_dev = priv->mac_dev;
@ -2905,9 +2907,11 @@ static int dpaa_phy_init(struct net_device *net_dev)
return -ENODEV;
}
phy_vendor = phy_dev->drv->phy_id & GENMASK(31, 10);
/* Unless the PHY is capable of rate adaptation */
if (mac_dev->phy_if != PHY_INTERFACE_MODE_XGMII ||
((phy_dev->drv->phy_id & GENMASK(31, 10)) != PHY_VEND_AQUANTIA)) {
(phy_vendor != PHY_VEND_AQUANTIA &&
phy_vendor != PHY_VEND_AQUANTIA2)) {
/* remove any features not supported by the controller */
ethtool_convert_legacy_u32_to_link_mode(mask,
mac_dev->if_support);

10
drivers/net/ethernet/freescale/fec.h
View File

@ -634,6 +634,13 @@ struct fec_enet_private {
int pps_enable;
unsigned int next_counter;
struct {
struct timespec64 ts_phc;
u64 ns_sys;
u32 at_corr;
u8 at_inc_corr;
} ptp_saved_state;
u64 ethtool_stats[];
};
@ -644,5 +651,8 @@ void fec_ptp_disable_hwts(struct net_device *ndev);
int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
void fec_ptp_save_state(struct fec_enet_private *fep);
int fec_ptp_restore_state(struct fec_enet_private *fep);
/****************************************************************************/
#endif /* FEC_H */

42
drivers/net/ethernet/freescale/fec_main.c
View File

@ -285,8 +285,11 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
#define FEC_MMFR_TA (2 << 16)
#define FEC_MMFR_DATA(v) (v & 0xffff)
/* FEC ECR bits definition */
#define FEC_ECR_MAGICEN (1 << 2)
#define FEC_ECR_SLEEP (1 << 3)
#define FEC_ECR_RESET BIT(0)
#define FEC_ECR_ETHEREN BIT(1)
#define FEC_ECR_MAGICEN BIT(2)
#define FEC_ECR_SLEEP BIT(3)
#define FEC_ECR_EN1588 BIT(4)
#define FEC_MII_TIMEOUT 30000 /* us */
@ -982,6 +985,9 @@ fec_restart(struct net_device *ndev)
u32 temp_mac[2];
u32 rcntl = OPT_FRAME_SIZE | 0x04;
u32 ecntl = 0x2; /* ETHEREN */
struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS };
fec_ptp_save_state(fep);
/* Whack a reset. We should wait for this.
* For i.MX6SX SOC, enet use AXI bus, we use disable MAC
@ -1135,7 +1141,7 @@ fec_restart(struct net_device *ndev)
}
if (fep->bufdesc_ex)
ecntl |= (1 << 4);
ecntl |= FEC_ECR_EN1588;
if (fep->quirks & FEC_QUIRK_DELAYED_CLKS_SUPPORT &&
fep->rgmii_txc_dly)
@ -1156,6 +1162,14 @@ fec_restart(struct net_device *ndev)
if (fep->bufdesc_ex)
fec_ptp_start_cyclecounter(ndev);
/* Restart PPS if needed */
if (fep->pps_enable) {
/* Clear flag so fec_ptp_enable_pps() doesn't return immediately */
fep->pps_enable = 0;
fec_ptp_restore_state(fep);
fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1);
}
/* Enable interrupts we wish to service */
if (fep->link)
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
@ -1206,6 +1220,8 @@ fec_stop(struct net_device *ndev)
struct fec_enet_private *fep = netdev_priv(ndev);
u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
u32 val;
struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS };
u32 ecntl = 0;
/* We cannot expect a graceful transmit stop without link !!! */
if (fep->link) {
@ -1215,6 +1231,8 @@ fec_stop(struct net_device *ndev)
netdev_err(ndev, "Graceful transmit stop did not complete!\n");
}
fec_ptp_save_state(fep);
/* Whack a reset. We should wait for this.
* For i.MX6SX SOC, enet use AXI bus, we use disable MAC
* instead of reset MAC itself.
@ -1234,12 +1252,28 @@ fec_stop(struct net_device *ndev)
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
if (fep->bufdesc_ex)
ecntl |= FEC_ECR_EN1588;
/* We have to keep ENET enabled to have MII interrupt stay working */
if (fep->quirks & FEC_QUIRK_ENET_MAC &&
!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
writel(2, fep->hwp + FEC_ECNTRL);
ecntl |= FEC_ECR_ETHEREN;
writel(rmii_mode, fep->hwp + FEC_R_CNTRL);
}
writel(ecntl, fep->hwp + FEC_ECNTRL);
if (fep->bufdesc_ex)
fec_ptp_start_cyclecounter(ndev);
/* Restart PPS if needed */
if (fep->pps_enable) {
/* Clear flag so fec_ptp_enable_pps() doesn't return immediately */
fep->pps_enable = 0;
fec_ptp_restore_state(fep);
fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1);
}
}

29
drivers/net/ethernet/freescale/fec_ptp.c
View File

@ -633,7 +633,36 @@ void fec_ptp_stop(struct platform_device *pdev)
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
if (fep->pps_enable)
fec_ptp_enable_pps(fep, 0);
cancel_delayed_work_sync(&fep->time_keep);
if (fep->ptp_clock)
ptp_clock_unregister(fep->ptp_clock);
}
void fec_ptp_save_state(struct fec_enet_private *fep)
{
u32 atime_inc_corr;
fec_ptp_gettime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc);
fep->ptp_saved_state.ns_sys = ktime_get_ns();
fep->ptp_saved_state.at_corr = readl(fep->hwp + FEC_ATIME_CORR);
atime_inc_corr = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_CORR_MASK;
fep->ptp_saved_state.at_inc_corr = (u8)(atime_inc_corr >> FEC_T_INC_CORR_OFFSET);
}
int fec_ptp_restore_state(struct fec_enet_private *fep)
{
u32 atime_inc = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK;
u64 ns_sys;
writel(fep->ptp_saved_state.at_corr, fep->hwp + FEC_ATIME_CORR);
atime_inc |= ((u32)fep->ptp_saved_state.at_inc_corr) << FEC_T_INC_CORR_OFFSET;
writel(atime_inc, fep->hwp + FEC_ATIME_INC);
ns_sys = ktime_get_ns() - fep->ptp_saved_state.ns_sys;
timespec64_add_ns(&fep->ptp_saved_state.ts_phc, ns_sys);
return fec_ptp_settime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc);
}

2
drivers/net/ethernet/intel/i40e/i40e_ethtool.c
View File

@ -4485,7 +4485,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
(struct in6_addr *)&ipv6_full_mask))
new_mask |= I40E_L3_V6_DST_MASK;
else if (ipv6_addr_any((struct in6_addr *)
&usr_ip6_spec->ip6src))
&usr_ip6_spec->ip6dst))
new_mask &= ~I40E_L3_V6_DST_MASK;
else
return -EOPNOTSUPP;

36
drivers/net/ethernet/intel/ice/ice.h
View File

@ -684,8 +684,8 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)
* ice_xsk_pool - get XSK buffer pool bound to a ring
* @ring: Rx ring to use
*
* Returns a pointer to xdp_umem structure if there is a buffer pool present,
* NULL otherwise.
* Returns a pointer to xsk_buff_pool structure if there is a buffer pool
* present, NULL otherwise.
*/
static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
{
@ -699,23 +699,33 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
}
/**
* ice_tx_xsk_pool - get XSK buffer pool bound to a ring
* @ring: Tx ring to use
* ice_tx_xsk_pool - assign XSK buff pool to XDP ring
* @vsi: pointer to VSI
* @qid: index of a queue to look at XSK buff pool presence
*
* Returns a pointer to xdp_umem structure if there is a buffer pool present,
* NULL otherwise. Tx equivalent of ice_xsk_pool.
* Sets XSK buff pool pointer on XDP ring.
*
* XDP ring is picked from Rx ring, whereas Rx ring is picked based on provided
* queue id. Reason for doing so is that queue vectors might have assigned more
* than one XDP ring, e.g. when user reduced the queue count on netdev; Rx ring
* carries a pointer to one of these XDP rings for its own purposes, such as
* handling XDP_TX action, therefore we can piggyback here on the
* rx_ring->xdp_ring assignment that was done during XDP rings initialization.
*/
static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring)
static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
{
struct ice_vsi *vsi = ring->vsi;
u16 qid;
struct ice_tx_ring *ring;
qid = ring->q_index - vsi->alloc_txq;
ring = vsi->rx_rings[qid]->xdp_ring;
if (!ring)
return;
if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
return NULL;
if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) {
ring->xsk_pool = NULL;
return;
}
return xsk_get_pool_from_qid(vsi->netdev, qid);
ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid);
}
/**

4
drivers/net/ethernet/intel/ice/ice_lib.c
View File

@ -1986,8 +1986,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi)
if (ret)
return ret;
ice_for_each_xdp_txq(vsi, i)
vsi->xdp_rings[i]->xsk_pool = ice_tx_xsk_pool(vsi->xdp_rings[i]);
ice_for_each_rxq(vsi, i)
ice_tx_xsk_pool(vsi, i);
return ret;
}

25
drivers/net/ethernet/intel/ice/ice_main.c
View File

@ -2581,7 +2581,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
if (ice_setup_tx_ring(xdp_ring))
goto free_xdp_rings;
ice_set_ring_xdp(xdp_ring);
xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring);
spin_lock_init(&xdp_ring->tx_lock);
for (j = 0; j < xdp_ring->count; j++) {
tx_desc = ICE_TX_DESC(xdp_ring, j);
@ -2589,13 +2588,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi)
}
}
ice_for_each_rxq(vsi, i) {
if (static_key_enabled(&ice_xdp_locking_key))
vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq];
else
vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i];
}
return 0;
free_xdp_rings:
@ -2685,6 +2677,23 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
xdp_rings_rem -= xdp_rings_per_v;
}
ice_for_each_rxq(vsi, i) {
if (static_key_enabled(&ice_xdp_locking_key)) {
vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq];
} else {
struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector;
struct ice_tx_ring *ring;
ice_for_each_tx_ring(ring, q_vector->tx) {
if (ice_ring_is_xdp(ring)) {
vsi->rx_rings[i]->xdp_ring = ring;
break;
}
}
}
ice_tx_xsk_pool(vsi, i);
}
/* omit the scheduler update if in reset path; XDP queues will be
* taken into account at the end of ice_vsi_rebuild, where
* ice_cfg_vsi_lan is being called

18
drivers/net/ethernet/intel/ice/ice_xsk.c
View File

@ -243,7 +243,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
if (err)
goto free_buf;
ice_set_ring_xdp(xdp_ring);
xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring);
ice_tx_xsk_pool(vsi, q_idx);
}
err = ice_vsi_cfg_rxq(rx_ring);
@ -329,6 +329,12 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
bool if_running, pool_present = !!pool;
int ret = 0, pool_failure = 0;
if (qid >= vsi->num_rxq || qid >= vsi->num_txq) {
netdev_err(vsi->netdev, "Please use queue id in scope of combined queues count\n");
pool_failure = -EINVAL;
goto failure;
}
if (!is_power_of_2(vsi->rx_rings[qid]->count) ||
!is_power_of_2(vsi->tx_rings[qid]->count)) {
netdev_err(vsi->netdev, "Please align ring sizes to power of 2\n");
@ -353,7 +359,7 @@ xsk_pool_if_up:
if (if_running) {
ret = ice_qp_ena(vsi, qid);
if (!ret && pool_present)
napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi);
napi_schedule(&vsi->rx_rings[qid]->xdp_ring->q_vector->napi);
else if (ret)
netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret);
}
@ -944,13 +950,13 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
if (!ice_is_xdp_ena_vsi(vsi))
return -EINVAL;
if (queue_id >= vsi->num_txq)
if (queue_id >= vsi->num_txq || queue_id >= vsi->num_rxq)
return -EINVAL;
if (!vsi->xdp_rings[queue_id]->xsk_pool)
return -EINVAL;
ring = vsi->rx_rings[queue_id]->xdp_ring;
ring = vsi->xdp_rings[queue_id];
if (!ring->xsk_pool)
return -EINVAL;
/* The idea here is that if NAPI is running, mark a miss, so
* it will run again. If not, trigger an interrupt and

59
drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
View File

@ -1214,7 +1214,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
struct cyclecounter cc;
unsigned long flags;
u32 incval = 0;
u32 tsauxc = 0;
u32 fuse0 = 0;
/* For some of the boards below this mask is technically incorrect.
@ -1249,18 +1248,6 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
case ixgbe_mac_x550em_a:
case ixgbe_mac_X550:
cc.read = ixgbe_ptp_read_X550;
/* enable SYSTIME counter */
IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
IXGBE_WRITE_FLUSH(hw);
break;
case ixgbe_mac_X540:
cc.read = ixgbe_ptp_read_82599;
@ -1292,6 +1279,50 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
}
/**
* ixgbe_ptp_init_systime - Initialize SYSTIME registers
* @adapter: the ixgbe private board structure
*
* Initialize and start the SYSTIME registers.
*/
static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
u32 tsauxc;
switch (hw->mac.type) {
case ixgbe_mac_X550EM_x:
case ixgbe_mac_x550em_a:
case ixgbe_mac_X550:
tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
/* Reset SYSTIME registers to 0 */
IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0);
IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
/* Reset interrupt settings */
IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS);
IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC);
/* Activate the SYSTIME counter */
IXGBE_WRITE_REG(hw, IXGBE_TSAUXC,
tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME);
break;
case ixgbe_mac_X540:
case ixgbe_mac_82599EB:
/* Reset SYSTIME registers to 0 */
IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0);
IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0);
break;
default:
/* Other devices aren't supported */
return;
};
IXGBE_WRITE_FLUSH(hw);
}
/**
* ixgbe_ptp_reset
* @adapter: the ixgbe private board structure
@ -1318,6 +1349,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
ixgbe_ptp_start_cyclecounter(adapter);
ixgbe_ptp_init_systime(adapter);
spin_lock_irqsave(&adapter->tmreg_lock, flags);
timecounter_init(&adapter->hw_tc, &adapter->hw_cc,
ktime_to_ns(ktime_get_real()));

9
drivers/net/ethernet/lantiq_xrx200.c
View File

@ -193,6 +193,7 @@ static int xrx200_alloc_buf(struct xrx200_chan *ch, void *(*alloc)(unsigned int
ch->rx_buff[ch->dma.desc] = alloc(priv->rx_skb_size);
if (!ch->rx_buff[ch->dma.desc]) {
ch->rx_buff[ch->dma.desc] = buf;
ret = -ENOMEM;
goto skip;
}
@ -239,6 +240,12 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
}
skb = build_skb(buf, priv->rx_skb_size);
if (!skb) {
skb_free_frag(buf);
net_dev->stats.rx_dropped++;
return -ENOMEM;
}
skb_reserve(skb, NET_SKB_PAD);
skb_put(skb, len);
@ -288,7 +295,7 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget)
if (ret == XRX200_DMA_PACKET_IN_PROGRESS)
continue;
if (ret != XRX200_DMA_PACKET_COMPLETE)
return ret;
break;
rx++;
} else {
break;

22
drivers/net/ethernet/mediatek/mtk_eth_soc.c
View File

@ -1891,10 +1891,19 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
skb->dev = netdev;
bytes += skb->len;
if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2))
if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
hash = trxd.rxd5 & MTK_RXD5_FOE_ENTRY;
if (hash != MTK_RXD5_FOE_ENTRY)
skb_set_hash(skb, jhash_1word(hash, 0),
PKT_HASH_TYPE_L4);
rxdcsum = &trxd.rxd3;
else
} else {
hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY;
if (hash != MTK_RXD4_FOE_ENTRY)
skb_set_hash(skb, jhash_1word(hash, 0),
PKT_HASH_TYPE_L4);
rxdcsum = &trxd.rxd4;
}
if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid)
skb->ip_summed = CHECKSUM_UNNECESSARY;
@ -1902,16 +1911,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
skb_checksum_none_assert(skb);
skb->protocol = eth_type_trans(skb, netdev);
hash = trxd.rxd4 & MTK_RXD4_FOE_ENTRY;
if (hash != MTK_RXD4_FOE_ENTRY) {
hash = jhash_1word(hash, 0);
skb_set_hash(skb, hash, PKT_HASH_TYPE_L4);
}
reason = FIELD_GET(MTK_RXD4_PPE_CPU_REASON, trxd.rxd4);
if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
mtk_ppe_check_skb(eth->ppe, skb,
trxd.rxd4 & MTK_RXD4_FOE_ENTRY);
mtk_ppe_check_skb(eth->ppe, skb, hash);
if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {

5
drivers/net/ethernet/mediatek/mtk_eth_soc.h
View File

@ -314,6 +314,11 @@
#define RX_DMA_L4_VALID_PDMA BIT(30) /* when PDMA is used */
#define RX_DMA_SPECIAL_TAG BIT(22)
/* PDMA descriptor rxd5 */
#define MTK_RXD5_FOE_ENTRY GENMASK(14, 0)
#define MTK_RXD5_PPE_CPU_REASON GENMASK(22, 18)
#define MTK_RXD5_SRC_PORT GENMASK(29, 26)
#define RX_DMA_GET_SPORT(x) (((x) >> 19) & 0xf)
#define RX_DMA_GET_SPORT_V2(x) (((x) >> 26) & 0x7)

4
drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
View File

@ -79,6 +79,10 @@ tc_act_police_offload(struct mlx5e_priv *priv,
struct mlx5e_flow_meter_handle *meter;
int err = 0;
err = mlx5e_policer_validate(&fl_act->action, act, fl_act->extack);
if (err)
return err;
err = fill_meter_params_from_act(act, &params);
if (err)
return err;

4
drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
View File

@ -246,7 +246,7 @@ static void mlx5e_tls_priv_tx_cleanup(struct mlx5e_ktls_offload_context_tx *priv
static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev,
struct list_head *list, int size)
{
struct mlx5e_ktls_offload_context_tx *obj;
struct mlx5e_ktls_offload_context_tx *obj, *n;
struct mlx5e_async_ctx *bulk_async;
int i;
@ -255,7 +255,7 @@ static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev,
return;
i = 0;
list_for_each_entry(obj, list, list_node) {
list_for_each_entry_safe(obj, n, list, list_node) {
mlx5e_tls_priv_tx_cleanup(obj, &bulk_async[i]);
i++;
}

5
drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
View File

@ -1395,10 +1395,11 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
}
return fs;
err_free_fs:
kvfree(fs);
err_free_vlan:
mlx5e_fs_vlan_free(fs);
err_free_fs:
kvfree(fs);
err:
return NULL;
}

12
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
View File

@ -3682,7 +3682,9 @@ static int set_feature_hw_tc(struct net_device *netdev, bool enable)
int err = 0;
#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) {
int tc_flag = mlx5e_is_uplink_rep(priv) ? MLX5_TC_FLAG(ESW_OFFLOAD) :
MLX5_TC_FLAG(NIC_OFFLOAD);
if (!enable && mlx5e_tc_num_filters(priv, tc_flag)) {
netdev_err(netdev,
"Active offloaded tc filters, can't turn hw_tc_offload off\n");
return -EINVAL;
@ -4769,14 +4771,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
/* RQ */
mlx5e_build_rq_params(mdev, params);
/* HW LRO */
if (MLX5_CAP_ETH(mdev, lro_cap) &&
params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
/* No XSK params: checking the availability of striding RQ in general. */
if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
params->packet_merge.type = slow_pci_heuristic(mdev) ?
MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
}
params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
/* CQ moderation params */

2
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
View File

@ -662,6 +662,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
params->mqprio.num_tc = 1;
params->tunneled_offload_en = false;
if (rep->vport != MLX5_VPORT_UPLINK)
params->vlan_strip_disable = true;
mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
}

7
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
View File

@ -427,7 +427,8 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
dest[dest_idx].vport.vhca_id =
MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
if (mlx5_lag_mpesw_is_activated(esw->dev))
if (dest[dest_idx].vport.num == MLX5_VPORT_UPLINK &&
mlx5_lag_mpesw_is_activated(esw->dev))
dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
}
if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) {
@ -3115,8 +3116,10 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
err = mlx5_eswitch_load_vf_vports(esw, new_num_vfs,
MLX5_VPORT_UC_ADDR_CHANGE);
if (err)
if (err) {
devl_unlock(devlink);
return;
}
}
esw->esw_funcs.num_vfs = new_num_vfs;
devl_unlock(devlink);

57
drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
View File

@ -1067,30 +1067,32 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev,
struct net_device *netdev)
{
unsigned int fn = mlx5_get_dev_index(dev);
unsigned long flags;
if (fn >= ldev->ports)
return;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev->pf[fn].netdev = netdev;
ldev->tracker.netdev_state[fn].link_up = 0;
ldev->tracker.netdev_state[fn].tx_enabled = 0;
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
}
static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
struct net_device *netdev)
{
unsigned long flags;
int i;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
for (i = 0; i < ldev->ports; i++) {
if (ldev->pf[i].netdev == netdev) {
ldev->pf[i].netdev = NULL;
break;
}
}
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
}
static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
@ -1234,7 +1236,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
mlx5_ldev_add_netdev(ldev, dev, netdev);
for (i = 0; i < ldev->ports; i++)
if (!ldev->pf[i].dev)
if (!ldev->pf[i].netdev)
break;
if (i >= ldev->ports)
@ -1246,12 +1248,13 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
unsigned long flags;
bool res;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
res = ldev && __mlx5_lag_is_roce(ldev);
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return res;
}
@ -1260,12 +1263,13 @@ EXPORT_SYMBOL(mlx5_lag_is_roce);
bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
unsigned long flags;
bool res;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
res = ldev && __mlx5_lag_is_active(ldev);
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return res;
}
@ -1274,13 +1278,14 @@ EXPORT_SYMBOL(mlx5_lag_is_active);
bool mlx5_lag_is_master(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
unsigned long flags;
bool res;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
res = ldev && __mlx5_lag_is_active(ldev) &&
dev == ldev->pf[MLX5_LAG_P1].dev;
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return res;
}
@ -1289,12 +1294,13 @@ EXPORT_SYMBOL(mlx5_lag_is_master);
bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
unsigned long flags;
bool res;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
res = ldev && __mlx5_lag_is_sriov(ldev);
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return res;
}
@ -1303,13 +1309,14 @@ EXPORT_SYMBOL(mlx5_lag_is_sriov);
bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
unsigned long flags;
bool res;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
res = ldev && __mlx5_lag_is_sriov(ldev) &&
test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return res;
}
@ -1352,9 +1359,10 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
{
struct net_device *ndev = NULL;
struct mlx5_lag *ldev;
unsigned long flags;
int i;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
if (!(ldev && __mlx5_lag_is_roce(ldev)))
@ -1373,7 +1381,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
dev_hold(ndev);
unlock:
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return ndev;
}
@ -1383,10 +1391,11 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
struct net_device *slave)
{
struct mlx5_lag *ldev;
unsigned long flags;
u8 port = 0;
int i;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
if (!(ldev && __mlx5_lag_is_roce(ldev)))
goto unlock;
@ -1401,7 +1410,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
port = ldev->v2p_map[port * ldev->buckets];
unlock:
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return port;
}
EXPORT_SYMBOL(mlx5_lag_get_slave_port);
@ -1422,8 +1431,9 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
{
struct mlx5_core_dev *peer_dev = NULL;
struct mlx5_lag *ldev;
unsigned long flags;
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
if (!ldev)
goto unlock;
@ -1433,7 +1443,7 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
ldev->pf[MLX5_LAG_P1].dev;
unlock:
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
return peer_dev;
}
EXPORT_SYMBOL(mlx5_lag_get_peer_mdev);
@ -1446,6 +1456,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
struct mlx5_core_dev **mdev;
struct mlx5_lag *ldev;
unsigned long flags;
int num_ports;
int ret, i, j;
void *out;
@ -1462,7 +1473,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
memset(values, 0, sizeof(*values) * num_counters);
spin_lock(&lag_lock);
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
if (ldev && __mlx5_lag_is_active(ldev)) {
num_ports = ldev->ports;
@ -1472,7 +1483,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
num_ports = 1;
mdev[MLX5_LAG_P1] = dev;
}
spin_unlock(&lag_lock);
spin_unlock_irqrestore(&lag_lock, flags);
for (i = 0; i < num_ports; ++i) {
u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};

4
drivers/net/ethernet/mellanox/mlx5/core/main.c
View File

@ -1530,7 +1530,9 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
INIT_LIST_HEAD(&priv->ctx_list);
spin_lock_init(&priv->ctx_lock);
lockdep_register_key(&dev->lock_key);
mutex_init(&dev->intf_state_mutex);
lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
mutex_init(&priv->bfregs.reg_head.lock);
mutex_init(&priv->bfregs.wc_head.lock);
@ -1597,6 +1599,7 @@ err_timeout_init:
mutex_destroy(&priv->bfregs.wc_head.lock);
mutex_destroy(&priv->bfregs.reg_head.lock);
mutex_destroy(&dev->intf_state_mutex);
lockdep_unregister_key(&dev->lock_key);
return err;
}
@ -1618,6 +1621,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
mutex_destroy(&priv->bfregs.wc_head.lock);
mutex_destroy(&priv->bfregs.reg_head.lock);
mutex_destroy(&dev->intf_state_mutex);
lockdep_unregister_key(&dev->lock_key);
}
static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)

9
drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
View File

@ -376,8 +376,8 @@ retry:
goto out_dropped;
}
}
err = mlx5_cmd_check(dev, err, in, out);
if (err) {
err = mlx5_cmd_check(dev, err, in, out);
mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
func_id, npages, err);
goto out_dropped;
@ -524,10 +524,13 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
dev->priv.reclaim_pages_discard += npages;
}
/* if triggered by FW event and failed by FW then ignore */
if (event && err == -EREMOTEIO)
if (event && err == -EREMOTEIO) {
err = 0;
goto out_free;
}
err = mlx5_cmd_check(dev, err, in, out);
if (err) {
err = mlx5_cmd_check(dev, err, in, out);
mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
goto out_free;
}

2
drivers/net/ethernet/mellanox/mlx5/core/sriov.c
View File

@ -159,11 +159,11 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
devl_lock(devlink);
err = mlx5_device_enable_sriov(dev, num_vfs);
devl_unlock(devlink);
if (err) {
mlx5_core_warn(dev, "mlx5_device_enable_sriov failed : %d\n", err);
return err;
}
devl_unlock(devlink);
err = pci_enable_sriov(pdev, num_vfs);
if (err) {

11
drivers/net/ethernet/moxa/moxart_ether.c
View File

@ -71,11 +71,6 @@ static int moxart_set_mac_address(struct net_device *ndev, void *addr)
static void moxart_mac_free_memory(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
int i;
for (i = 0; i < RX_DESC_NUM; i++)
dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
priv->rx_buf_size, DMA_FROM_DEVICE);
if (priv->tx_desc_base)
dma_free_coherent(&priv->pdev->dev,
@ -187,6 +182,7 @@ static int moxart_mac_open(struct net_device *ndev)
static int moxart_mac_stop(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
int i;
napi_disable(&priv->napi);
@ -198,6 +194,11 @@ static int moxart_mac_stop(struct net_device *ndev)
/* disable all functions */
writel(0, priv->base + REG_MAC_CTRL);
/* unmap areas mapped in moxart_mac_setup_desc_ring() */
for (i = 0; i < RX_DESC_NUM; i++)
dma_unmap_single(&priv->pdev->dev, priv->rx_mapping[i],
priv->rx_buf_size, DMA_FROM_DEVICE);
return 0;
}

95
drivers/net/ethernet/pensando/ionic/ionic_lif.c
View File

@ -1564,8 +1564,67 @@ static int ionic_set_features(struct net_device *netdev,
return err;
}
static int ionic_set_attr_mac(struct ionic_lif *lif, u8 *mac)
{
struct ionic_admin_ctx ctx = {
.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
.cmd.lif_setattr = {
.opcode = IONIC_CMD_LIF_SETATTR,
.index = cpu_to_le16(lif->index),
.attr = IONIC_LIF_ATTR_MAC,
},
};
ether_addr_copy(ctx.cmd.lif_setattr.mac, mac);
return ionic_adminq_post_wait(lif, &ctx);
}
static int ionic_get_attr_mac(struct ionic_lif *lif, u8 *mac_addr)
{
struct ionic_admin_ctx ctx = {
.work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
.cmd.lif_getattr = {
.opcode = IONIC_CMD_LIF_GETATTR,
.index = cpu_to_le16(lif->index),
.attr = IONIC_LIF_ATTR_MAC,
},
};
int err;
err = ionic_adminq_post_wait(lif, &ctx);
if (err)
return err;
ether_addr_copy(mac_addr, ctx.comp.lif_getattr.mac);
return 0;
}
static int ionic_program_mac(struct ionic_lif *lif, u8 *mac)
{
u8 get_mac[ETH_ALEN];
int err;
err = ionic_set_attr_mac(lif, mac);
if (err)
return err;
err = ionic_get_attr_mac(lif, get_mac);
if (err)
return err;
/* To deal with older firmware that silently ignores the set attr mac:
* doesn't actually change the mac and doesn't return an error, so we
* do the get attr to verify whether or not the set actually happened
*/
if (!ether_addr_equal(get_mac, mac))
return 1;
return 0;
}
static int ionic_set_mac_address(struct net_device *netdev, void *sa)
{
struct ionic_lif *lif = netdev_priv(netdev);
struct sockaddr *addr = sa;
u8 *mac;
int err;
@ -1574,6 +1633,14 @@ static int ionic_set_mac_address(struct net_device *netdev, void *sa)
if (ether_addr_equal(netdev->dev_addr, mac))
return 0;
err = ionic_program_mac(lif, mac);
if (err < 0)
return err;
if (err > 0)
netdev_dbg(netdev, "%s: SET and GET ATTR Mac are not equal-due to old FW running\n",
__func__);
err = eth_prepare_mac_addr_change(netdev, addr);
if (err)
return err;
@ -2963,6 +3030,9 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif)
mutex_lock(&lif->queue_lock);
if (test_and_clear_bit(IONIC_LIF_F_BROKEN, lif->state))
dev_info(ionic->dev, "FW Up: clearing broken state\n");
err = ionic_qcqs_alloc(lif);
if (err)
goto err_unlock;
@ -3169,6 +3239,7 @@ static int ionic_station_set(struct ionic_lif *lif)
.attr = IONIC_LIF_ATTR_MAC,
},
};
u8 mac_address[ETH_ALEN];
struct sockaddr addr;
int err;
@ -3177,8 +3248,23 @@ static int ionic_station_set(struct ionic_lif *lif)
return err;
netdev_dbg(lif->netdev, "found initial MAC addr %pM\n",
ctx.comp.lif_getattr.mac);
if (is_zero_ether_addr(ctx.comp.lif_getattr.mac))
return 0;
ether_addr_copy(mac_address, ctx.comp.lif_getattr.mac);
if (is_zero_ether_addr(mac_address)) {
eth_hw_addr_random(netdev);
netdev_dbg(netdev, "Random Mac generated: %pM\n", netdev->dev_addr);
ether_addr_copy(mac_address, netdev->dev_addr);
err = ionic_program_mac(lif, mac_address);
if (err < 0)
return err;
if (err > 0) {
netdev_dbg(netdev, "%s:SET/GET ATTR Mac are not same-due to old FW running\n",
__func__);
return 0;
}
}
if (!is_zero_ether_addr(netdev->dev_addr)) {
/* If the netdev mac is non-zero and doesn't match the default
@ -3186,12 +3272,11 @@ static int ionic_station_set(struct ionic_lif *lif)
* likely here again after a fw-upgrade reset. We need to be
* sure the netdev mac is in our filter list.
*/
if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
netdev->dev_addr))
if (!ether_addr_equal(mac_address, netdev->dev_addr))
ionic_lif_addr_add(lif, netdev->dev_addr);
} else {
/* Update the netdev mac with the device's mac */
memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
ether_addr_copy(addr.sa_data, mac_address);
addr.sa_family = AF_INET;
err = eth_prepare_mac_addr_change(netdev, &addr);
if (err) {

4
drivers/net/ethernet/pensando/ionic/ionic_main.c
View File

@ -474,8 +474,8 @@ try_again:
ionic_opcode_to_str(opcode), opcode,
ionic_error_to_str(err), err);
msleep(1000);
iowrite32(0, &idev->dev_cmd_regs->done);
msleep(1000);
iowrite32(1, &idev->dev_cmd_regs->doorbell);
goto try_again;
}
@ -488,6 +488,8 @@ try_again:
return ionic_error_to_errno(err);
}
ionic_dev_cmd_clean(ionic);
return 0;
}

8
drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
View File

@ -258,14 +258,18 @@ EXPORT_SYMBOL_GPL(stmmac_set_mac_addr);
/* Enable disable MAC RX/TX */
void stmmac_set_mac(void __iomem *ioaddr, bool enable)
{
u32 value = readl(ioaddr + MAC_CTRL_REG);
u32 old_val, value;
old_val = readl(ioaddr + MAC_CTRL_REG);
value = old_val;
if (enable)
value |= MAC_ENABLE_RX | MAC_ENABLE_TX;
else
value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
writel(value, ioaddr + MAC_CTRL_REG);
if (value != old_val)
writel(value, ioaddr + MAC_CTRL_REG);
}
void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,

9
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
View File

@ -986,10 +986,10 @@ static void stmmac_mac_link_up(struct phylink_config *config,
bool tx_pause, bool rx_pause)
{
struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
u32 ctrl;
u32 old_ctrl, ctrl;
ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
ctrl &= ~priv->hw->link.speed_mask;
old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
ctrl = old_ctrl & ~priv->hw->link.speed_mask;
if (interface == PHY_INTERFACE_MODE_USXGMII) {
switch (speed) {
@ -1064,7 +1064,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
if (tx_pause && rx_pause)
stmmac_mac_flow_ctrl(priv, duplex);
writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
if (ctrl != old_ctrl)
writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
stmmac_mac_set(priv, priv->ioaddr, true);
if (phy && priv->dma_cap.eee) {

2
drivers/net/ipa/ipa_mem.c
View File

@ -568,7 +568,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size)
}
/* Align the address down and the size up to a page boundary */
addr = qcom_smem_virt_to_phys(virt) & PAGE_MASK;
addr = qcom_smem_virt_to_phys(virt);
phys = addr & PAGE_MASK;
size = PAGE_ALIGN(size + addr - phys);
iova = phys; /* We just want a direct mapping */

4
drivers/net/ipvlan/ipvtap.c
View File

@ -194,7 +194,7 @@ static struct notifier_block ipvtap_notifier_block __read_mostly = {
.notifier_call = ipvtap_device_event,
};
static int ipvtap_init(void)
static int __init ipvtap_init(void)
{
int err;
@ -228,7 +228,7 @@ out1:
}
module_init(ipvtap_init);
static void ipvtap_exit(void)
static void __exit ipvtap_exit(void)
{
rtnl_link_unregister(&ipvtap_link_ops);
unregister_netdevice_notifier(&ipvtap_notifier_block);

11
drivers/net/macsec.c
View File

@ -462,11 +462,6 @@ static struct macsec_eth_header *macsec_ethhdr(struct sk_buff *skb)
return (struct macsec_eth_header *)skb_mac_header(skb);
}
static sci_t dev_to_sci(struct net_device *dev, __be16 port)
{
return make_sci(dev->dev_addr, port);
}
static void __macsec_pn_wrapped(struct macsec_secy *secy,
struct macsec_tx_sa *tx_sa)
{
@ -3661,7 +3656,6 @@ static int macsec_set_mac_address(struct net_device *dev, void *p)
out:
eth_hw_addr_set(dev, addr->sa_data);
macsec->secy.sci = dev_to_sci(dev, MACSEC_PORT_ES);
/* If h/w offloading is available, propagate to the device */
if (macsec_is_offloaded(macsec)) {
@ -4000,6 +3994,11 @@ static bool sci_exists(struct net_device *dev, sci_t sci)
return false;
}
static sci_t dev_to_sci(struct net_device *dev, __be16 port)
{
return make_sci(dev->dev_addr, port);
}
static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
{
struct macsec_dev *macsec = macsec_priv(dev);

8
drivers/net/phy/phy_device.c
View File

@ -316,11 +316,11 @@ static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
phydev->suspended_by_mdio_bus = 0;
/* If we managed to get here with the PHY state machine in a state other
* than PHY_HALTED this is an indication that something went wrong and
* we should most likely be using MAC managed PM and we are not.
/* If we manged to get here with the PHY state machine in a state neither
* PHY_HALTED nor PHY_READY this is an indication that something went wrong
* and we should most likely be using MAC managed PM and we are not.
*/
WARN_ON(phydev->state != PHY_HALTED && !phydev->mac_managed_pm);
WARN_ON(phydev->state != PHY_HALTED && phydev->state != PHY_READY);
ret = phy_init_hw(phydev);
if (ret < 0)

27
drivers/net/usb/r8152.c
View File

@ -5906,6 +5906,11 @@ static void r8153_enter_oob(struct r8152 *tp)
ocp_data &= ~NOW_IS_OOB;
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
/* RX FIFO settings for OOB */
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL0, RXFIFO_THR1_OOB);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL1, RXFIFO_THR2_OOB);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL2, RXFIFO_THR3_OOB);
rtl_disable(tp);
rtl_reset_bmu(tp);
@ -6431,21 +6436,8 @@ static void r8156_fc_parameter(struct r8152 *tp)
u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp);
u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp);
switch (tp->version) {
case RTL_VER_10:
case RTL_VER_11:
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 8);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 8);
break;
case RTL_VER_12:
case RTL_VER_13:
case RTL_VER_15:
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
break;
default:
break;
}
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16);
}
static void rtl8156_change_mtu(struct r8152 *tp)
@ -6557,6 +6549,11 @@ static void rtl8156_down(struct r8152 *tp)
ocp_data &= ~NOW_IS_OOB;
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
/* RX FIFO settings for OOB */
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RXFIFO_FULL, 64 / 16);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, 1024 / 16);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, 4096 / 16);
rtl_disable(tp);
rtl_reset_bmu(tp);

1
drivers/nfc/pn533/uart.c
View File

@ -310,6 +310,7 @@ static void pn532_uart_remove(struct serdev_device *serdev)
pn53x_unregister_nfc(pn532->priv);
serdev_device_close(serdev);
pn53x_common_clean(pn532->priv);
del_timer_sync(&pn532->cmd_timeout);
kfree_skb(pn532->recv_skb);
kfree(pn532);
}

14
fs/inode.c
View File

@ -2018,23 +2018,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags)
{
struct dentry *dentry = file_dentry(file);
struct inode *inode = file_inode(file);
int error;
int error = 0;
int kill;
if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
kill = dentry_needs_remove_privs(dentry);
if (kill <= 0)
if (kill < 0)
return kill;
if (flags & IOCB_NOWAIT)
return -EAGAIN;
if (kill) {
if (flags & IOCB_NOWAIT)
return -EAGAIN;
error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
}
error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
if (!error)
inode_has_no_xattr(inode);
return error;
}

5
include/linux/cgroup.h
View File

@ -734,11 +734,6 @@ static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
return NULL;
}
static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
{
return NULL;
}
static inline bool cgroup_psi_enabled(void)
{
return false;

1
include/linux/mlx5/driver.h
View File

@ -779,6 +779,7 @@ struct mlx5_core_dev {
enum mlx5_device_state state;
/* sync interface state */
struct mutex intf_state_mutex;
struct lock_class_key lock_key;
unsigned long intf_state;
struct mlx5_priv priv;
struct mlx5_profile profile;

20
include/linux/netdevice.h
View File

@ -640,9 +640,23 @@ extern int sysctl_devconf_inherit_init_net;
*/
static inline bool net_has_fallback_tunnels(const struct net *net)
{
return !IS_ENABLED(CONFIG_SYSCTL) ||
!sysctl_fb_tunnels_only_for_init_net ||
(net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1);
#if IS_ENABLED(CONFIG_SYSCTL)
int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net);
return !fb_tunnels_only_for_init_net ||
(net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1);
#else
return true;
#endif
}
static inline int net_inherit_devconf(void)
{
#if IS_ENABLED(CONFIG_SYSCTL)
return READ_ONCE(sysctl_devconf_inherit_init_net);
#else
return 0;
#endif
}
static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)

4
include/linux/netfilter_bridge/ebtables.h
View File

@ -94,10 +94,6 @@ struct ebt_table {
struct ebt_replace_kernel *table;
unsigned int valid_hooks;
rwlock_t lock;
/* e.g. could be the table explicitly only allows certain
* matches, targets, ... 0 == let it in */
int (*check)(const struct ebt_table_info *info,
unsigned int valid_hooks);
/* the data used by the kernel */
struct ebt_table_info *private;
struct nf_hook_ops *ops;

2
include/linux/psi.h
View File

@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags);
int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
struct psi_trigger *psi_trigger_create(struct psi_group *group,
char *buf, size_t nbytes, enum psi_res res);
char *buf, enum psi_res res);
void psi_trigger_destroy(struct psi_trigger *t);
__poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,

2
include/net/bond_3ad.h
View File

@ -290,7 +290,7 @@ static inline const char *bond_3ad_churn_desc(churn_state_t state)
}
/* ========== AD Exported functions to the main bonding code ========== */
void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution);
void bond_3ad_initialize(struct bonding *bond);
void bond_3ad_bind_slave(struct slave *slave);
void bond_3ad_unbind_slave(struct slave *slave);
void bond_3ad_state_machine_handler(struct work_struct *);

2
include/net/busy_poll.h
View File

@ -33,7 +33,7 @@ extern unsigned int sysctl_net_busy_poll __read_mostly;
static inline bool net_busy_loop_on(void)
{
return sysctl_net_busy_poll;
return READ_ONCE(sysctl_net_busy_poll);
}
static inline bool sk_can_busy_loop(const struct sock *sk)

2
include/net/gro.h
View File

@ -439,7 +439,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb,
{
list_add_tail(&skb->list, &napi->rx_list);
napi->rx_count += segs;
if (napi->rx_count >= gro_normal_batch)
if (napi->rx_count >= READ_ONCE(gro_normal_batch))
gro_normal_list(napi);
}

3
include/net/netfilter/nf_flow_table.h
View File

@ -270,6 +270,7 @@ void flow_offload_refresh(struct nf_flowtable *flow_table,
struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple);
void nf_flow_table_gc_run(struct nf_flowtable *flow_table);
void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable,
struct net_device *dev);
void nf_flow_table_cleanup(struct net_device *dev);
@ -306,6 +307,8 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
struct flow_offload *flow);
void nf_flow_table_offload_flush(struct nf_flowtable *flowtable);
void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable);
int nf_flow_table_offload_setup(struct nf_flowtable *flowtable,
struct net_device *dev,
enum flow_block_command cmd);

1
include/net/netfilter/nf_tables.h
View File

@ -1652,6 +1652,7 @@ struct nftables_pernet {
struct list_head module_list;
struct list_head notify_list;
struct mutex commit_mutex;
u64 table_handle;
unsigned int base_seq;
u8 validate_state;
};

2
include/uapi/linux/xfrm.h
View File

@ -296,7 +296,7 @@ enum xfrm_attr_type_t {
XFRMA_ETIMER_THRESH,
XFRMA_SRCADDR, /* xfrm_address_t */
XFRMA_COADDR, /* xfrm_address_t */
XFRMA_LASTUSED, /* unsigned long */
XFRMA_LASTUSED, /* __u64 */
XFRMA_POLICY_TYPE, /* struct xfrm_userpolicy_type */
XFRMA_MIGRATE,
XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */

1
kernel/audit_fsnotify.c
View File

@ -102,6 +102,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0);
if (ret < 0) {
audit_mark->path = NULL;
fsnotify_put_mark(&audit_mark->mark);
audit_mark = ERR_PTR(ret);
}

2
kernel/cgroup/cgroup-v1.c
View File

@ -59,6 +59,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
int retval = 0;
mutex_lock(&cgroup_mutex);
cpus_read_lock();
percpu_down_write(&cgroup_threadgroup_rwsem);
for_each_root(root) {
struct cgroup *from_cgrp;
@ -72,6 +73,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
break;
}
percpu_up_write(&cgroup_threadgroup_rwsem);
cpus_read_unlock();
mutex_unlock(&cgroup_mutex);
return retval;

80
kernel/cgroup/cgroup.c
View File

@ -1820,6 +1820,7 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
if (ss->css_rstat_flush) {
list_del_rcu(&css->rstat_css_node);
synchronize_rcu();
list_add_rcu(&css->rstat_css_node,
&dcgrp->rstat_css_list);
}
@ -2369,6 +2370,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
}
EXPORT_SYMBOL_GPL(task_cgroup_path);
/**
* cgroup_attach_lock - Lock for ->attach()
* @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem
*
* cgroup migration sometimes needs to stabilize threadgroups against forks and
* exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach()
* implementations (e.g. cpuset), also need to disable CPU hotplug.
* Unfortunately, letting ->attach() operations acquire cpus_read_lock() can
* lead to deadlocks.
*
* Bringing up a CPU may involve creating and destroying tasks which requires
* read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
* cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while
* write-locking threadgroup_rwsem, the locking order is reversed and we end up
* waiting for an on-going CPU hotplug operation which in turn is waiting for
* the threadgroup_rwsem to be released to create new tasks. For more details:
*
* http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu
*
* Resolve the situation by always acquiring cpus_read_lock() before optionally
* write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that
* CPU hotplug is disabled on entry.
*/
static void cgroup_attach_lock(bool lock_threadgroup)
{
cpus_read_lock();
if (lock_threadgroup)
percpu_down_write(&cgroup_threadgroup_rwsem);
}
/**
* cgroup_attach_unlock - Undo cgroup_attach_lock()
* @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem
*/
static void cgroup_attach_unlock(bool lock_threadgroup)
{
if (lock_threadgroup)
percpu_up_write(&cgroup_threadgroup_rwsem);
cpus_read_unlock();
}
/**
* cgroup_migrate_add_task - add a migration target task to a migration context
* @task: target task
@ -2841,8 +2883,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
}
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
bool *locked)
__acquires(&cgroup_threadgroup_rwsem)
bool *threadgroup_locked)
{
struct task_struct *tsk;
pid_t pid;
@ -2859,12 +2900,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
* Therefore, we can skip the global lock.
*/
lockdep_assert_held(&cgroup_mutex);
if (pid || threadgroup) {
percpu_down_write(&cgroup_threadgroup_rwsem);
*locked = true;
} else {
*locked = false;
}
*threadgroup_locked = pid || threadgroup;
cgroup_attach_lock(*threadgroup_locked);
rcu_read_lock();
if (pid) {
@ -2895,17 +2932,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup,
goto out_unlock_rcu;
out_unlock_threadgroup:
if (*locked) {
percpu_up_write(&cgroup_threadgroup_rwsem);
*locked = false;
}
cgroup_attach_unlock(*threadgroup_locked);
*threadgroup_locked = false;
out_unlock_rcu:
rcu_read_unlock();
return tsk;
}
void cgroup_procs_write_finish(struct task_struct *task, bool locked)
__releases(&cgroup_threadgroup_rwsem)
void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked)
{
struct cgroup_subsys *ss;
int ssid;
@ -2913,8 +2947,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked)
/* release reference from cgroup_procs_write_start() */
put_task_struct(task);
if (locked)
percpu_up_write(&cgroup_threadgroup_rwsem);
cgroup_attach_unlock(threadgroup_locked);
for_each_subsys(ss, ssid)
if (ss->post_attach)
ss->post_attach();
@ -3000,8 +3034,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
* write-locking can be skipped safely.
*/
has_tasks = !list_empty(&mgctx.preloaded_src_csets);
if (has_tasks)
percpu_down_write(&cgroup_threadgroup_rwsem);
cgroup_attach_lock(has_tasks);
/* NULL dst indicates self on default hierarchy */
ret = cgroup_migrate_prepare_dst(&mgctx);
@ -3022,8 +3055,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
ret = cgroup_migrate_execute(&mgctx);
out_finish:
cgroup_migrate_finish(&mgctx);
if (has_tasks)
percpu_up_write(&cgroup_threadgroup_rwsem);
cgroup_attach_unlock(has_tasks);
return ret;
}
@ -3698,7 +3730,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf,
}
psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi;
new = psi_trigger_create(psi, buf, nbytes, res);
new = psi_trigger_create(psi, buf, res);
if (IS_ERR(new)) {
cgroup_put(cgrp);
return PTR_ERR(new);
@ -4971,13 +5003,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
struct task_struct *task;
const struct cred *saved_cred;
ssize_t ret;
bool locked;
bool threadgroup_locked;
dst_cgrp = cgroup_kn_lock_live(of->kn, false);
if (!dst_cgrp)
return -ENODEV;
task = cgroup_procs_write_start(buf, threadgroup, &locked);
task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked);
ret = PTR_ERR_OR_ZERO(task);
if (ret)
goto out_unlock;
@ -5003,7 +5035,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
out_finish:
cgroup_procs_write_finish(task, locked);
cgroup_procs_write_finish(task, threadgroup_locked);
out_unlock:
cgroup_kn_unlock(of->kn);

3
kernel/cgroup/cpuset.c
View File

@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
cgroup_taskset_first(tset, &css);
cs = css_cs(css);
cpus_read_lock();
lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */
percpu_down_write(&cpuset_rwsem);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset)
wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem);
cpus_read_unlock();
}
/* The various types of files and directories in a cpuset file system */

10
kernel/sched/psi.c
View File

@ -190,12 +190,8 @@ static void group_init(struct psi_group *group)
/* Init trigger-related members */
mutex_init(&group->trigger_lock);
INIT_LIST_HEAD(&group->triggers);
memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
group->poll_states = 0;
group->poll_min_period = U32_MAX;
memset(group->polling_total, 0, sizeof(group->polling_total));
group->polling_next_update = ULLONG_MAX;
group->polling_until = 0;
init_waitqueue_head(&group->poll_wait);
timer_setup(&group->poll_timer, poll_timer_fn, 0);
rcu_assign_pointer(group->poll_task, NULL);
@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
if (static_branch_likely(&psi_disabled))
return 0;
cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL);
cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL);
if (!cgroup->psi)
return -ENOMEM;
@ -1091,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
}
struct psi_trigger *psi_trigger_create(struct psi_group *group,
char *buf, size_t nbytes, enum psi_res res)
char *buf, enum psi_res res)
{
struct psi_trigger *t;
enum psi_states state;
@ -1320,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
return -EBUSY;
}
new = psi_trigger_create(&psi_system, buf, nbytes, res);
new = psi_trigger_create(&psi_system, buf, res);
if (IS_ERR(new)) {
mutex_unlock(&seq->lock);
return PTR_ERR(new);

79
kernel/trace/ftrace.c
View File

@ -1861,8 +1861,6 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops,
ftrace_hash_rec_update_modify(ops, filter_hash, 1);
}
static bool ops_references_ip(struct ftrace_ops *ops, unsigned long ip);
/*
* Try to update IPMODIFY flag on each ftrace_rec. Return 0 if it is OK
* or no-needed to update, -EBUSY if it detects a conflict of the flag
@ -3118,49 +3116,6 @@ static inline int ops_traces_mod(struct ftrace_ops *ops)
ftrace_hash_empty(ops->func_hash->notrace_hash);
}
/*
* Check if the current ops references the given ip.
*
* If the ops traces all functions, then it was already accounted for.
* If the ops does not trace the current record function, skip it.
* If the ops ignores the function via notrace filter, skip it.
*/
static bool
ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
{
/* If ops isn't enabled, ignore it */
if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
return false;
/* If ops traces all then it includes this function */
if (ops_traces_mod(ops))
return true;
/* The function must be in the filter */
if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
!__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
return false;
/* If in notrace hash, we ignore it too */
if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
return false;
return true;
}
/*
* Check if the current ops references the record.
*
* If the ops traces all functions, then it was already accounted for.
* If the ops does not trace the current record function, skip it.
* If the ops ignores the function via notrace filter, skip it.
*/
static bool
ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
{
return ops_references_ip(ops, rec->ip);
}
static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
{
bool init_nop = ftrace_need_init_nop();
@ -6822,6 +6777,38 @@ static int ftrace_get_trampoline_kallsym(unsigned int symnum,
return -ERANGE;
}
#if defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) || defined(CONFIG_MODULES)
/*
* Check if the current ops references the given ip.
*
* If the ops traces all functions, then it was already accounted for.
* If the ops does not trace the current record function, skip it.
* If the ops ignores the function via notrace filter, skip it.
*/
static bool
ops_references_ip(struct ftrace_ops *ops, unsigned long ip)
{
/* If ops isn't enabled, ignore it */
if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
return false;
/* If ops traces all then it includes this function */
if (ops_traces_mod(ops))
return true;
/* The function must be in the filter */
if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
!__ftrace_lookup_ip(ops->func_hash->filter_hash, ip))
return false;
/* If in notrace hash, we ignore it too */
if (ftrace_lookup_ip(ops->func_hash->notrace_hash, ip))
return false;
return true;
}
#endif
#ifdef CONFIG_MODULES
#define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
@ -6834,7 +6821,7 @@ static int referenced_filters(struct dyn_ftrace *rec)
int cnt = 0;
for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
if (ops_references_rec(ops, rec)) {
if (ops_references_ip(ops, rec->ip)) {
if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_DIRECT))
continue;
if (WARN_ON_ONCE(ops->flags & FTRACE_OPS_FL_IPMODIFY))

12
lib/ratelimit.c
View File

@ -26,10 +26,16 @@
*/
int ___ratelimit(struct ratelimit_state *rs, const char *func)
{
/* Paired with WRITE_ONCE() in .proc_handler().
* Changing two values seperately could be inconsistent
* and some message could be lost. (See: net_ratelimit_state).
*/
int interval = READ_ONCE(rs->interval);
int burst = READ_ONCE(rs->burst);
unsigned long flags;
int ret;
if (!rs->interval)
if (!interval)
return 1;
/*
@ -44,7 +50,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
if (!rs->begin)
rs->begin = jiffies;
if (time_is_before_jiffies(rs->begin + rs->interval)) {
if (time_is_before_jiffies(rs->begin + interval)) {
if (rs->missed) {
if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) {
printk_deferred(KERN_WARNING
@ -56,7 +62,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
rs->begin = jiffies;
rs->printed = 0;
}
if (rs->burst && rs->burst > rs->printed) {
if (burst && burst > rs->printed) {
rs->printed++;
ret = 1;
} else {

8
net/bridge/netfilter/ebtable_broute.c
View File

@ -36,18 +36,10 @@ static struct ebt_replace_kernel initial_table = {
.entries = (char *)&initial_chain,
};
static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
{
if (valid_hooks & ~(1 << NF_BR_BROUTING))
return -EINVAL;
return 0;
}
static const struct ebt_table broute_table = {
.name = "broute",
.table = &initial_table,
.valid_hooks = 1 << NF_BR_BROUTING,
.check = check,
.me = THIS_MODULE,
};

8
net/bridge/netfilter/ebtable_filter.c
View File

@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
.entries = (char *)initial_chains,
};
static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
{
if (valid_hooks & ~FILTER_VALID_HOOKS)
return -EINVAL;
return 0;
}
static const struct ebt_table frame_filter = {
.name = "filter",
.table = &initial_table,
.valid_hooks = FILTER_VALID_HOOKS,
.check = check,
.me = THIS_MODULE,
};

8
net/bridge/netfilter/ebtable_nat.c
View File

@ -43,18 +43,10 @@ static struct ebt_replace_kernel initial_table = {
.entries = (char *)initial_chains,
};
static int check(const struct ebt_table_info *info, unsigned int valid_hooks)
{
if (valid_hooks & ~NAT_VALID_HOOKS)
return -EINVAL;
return 0;
}
static const struct ebt_table frame_nat = {
.name = "nat",
.table = &initial_table,
.valid_hooks = NAT_VALID_HOOKS,
.check = check,
.me = THIS_MODULE,
};

8
net/bridge/netfilter/ebtables.c
View File

@ -1040,8 +1040,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
goto free_iterate;
}
/* the table doesn't like it */
if (t->check && (ret = t->check(newinfo, repl->valid_hooks)))
if (repl->valid_hooks != t->valid_hooks)
goto free_unlock;
if (repl->num_counters && repl->num_counters != t->private->nentries) {
@ -1231,11 +1230,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
if (ret != 0)
goto free_chainstack;
if (table->check && table->check(newinfo, table->valid_hooks)) {
ret = -EINVAL;
goto free_chainstack;
}
table->private = newinfo;
rwlock_init(&table->lock);
mutex_lock(&ebt_mutex);

5
net/core/bpf_sk_storage.c
View File

@ -310,11 +310,12 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
void *owner, u32 size)
{
int optmem_max = READ_ONCE(sysctl_optmem_max);
struct sock *sk = (struct sock *)owner;
/* same check as in sock_kmalloc() */
if (size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
if (size <= optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
atomic_add(size, &sk->sk_omem_alloc);
return 0;
}

20
net/core/dev.c
View File

@ -4624,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
struct softnet_data *sd;
unsigned int old_flow, new_flow;
if (qlen < (netdev_max_backlog >> 1))
if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
return false;
sd = this_cpu_ptr(&softnet_data);
@ -4672,7 +4672,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
if (!netif_running(skb->dev))
goto drop;
qlen = skb_queue_len(&sd->input_pkt_queue);
if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
if (qlen) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
@ -4928,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
net_timestamp_check(netdev_tstamp_prequeue, skb);
net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
trace_netif_rx(skb);
@ -5281,7 +5281,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
int ret = NET_RX_DROP;
__be16 type;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
trace_netif_receive_skb(skb);
@ -5664,7 +5664,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
{
int ret;
net_timestamp_check(netdev_tstamp_prequeue, skb);
net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
@ -5694,7 +5694,7 @@ void netif_receive_skb_list_internal(struct list_head *head)
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
net_timestamp_check(netdev_tstamp_prequeue, skb);
net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
skb_list_del_init(skb);
if (!skb_defer_rx_timestamp(skb))
list_add_tail(&skb->list, &sublist);
@ -5918,7 +5918,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
net_rps_action_and_irq_enable(sd);
}
napi->weight = dev_rx_weight;
napi->weight = READ_ONCE(dev_rx_weight);
while (again) {
struct sk_buff *skb;
@ -6665,8 +6665,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies +
usecs_to_jiffies(netdev_budget_usecs);
int budget = netdev_budget;
usecs_to_jiffies(READ_ONCE(netdev_budget_usecs));
int budget = READ_ONCE(netdev_budget);
LIST_HEAD(list);
LIST_HEAD(repoll);
@ -10284,7 +10284,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
return dev;
if (time_after(jiffies, warning_time +
netdev_unregister_timeout_secs * HZ)) {
READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
list_for_each_entry(dev, list, todo_list) {
pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
dev->name, netdev_refcnt_read(dev));

13
net/core/filter.c
View File

@ -1214,10 +1214,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
u32 filter_size = bpf_prog_size(fp->prog->len);
int optmem_max = READ_ONCE(sysctl_optmem_max);
/* same check as in sock_kmalloc() */
if (filter_size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
if (filter_size <= optmem_max &&
atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) {
atomic_add(filter_size, &sk->sk_omem_alloc);
return true;
}
@ -1548,7 +1549,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
if (IS_ERR(prog))
return PTR_ERR(prog);
if (bpf_prog_size(prog->len) > sysctl_optmem_max)
if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max))
err = -ENOMEM;
else
err = reuseport_attach_prog(sk, prog);
@ -1615,7 +1616,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
}
} else {
/* BPF_PROG_TYPE_SOCKET_FILTER */
if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) {
err = -ENOMEM;
goto err_prog_put;
}
@ -5034,14 +5035,14 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
/* Only some socketops are supported */
switch (optname) {
case SO_RCVBUF:
val = min_t(u32, val, sysctl_rmem_max);
val = min_t(u32, val, READ_ONCE(sysctl_rmem_max));
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
WRITE_ONCE(sk->sk_rcvbuf,
max_t(int, val * 2, SOCK_MIN_RCVBUF));
break;
case SO_SNDBUF:
val = min_t(u32, val, sysctl_wmem_max);
val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
WRITE_ONCE(sk->sk_sndbuf,

2
net/core/gro_cells.c
View File

@ -26,7 +26,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
cell = this_cpu_ptr(gcells->cells);
if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
drop:
dev_core_stats_rx_dropped_inc(dev);
kfree_skb(skb);

12
net/core/neighbour.c
View File

@ -309,14 +309,17 @@ static int neigh_del_timer(struct neighbour *n)
static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
{
struct sk_buff_head tmp;
unsigned long flags;
struct sk_buff *skb;
skb_queue_head_init(&tmp);
spin_lock_irqsave(&list->lock, flags);
skb = skb_peek(list);
while (skb != NULL) {
struct sk_buff *skb_next = skb_peek_next(skb, list);
struct net_device *dev = skb->dev;
if (net == NULL || net_eq(dev_net(dev), net)) {
struct in_device *in_dev;
@ -326,13 +329,16 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
in_dev->arp_parms->qlen--;
rcu_read_unlock();
__skb_unlink(skb, list);
dev_put(dev);
kfree_skb(skb);
__skb_queue_tail(&tmp, skb);
}
skb = skb_next;
}
spin_unlock_irqrestore(&list->lock, flags);
while ((skb = __skb_dequeue(&tmp))) {
dev_put(skb->dev);
kfree_skb(skb);
}
}
static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev,

7
net/core/skbuff.c
View File

@ -4205,9 +4205,8 @@ normal:
SKB_GSO_CB(nskb)->csum_start =
skb_headroom(nskb) + doffset;
} else {
skb_copy_bits(head_skb, offset,
skb_put(nskb, len),
len);
if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
goto err;
}
continue;
}
@ -4798,7 +4797,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
{
bool ret;
if (likely(sysctl_tstamp_allow_data || tsonly))
if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
return true;
read_lock_bh(&sk->sk_callback_lock);

18
net/core/sock.c
View File

@ -1101,7 +1101,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
val = min_t(u32, val, sysctl_wmem_max);
val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
set_sndbuf:
/* Ensure val * 2 fits into an int, to prevent max_t()
* from treating it as a negative value.
@ -1133,7 +1133,7 @@ set_sndbuf:
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
break;
case SO_RCVBUFFORCE:
@ -2536,7 +2536,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
sysctl_optmem_max)
READ_ONCE(sysctl_optmem_max))
return NULL;
skb = alloc_skb(size, priority);
@ -2554,8 +2554,10 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
if ((unsigned int)size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
int optmem_max = READ_ONCE(sysctl_optmem_max);
if ((unsigned int)size <= optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < optmem_max) {
void *mem;
/* First do the add, to avoid the race if kmalloc
* might sleep.
@ -3309,8 +3311,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
timer_setup(&sk->sk_timer, NULL, 0);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_sndbuf = sysctl_wmem_default;
sk->sk_rcvbuf = READ_ONCE(sysctl_rmem_default);
sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
sk->sk_state = TCP_CLOSE;
sk_set_socket(sk, sock);
@ -3365,7 +3367,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = 0;
sk->sk_ll_usec = sysctl_net_busy_read;
sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read);
#endif
sk->sk_max_pacing_rate = ~0UL;

15
net/core/sysctl_net_core.c
View File

@ -234,14 +234,17 @@ static int set_default_qdisc(struct ctl_table *table, int write,
static int proc_do_dev_weight(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
static DEFINE_MUTEX(dev_weight_mutex);
int ret, weight;
mutex_lock(&dev_weight_mutex);
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret != 0)
return ret;
dev_rx_weight = weight_p * dev_weight_rx_bias;
dev_tx_weight = weight_p * dev_weight_tx_bias;
if (!ret && write) {
weight = READ_ONCE(weight_p);
WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
}
mutex_unlock(&dev_weight_mutex);
return ret;
}

2
net/dsa/slave.c
View File

@ -2484,7 +2484,7 @@ static int dsa_slave_changeupper(struct net_device *dev,
if (!err)
dsa_bridge_mtu_normalization(dp);
if (err == -EOPNOTSUPP) {
if (!extack->_msg)
if (extack && !extack->_msg)
NL_SET_ERR_MSG_MOD(extack,
"Offloading not supported");
err = 0;

16
net/ipv4/devinet.c
View File

@ -2682,23 +2682,27 @@ static __net_init int devinet_init_net(struct net *net)
#endif
if (!net_eq(net, &init_net)) {
if (IS_ENABLED(CONFIG_SYSCTL) &&
sysctl_devconf_inherit_init_net == 3) {
switch (net_inherit_devconf()) {
case 3:
/* copy from the current netns */
memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all,
sizeof(ipv4_devconf));
memcpy(dflt,
current->nsproxy->net_ns->ipv4.devconf_dflt,
sizeof(ipv4_devconf_dflt));
} else if (!IS_ENABLED(CONFIG_SYSCTL) ||
sysctl_devconf_inherit_init_net != 2) {
/* inherit == 0 or 1: copy from init_net */
break;
case 0:
case 1:
/* copy from init_net */
memcpy(all, init_net.ipv4.devconf_all,
sizeof(ipv4_devconf));
memcpy(dflt, init_net.ipv4.devconf_dflt,
sizeof(ipv4_devconf_dflt));
break;
case 2:
/* use compiled values */
break;
}
/* else inherit == 2: use compiled values */
}
#ifdef CONFIG_SYSCTL

2
net/ipv4/ip_output.c
View File

@ -1730,7 +1730,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
sk->sk_sndbuf = sysctl_wmem_default;
sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
ipc.sockc.mark = fl4.flowi4_mark;
err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
len, 0, &ipc, &rt, MSG_DONTWAIT);

6
net/ipv4/ip_sockglue.c
View File

@ -772,7 +772,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
if (optlen < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (optlen > sysctl_optmem_max)
if (optlen > READ_ONCE(sysctl_optmem_max))
return -ENOBUFS;
gsf = memdup_sockptr(optval, optlen);
@ -808,7 +808,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
if (optlen < size0)
return -EINVAL;
if (optlen > sysctl_optmem_max - 4)
if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
return -ENOBUFS;
p = kmalloc(optlen + 4, GFP_KERNEL);
@ -1233,7 +1233,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
if (optlen > sysctl_optmem_max) {
if (optlen > READ_ONCE(sysctl_optmem_max)) {
err = -ENOBUFS;
break;
}

4
net/ipv4/tcp.c
View File

@ -1000,7 +1000,7 @@ new_segment:
i = skb_shinfo(skb)->nr_frags;
can_coalesce = skb_can_coalesce(skb, i, page, offset);
if (!can_coalesce && i >= sysctl_max_skb_frags) {
if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tp, skb);
goto new_segment;
}
@ -1354,7 +1354,7 @@ new_segment:
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
if (i >= sysctl_max_skb_frags) {
if (i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tp, skb);
goto new_segment;
}

2
net/ipv4/tcp_output.c
View File

@ -239,7 +239,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
if (wscale_ok) {
/* Set window scaling on max possible window */
space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
space = max_t(u32, space, sysctl_rmem_max);
space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
0, TCP_MAX_WSCALE);

5
net/ipv6/addrconf.c
View File

@ -7162,9 +7162,8 @@ static int __net_init addrconf_init_net(struct net *net)
if (!dflt)
goto err_alloc_dflt;
if (IS_ENABLED(CONFIG_SYSCTL) &&
!net_eq(net, &init_net)) {
switch (sysctl_devconf_inherit_init_net) {
if (!net_eq(net, &init_net)) {
switch (net_inherit_devconf()) {
case 1: /* copy from init_net */
memcpy(all, init_net.ipv6.devconf_all,
sizeof(ipv6_devconf));

4
net/ipv6/ipv6_sockglue.c
View File

@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
if (optlen < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (optlen > sysctl_optmem_max)
if (optlen > READ_ONCE(sysctl_optmem_max))
return -ENOBUFS;
gsf = memdup_sockptr(optval, optlen);
@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
if (optlen < size0)
return -EINVAL;
if (optlen > sysctl_optmem_max - 4)
if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
return -ENOBUFS;
p = kmalloc(optlen + 4, GFP_KERNEL);

1
net/ipv6/netfilter/nf_conntrack_reasm.c
View File

@ -86,7 +86,6 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
table[1].extra2 = &nf_frag->fqdir->high_thresh;
table[2].data = &nf_frag->fqdir->high_thresh;
table[2].extra1 = &nf_frag->fqdir->low_thresh;
table[2].extra2 = &nf_frag->fqdir->high_thresh;
hdr = register_net_sysctl(net, "net/netfilter", table);
if (hdr == NULL)

3
net/key/af_key.c
View File

@ -1697,9 +1697,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad
pfk->registered |= (1<<hdr->sadb_msg_satype);
}
mutex_lock(&pfkey_mutex);
xfrm_probe_algs();
supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO);
mutex_unlock(&pfkey_mutex);
if (!supp_skb) {
if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC)
pfk->registered &= ~(1<<hdr->sadb_msg_satype);

2
net/mptcp/protocol.c
View File

@ -1263,7 +1263,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
i = skb_shinfo(skb)->nr_frags;
can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset);
if (!can_coalesce && i >= sysctl_max_skb_frags) {
if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
tcp_mark_push(tcp_sk(ssk), skb);
goto alloc_skb;
}

4
net/netfilter/ipvs/ip_vs_sync.c
View File

@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val)
lock_sock(sk);
if (mode) {
val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
sysctl_wmem_max);
READ_ONCE(sysctl_wmem_max));
sk->sk_sndbuf = val * 2;
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
} else {
val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
sysctl_rmem_max);
READ_ONCE(sysctl_rmem_max));
sk->sk_rcvbuf = val * 2;
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
}

31
net/netfilter/nf_conntrack_proto_tcp.c
View File

@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct,
tn->tcp_be_liberal)
res = true;
if (!res) {
bool seq_ok = before(seq, sender->td_maxend + 1);
if (!seq_ok) {
u32 overshot = end - sender->td_maxend + 1;
bool ack_ok;
ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1);
if (in_recv_win &&
ack_ok &&
overshot <= receiver->td_maxwin &&
before(sack, receiver->td_end + 1)) {
/* Work around TCPs that send more bytes than allowed by
* the receive window.
*
* If the (marked as invalid) packet is allowed to pass by
* the ruleset and the peer acks this data, then its possible
* all future packets will trigger 'ACK is over upper bound' check.
*
* Thus if only the sequence check fails then do update td_end so
* possible ACK for this data can update internal state.
*/
sender->td_end = end;
sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED;
nf_ct_l4proto_log_invalid(skb, ct, hook_state,
"%u bytes more than expected", overshot);
return res;
}
}
nf_ct_l4proto_log_invalid(skb, ct, hook_state,
"%s",
before(seq, sender->td_maxend + 1) ?

15
net/netfilter/nf_flow_table_core.c
View File

@ -437,12 +437,17 @@ static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table,
}
}
void nf_flow_table_gc_run(struct nf_flowtable *flow_table)
{
nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
}
static void nf_flow_offload_work_gc(struct work_struct *work)
{
struct nf_flowtable *flow_table;
flow_table = container_of(work, struct nf_flowtable, gc_work.work);
nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
nf_flow_table_gc_run(flow_table);
queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
@ -600,11 +605,11 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
mutex_unlock(&flowtable_lock);
cancel_delayed_work_sync(&flow_table->gc_work);
nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
nf_flow_table_offload_flush(flow_table);
if (nf_flowtable_hw_offload(flow_table))
nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL);
/* ... no more pending work after this stage ... */
nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
nf_flow_table_gc_run(flow_table);
nf_flow_table_offload_flush_cleanup(flow_table);
rhashtable_destroy(&flow_table->rhashtable);
}
EXPORT_SYMBOL_GPL(nf_flow_table_free);

8
net/netfilter/nf_flow_table_offload.c
View File

@ -1074,6 +1074,14 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable,
flow_offload_queue_work(offload);
}
void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable)
{
if (nf_flowtable_hw_offload(flowtable)) {
flush_workqueue(nf_flow_offload_del_wq);
nf_flow_table_gc_run(flowtable);
}
}
void nf_flow_table_offload_flush(struct nf_flowtable *flowtable)
{
if (nf_flowtable_hw_offload(flowtable)) {

14
net/netfilter/nf_tables_api.c
View File

@ -32,7 +32,6 @@ static LIST_HEAD(nf_tables_objects);
static LIST_HEAD(nf_tables_flowtables);
static LIST_HEAD(nf_tables_destroy_list);
static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
static u64 table_handle;
enum {
NFT_VALIDATE_SKIP = 0,
@ -1235,7 +1234,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info,
INIT_LIST_HEAD(&table->flowtables);
table->family = family;
table->flags = flags;
table->handle = ++table_handle;
table->handle = ++nft_net->table_handle;
if (table->flags & NFT_TABLE_F_OWNER)
table->nlpid = NETLINK_CB(skb).portid;
@ -2196,9 +2195,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
struct netlink_ext_ack *extack)
{
const struct nlattr * const *nla = ctx->nla;
struct nft_stats __percpu *stats = NULL;
struct nft_table *table = ctx->table;
struct nft_base_chain *basechain;
struct nft_stats __percpu *stats;
struct net *net = ctx->net;
char name[NFT_NAME_MAXLEN];
struct nft_rule_blob *blob;
@ -2236,7 +2235,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
return PTR_ERR(stats);
}
rcu_assign_pointer(basechain->stats, stats);
static_branch_inc(&nft_counters_enabled);
}
err = nft_basechain_init(basechain, family, &hook, flags);
@ -2319,6 +2317,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
goto err_unregister_hook;
}
if (stats)
static_branch_inc(&nft_counters_enabled);
table->use++;
return 0;
@ -2574,6 +2575,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla);
if (chain != NULL) {
if (chain->flags & NFT_CHAIN_BINDING)
return -EINVAL;
if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
NL_SET_BAD_ATTR(extack, attr);
return -EEXIST;
@ -9707,6 +9711,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
return PTR_ERR(chain);
if (nft_is_base_chain(chain))
return -EOPNOTSUPP;
if (nft_chain_is_bound(chain))
return -EINVAL;
if (desc->flags & NFT_DATA_DESC_SETELEM &&
chain->flags & NFT_CHAIN_BINDING)
return -EINVAL;

18
net/netfilter/nft_osf.c
View File

@ -115,9 +115,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
{
return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) |
(1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_FORWARD));
unsigned int hooks;
switch (ctx->family) {
case NFPROTO_IPV4:
case NFPROTO_IPV6:
case NFPROTO_INET:
hooks = (1 << NF_INET_LOCAL_IN) |
(1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_FORWARD);
break;
default:
return -EOPNOTSUPP;
}
return nft_chain_validate_hooks(ctx->chain, hooks);
}
static bool nft_osf_reduce(struct nft_regs_track *track,

29
net/netfilter/nft_payload.c
View File

@ -740,17 +740,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_payload_set *priv = nft_expr_priv(expr);
u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE;
int err;
priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
if (tb[NFTA_PAYLOAD_CSUM_TYPE])
priv->csum_type =
ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
if (tb[NFTA_PAYLOAD_CSUM_OFFSET])
priv->csum_offset =
ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET]));
csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE]));
if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) {
err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX,
&csum_offset);
if (err < 0)
return err;
priv->csum_offset = csum_offset;
}
if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) {
u32 flags;
@ -761,7 +767,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
priv->csum_flags = flags;
}
switch (priv->csum_type) {
switch (csum_type) {
case NFT_PAYLOAD_CSUM_NONE:
case NFT_PAYLOAD_CSUM_INET:
break;
@ -775,6 +781,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
default:
return -EOPNOTSUPP;
}
priv->csum_type = csum_type;
return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg,
priv->len);
@ -833,6 +840,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
{
enum nft_payload_bases base;
unsigned int offset, len;
int err;
if (tb[NFTA_PAYLOAD_BASE] == NULL ||
tb[NFTA_PAYLOAD_OFFSET] == NULL ||
@ -859,8 +867,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx,
if (tb[NFTA_PAYLOAD_DREG] == NULL)
return ERR_PTR(-EINVAL);
offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET]));
len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset);
if (err < 0)
return ERR_PTR(err);
err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len);
if (err < 0)
return ERR_PTR(err);
if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER)

8
net/netfilter/nft_tproxy.c
View File

@ -312,6 +312,13 @@ static int nft_tproxy_dump(struct sk_buff *skb,
return 0;
}
static int nft_tproxy_validate(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nft_data **data)
{
return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
}
static struct nft_expr_type nft_tproxy_type;
static const struct nft_expr_ops nft_tproxy_ops = {
.type = &nft_tproxy_type,
@ -321,6 +328,7 @@ static const struct nft_expr_ops nft_tproxy_ops = {
.destroy = nft_tproxy_destroy,
.dump = nft_tproxy_dump,
.reduce = NFT_REDUCE_READONLY,
.validate = nft_tproxy_validate,
};
static struct nft_expr_type nft_tproxy_type __read_mostly = {

1
net/netfilter/nft_tunnel.c
View File

@ -161,6 +161,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = {
static struct nft_expr_type nft_tunnel_type __read_mostly = {
.name = "tunnel",
.family = NFPROTO_NETDEV,
.ops = &nft_tunnel_get_ops,
.policy = nft_tunnel_policy,
.maxattr = NFTA_TUNNEL_MAX,

3
net/rose/rose_loopback.c
View File

@ -96,7 +96,8 @@ static void rose_loopback_timer(struct timer_list *unused)
}
if (frametype == ROSE_CALL_REQUEST) {
if (!rose_loopback_neigh->dev) {
if (!rose_loopback_neigh->dev &&
!rose_loopback_neigh->loopback) {
kfree_skb(skb);
continue;
}

4
net/rxrpc/call_object.c
View File

@ -285,8 +285,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
_enter("%p,%lx", rx, p->user_call_ID);
limiter = rxrpc_get_call_slot(p, gfp);
if (!limiter)
if (!limiter) {
release_sock(&rx->sk);
return ERR_PTR(-ERESTARTSYS);
}
call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
if (IS_ERR(call)) {

90
net/rxrpc/sendmsg.c
View File

@ -51,10 +51,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
return sock_intr_errno(*timeo);
trace_rxrpc_transmit(call, rxrpc_transmit_wait);
mutex_unlock(&call->user_mutex);
*timeo = schedule_timeout(*timeo);
if (mutex_lock_interruptible(&call->user_mutex) < 0)
return sock_intr_errno(*timeo);
}
}
@ -290,37 +287,48 @@ out:
static int rxrpc_send_data(struct rxrpc_sock *rx,
struct rxrpc_call *call,
struct msghdr *msg, size_t len,
rxrpc_notify_end_tx_t notify_end_tx)
rxrpc_notify_end_tx_t notify_end_tx,
bool *_dropped_lock)
{
struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
struct sock *sk = &rx->sk;
enum rxrpc_call_state state;
long timeo;
bool more;
int ret, copied;
bool more = msg->msg_flags & MSG_MORE;
int ret, copied = 0;
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
/* this should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
reload:
ret = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
return -EPIPE;
more = msg->msg_flags & MSG_MORE;
goto maybe_error;
state = READ_ONCE(call->state);
ret = -ESHUTDOWN;
if (state >= RXRPC_CALL_COMPLETE)
goto maybe_error;
ret = -EPROTO;
if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
state != RXRPC_CALL_SERVER_ACK_REQUEST &&
state != RXRPC_CALL_SERVER_SEND_REPLY)
goto maybe_error;
ret = -EMSGSIZE;
if (call->tx_total_len != -1) {
if (len > call->tx_total_len)
return -EMSGSIZE;
if (!more && len != call->tx_total_len)
return -EMSGSIZE;
if (len - copied > call->tx_total_len)
goto maybe_error;
if (!more && len - copied != call->tx_total_len)
goto maybe_error;
}
skb = call->tx_pending;
call->tx_pending = NULL;
rxrpc_see_skb(skb, rxrpc_skb_seen);
copied = 0;
do {
/* Check to see if there's a ping ACK to reply to. */
if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
@ -331,16 +339,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
_debug("alloc");
if (!rxrpc_check_tx_space(call, NULL)) {
ret = -EAGAIN;
if (msg->msg_flags & MSG_DONTWAIT)
goto maybe_error;
ret = rxrpc_wait_for_tx_window(rx, call,
&timeo,
msg->msg_flags & MSG_WAITALL);
if (ret < 0)
goto maybe_error;
}
if (!rxrpc_check_tx_space(call, NULL))
goto wait_for_space;
/* Work out the maximum size of a packet. Assume that
* the security header is going to be in the padded
@ -468,6 +468,27 @@ maybe_error:
efault:
ret = -EFAULT;
goto out;
wait_for_space:
ret = -EAGAIN;
if (msg->msg_flags & MSG_DONTWAIT)
goto maybe_error;
mutex_unlock(&call->user_mutex);
*_dropped_lock = true;
ret = rxrpc_wait_for_tx_window(rx, call, &timeo,
msg->msg_flags & MSG_WAITALL);
if (ret < 0)
goto maybe_error;
if (call->interruptibility == RXRPC_INTERRUPTIBLE) {
if (mutex_lock_interruptible(&call->user_mutex) < 0) {
ret = sock_intr_errno(timeo);
goto maybe_error;
}
} else {
mutex_lock(&call->user_mutex);
}
*_dropped_lock = false;
goto reload;
}
/*
@ -629,6 +650,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
enum rxrpc_call_state state;
struct rxrpc_call *call;
unsigned long now, j;
bool dropped_lock = false;
int ret;
struct rxrpc_send_params p = {
@ -737,21 +759,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
ret = rxrpc_send_abort_packet(call);
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else if (rxrpc_is_client_call(call) &&
state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
/* request phase complete for this client call */
ret = -EPROTO;
} else if (rxrpc_is_service_call(call) &&
state != RXRPC_CALL_SERVER_ACK_REQUEST &&
state != RXRPC_CALL_SERVER_SEND_REPLY) {
/* Reply phase not begun or not complete for service call. */
ret = -EPROTO;
} else {
ret = rxrpc_send_data(rx, call, msg, len, NULL);
ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock);
}
out_put_unlock:
mutex_unlock(&call->user_mutex);
if (!dropped_lock)
mutex_unlock(&call->user_mutex);
error_put:
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = %d", ret);
@ -779,6 +793,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, size_t len,
rxrpc_notify_end_tx_t notify_end_tx)
{
bool dropped_lock = false;
int ret;
_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
@ -796,7 +811,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
case RXRPC_CALL_SERVER_ACK_REQUEST:
case RXRPC_CALL_SERVER_SEND_REPLY:
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
notify_end_tx);
notify_end_tx, &dropped_lock);
break;
case RXRPC_CALL_COMPLETE:
read_lock_bh(&call->state_lock);
@ -810,7 +825,8 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
break;
}
mutex_unlock(&call->user_mutex);
if (!dropped_lock)
mutex_unlock(&call->user_mutex);
_leave(" = %d", ret);
return ret;
}

Some files were not shown because too many files have changed in this diff Show More