subject to change and can break with newer kernels. BPF programs need to change
accordingly when this happens.
+Q: Are places where kprobes can attach part of the stable ABI?
+--------------------------------------------------------------
+A: NO. The places to which kprobes can attach are internal implementation
+details, which means that they are subject to change and can break with
+newer kernels. BPF programs need to change accordingly when this happens.
+
Q: How much stack space a BPF program uses?
-------------------------------------------
A: Currently all program types are limited to 512 bytes of stack
functions has changed, both the in-tree and out-of-tree kernel tcp cc
implementations have to be changed. The same goes for the bpf
programs and they have to be adjusted accordingly.
+
+Q: Attaching to arbitrary kernel functions is an ABI?
+-----------------------------------------------------
+Q: BPF programs can be attached to many kernel functions. Do these
+kernel functions become part of the ABI?
+
+A: NO.
+
+The kernel function prototypes will change, and BPF programs attaching to
+them will need to change. The BPF compile-once-run-everywhere (CO-RE)
+should be used in order to make it easier to adapt your BPF programs to
+different versions of the kernel.
+
+Q: Marking a function with BTF_ID makes that function an ABI?
+-------------------------------------------------------------
+A: NO.
+
+The BTF_ID macro does not cause a function to become part of the ABI
+any more than does the EXPORT_SYMBOL_GPL macro.
gives some assurance that traffic is actually flowing to and from one
or more peers on the local network.
-The ARP monitor relies on the device driver itself to verify
-that traffic is flowing. In particular, the driver must keep up to
-date the last receive time, dev->last_rx. Drivers that use NETIF_F_LLTX
-flag must also update netdev_queue->trans_start. If they do not, then the
-ARP monitor will immediately fail any slaves using that driver, and
-those slaves will stay down. If networking monitoring (tcpdump, etc)
-shows the ARP requests and replies on the network, then it may be that
-your device driver is not updating last_rx and trans_start.
-
7.2 Configuring Multiple ARP Targets
------------------------------------
F: arch/powerpc/platforms/powernv/vas*
IBM Power Virtual Ethernet Device Driver
-M: Cristobal Forno <cforno12@linux.ibm.com>
+M: Nick Child <nnac123@linux.ibm.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/ibm/ibmveth.*
F: drivers/net/wireless/mediatek/mt76/
MEDIATEK MT7601U WIRELESS LAN DRIVER
-M: Jakub Kicinski <kubakici@wp.pl>
+M: Jakub Kicinski <kuba@kernel.org>
L: linux-wireless@vger.kernel.org
S: Maintained
F: drivers/net/wireless/mediatek/mt7601u/
memset(&ctx, 0, sizeof(ctx));
ctx.prog = prog;
- ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
+ ctx.offset = kvcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
if (ctx.offset == NULL) {
prog = orig_prog;
goto out_off;
ctx.offset[i] *= AARCH64_INSN_SIZE;
bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
out_off:
- kfree(ctx.offset);
+ kvfree(ctx.offset);
kfree(jit_data);
prog->aux->jit_data = NULL;
}
int args_off, int retval_off, int run_ctx_off,
bool save_ret)
{
- u32 *branch;
+ __le32 *branch;
u64 enter_prog;
u64 exit_prog;
struct bpf_prog *p = l->link.prog;
if (ctx->image) {
int offset = &ctx->image[ctx->idx] - branch;
- *branch = A64_CBZ(1, A64_R(0), offset);
+ *branch = cpu_to_le32(A64_CBZ(1, A64_R(0), offset));
}
/* arg1: prog */
static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
int args_off, int retval_off, int run_ctx_off,
- u32 **branches)
+ __le32 **branches)
{
int i;
struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
bool save_ret;
- u32 **branches = NULL;
+ __le32 **branches = NULL;
/* trampoline stack layout:
* [ parent ip ]
flags & BPF_TRAMP_F_RET_FENTRY_RET);
if (fmod_ret->nr_links) {
- branches = kcalloc(fmod_ret->nr_links, sizeof(u32 *),
+ branches = kcalloc(fmod_ret->nr_links, sizeof(__le32 *),
GFP_KERNEL);
if (!branches)
return -ENOMEM;
/* update the branches saved in invoke_bpf_mod_ret with cbnz */
for (i = 0; i < fmod_ret->nr_links && ctx->image != NULL; i++) {
int offset = &ctx->image[ctx->idx] - branches[i];
- *branches[i] = A64_CBNZ(1, A64_R(10), offset);
+ *branches[i] = cpu_to_le32(A64_CBNZ(1, A64_R(10), offset));
}
for (i = 0; i < fexit->nr_links; i++)
card = idt77252_chain;
dev = card->atmdev;
idt77252_chain = card->next;
+ del_timer_sync(&card->tst_timer);
if (dev->phy->stop)
dev->phy->stop(dev);
static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
{
struct slave *tx_slave = NULL;
+ struct net_device *dev;
struct arp_pkt *arp;
if (!pskb_network_may_pull(skb, sizeof(*arp)))
if (!bond_slave_has_mac_rx(bond, arp->mac_src))
return NULL;
+ dev = ip_dev_find(dev_net(bond->dev), arp->ip_src);
+ if (dev) {
+ if (netif_is_bridge_master(dev)) {
+ dev_put(dev);
+ return NULL;
+ }
+ dev_put(dev);
+ }
+
if (arp->op_code == htons(ARPOP_REPLY)) {
/* the arp must be sent on the selected rx channel */
tx_slave = rlb_choose_channel(skb, bond, arp);
for (i = 0; i < BOND_MAX_ARP_TARGETS; i++)
new_slave->target_last_arp_rx[i] = new_slave->last_rx;
+ new_slave->last_tx = new_slave->last_rx;
+
if (bond->params.miimon && !bond->params.use_carrier) {
link_reporting = bond_check_dev_link(bond, slave_dev, 1);
return;
}
- if (bond_handle_vlan(slave, tags, skb))
+ if (bond_handle_vlan(slave, tags, skb)) {
+ slave_update_last_tx(slave);
arp_xmit(skb);
+ }
+
return;
}
curr_active_slave->last_link_up))
bond_validate_arp(bond, slave, tip, sip);
else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) &&
- bond_time_in_interval(bond,
- dev_trans_start(curr_arp_slave->dev), 1))
+ bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1))
bond_validate_arp(bond, slave, sip, tip);
out_unlock:
}
addrconf_addr_solict_mult(daddr, &mcaddr);
- if (bond_handle_vlan(slave, tags, skb))
+ if (bond_handle_vlan(slave, tags, skb)) {
+ slave_update_last_tx(slave);
ndisc_send_skb(skb, &mcaddr, saddr);
+ }
}
static void bond_ns_send_all(struct bonding *bond, struct slave *slave)
curr_active_slave->last_link_up))
bond_validate_ns(bond, slave, saddr, daddr);
else if (curr_arp_slave &&
- bond_time_in_interval(bond,
- dev_trans_start(curr_arp_slave->dev), 1))
+ bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1))
bond_validate_ns(bond, slave, saddr, daddr);
out:
* so it can wait
*/
bond_for_each_slave_rcu(bond, slave, iter) {
- unsigned long trans_start = dev_trans_start(slave->dev);
+ unsigned long last_tx = slave_last_tx(slave);
bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
if (slave->link != BOND_LINK_UP) {
- if (bond_time_in_interval(bond, trans_start, 1) &&
+ if (bond_time_in_interval(bond, last_tx, 1) &&
bond_time_in_interval(bond, slave->last_rx, 1)) {
bond_propose_link_state(slave, BOND_LINK_UP);
* when the source ip is 0, so don't take the link down
* if we don't know our ip yet
*/
- if (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) ||
+ if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) ||
!bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
*/
static int bond_ab_arp_inspect(struct bonding *bond)
{
- unsigned long trans_start, last_rx;
+ unsigned long last_tx, last_rx;
struct list_head *iter;
struct slave *slave;
int commit = 0;
* - (more than missed_max*delta since receive AND
* the bond has an IP address)
*/
- trans_start = dev_trans_start(slave->dev);
+ last_tx = slave_last_tx(slave);
if (bond_is_active_slave(slave) &&
- (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) ||
+ (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) ||
!bond_time_in_interval(bond, last_rx, bond->params.missed_max))) {
bond_propose_link_state(slave, BOND_LINK_DOWN);
commit++;
*/
static void bond_ab_arp_commit(struct bonding *bond)
{
- unsigned long trans_start;
struct list_head *iter;
+ unsigned long last_tx;
struct slave *slave;
bond_for_each_slave(bond, slave, iter) {
continue;
case BOND_LINK_UP:
- trans_start = dev_trans_start(slave->dev);
+ last_tx = slave_last_tx(slave);
if (rtnl_dereference(bond->curr_active_slave) != slave ||
(!rtnl_dereference(bond->curr_active_slave) &&
- bond_time_in_interval(bond, trans_start, 1))) {
+ bond_time_in_interval(bond, last_tx, 1))) {
struct slave *current_arp_slave;
current_arp_slave = rtnl_dereference(bond->current_arp_slave);
static netdev_tx_t bond_tls_device_xmit(struct bonding *bond, struct sk_buff *skb,
struct net_device *dev)
{
- if (likely(bond_get_slave_by_dev(bond, tls_get_ctx(skb->sk)->netdev)))
- return bond_dev_queue_xmit(bond, skb, tls_get_ctx(skb->sk)->netdev);
+ struct net_device *tls_netdev = rcu_dereference(tls_get_ctx(skb->sk)->netdev);
+
+ /* tls_netdev might become NULL, even if tls_is_sk_tx_device_offloaded
+ * was true, if tls_device_down is running in parallel, but it's OK,
+ * because bond_get_slave_by_dev has a NULL check.
+ */
+ if (likely(bond_get_slave_by_dev(bond, tls_netdev)))
+ return bond_dev_queue_xmit(bond, skb, tls_netdev);
return bond_tx_drop(dev, skb);
}
#endif
mcp251x_read_2regs(spi, CANINTF, &intf, &eflag);
- /* mask out flags we don't care about */
- intf &= CANINTF_RX | CANINTF_TX | CANINTF_ERR;
-
/* receive buffer 0 */
if (intf & CANINTF_RX0IF) {
mcp251x_hw_rx(spi, 0);
if (mcp251x_is_2510(spi))
mcp251x_write_bits(spi, CANINTF,
CANINTF_RX0IF, 0x00);
+
+ /* check if buffer 1 is already known to be full, no need to re-read */
+ if (!(intf & CANINTF_RX1IF)) {
+ u8 intf1, eflag1;
+
+ /* intf needs to be read again to avoid a race condition */
+ mcp251x_read_2regs(spi, CANINTF, &intf1, &eflag1);
+
+ /* combine flags from both operations for error handling */
+ intf |= intf1;
+ eflag |= eflag1;
+ }
}
/* receive buffer 1 */
clear_intf |= CANINTF_RX1IF;
}
+ /* mask out flags we don't care about */
+ intf &= CANINTF_RX | CANINTF_TX | CANINTF_ERR;
+
/* any error or tx interrupt we need to clear? */
if (intf & (CANINTF_ERR | CANINTF_TX))
clear_intf |= intf & (CANINTF_ERR | CANINTF_TX);
__le32 ts_sec; /* timestamp in seconds */
__le32 ts_nsec; /* timestamp in nano seconds */
- union {
+ union __packed {
u8 generic[64];
struct cpc_can_msg can_msg;
struct cpc_can_params can_params;
old_proto_ops = felix->tag_proto_ops;
+ if (proto_ops == old_proto_ops)
+ return 0;
+
err = proto_ops->setup(ds);
if (err)
goto setup_failed;
{
struct tc_taprio_sched_entry *entry;
u64 gate_len[OCELOT_NUM_TC];
+ u8 gates_ever_opened = 0;
int tc, i, n;
/* Initialize arrays */
for (tc = 0; tc < OCELOT_NUM_TC; tc++) {
if (entry->gate_mask & BIT(tc)) {
gate_len[tc] += entry->interval;
+ gates_ever_opened |= BIT(tc);
} else {
/* Gate closes now, record a potential new
* minimum and reinitialize length
*/
- if (min_gate_len[tc] > gate_len[tc])
+ if (min_gate_len[tc] > gate_len[tc] &&
+ gate_len[tc])
min_gate_len[tc] = gate_len[tc];
gate_len[tc] = 0;
}
}
}
+
+ /* min_gate_len[tc] actually tracks minimum *open* gate time, so for
+ * permanently closed gates, min_gate_len[tc] will still be U64_MAX.
+ * Therefore they are currently indistinguishable from permanently
+ * open gates. Overwrite the gate len with 0 when we know they're
+ * actually permanently closed, i.e. after the loop above.
+ */
+ for (tc = 0; tc < OCELOT_NUM_TC; tc++)
+ if (!(gates_ever_opened & BIT(tc)))
+ min_gate_len[tc] = 0;
}
/* Update QSYS_PORT_MAX_SDU to make sure the static guard bands added by the
static void aq_nic_polling_timer_cb(struct timer_list *t)
{
struct aq_nic_s *self = from_timer(self, t, polling_timer);
- struct aq_vec_s *aq_vec = NULL;
unsigned int i = 0U;
- for (i = 0U, aq_vec = self->aq_vec[0];
- self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
- aq_vec_isr(i, (void *)aq_vec);
+ for (i = 0U; self->aq_vecs > i; ++i)
+ aq_vec_isr(i, (void *)self->aq_vec[i]);
mod_timer(&self->polling_timer, jiffies +
AQ_CFG_POLLING_TIMER_INTERVAL);
u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
{
- struct aq_vec_s *aq_vec = NULL;
struct aq_stats_s *stats;
unsigned int count = 0U;
unsigned int i = 0U;
data += i;
for (tc = 0U; tc < self->aq_nic_cfg.tcs; tc++) {
- for (i = 0U, aq_vec = self->aq_vec[0];
- aq_vec && self->aq_vecs > i;
- ++i, aq_vec = self->aq_vec[i]) {
+ for (i = 0U; self->aq_vecs > i; ++i) {
+ if (!self->aq_vec[i])
+ break;
data += count;
- count = aq_vec_get_sw_stats(aq_vec, tc, data);
+ count = aq_vec_get_sw_stats(self->aq_vec[i], tc, data);
}
}
int aq_nic_stop(struct aq_nic_s *self)
{
- struct aq_vec_s *aq_vec = NULL;
unsigned int i = 0U;
netif_tx_disable(self->ndev);
aq_ptp_irq_free(self);
- for (i = 0U, aq_vec = self->aq_vec[0];
- self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
- aq_vec_stop(aq_vec);
+ for (i = 0U; self->aq_vecs > i; ++i)
+ aq_vec_stop(self->aq_vec[i]);
aq_ptp_ring_stop(self);
}
slot->skb = skb;
- ring->end += nr_frags + 1;
netdev_sent_queue(net_dev, skb->len);
+ ring->end += nr_frags + 1;
wmb();
#include "bnxt_ptp.h"
#include "bnxt_coredump.h"
#include "bnxt_nvm_defs.h"
-#include "bnxt_ethtool.h"
static void __bnxt_fw_recover(struct bnxt *bp)
{
if (priv->internal_phy && !GENET_IS_V5(priv))
dev->phydev->irq = PHY_MAC_INTERRUPT;
+ /* Indicate that the MAC is responsible for PHY PM */
+ dev->phydev->mac_managed_pm = true;
+
return 0;
}
int data_len, qidx, ret = 0, mss;
struct tls_record_info *record;
struct chcr_ktls_info *tx_info;
+ struct net_device *tls_netdev;
struct tls_context *tls_ctx;
struct sge_eth_txq *q;
struct adapter *adap;
mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len;
tls_ctx = tls_get_ctx(skb->sk);
- if (unlikely(tls_ctx->netdev != dev))
+ tls_netdev = rcu_dereference_bh(tls_ctx->netdev);
+ /* Don't quit on NULL: if tls_device_down is running in parallel,
+ * netdev might become NULL, even if tls_is_sk_tx_device_offloaded was
+ * true. Rather continue processing this packet.
+ */
+ if (unlikely(tls_netdev && tls_netdev != dev))
goto out;
tx_ctx = chcr_get_ktls_tx_context(tls_ctx);
return 0;
}
-static void tsnep_tx_unmap(struct tsnep_tx *tx, int count)
+static void tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count)
{
struct device *dmadev = tx->adapter->dmadev;
struct tsnep_tx_entry *entry;
int i;
for (i = 0; i < count; i++) {
- entry = &tx->entry[(tx->read + i) % TSNEP_RING_SIZE];
+ entry = &tx->entry[(index + i) % TSNEP_RING_SIZE];
if (entry->len) {
if (i == 0)
retval = tsnep_tx_map(skb, tx, count);
if (retval != 0) {
- tsnep_tx_unmap(tx, count);
+ tsnep_tx_unmap(tx, tx->write, count);
dev_kfree_skb_any(entry->skb);
entry->skb = NULL;
if (skb_shinfo(entry->skb)->nr_frags > 0)
count += skb_shinfo(entry->skb)->nr_frags;
- tsnep_tx_unmap(tx, count);
+ tsnep_tx_unmap(tx, tx->read, count);
if ((skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) &&
(__le32_to_cpu(entry->desc_wb->properties) &
static struct platform_driver tsnep_driver = {
.driver = {
.name = TSNEP,
- .of_match_table = of_match_ptr(tsnep_of_match),
+ .of_match_table = tsnep_of_match,
},
.probe = tsnep_probe,
.remove = tsnep_remove,
buf_array[i] = addr;
/* tracing point */
- trace_dpaa2_eth_buf_seed(priv->net_dev,
- page, DPAA2_ETH_RX_BUF_RAW_SIZE,
+ trace_dpaa2_eth_buf_seed(priv->net_dev, page_address(page),
+ DPAA2_ETH_RX_BUF_RAW_SIZE,
addr, priv->rx_buf_size,
bpid);
}
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA);
rvu_reset_lmt_map_tbl(rvu, pcifunc);
rvu_detach_rsrcs(rvu, NULL, pcifunc);
+ /* In scenarios where PF/VF drivers detach NIXLF without freeing MCAM
+ * entries, check and free the MCAM entries explicitly to avoid leak.
+ * Since LF is detached use LF number as -1.
+ */
+ rvu_npc_free_mcam_entries(rvu, pcifunc, -1);
+
mutex_unlock(&rvu->flr_lock);
}
void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
{
+ if (nixlf < 0)
+ return;
+
npc_enadis_default_entries(rvu, pcifunc, nixlf, false);
/* Delete multicast and promisc MCAM entries */
void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
{
+ if (nixlf < 0)
+ return;
+
/* Enables only broadcast match entry. Promisc/Allmulti are enabled
* in set_rx_mode mbox handler.
*/
* Firmware database method.
* Default KPU profile.
*/
- if (!request_firmware(&fw, kpu_profile, rvu->dev)) {
+ if (!request_firmware_direct(&fw, kpu_profile, rvu->dev)) {
dev_info(rvu->dev, "Loading KPU profile from firmware: %s\n",
kpu_profile);
rvu->kpu_fwdata = kzalloc(fw->size, GFP_KERNEL);
static void rvu_npc_setup_interfaces(struct rvu *rvu, int blkaddr)
{
+ struct npc_mcam_kex *mkex = rvu->kpu.mkex;
struct npc_mcam *mcam = &rvu->hw->mcam;
struct rvu_hwinfo *hw = rvu->hw;
u64 nibble_ena, rx_kex, tx_kex;
mcam->counters.max--;
mcam->rx_miss_act_cntr = mcam->counters.max;
- rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX];
- tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX];
+ rx_kex = mkex->keyx_cfg[NIX_INTF_RX];
+ tx_kex = mkex->keyx_cfg[NIX_INTF_TX];
nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex);
nibble_ena = rvu_npc_get_tx_nibble_cfg(rvu, nibble_ena);
if (nibble_ena) {
tx_kex &= ~NPC_PARSE_NIBBLE;
tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena);
- npc_mkex_default.keyx_cfg[NIX_INTF_TX] = tx_kex;
+ mkex->keyx_cfg[NIX_INTF_TX] = tx_kex;
}
/* Configure RX interfaces */
NPC_SCAN_HDR(NPC_VLAN_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 2, 2);
NPC_SCAN_HDR(NPC_VLAN_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 2, 2);
NPC_SCAN_HDR(NPC_DMAC, NPC_LID_LA, la_ltype, la_start, 6);
- NPC_SCAN_HDR(NPC_SMAC, NPC_LID_LA, la_ltype, la_start, 6);
+ /* SMAC follows the DMAC(which is 6 bytes) */
+ NPC_SCAN_HDR(NPC_SMAC, NPC_LID_LA, la_ltype, la_start + 6, 6);
/* PF_FUNC is 2 bytes at 0th byte of NPC_LT_LA_IH_NIX_ETHER */
NPC_SCAN_HDR(NPC_PF_FUNC, NPC_LID_LA, NPC_LT_LA_IH_NIX_ETHER, 0, 2);
}
req->num_regs++;
req->reg[1] = NIX_AF_TL3X_SCHEDULE(schq);
req->regval[1] = dwrr_val;
+ if (lvl == hw->txschq_link_cfg_lvl) {
+ req->num_regs++;
+ req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
+ /* Enable this queue and backpressure */
+ req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
+ }
} else if (lvl == NIX_TXSCH_LVL_TL2) {
parent = hw->txschq_list[NIX_TXSCH_LVL_TL1][0];
req->reg[0] = NIX_AF_TL2X_PARENT(schq);
req->reg[1] = NIX_AF_TL2X_SCHEDULE(schq);
req->regval[1] = TXSCH_TL1_DFLT_RR_PRIO << 24 | dwrr_val;
- req->num_regs++;
- req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
- /* Enable this queue and backpressure */
- req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
-
+ if (lvl == hw->txschq_link_cfg_lvl) {
+ req->num_regs++;
+ req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link);
+ /* Enable this queue and backpressure */
+ req->regval[2] = BIT_ULL(13) | BIT_ULL(12);
+ }
} else if (lvl == NIX_TXSCH_LVL_TL1) {
/* Default config for TL1.
* For VF this is always ignored.
for (schq = 0; schq < rsp->schq[lvl]; schq++)
pf->hw.txschq_list[lvl][schq] =
rsp->schq_list[lvl][schq];
+
+ pf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl;
}
EXPORT_SYMBOL(mbox_handler_nix_txsch_alloc);
u16 sqb_size;
/* NIX */
+ u8 txschq_link_cfg_lvl;
u16 txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC];
u16 matchall_ipolicer;
u32 dwrr_mtu;
int err;
attr.ttl = tun_key->ttl;
- attr.fl.fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+ attr.fl.fl6.flowlabel = ip6_make_flowinfo(tun_key->tos, tun_key->label);
attr.fl.fl6.daddr = tun_key->u.ipv6.dst;
attr.fl.fl6.saddr = tun_key->u.ipv6.src;
attr.ttl = tun_key->ttl;
- attr.fl.fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+ attr.fl.fl6.flowlabel = ip6_make_flowinfo(tun_key->tos, tun_key->label);
attr.fl.fl6.daddr = tun_key->u.ipv6.dst;
attr.fl.fl6.saddr = tun_key->u.ipv6.src;
{
struct mlx5e_ktls_offload_context_tx *priv_tx;
struct mlx5e_sq_stats *stats = sq->stats;
+ struct net_device *tls_netdev;
struct tls_context *tls_ctx;
int datalen;
u32 seq;
mlx5e_tx_mpwqe_ensure_complete(sq);
tls_ctx = tls_get_ctx(skb->sk);
- if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
+ tls_netdev = rcu_dereference_bh(tls_ctx->netdev);
+ /* Don't WARN on NULL: if tls_device_down is running in parallel,
+ * netdev might become NULL, even if tls_is_sk_tx_device_offloaded was
+ * true. Rather continue processing this packet.
+ */
+ if (WARN_ON_ONCE(tls_netdev && tls_netdev != netdev))
goto err_out;
priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m)
{
unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core);
- struct devlink *devlink = priv_to_devlink(mlxsw_m->core);
u8 last_module = max_ports;
int i;
int err;
}
/* Create port objects for each valid entry */
- devl_lock(devlink);
for (i = 0; i < mlxsw_m->max_ports; i++) {
if (mlxsw_m->module_to_port[i] > 0) {
err = mlxsw_m_port_create(mlxsw_m,
goto err_module_to_port_create;
}
}
- devl_unlock(devlink);
return 0;
mlxsw_m_port_remove(mlxsw_m,
mlxsw_m->module_to_port[i]);
}
- devl_unlock(devlink);
i = max_ports;
err_module_to_port_map:
for (i--; i > 0; i--)
static void mlxsw_m_ports_remove(struct mlxsw_m *mlxsw_m)
{
- struct devlink *devlink = priv_to_devlink(mlxsw_m->core);
int i;
- devl_lock(devlink);
for (i = 0; i < mlxsw_m->max_ports; i++) {
if (mlxsw_m->module_to_port[i] > 0) {
mlxsw_m_port_remove(mlxsw_m,
mlxsw_m_port_module_unmap(mlxsw_m, i);
}
}
- devl_unlock(devlink);
kfree(mlxsw_m->module_to_port);
kfree(mlxsw_m->ports);
u8 data;
port = nfp_port_from_netdev(netdev);
+ /* update port state to get latest interface */
+ set_bit(NFP_PORT_CHANGED, &port->flags);
eth_port = nfp_port_get_eth_port(port);
if (!eth_port)
return -EOPNOTSUPP;
}
/* Adjust the start address to be cache size aligned */
- cache->id = id;
cache->addr = addr & ~(u64)(cache->size - 1);
/* Re-init to the new ID and address */
return NULL;
}
+ cache->id = id;
+
exit:
/* Adjust offset */
*offset = addr - cache->addr;
bool "Wangxun devices"
default y
help
- If you have a network (Ethernet) card belonging to this class, say Y.
+ If you have a network (Ethernet) card from Wangxun(R), say Y.
Note that the answer to this question doesn't directly affect the
kernel: saying N will just cause the configurator to skip all
- the questions about Intel cards. If you say Y, you will be asked for
- your specific card in the following questions.
+ the questions about Wangxun(R) cards. If you say Y, you will
+ be asked for your specific card in the following questions.
if NET_VENDOR_WANGXUN
struct geneve_sock *gs4,
struct flowi4 *fl4,
const struct ip_tunnel_info *info,
- __be16 dport, __be16 sport)
+ __be16 dport, __be16 sport,
+ __u8 *full_tos)
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
use_cache = false;
}
fl4->flowi4_tos = RT_TOS(tos);
+ if (full_tos)
+ *full_tos = tos;
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
use_cache = false;
}
- fl6->flowlabel = ip6_make_flowinfo(RT_TOS(prio),
- info->key.label);
+ fl6->flowlabel = ip6_make_flowinfo(prio, info->key.label);
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
dst = dst_cache_get_ip6(dst_cache, &fl6->saddr);
const struct ip_tunnel_key *key = &info->key;
struct rtable *rt;
struct flowi4 fl4;
+ __u8 full_tos;
__u8 tos, ttl;
__be16 df = 0;
__be16 sport;
sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
- geneve->cfg.info.key.tp_dst, sport);
+ geneve->cfg.info.key.tp_dst, sport, &full_tos);
if (IS_ERR(rt))
return PTR_ERR(rt);
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
} else {
- tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
+ tos = ip_tunnel_ecn_encap(full_tos, ip_hdr(skb), skb);
if (geneve->cfg.ttl_inherit)
ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
else
1, USHRT_MAX, true);
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
- geneve->cfg.info.key.tp_dst, sport);
+ geneve->cfg.info.key.tp_dst, sport, NULL);
if (IS_ERR(rt))
return PTR_ERR(rt);
return sa;
}
+static struct macsec_rx_sa *macsec_active_rxsa_get(struct macsec_rx_sc *rx_sc)
+{
+ struct macsec_rx_sa *sa = NULL;
+ int an;
+
+ for (an = 0; an < MACSEC_NUM_AN; an++) {
+ sa = macsec_rxsa_get(rx_sc->sa[an]);
+ if (sa)
+ break;
+ }
+ return sa;
+}
+
static void free_rx_sc_rcu(struct rcu_head *head)
{
struct macsec_rx_sc *rx_sc = container_of(head, struct macsec_rx_sc, rcu_head);
skb->protocol = eth_hdr(skb)->h_proto;
}
+static unsigned int macsec_msdu_len(struct sk_buff *skb)
+{
+ struct macsec_dev *macsec = macsec_priv(skb->dev);
+ struct macsec_secy *secy = &macsec->secy;
+ bool sci_present = macsec_skb_cb(skb)->has_sci;
+
+ return skb->len - macsec_hdr_len(sci_present) - secy->icv_len;
+}
+
static void macsec_count_tx(struct sk_buff *skb, struct macsec_tx_sc *tx_sc,
struct macsec_tx_sa *tx_sa)
{
+ unsigned int msdu_len = macsec_msdu_len(skb);
struct pcpu_tx_sc_stats *txsc_stats = this_cpu_ptr(tx_sc->stats);
u64_stats_update_begin(&txsc_stats->syncp);
if (tx_sc->encrypt) {
- txsc_stats->stats.OutOctetsEncrypted += skb->len;
+ txsc_stats->stats.OutOctetsEncrypted += msdu_len;
txsc_stats->stats.OutPktsEncrypted++;
this_cpu_inc(tx_sa->stats->OutPktsEncrypted);
} else {
- txsc_stats->stats.OutOctetsProtected += skb->len;
+ txsc_stats->stats.OutOctetsProtected += msdu_len;
txsc_stats->stats.OutPktsProtected++;
this_cpu_inc(tx_sa->stats->OutPktsProtected);
}
aead_request_free(macsec_skb_cb(skb)->req);
rcu_read_lock_bh();
- macsec_encrypt_finish(skb, dev);
macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa);
- len = skb->len;
+ /* packet is encrypted/protected so tx_bytes must be calculated */
+ len = macsec_msdu_len(skb) + 2 * ETH_ALEN;
+ macsec_encrypt_finish(skb, dev);
ret = dev_queue_xmit(skb);
count_tx(dev, ret, len);
rcu_read_unlock_bh();
macsec_skb_cb(skb)->req = req;
macsec_skb_cb(skb)->tx_sa = tx_sa;
+ macsec_skb_cb(skb)->has_sci = sci_present;
aead_request_set_callback(req, 0, macsec_encrypt_done, skb);
dev_hold(skb->dev);
u64_stats_update_begin(&rxsc_stats->syncp);
rxsc_stats->stats.InPktsLate++;
u64_stats_update_end(&rxsc_stats->syncp);
+ secy->netdev->stats.rx_dropped++;
return false;
}
if (secy->validate_frames != MACSEC_VALIDATE_DISABLED) {
+ unsigned int msdu_len = macsec_msdu_len(skb);
u64_stats_update_begin(&rxsc_stats->syncp);
if (hdr->tci_an & MACSEC_TCI_E)
- rxsc_stats->stats.InOctetsDecrypted += skb->len;
+ rxsc_stats->stats.InOctetsDecrypted += msdu_len;
else
- rxsc_stats->stats.InOctetsValidated += skb->len;
+ rxsc_stats->stats.InOctetsValidated += msdu_len;
u64_stats_update_end(&rxsc_stats->syncp);
}
u64_stats_update_begin(&rxsc_stats->syncp);
rxsc_stats->stats.InPktsNotValid++;
u64_stats_update_end(&rxsc_stats->syncp);
+ this_cpu_inc(rx_sa->stats->InPktsNotValid);
+ secy->netdev->stats.rx_errors++;
return false;
}
macsec_finalize_skb(skb, macsec->secy.icv_len,
macsec_extra_len(macsec_skb_cb(skb)->has_sci));
+ len = skb->len;
macsec_reset_skb(skb, macsec->secy.netdev);
- len = skb->len;
if (gro_cells_receive(&macsec->gro_cells, skb) == NET_RX_SUCCESS)
count_rx(dev, len);
u64_stats_update_begin(&secy_stats->syncp);
secy_stats->stats.InPktsNoTag++;
u64_stats_update_end(&secy_stats->syncp);
+ macsec->secy.netdev->stats.rx_dropped++;
continue;
}
u64_stats_update_begin(&secy_stats->syncp);
secy_stats->stats.InPktsBadTag++;
u64_stats_update_end(&secy_stats->syncp);
+ secy->netdev->stats.rx_errors++;
goto drop_nosa;
}
/* If validateFrames is Strict or the C bit in the
* SecTAG is set, discard
*/
+ struct macsec_rx_sa *active_rx_sa = macsec_active_rxsa_get(rx_sc);
if (hdr->tci_an & MACSEC_TCI_C ||
secy->validate_frames == MACSEC_VALIDATE_STRICT) {
u64_stats_update_begin(&rxsc_stats->syncp);
rxsc_stats->stats.InPktsNotUsingSA++;
u64_stats_update_end(&rxsc_stats->syncp);
+ secy->netdev->stats.rx_errors++;
+ if (active_rx_sa)
+ this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA);
goto drop_nosa;
}
u64_stats_update_begin(&rxsc_stats->syncp);
rxsc_stats->stats.InPktsUnusedSA++;
u64_stats_update_end(&rxsc_stats->syncp);
+ if (active_rx_sa)
+ this_cpu_inc(active_rx_sa->stats->InPktsUnusedSA);
goto deliver;
}
u64_stats_update_begin(&rxsc_stats->syncp);
rxsc_stats->stats.InPktsLate++;
u64_stats_update_end(&rxsc_stats->syncp);
+ macsec->secy.netdev->stats.rx_dropped++;
goto drop;
}
}
deliver:
macsec_finalize_skb(skb, secy->icv_len,
macsec_extra_len(macsec_skb_cb(skb)->has_sci));
+ len = skb->len;
macsec_reset_skb(skb, secy->netdev);
if (rx_sa)
macsec_rxsc_put(rx_sc);
skb_orphan(skb);
- len = skb->len;
ret = gro_cells_receive(&macsec->gro_cells, skb);
if (ret == NET_RX_SUCCESS)
count_rx(dev, len);
u64_stats_update_begin(&secy_stats->syncp);
secy_stats->stats.InPktsNoSCI++;
u64_stats_update_end(&secy_stats->syncp);
+ macsec->secy.netdev->stats.rx_errors++;
continue;
}
return NETDEV_TX_OK;
}
+ len = skb->len;
skb = macsec_encrypt(skb, dev);
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EINPROGRESS)
macsec_count_tx(skb, &macsec->secy.tx_sc, macsec_skb_cb(skb)->tx_sa);
macsec_encrypt_finish(skb, dev);
- len = skb->len;
ret = dev_queue_xmit(skb);
count_tx(dev, ret, len);
return ret;
s->rx_dropped = dev->stats.rx_dropped;
s->tx_dropped = dev->stats.tx_dropped;
+ s->rx_errors = dev->stats.rx_errors;
}
static int macsec_get_iflink(const struct net_device *dev)
cell = of_nvmem_cell_get(of_node, "io_impedance_ctrl");
if (IS_ERR(cell)) {
ret = PTR_ERR(cell);
- if (ret != -ENOENT)
+ if (ret != -ENOENT && ret != -EOPNOTSUPP)
return phydev_err_probe(phydev, ret,
"failed to get nvmem cell io_impedance_ctrl\n");
*/
static int genphy_c45_baset1_an_config_aneg(struct phy_device *phydev)
{
+ u16 adv_l_mask, adv_l = 0;
+ u16 adv_m_mask, adv_m = 0;
int changed = 0;
- u16 adv_l = 0;
- u16 adv_m = 0;
int ret;
+ adv_l_mask = MDIO_AN_T1_ADV_L_FORCE_MS | MDIO_AN_T1_ADV_L_PAUSE_CAP |
+ MDIO_AN_T1_ADV_L_PAUSE_ASYM;
+ adv_m_mask = MDIO_AN_T1_ADV_M_MST | MDIO_AN_T1_ADV_M_B10L;
+
switch (phydev->master_slave_set) {
case MASTER_SLAVE_CFG_MASTER_FORCE:
+ adv_m |= MDIO_AN_T1_ADV_M_MST;
+ fallthrough;
case MASTER_SLAVE_CFG_SLAVE_FORCE:
adv_l |= MDIO_AN_T1_ADV_L_FORCE_MS;
break;
case MASTER_SLAVE_CFG_MASTER_PREFERRED:
+ adv_m |= MDIO_AN_T1_ADV_M_MST;
+ fallthrough;
case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
break;
case MASTER_SLAVE_CFG_UNKNOWN:
case MASTER_SLAVE_CFG_UNSUPPORTED:
- return 0;
+ /* if master/slave role is not specified, do not overwrite it */
+ adv_l_mask &= ~MDIO_AN_T1_ADV_L_FORCE_MS;
+ adv_m_mask &= ~MDIO_AN_T1_ADV_M_MST;
+ break;
default:
phydev_warn(phydev, "Unsupported Master/Slave mode\n");
return -EOPNOTSUPP;
}
- switch (phydev->master_slave_set) {
- case MASTER_SLAVE_CFG_MASTER_FORCE:
- case MASTER_SLAVE_CFG_MASTER_PREFERRED:
- adv_m |= MDIO_AN_T1_ADV_M_MST;
- break;
- case MASTER_SLAVE_CFG_SLAVE_FORCE:
- case MASTER_SLAVE_CFG_SLAVE_PREFERRED:
- break;
- default:
- break;
- }
-
adv_l |= linkmode_adv_to_mii_t1_adv_l_t(phydev->advertising);
ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_T1_ADV_L,
- (MDIO_AN_T1_ADV_L_FORCE_MS | MDIO_AN_T1_ADV_L_PAUSE_CAP
- | MDIO_AN_T1_ADV_L_PAUSE_ASYM), adv_l);
+ adv_l_mask, adv_l);
if (ret < 0)
return ret;
if (ret > 0)
adv_m |= linkmode_adv_to_mii_t1_adv_m_t(phydev->advertising);
ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_T1_ADV_M,
- MDIO_AN_T1_ADV_M_MST | MDIO_AN_T1_ADV_M_B10L, adv_m);
+ adv_m_mask, adv_m);
if (ret < 0)
return ret;
if (ret > 0)
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.
+ */
+ WARN_ON(phydev->state != PHY_HALTED && !phydev->mac_managed_pm);
+
ret = phy_init_hw(phydev);
if (ret < 0)
return ret;
/* Any address will do - we take the first. We already
have the first two bytes filled with 0xfc, from
plip_init_dev(). */
- const struct in_ifaddr *ifa = rcu_dereference(in_dev->ifa_list);
+ const struct in_ifaddr *ifa = rtnl_dereference(in_dev->ifa_list);
if (ifa != NULL) {
dev_addr_mod(dev, 2, &ifa->ifa_local, 4);
}
skb_reset_mac_header(skb);
skb->protocol = eth_hdr(skb)->h_proto;
+ rcu_read_lock();
+ tap = rcu_dereference(q->tap);
+ if (!tap) {
+ kfree_skb(skb);
+ rcu_read_unlock();
+ return total_len;
+ }
+ skb->dev = tap->dev;
+
if (vnet_hdr_len) {
err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
tap_is_little_endian(q));
if (err) {
+ rcu_read_unlock();
drop_reason = SKB_DROP_REASON_DEV_HDR;
goto err_kfree;
}
__vlan_get_protocol(skb, skb->protocol, &depth) != 0)
skb_set_network_header(skb, depth);
- rcu_read_lock();
- tap = rcu_dereference(q->tap);
/* copy skb_ubuf_info for callback when skb has no error */
if (zerocopy) {
skb_zcopy_init(skb, msg_control);
uarg->callback(NULL, uarg, false);
}
- if (tap) {
- skb->dev = tap->dev;
- dev_queue_xmit(skb);
- } else {
- kfree_skb(skb);
- }
+ dev_queue_xmit(skb);
rcu_read_unlock();
-
return total_len;
err_kfree:
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
.link_reset = ax88179_link_reset,
.reset = ax88179_reset,
.stop = ax88179_stop,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_SEND_ZLP,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
.tx_fixup = ax88179_tx_fixup,
};
{QMI_QUIRK_SET_DTR(0x1e2d, 0x00b0, 4)}, /* Cinterion CLS8 */
{QMI_FIXED_INTF(0x1e2d, 0x00b7, 0)}, /* Cinterion MV31 RmNet */
{QMI_FIXED_INTF(0x1e2d, 0x00b9, 0)}, /* Cinterion MV31 RmNet based on new baseline */
+ {QMI_FIXED_INTF(0x1e2d, 0x00f3, 0)}, /* Cinterion MV32-W-A RmNet */
+ {QMI_FIXED_INTF(0x1e2d, 0x00f4, 0)}, /* Cinterion MV32-W-B RmNet */
{QMI_FIXED_INTF(0x413c, 0x81a2, 8)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
{QMI_FIXED_INTF(0x413c, 0x81a3, 8)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
{QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
- struct netdev_queue *queue = NULL;
struct veth_rq *rq = NULL;
struct net_device *rcv;
int length = skb->len;
rxq = skb_get_queue_mapping(skb);
if (rxq < rcv->real_num_rx_queues) {
rq = &rcv_priv->rq[rxq];
- queue = netdev_get_tx_queue(dev, rxq);
/* The napi pointer is available when an XDP program is
* attached or when GRO is enabled
skb_tx_timestamp(skb);
if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) {
- if (queue)
- txq_trans_cond_update(queue);
if (!use_napi)
dev_lstats_add(dev, length);
} else {
case XDP_TX:
stats->xdp_tx++;
xdpf = xdp_convert_buff_to_frame(&xdp);
- if (unlikely(!xdpf))
+ if (unlikely(!xdpf)) {
+ if (unlikely(xdp_page != page))
+ put_page(xdp_page);
goto err_xdp;
+ }
err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
if (unlikely(!err)) {
xdp_return_frame_rx_napi(xdpf);
fl6.flowi6_oif = oif;
fl6.daddr = *daddr;
fl6.saddr = *saddr;
- fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
+ fl6.flowlabel = ip6_make_flowinfo(tos, label);
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = IPPROTO_UDP;
fl6.fl6_dport = dport;
conn_info->req_ies_len = 0;
}
-inline void wilc_handle_disconnect(struct wilc_vif *vif)
+void wilc_handle_disconnect(struct wilc_vif *vif)
{
struct host_if_drv *hif_drv = vif->hif_drv;
void *wilc_parse_join_bss_param(struct cfg80211_bss *bss,
struct cfg80211_crypto_settings *crypto);
int wilc_set_default_mgmt_key_index(struct wilc_vif *vif, u8 index);
-inline void wilc_handle_disconnect(struct wilc_vif *vif);
+void wilc_handle_disconnect(struct wilc_vif *vif);
+
#endif
ipa_name, com, CARD_DEVID(card));
}
+static void qeth_default_link_info(struct qeth_card *card)
+{
+ struct qeth_link_info *link_info = &card->info.link_info;
+
+ QETH_CARD_TEXT(card, 2, "dftlinfo");
+ link_info->duplex = DUPLEX_FULL;
+
+ if (IS_IQD(card) || IS_VM_NIC(card)) {
+ link_info->speed = SPEED_10000;
+ link_info->port = PORT_FIBRE;
+ link_info->link_mode = QETH_LINK_MODE_FIBRE_SHORT;
+ } else {
+ switch (card->info.link_type) {
+ case QETH_LINK_TYPE_FAST_ETH:
+ case QETH_LINK_TYPE_LANE_ETH100:
+ link_info->speed = SPEED_100;
+ link_info->port = PORT_TP;
+ break;
+ case QETH_LINK_TYPE_GBIT_ETH:
+ case QETH_LINK_TYPE_LANE_ETH1000:
+ link_info->speed = SPEED_1000;
+ link_info->port = PORT_FIBRE;
+ break;
+ case QETH_LINK_TYPE_10GBIT_ETH:
+ link_info->speed = SPEED_10000;
+ link_info->port = PORT_FIBRE;
+ break;
+ case QETH_LINK_TYPE_25GBIT_ETH:
+ link_info->speed = SPEED_25000;
+ link_info->port = PORT_FIBRE;
+ break;
+ default:
+ dev_info(&card->gdev->dev,
+ "Unknown link type %x\n",
+ card->info.link_type);
+ link_info->speed = SPEED_UNKNOWN;
+ link_info->port = PORT_OTHER;
+ }
+
+ link_info->link_mode = QETH_LINK_MODE_UNKNOWN;
+ }
+}
+
static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
struct qeth_ipa_cmd *cmd)
{
netdev_name(card->dev), card->info.chpid);
qeth_issue_ipa_msg(cmd, cmd->hdr.return_code, card);
netif_carrier_off(card->dev);
+ qeth_default_link_info(card);
}
return NULL;
case IPA_CMD_STARTLAN:
return rc;
}
-static int qeth_query_card_info_cb(struct qeth_card *card,
- struct qeth_reply *reply, unsigned long data)
-{
- struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data;
- struct qeth_link_info *link_info = reply->param;
- struct qeth_query_card_info *card_info;
-
- QETH_CARD_TEXT(card, 2, "qcrdincb");
- if (qeth_setadpparms_inspect_rc(cmd))
- return -EIO;
-
- card_info = &cmd->data.setadapterparms.data.card_info;
- netdev_dbg(card->dev,
- "card info: card_type=0x%02x, port_mode=0x%04x, port_speed=0x%08x\n",
- card_info->card_type, card_info->port_mode,
- card_info->port_speed);
-
- switch (card_info->port_mode) {
- case CARD_INFO_PORTM_FULLDUPLEX:
- link_info->duplex = DUPLEX_FULL;
- break;
- case CARD_INFO_PORTM_HALFDUPLEX:
- link_info->duplex = DUPLEX_HALF;
- break;
- default:
- link_info->duplex = DUPLEX_UNKNOWN;
- }
-
- switch (card_info->card_type) {
- case CARD_INFO_TYPE_1G_COPPER_A:
- case CARD_INFO_TYPE_1G_COPPER_B:
- link_info->speed = SPEED_1000;
- link_info->port = PORT_TP;
- break;
- case CARD_INFO_TYPE_1G_FIBRE_A:
- case CARD_INFO_TYPE_1G_FIBRE_B:
- link_info->speed = SPEED_1000;
- link_info->port = PORT_FIBRE;
- break;
- case CARD_INFO_TYPE_10G_FIBRE_A:
- case CARD_INFO_TYPE_10G_FIBRE_B:
- link_info->speed = SPEED_10000;
- link_info->port = PORT_FIBRE;
- break;
- default:
- switch (card_info->port_speed) {
- case CARD_INFO_PORTS_10M:
- link_info->speed = SPEED_10;
- break;
- case CARD_INFO_PORTS_100M:
- link_info->speed = SPEED_100;
- break;
- case CARD_INFO_PORTS_1G:
- link_info->speed = SPEED_1000;
- break;
- case CARD_INFO_PORTS_10G:
- link_info->speed = SPEED_10000;
- break;
- case CARD_INFO_PORTS_25G:
- link_info->speed = SPEED_25000;
- break;
- default:
- link_info->speed = SPEED_UNKNOWN;
- }
-
- link_info->port = PORT_OTHER;
- }
-
- return 0;
-}
-
-int qeth_query_card_info(struct qeth_card *card,
- struct qeth_link_info *link_info)
-{
- struct qeth_cmd_buffer *iob;
-
- QETH_CARD_TEXT(card, 2, "qcrdinfo");
- if (!qeth_adp_supported(card, IPA_SETADP_QUERY_CARD_INFO))
- return -EOPNOTSUPP;
- iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_CARD_INFO, 0);
- if (!iob)
- return -ENOMEM;
-
- return qeth_send_ipa_cmd(card, iob, qeth_query_card_info_cb, link_info);
-}
-
static int qeth_init_link_info_oat_cb(struct qeth_card *card,
struct qeth_reply *reply_priv,
unsigned long data)
struct qeth_query_oat_physical_if *phys_if;
struct qeth_query_oat_reply *reply;
+ QETH_CARD_TEXT(card, 2, "qoatincb");
if (qeth_setadpparms_inspect_rc(cmd))
return -EIO;
static void qeth_init_link_info(struct qeth_card *card)
{
- card->info.link_info.duplex = DUPLEX_FULL;
-
- if (IS_IQD(card) || IS_VM_NIC(card)) {
- card->info.link_info.speed = SPEED_10000;
- card->info.link_info.port = PORT_FIBRE;
- card->info.link_info.link_mode = QETH_LINK_MODE_FIBRE_SHORT;
- } else {
- switch (card->info.link_type) {
- case QETH_LINK_TYPE_FAST_ETH:
- case QETH_LINK_TYPE_LANE_ETH100:
- card->info.link_info.speed = SPEED_100;
- card->info.link_info.port = PORT_TP;
- break;
- case QETH_LINK_TYPE_GBIT_ETH:
- case QETH_LINK_TYPE_LANE_ETH1000:
- card->info.link_info.speed = SPEED_1000;
- card->info.link_info.port = PORT_FIBRE;
- break;
- case QETH_LINK_TYPE_10GBIT_ETH:
- card->info.link_info.speed = SPEED_10000;
- card->info.link_info.port = PORT_FIBRE;
- break;
- case QETH_LINK_TYPE_25GBIT_ETH:
- card->info.link_info.speed = SPEED_25000;
- card->info.link_info.port = PORT_FIBRE;
- break;
- default:
- dev_info(&card->gdev->dev, "Unknown link type %x\n",
- card->info.link_type);
- card->info.link_info.speed = SPEED_UNKNOWN;
- card->info.link_info.port = PORT_OTHER;
- }
-
- card->info.link_info.link_mode = QETH_LINK_MODE_UNKNOWN;
- }
+ qeth_default_link_info(card);
/* Get more accurate data via QUERY OAT: */
if (qeth_adp_supported(card, IPA_SETADP_QUERY_OAT)) {
qeth_clear_working_pool_list(card);
qeth_flush_local_addrs(card);
card->info.promisc_mode = 0;
+ qeth_default_link_info(card);
rc = qeth_stop_channel(&card->data);
rc2 = qeth_stop_channel(&card->write);
struct ethtool_link_ksettings *cmd)
{
struct qeth_card *card = netdev->ml_priv;
- struct qeth_link_info link_info;
+ QETH_CARD_TEXT(card, 4, "ethtglks");
cmd->base.speed = card->info.link_info.speed;
cmd->base.duplex = card->info.link_info.duplex;
cmd->base.port = card->info.link_info.port;
cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID;
- /* Check if we can obtain more accurate information. */
- if (!qeth_query_card_info(card, &link_info)) {
- if (link_info.speed != SPEED_UNKNOWN)
- cmd->base.speed = link_info.speed;
- if (link_info.duplex != DUPLEX_UNKNOWN)
- cmd->base.duplex = link_info.duplex;
- if (link_info.port != PORT_OTHER)
- cmd->base.port = link_info.port;
- }
-
qeth_set_ethtool_link_modes(cmd, card->info.link_info.link_mode);
return 0;
static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src,
size_t offset, size_t size)
{
- return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size);
+ if (!bpfptr_is_kernel(src))
+ return copy_from_user(dst, src.user + offset, size);
+ return copy_from_kernel_nofault(dst, src.kernel + offset, size);
}
static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size)
static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count)
{
- return strncpy_from_sockptr(dst, (sockptr_t) src, count);
+ if (bpfptr_is_kernel(src))
+ return strncpy_from_kernel_nofault(dst, src.kernel, count);
+ return strncpy_from_user(dst, src.user, count);
}
#endif /* _LINUX_BPFPTR_H */
static inline struct sk_psock *sk_psock(const struct sock *sk)
{
- return rcu_dereference_sk_user_data(sk);
+ return __rcu_dereference_sk_user_data_with_flags(sk,
+ SK_USER_DATA_PSOCK);
}
static inline void sk_psock_set_state(struct sk_psock *psock,
const unsigned char *buf, int star_page);
void (*block_input)(struct net_device *dev, int count,
struct sk_buff *skb, int ring_offset);
- /* returns nonzero if a pending interrupt request might by caused by
- * the ax88786. Handles all interrupts if set to NULL
+ /* returns nonzero if a pending interrupt request might be caused by
+ * the ax88796. Handles all interrupts if set to NULL
*/
int (*check_irq)(struct platform_device *pdev);
};
struct net_device *dev; /* first - useful for panic debug */
struct bonding *bond; /* our master */
int delay;
- /* all three in jiffies */
+ /* all 4 in jiffies */
unsigned long last_link_up;
+ unsigned long last_tx;
unsigned long last_rx;
unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
s8 link; /* one of BOND_LINK_XXXX */
return slave->last_rx;
}
+static inline void slave_update_last_tx(struct slave *slave)
+{
+ WRITE_ONCE(slave->last_tx, jiffies);
+}
+
+static inline unsigned long slave_last_tx(struct slave *slave)
+{
+ return READ_ONCE(slave->last_tx);
+}
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave,
struct sk_buff *skb)
/**
* struct genl_multicast_group - generic netlink multicast group
* @name: name of the multicast group, names are per-family
+ * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
*/
struct genl_multicast_group {
char name[GENL_NAMSIZ];
* struct genl_small_ops - generic netlink operations (small version)
* @cmd: command identifier
* @internal_flags: flags used by the family
- * @flags: flags
+ * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
* @validate: validation flags from enum genl_validate_flags
* @doit: standard command callback
* @dumpit: callback for dumpers
* struct genl_ops - generic netlink operations
* @cmd: command identifier
* @internal_flags: flags used by the family
- * @flags: flags
+ * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
* @maxattr: maximum number of attributes supported
* @policy: netlink policy (takes precedence over family policy)
* @validate: validation flags from enum genl_validate_flags
static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; }
#endif
+#if !IS_ENABLED(CONFIG_MPTCP)
+struct mptcp_sock { };
+#endif
+
#endif /* __NET_MPTCP_H */
bool report;
};
+enum nft_data_desc_flags {
+ NFT_DATA_DESC_SETELEM = (1 << 0),
+};
+
struct nft_data_desc {
enum nft_data_types type;
+ unsigned int size;
unsigned int len;
+ unsigned int flags;
};
-int nft_data_init(const struct nft_ctx *ctx,
- struct nft_data *data, unsigned int size,
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
struct nft_data_desc *desc, const struct nlattr *nla);
void nft_data_hold(const struct nft_data *data, enum nft_data_types type);
void nft_data_release(const struct nft_data *data, enum nft_data_types type);
struct nft_set_ext_tmpl {
u16 len;
u8 offset[NFT_SET_EXT_NUM];
+ u8 ext_len[NFT_SET_EXT_NUM];
};
/**
return -EINVAL;
tmpl->offset[id] = tmpl->len;
- tmpl->len += nft_set_ext_types[id].len + len;
+ tmpl->ext_len[id] = nft_set_ext_types[id].len + len;
+ tmpl->len += tmpl->ext_len[id];
return 0;
}
SK_PACING_FQ = 2,
};
-/* Pointer stored in sk_user_data might not be suitable for copying
- * when cloning the socket. For instance, it can point to a reference
- * counted object. sk_user_data bottom bit is set if pointer must not
- * be copied.
+/* flag bits in sk_user_data
+ *
+ * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might
+ * not be suitable for copying when cloning the socket. For instance,
+ * it can point to a reference counted object. sk_user_data bottom
+ * bit is set if pointer must not be copied.
+ *
+ * - SK_USER_DATA_BPF: Mark whether sk_user_data field is
+ * managed/owned by a BPF reuseport array. This bit should be set
+ * when sk_user_data's sk is added to the bpf's reuseport_array.
+ *
+ * - SK_USER_DATA_PSOCK: Mark whether pointer stored in
+ * sk_user_data points to psock type. This bit should be set
+ * when sk_user_data is assigned to a psock object.
*/
#define SK_USER_DATA_NOCOPY 1UL
-#define SK_USER_DATA_BPF 2UL /* Managed by BPF */
-#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF)
+#define SK_USER_DATA_BPF 2UL
+#define SK_USER_DATA_PSOCK 4UL
+#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\
+ SK_USER_DATA_PSOCK)
/**
* sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied
#define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
+/**
+ * __rcu_dereference_sk_user_data_with_flags - return the pointer
+ * only if argument flags all has been set in sk_user_data. Otherwise
+ * return NULL
+ *
+ * @sk: socket
+ * @flags: flag bits
+ */
+static inline void *
+__rcu_dereference_sk_user_data_with_flags(const struct sock *sk,
+ uintptr_t flags)
+{
+ uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk));
+
+ WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK);
+
+ if ((sk_user_data & flags) == flags)
+ return (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
+ return NULL;
+}
+
#define rcu_dereference_sk_user_data(sk) \
+ __rcu_dereference_sk_user_data_with_flags(sk, 0)
+#define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \
({ \
- void *__tmp = rcu_dereference(__sk_user_data((sk))); \
- (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \
-})
-#define rcu_assign_sk_user_data(sk, ptr) \
-({ \
- uintptr_t __tmp = (uintptr_t)(ptr); \
- WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \
- rcu_assign_pointer(__sk_user_data((sk)), __tmp); \
-})
-#define rcu_assign_sk_user_data_nocopy(sk, ptr) \
-({ \
- uintptr_t __tmp = (uintptr_t)(ptr); \
- WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \
+ uintptr_t __tmp1 = (uintptr_t)(ptr), \
+ __tmp2 = (uintptr_t)(flags); \
+ WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \
+ WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \
rcu_assign_pointer(__sk_user_data((sk)), \
- __tmp | SK_USER_DATA_NOCOPY); \
+ __tmp1 | __tmp2); \
})
+#define rcu_assign_sk_user_data(sk, ptr) \
+ __rcu_assign_sk_user_data_with_flags(sk, ptr, 0)
static inline
struct net *sock_net(const struct sock *sk)
void *priv_ctx_tx;
void *priv_ctx_rx;
- struct net_device *netdev;
+ struct net_device __rcu *netdev;
/* rw cache line */
struct cipher_context tx;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by
+ driver-specific utilities) */
+
+/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */
+
+
+#ifndef LINUX_ATM_ZATM_H
+#define LINUX_ATM_ZATM_H
+
+/*
+ * Note: non-kernel programs including this file must also include
+ * sys/types.h for struct timeval
+ */
+
+#include <linux/atmapi.h>
+#include <linux/atmioc.h>
+
+#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc)
+ /* get pool statistics */
+#define ZATM_GETPOOLZ _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc)
+ /* get statistics and zero */
+#define ZATM_SETPOOL _IOW('a',ATMIOC_SARPRV+3,struct atmif_sioc)
+ /* set pool parameters */
+
+struct zatm_pool_info {
+ int ref_count; /* free buffer pool usage counters */
+ int low_water,high_water; /* refill parameters */
+ int rqa_count,rqu_count; /* queue condition counters */
+ int offset,next_off; /* alignment optimizations: offset */
+ int next_cnt,next_thres; /* repetition counter and threshold */
+};
+
+struct zatm_pool_req {
+ int pool_num; /* pool number */
+ struct zatm_pool_info info; /* actual information */
+};
+
+#define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */
+#define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */
+#define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */
+#define ZATM_LAST_POOL ZATM_AAL5_POOL_BASE+10 /* max. 64 kB */
+
+#define ZATM_TIMER_HISTORY_SIZE 16 /* number of timer adjustments to
+ record; must be 2^n */
+
+#endif
__CTRL_ATTR_MCAST_GRP_MAX,
};
+#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
+
enum {
CTRL_ATTR_POLICY_UNSPEC,
CTRL_ATTR_POLICY_DO,
CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1
};
-#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
-
+#define CTRL_ATTR_POLICY_MAX (__CTRL_ATTR_POLICY_DUMP_MAX - 1)
#endif /* _UAPI__LINUX_GENERIC_NETLINK_H */
char prefix[30];
};
-#endif /*_IPT_LOG_H*/
+#endif /* _IP6T_LOG_H */
seq_info->percpu_value_buf = value_buf;
}
+ /* bpf_iter_attach_map() acquires a map uref, and the uref may be
+ * released before or in the middle of iterating map elements, so
+ * acquire an extra map uref for iterator.
+ */
+ bpf_map_inc_with_uref(map);
seq_info->map = map;
return 0;
}
{
struct bpf_iter_seq_array_map_info *seq_info = priv_data;
+ bpf_map_put_with_uref(seq_info->map);
kfree(seq_info->percpu_value_buf);
}
iter_priv->done_stop = true;
}
+static inline bool bpf_iter_target_support_resched(const struct bpf_iter_target_info *tinfo)
+{
+ return tinfo->reg_info->feature & BPF_ITER_RESCHED;
+}
+
static bool bpf_iter_support_resched(struct seq_file *seq)
{
struct bpf_iter_priv_data *iter_priv;
iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
target_private);
- return iter_priv->tinfo->reg_info->feature & BPF_ITER_RESCHED;
+ return bpf_iter_target_support_resched(iter_priv->tinfo);
}
/* maximum visited objects before bailing out */
if (!tinfo)
return -ENOENT;
+ /* Only allow sleepable program for resched-able iterator */
+ if (prog->aux->sleepable && !bpf_iter_target_support_resched(tinfo))
+ return -EINVAL;
+
link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
if (!link)
return -ENOMEM;
struct htab_elem *l;
if (node) {
- u32 key_size = htab->map.key_size;
-
l = container_of(node, struct htab_elem, lru_node);
- memcpy(l->key, key, key_size);
- check_and_init_map_value(&htab->map,
- l->key + round_up(key_size, 8));
+ memcpy(l->key, key, htab->map.key_size);
return l;
}
seq_info->percpu_value_buf = value_buf;
}
+ bpf_map_inc_with_uref(map);
seq_info->map = map;
seq_info->htab = container_of(map, struct bpf_htab, map);
return 0;
{
struct bpf_iter_seq_hash_map_info *seq_info = priv_data;
+ bpf_map_put_with_uref(seq_info->map);
kfree(seq_info->percpu_value_buf);
}
/* The caller must hold the reuseport_lock */
void bpf_sk_reuseport_detach(struct sock *sk)
{
- uintptr_t sk_user_data;
+ struct sock __rcu **socks;
write_lock_bh(&sk->sk_callback_lock);
- sk_user_data = (uintptr_t)sk->sk_user_data;
- if (sk_user_data & SK_USER_DATA_BPF) {
- struct sock __rcu **socks;
-
- socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
+ socks = __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_BPF);
+ if (socks) {
WRITE_ONCE(sk->sk_user_data, NULL);
/*
* Do not move this NULL assignment outside of
union bpf_attr __user *uattr)
{
struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ struct btf *attach_btf = bpf_prog_get_target_btf(prog);
struct bpf_prog_info info;
u32 info_len = attr->info.info_len;
struct bpf_prog_kstats stats;
if (prog->aux->btf)
info.btf_id = btf_obj_id(prog->aux->btf);
info.attach_btf_id = prog->aux->attach_btf_id;
- if (prog->aux->attach_btf)
- info.attach_btf_obj_id = btf_obj_id(prog->aux->attach_btf);
- else if (prog->aux->dst_prog)
- info.attach_btf_obj_id = btf_obj_id(prog->aux->dst_prog->aux->attach_btf);
+ if (attach_btf)
+ info.attach_btf_obj_id = btf_obj_id(attach_btf);
ulen = info.nr_func_info;
info.nr_func_info = prog->aux->func_info_cnt;
BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
{
- struct bpf_prog * __maybe_unused prog;
- struct bpf_tramp_run_ctx __maybe_unused run_ctx;
-
switch (cmd) {
case BPF_MAP_CREATE:
case BPF_MAP_UPDATE_ELEM:
case BPF_LINK_CREATE:
case BPF_RAW_TRACEPOINT_OPEN:
break;
+ default:
+ return -EINVAL;
+ }
+ return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size);
+}
+
+
+/* To shut up -Wmissing-prototypes.
+ * This function is used by the kernel light skeleton
+ * to load bpf programs when modules are loaded or during kernel boot.
+ * See tools/lib/bpf/skel_internal.h
+ */
+int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+
+int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
+{
+ struct bpf_prog * __maybe_unused prog;
+ struct bpf_tramp_run_ctx __maybe_unused run_ctx;
+
+ switch (cmd) {
#ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */
case BPF_PROG_TEST_RUN:
if (attr->test.data_in || attr->test.data_out ||
return 0;
#endif
default:
- return -EINVAL;
+ return ____bpf_sys_bpf(cmd, attr, size);
}
- return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size);
}
-EXPORT_SYMBOL(bpf_sys_bpf);
+EXPORT_SYMBOL(kern_sys_bpf);
static const struct bpf_func_proto bpf_sys_bpf_proto = {
.func = bpf_sys_bpf,
* multiple rcu callbacks.
*/
hlist_del(&tr->hlist);
- kfree(tr->fops);
+ if (tr->fops) {
+ ftrace_free_filter(tr->fops);
+ kfree(tr->fops);
+ }
kfree(tr);
out:
mutex_unlock(&trampoline_mutex);
unsigned long ax25_display_timer(struct timer_list *timer)
{
+ long delta = timer->expires - jiffies;
+
if (!timer_pending(timer))
return 0;
- return timer->expires - jiffies;
+ return max(0L, delta);
}
EXPORT_SYMBOL(ax25_display_timer);
/* LE Get Vendor Capabilities Command */
skb = __hci_cmd_sync(hdev, hci_opcode_pack(0x3f, 0x153), 0, NULL,
HCI_CMD_TIMEOUT);
- if (IS_ERR(skb)) {
+ if (IS_ERR_OR_NULL(skb)) {
+ if (!skb)
+ skb = ERR_PTR(-EIO);
+
bt_dev_err(hdev, "AOSP get vendor capabilities (%ld)",
PTR_ERR(skb));
return;
skb = __hci_cmd_sync(hdev, BQR_OPCODE, sizeof(cp), &cp,
HCI_CMD_TIMEOUT);
- if (IS_ERR(skb)) {
+ if (IS_ERR_OR_NULL(skb)) {
+ if (!skb)
+ skb = ERR_PTR(-EIO);
+
bt_dev_err(hdev, "Enabling Android BQR failed (%ld)",
PTR_ERR(skb));
return PTR_ERR(skb);
skb = __hci_cmd_sync(hdev, BQR_OPCODE, sizeof(cp), &cp,
HCI_CMD_TIMEOUT);
- if (IS_ERR(skb)) {
+ if (IS_ERR_OR_NULL(skb)) {
+ if (!skb)
+ skb = ERR_PTR(-EIO);
+
bt_dev_err(hdev, "Disabling Android BQR failed (%ld)",
PTR_ERR(skb));
return PTR_ERR(skb);
cis->cis_id = qos->cis;
cis->c_sdu = cpu_to_le16(qos->out.sdu);
cis->p_sdu = cpu_to_le16(qos->in.sdu);
- cis->c_phy = qos->out.phy;
- cis->p_phy = qos->in.phy;
+ cis->c_phy = qos->out.phy ? qos->out.phy : qos->in.phy;
+ cis->p_phy = qos->in.phy ? qos->in.phy : qos->out.phy;
cis->c_rtn = qos->out.rtn;
cis->p_rtn = qos->in.rtn;
if (!qos->in.latency)
qos->in.latency = qos->out.latency;
- /* Mirror PHYs that are disabled as SDU will be set to 0 */
- if (!qos->in.phy)
- qos->in.phy = qos->out.phy;
-
- if (!qos->out.phy)
- qos->out.phy = qos->in.phy;
-
if (!hci_le_set_cig_params(cis, qos)) {
hci_conn_drop(cis);
return ERR_PTR(-EINVAL);
struct sk_buff *skb)
{
struct hci_rp_delete_stored_link_key *rp = data;
+ u16 num_keys;
bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
if (rp->status)
return rp->status;
- if (rp->num_keys <= hdev->stored_num_keys)
- hdev->stored_num_keys -= le16_to_cpu(rp->num_keys);
+ num_keys = le16_to_cpu(rp->num_keys);
+
+ if (num_keys <= hdev->stored_num_keys)
+ hdev->stored_num_keys -= num_keys;
else
hdev->stored_num_keys = 0;
/* ----- ISO socket info ----- */
#define iso_pi(sk) ((struct iso_pinfo *)sk)
+#define EIR_SERVICE_DATA_LENGTH 4
+#define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH)
+
struct iso_pinfo {
struct bt_sock bt;
bdaddr_t src;
__u32 flags;
struct bt_iso_qos qos;
__u8 base_len;
- __u8 base[HCI_MAX_PER_AD_LENGTH];
+ __u8 base[BASE_MAX_LENGTH];
struct iso_conn *conn;
};
return err;
}
+static struct bt_iso_qos *iso_sock_get_qos(struct sock *sk)
+{
+ if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONNECT2)
+ return &iso_pi(sk)->conn->hcon->iso_qos;
+
+ return &iso_pi(sk)->qos;
+}
+
static int iso_send_frame(struct sock *sk, struct sk_buff *skb)
{
struct iso_conn *conn = iso_pi(sk)->conn;
+ struct bt_iso_qos *qos = iso_sock_get_qos(sk);
struct hci_iso_data_hdr *hdr;
int len = 0;
BT_DBG("sk %p len %d", sk, skb->len);
- if (skb->len > iso_pi(sk)->qos.out.sdu)
+ if (skb->len > qos->out.sdu)
return -EMSGSIZE;
len = skb->len;
}
len = min_t(unsigned int, sizeof(qos), optlen);
- if (len != sizeof(qos))
- return -EINVAL;
+ if (len != sizeof(qos)) {
+ err = -EINVAL;
+ break;
+ }
memset(&qos, 0, sizeof(qos));
{
struct sock *sk = sock->sk;
int len, err = 0;
- struct bt_iso_qos qos;
+ struct bt_iso_qos *qos;
u8 base_len;
u8 *base;
switch (optname) {
case BT_DEFER_SETUP:
- if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) {
+ if (sk->sk_state == BT_CONNECTED) {
err = -EINVAL;
break;
}
break;
case BT_ISO_QOS:
- if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONNECT2)
- qos = iso_pi(sk)->conn->hcon->iso_qos;
- else
- qos = iso_pi(sk)->qos;
+ qos = iso_sock_get_qos(sk);
- len = min_t(unsigned int, len, sizeof(qos));
- if (copy_to_user(optval, (char *)&qos, len))
+ len = min_t(unsigned int, len, sizeof(*qos));
+ if (copy_to_user(optval, qos, len))
err = -EFAULT;
break;
bdaddr_t *dst,
u8 link_type)
{
- struct l2cap_chan *c, *c1 = NULL;
+ struct l2cap_chan *c, *tmp, *c1 = NULL;
read_lock(&chan_list_lock);
- list_for_each_entry(c, &chan_list, global_l) {
+ list_for_each_entry_safe(c, tmp, &chan_list, global_l) {
if (state && c->state != state)
continue;
dst_match = !bacmp(&c->dst, dst);
if (src_match && dst_match) {
c = l2cap_chan_hold_unless_zero(c);
- if (!c)
- continue;
-
- read_unlock(&chan_list_lock);
- return c;
+ if (c) {
+ read_unlock(&chan_list_lock);
+ return c;
+ }
}
/* Closest match */
hci_blocked_keys_clear(hdev);
- for (i = 0; i < keys->key_count; ++i) {
+ for (i = 0; i < key_count; ++i) {
struct blocked_key *b = kzalloc(sizeof(*b), GFP_KERNEL);
if (!b) {
u32 current_flags = __le32_to_cpu(cp->current_flags);
bt_dev_dbg(hdev, "Set device flags %pMR (type 0x%x) = 0x%x",
- &cp->addr.bdaddr, cp->addr.type,
- __le32_to_cpu(current_flags));
+ &cp->addr.bdaddr, cp->addr.type, current_flags);
// We should take hci_dev_lock() early, I think.. conn_flags can change
supported_flags = hdev->conn_flags;
HCI_MGMT_EXT_INDEX_EVENTS);
/* Cancel any remaining timed work */
+ if (!hci_dev_test_flag(hdev, HCI_MGMT))
+ return;
cancel_delayed_work_sync(&hdev->discov_off);
cancel_delayed_work_sync(&hdev->service_cache);
cancel_delayed_work_sync(&hdev->rpa_expired);
skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp,
HCI_CMD_TIMEOUT);
- if (IS_ERR(skb)) {
+ if (IS_ERR_OR_NULL(skb)) {
+ if (!skb)
+ skb = ERR_PTR(-EIO);
+
bt_dev_err(hdev, "Failed to read MSFT supported features (%ld)",
PTR_ERR(skb));
return false;
skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp,
HCI_CMD_TIMEOUT);
- if (IS_ERR(skb))
+ if (IS_ERR_OR_NULL(skb)) {
+ if (!skb)
+ return -EIO;
return PTR_ERR(skb);
+ }
return msft_le_cancel_monitor_advertisement_cb(hdev, hdev->msft_opcode,
monitor, skb);
HCI_CMD_TIMEOUT);
kfree(cp);
- if (IS_ERR(skb))
+ if (IS_ERR_OR_NULL(skb)) {
+ if (!skb)
+ return -EIO;
return PTR_ERR(skb);
+ }
return msft_le_monitor_advertisement_cb(hdev, hdev->msft_opcode,
monitor, skb);
int ret;
ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set);
+ ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_prog_test_kfunc_set);
return ret ?: register_btf_id_dtor_kfuncs(bpf_prog_test_dtor_kfunc,
ARRAY_SIZE(bpf_prog_test_dtor_kfunc),
THIS_MODULE);
if (!first)
return;
- if (WARN_ON_ONCE(j1939_session_activate(first))) {
+ if (j1939_session_activate(first)) {
+ netdev_warn_once(first->priv->ndev,
+ "%s: 0x%p: Identical session is already activated.\n",
+ __func__, first);
first->err = -EBUSY;
goto activate_next;
} else {
static void j1939_session_destroy(struct j1939_session *session)
{
+ struct sk_buff *skb;
+
if (session->transmission) {
if (session->err)
j1939_sk_errqueue(session, J1939_ERRQUEUE_TX_ABORT);
WARN_ON_ONCE(!list_empty(&session->sk_session_queue_entry));
WARN_ON_ONCE(!list_empty(&session->active_session_list_entry));
- skb_queue_purge(&session->skb_queue);
+ while ((skb = skb_dequeue(&session->skb_queue)) != NULL) {
+ /* drop ref taken in j1939_session_skb_queue() */
+ skb_unref(skb);
+ kfree_skb(skb);
+ }
__j1939_session_drop(session);
j1939_priv_put(session->priv);
kfree(session);
{
struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;
+ bpf_map_inc_with_uref(aux->map);
seq_info->map = aux->map;
return 0;
}
+static void bpf_iter_fini_sk_storage_map(void *priv_data)
+{
+ struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data;
+
+ bpf_map_put_with_uref(seq_info->map);
+}
+
static int bpf_iter_attach_map(struct bpf_prog *prog,
union bpf_iter_link_info *linfo,
struct bpf_iter_aux_info *aux)
if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
goto put_map;
- if (prog->aux->max_rdonly_access > map->value_size) {
+ if (prog->aux->max_rdwr_access > map->value_size) {
err = -EACCES;
goto put_map;
}
static const struct bpf_iter_seq_info iter_seq_info = {
.seq_ops = &bpf_sk_storage_map_seq_ops,
.init_seq_private = bpf_iter_init_sk_storage_map,
- .fini_seq_private = NULL,
+ .fini_seq_private = bpf_iter_fini_sk_storage_map,
.seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info),
};
const struct devlink_param *param,
struct devlink_param_gset_ctx *ctx)
{
- if (!param->get)
+ if (!param->get || devlink->reload_failed)
return -EOPNOTSUPP;
return param->get(devlink, param->id, ctx);
}
const struct devlink_param *param,
struct devlink_param_gset_ctx *ctx)
{
- if (!param->set)
+ if (!param->set || devlink->reload_failed)
return -EOPNOTSUPP;
return param->set(devlink, param->id, ctx);
}
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
- WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
+ if (sk->sk_socket && sk->sk_socket->ops->set_rcvlowat)
+ ret = sk->sk_socket->ops->set_rcvlowat(sk, val);
+ else
+ WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
case SO_MARK:
if (sk->sk_mark != val) {
sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED);
refcount_set(&psock->refcnt, 1);
- rcu_assign_sk_user_data_nocopy(sk, psock);
+ __rcu_assign_sk_user_data_with_flags(sk, psock,
+ SK_USER_DATA_NOCOPY |
+ SK_USER_DATA_PSOCK);
sock_hold(sk);
out:
{
struct sock_map_seq_info *info = priv_data;
+ bpf_map_inc_with_uref(aux->map);
info->map = aux->map;
return 0;
}
+static void sock_map_fini_seq_private(void *priv_data)
+{
+ struct sock_map_seq_info *info = priv_data;
+
+ bpf_map_put_with_uref(info->map);
+}
+
static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
.seq_ops = &sock_map_seq_ops,
.init_seq_private = sock_map_init_seq_private,
+ .fini_seq_private = sock_map_fini_seq_private,
.seq_priv_size = sizeof(struct sock_map_seq_info),
};
};
static int sock_hash_init_seq_private(void *priv_data,
- struct bpf_iter_aux_info *aux)
+ struct bpf_iter_aux_info *aux)
{
struct sock_hash_seq_info *info = priv_data;
+ bpf_map_inc_with_uref(aux->map);
info->map = aux->map;
info->htab = container_of(aux->map, struct bpf_shtab, map);
return 0;
}
+static void sock_hash_fini_seq_private(void *priv_data)
+{
+ struct sock_hash_seq_info *info = priv_data;
+
+ bpf_map_put_with_uref(info->map);
+}
+
static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
.seq_ops = &sock_hash_seq_ops,
.init_seq_private = sock_hash_init_seq_private,
+ .fini_seq_private = sock_hash_fini_seq_private,
.seq_priv_size = sizeof(struct sock_hash_seq_info),
};
fl6.daddr = info->key.u.ipv6.dst;
fl6.saddr = info->key.u.ipv6.src;
prio = info->key.tos;
- fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio),
- info->key.label);
+ fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label);
dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6,
NULL);
* callback. If the callback is not available, then we skip to the next
* attribute; otherwise, we call the destroy() callback.
*/
- for (i = 0; i < max_parsed; ++i) {
+ for (i = SEG6_LOCAL_SRH; i < max_parsed; ++i) {
if (!(parsed_attrs & SEG6_F_ATTR(i)))
continue;
struct seg6_action_param *param;
int err, i;
- for (i = 0; i < SEG6_LOCAL_MAX + 1; ++i) {
+ for (i = SEG6_LOCAL_SRH; i < SEG6_LOCAL_MAX + 1; ++i) {
if (!(desc->optattrs & SEG6_F_ATTR(i)) || !attrs[i])
continue;
}
/* parse the required attributes */
- for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
+ for (i = SEG6_LOCAL_SRH; i < SEG6_LOCAL_MAX + 1; i++) {
if (desc->attrs & SEG6_F_ATTR(i)) {
if (!attrs[i])
return -EINVAL;
attrs = slwt->desc->attrs | slwt->parsed_optattrs;
- for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
+ for (i = SEG6_LOCAL_SRH; i < SEG6_LOCAL_MAX + 1; i++) {
if (attrs & SEG6_F_ATTR(i)) {
param = &seg6_action_params[i];
err = param->put(skb, slwt);
if (attrs_a != attrs_b)
return 1;
- for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
+ for (i = SEG6_LOCAL_SRH; i < SEG6_LOCAL_MAX + 1; i++) {
if (attrs_a & SEG6_F_ATTR(i)) {
param = &seg6_action_params[i];
if (param->cmp(slwt_a, slwt_b))
info->limit > dfrag->data_len))
return 0;
+ if (unlikely(!__tcp_can_send(ssk)))
+ return -EAGAIN;
+
/* compute send limit */
info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
copy = info->size_goal;
if (__mptcp_check_fallback(msk)) {
if (!msk->first)
return NULL;
- return sk_stream_memory_free(msk->first) ? msk->first : NULL;
+ return __tcp_can_send(msk->first) &&
+ sk_stream_memory_free(msk->first) ? msk->first : NULL;
}
/* re-use last subflow, if the burst allow that */
ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
if (ret <= 0) {
+ if (ret == -EAGAIN)
+ continue;
mptcp_push_release(ssk, &info);
goto out;
}
static void __mptcp_destroy_sock(struct sock *sk)
{
- struct mptcp_subflow_context *subflow, *tmp;
struct mptcp_sock *msk = mptcp_sk(sk);
- LIST_HEAD(conn_list);
pr_debug("msk=%p", msk);
might_sleep();
- /* join list will be eventually flushed (with rst) at sock lock release time*/
- list_splice_init(&msk->conn_list, &conn_list);
-
mptcp_stop_timer(sk);
sk_stop_timer(sk, &sk->sk_timer);
msk->pm.status = 0;
- /* clears msk->subflow, allowing the following loop to close
- * even the initial subflow
- */
- mptcp_dispose_initial_subflow(msk);
- list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- __mptcp_close_ssk(sk, ssk, subflow, 0);
- }
-
sk->sk_prot->destroy(sk);
WARN_ON_ONCE(msk->rmem_fwd_alloc);
static int mptcp_disconnect(struct sock *sk, int flags)
{
- struct mptcp_subflow_context *subflow, *tmp;
struct mptcp_sock *msk = mptcp_sk(sk);
inet_sk_state_store(sk, TCP_CLOSE);
- list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
- __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_FASTCLOSE);
- }
-
mptcp_stop_timer(sk);
sk_stop_timer(sk, &sk->sk_timer);
if (mptcp_sk(sk)->token)
mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
- mptcp_destroy_common(msk);
+ /* msk->subflow is still intact, the following will not free the first
+ * subflow
+ */
+ mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE);
msk->last_snd = NULL;
WRITE_ONCE(msk->flags, 0);
msk->cb_flags = 0;
return newsk;
}
-void mptcp_destroy_common(struct mptcp_sock *msk)
+void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
{
+ struct mptcp_subflow_context *subflow, *tmp;
struct sock *sk = (struct sock *)msk;
__mptcp_clear_xmit(sk);
+ /* join list will be eventually flushed (with rst) at sock lock release time */
+ list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node)
+ __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags);
+
/* move to sk_receive_queue, sk_stream_kill_queues will purge it */
mptcp_data_lock(sk);
skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue);
{
struct mptcp_sock *msk = mptcp_sk(sk);
- mptcp_destroy_common(msk);
+ /* clears msk->subflow, allowing the following to close
+ * even the initial subflow
+ */
+ mptcp_dispose_initial_subflow(msk);
+ mptcp_destroy_common(msk, 0);
sk_sockets_allocated_dec(sk);
}
struct sockaddr_storage *addr,
unsigned short family);
-static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+static inline bool __tcp_can_send(const struct sock *ssk)
{
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ /* only send if our side has not closed yet */
+ return ((1 << inet_sk_state_load(ssk)) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+static inline bool __mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
if (subflow->request_join && !subflow->fully_established)
return false;
- /* only send if our side has not closed yet */
- return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+ return __tcp_can_send(mptcp_subflow_tcp_sock(subflow));
}
void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow);
}
}
-void mptcp_destroy_common(struct mptcp_sock *msk);
+void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags);
#define MPTCP_TOKEN_MAX_RETRIES 4
sock_orphan(sk);
}
- mptcp_destroy_common(mptcp_sk(sk));
+ /* We don't need to clear msk->subflow, as it's still NULL at this point */
+ mptcp_destroy_common(mptcp_sk(sk), 0);
inet_sock_destruct(sk);
}
config NF_FLOW_TABLE_PROCFS
bool "Supply flow table statistics in procfs"
- default y
+ depends on NF_FLOW_TABLE
depends on PROC_FS
- depends on SYSCTL
help
This option enables for the flow table offload statistics
to be shown in procfs under net/netfilter/nf_flowtable.
if (trans == NULL)
return NULL;
+ INIT_LIST_HEAD(&trans->list);
trans->msg_type = msg_type;
trans->ctx = *ctx;
}
static struct nft_chain *nft_chain_lookup_byid(const struct net *net,
+ const struct nft_table *table,
const struct nlattr *nla)
{
struct nftables_pernet *nft_net = nft_pernet(net);
struct nft_chain *chain = trans->ctx.chain;
if (trans->msg_type == NFT_MSG_NEWCHAIN &&
+ chain->table == table &&
id == nft_trans_chain_id(trans))
return chain;
}
}
static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
+ const struct nft_chain *chain,
const struct nlattr *nla);
#define NFT_RULE_MAXEXPRS 128
return -EOPNOTSUPP;
} else if (nla[NFTA_RULE_CHAIN_ID]) {
- chain = nft_chain_lookup_byid(net, nla[NFTA_RULE_CHAIN_ID]);
+ chain = nft_chain_lookup_byid(net, table, nla[NFTA_RULE_CHAIN_ID]);
if (IS_ERR(chain)) {
NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN_ID]);
return PTR_ERR(chain);
return PTR_ERR(old_rule);
}
} else if (nla[NFTA_RULE_POSITION_ID]) {
- old_rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_POSITION_ID]);
+ old_rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_POSITION_ID]);
if (IS_ERR(old_rule)) {
NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]);
return PTR_ERR(old_rule);
}
static struct nft_rule *nft_rule_lookup_byid(const struct net *net,
+ const struct nft_chain *chain,
const struct nlattr *nla)
{
struct nftables_pernet *nft_net = nft_pernet(net);
struct nft_rule *rule = nft_trans_rule(trans);
if (trans->msg_type == NFT_MSG_NEWRULE &&
+ trans->ctx.chain == chain &&
id == nft_trans_rule_id(trans))
return rule;
}
err = nft_delrule(&ctx, rule);
} else if (nla[NFTA_RULE_ID]) {
- rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]);
+ rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_ID]);
if (IS_ERR(rule)) {
NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]);
return PTR_ERR(rule);
}
static struct nft_set *nft_set_lookup_byid(const struct net *net,
+ const struct nft_table *table,
const struct nlattr *nla, u8 genmask)
{
struct nftables_pernet *nft_net = nft_pernet(net);
struct nft_set *set = nft_trans_set(trans);
if (id == nft_trans_set_id(trans) &&
+ set->table == table &&
nft_active_genmask(set, genmask))
return set;
}
if (!nla_set_id)
return set;
- set = nft_set_lookup_byid(net, nla_set_id, genmask);
+ set = nft_set_lookup_byid(net, table, nla_set_id, genmask);
}
return set;
}
static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set,
struct nft_data *key, struct nlattr *attr)
{
- struct nft_data_desc desc;
- int err;
-
- err = nft_data_init(ctx, key, NFT_DATA_VALUE_MAXLEN, &desc, attr);
- if (err < 0)
- return err;
-
- if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) {
- nft_data_release(key, desc.type);
- return -EINVAL;
- }
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = NFT_DATA_VALUE_MAXLEN,
+ .len = set->klen,
+ };
- return 0;
+ return nft_data_init(ctx, key, &desc, attr);
}
static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set,
struct nlattr *attr)
{
u32 dtype;
- int err;
-
- err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr);
- if (err < 0)
- return err;
if (set->dtype == NFT_DATA_VERDICT)
dtype = NFT_DATA_VERDICT;
else
dtype = NFT_DATA_VALUE;
- if (dtype != desc->type ||
- set->dlen != desc->len) {
- nft_data_release(data, desc->type);
- return -EINVAL;
- }
+ desc->type = dtype;
+ desc->size = NFT_DATA_VALUE_MAXLEN;
+ desc->len = set->dlen;
+ desc->flags = NFT_DATA_DESC_SETELEM;
- return 0;
+ return nft_data_init(ctx, data, desc, attr);
}
static void *nft_setelem_catchall_get(const struct net *net,
return ERR_PTR(err);
}
+static int nft_set_ext_check(const struct nft_set_ext_tmpl *tmpl, u8 id, u32 len)
+{
+ len += nft_set_ext_types[id].len;
+ if (len > tmpl->ext_len[id] ||
+ len > U8_MAX)
+ return -1;
+
+ return 0;
+}
+
+static int nft_set_ext_memcpy(const struct nft_set_ext_tmpl *tmpl, u8 id,
+ void *to, const void *from, u32 len)
+{
+ if (nft_set_ext_check(tmpl, id, len) < 0)
+ return -1;
+
+ memcpy(to, from, len);
+
+ return 0;
+}
+
void *nft_set_elem_init(const struct nft_set *set,
const struct nft_set_ext_tmpl *tmpl,
const u32 *key, const u32 *key_end,
elem = kzalloc(set->ops->elemsize + tmpl->len, gfp);
if (elem == NULL)
- return NULL;
+ return ERR_PTR(-ENOMEM);
ext = nft_set_elem_ext(set, elem);
nft_set_ext_init(ext, tmpl);
- if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY))
- memcpy(nft_set_ext_key(ext), key, set->klen);
- if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END))
- memcpy(nft_set_ext_key_end(ext), key_end, set->klen);
- if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
- memcpy(nft_set_ext_data(ext), data, set->dlen);
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY) &&
+ nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY,
+ nft_set_ext_key(ext), key, set->klen) < 0)
+ goto err_ext_check;
+
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END) &&
+ nft_set_ext_memcpy(tmpl, NFT_SET_EXT_KEY_END,
+ nft_set_ext_key_end(ext), key_end, set->klen) < 0)
+ goto err_ext_check;
+
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) &&
+ nft_set_ext_memcpy(tmpl, NFT_SET_EXT_DATA,
+ nft_set_ext_data(ext), data, set->dlen) < 0)
+ goto err_ext_check;
+
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
*nft_set_ext_expiration(ext) = get_jiffies_64() + expiration;
if (expiration == 0)
*nft_set_ext_timeout(ext) = timeout;
return elem;
+
+err_ext_check:
+ kfree(elem);
+
+ return ERR_PTR(-EINVAL);
}
static void __nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
}
static int nft_set_elem_expr_setup(struct nft_ctx *ctx,
+ const struct nft_set_ext_tmpl *tmpl,
const struct nft_set_ext *ext,
struct nft_expr *expr_array[],
u32 num_exprs)
{
struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
+ u32 len = sizeof(struct nft_set_elem_expr);
struct nft_expr *expr;
int i, err;
+ if (num_exprs == 0)
+ return 0;
+
+ for (i = 0; i < num_exprs; i++)
+ len += expr_array[i]->ops->size;
+
+ if (nft_set_ext_check(tmpl, NFT_SET_EXT_EXPRESSIONS, len) < 0)
+ return -EINVAL;
+
for (i = 0; i < num_exprs; i++) {
expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
err = nft_expr_clone(expr, expr_array[i]);
}
}
- err = -ENOMEM;
elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
elem.key_end.val.data, elem.data.val.data,
timeout, expiration, GFP_KERNEL_ACCOUNT);
- if (elem.priv == NULL)
+ if (IS_ERR(elem.priv)) {
+ err = PTR_ERR(elem.priv);
goto err_parse_data;
+ }
ext = nft_set_elem_ext(set, elem.priv);
if (flags)
*nft_set_ext_flags(ext) = flags;
+
if (ulen > 0) {
+ if (nft_set_ext_check(&tmpl, NFT_SET_EXT_USERDATA, ulen) < 0) {
+ err = -EINVAL;
+ goto err_elem_userdata;
+ }
udata = nft_set_ext_userdata(ext);
udata->len = ulen - 1;
nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen);
*nft_set_ext_obj(ext) = obj;
obj->use++;
}
- err = nft_set_elem_expr_setup(ctx, ext, expr_array, num_exprs);
+ err = nft_set_elem_expr_setup(ctx, &tmpl, ext, expr_array, num_exprs);
if (err < 0)
- goto err_elem_expr;
+ goto err_elem_free;
trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
if (trans == NULL) {
err = -ENOMEM;
- goto err_elem_expr;
+ goto err_elem_free;
}
ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
nft_setelem_remove(ctx->net, set, &elem);
err_element_clash:
kfree(trans);
-err_elem_expr:
+err_elem_free:
if (obj)
obj->use--;
-
+err_elem_userdata:
nf_tables_set_elem_destroy(ctx, set, elem.priv);
err_parse_data:
if (nla[NFTA_SET_ELEM_DATA] != NULL)
elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
elem.key_end.val.data, NULL, 0, 0,
GFP_KERNEL_ACCOUNT);
- if (elem.priv == NULL)
+ if (IS_ERR(elem.priv)) {
+ err = PTR_ERR(elem.priv);
goto fail_elem_key_end;
+ }
ext = nft_set_elem_ext(set, elem.priv);
if (flags)
tb[NFTA_VERDICT_CHAIN],
genmask);
} else if (tb[NFTA_VERDICT_CHAIN_ID]) {
- chain = nft_chain_lookup_byid(ctx->net,
+ chain = nft_chain_lookup_byid(ctx->net, ctx->table,
tb[NFTA_VERDICT_CHAIN_ID]);
if (IS_ERR(chain))
return PTR_ERR(chain);
return PTR_ERR(chain);
if (nft_is_base_chain(chain))
return -EOPNOTSUPP;
+ if (desc->flags & NFT_DATA_DESC_SETELEM &&
+ chain->flags & NFT_CHAIN_BINDING)
+ return -EINVAL;
chain->use++;
data->verdict.chain = chain;
}
desc->len = sizeof(data->verdict);
- desc->type = NFT_DATA_VERDICT;
+
return 0;
}
}
static int nft_value_init(const struct nft_ctx *ctx,
- struct nft_data *data, unsigned int size,
- struct nft_data_desc *desc, const struct nlattr *nla)
+ struct nft_data *data, struct nft_data_desc *desc,
+ const struct nlattr *nla)
{
unsigned int len;
len = nla_len(nla);
if (len == 0)
return -EINVAL;
- if (len > size)
+ if (len > desc->size)
return -EOVERFLOW;
+ if (desc->len) {
+ if (len != desc->len)
+ return -EINVAL;
+ } else {
+ desc->len = len;
+ }
nla_memcpy(data->data, nla, len);
- desc->type = NFT_DATA_VALUE;
- desc->len = len;
+
return 0;
}
*
* @ctx: context of the expression using the data
* @data: destination struct nft_data
- * @size: maximum data length
* @desc: data description
* @nla: netlink attribute containing data
*
* The caller can indicate that it only wants to accept data of type
* NFT_DATA_VALUE by passing NULL for the ctx argument.
*/
-int nft_data_init(const struct nft_ctx *ctx,
- struct nft_data *data, unsigned int size,
+int nft_data_init(const struct nft_ctx *ctx, struct nft_data *data,
struct nft_data_desc *desc, const struct nlattr *nla)
{
struct nlattr *tb[NFTA_DATA_MAX + 1];
int err;
+ if (WARN_ON_ONCE(!desc->size))
+ return -EINVAL;
+
err = nla_parse_nested_deprecated(tb, NFTA_DATA_MAX, nla,
nft_data_policy, NULL);
if (err < 0)
return err;
- if (tb[NFTA_DATA_VALUE])
- return nft_value_init(ctx, data, size, desc,
- tb[NFTA_DATA_VALUE]);
- if (tb[NFTA_DATA_VERDICT] && ctx != NULL)
- return nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
- return -EINVAL;
+ if (tb[NFTA_DATA_VALUE]) {
+ if (desc->type != NFT_DATA_VALUE)
+ return -EINVAL;
+
+ err = nft_value_init(ctx, data, desc, tb[NFTA_DATA_VALUE]);
+ } else if (tb[NFTA_DATA_VERDICT] && ctx != NULL) {
+ if (desc->type != NFT_DATA_VERDICT)
+ return -EINVAL;
+
+ err = nft_verdict_init(ctx, data, desc, tb[NFTA_DATA_VERDICT]);
+ } else {
+ err = -EINVAL;
+ }
+
+ return err;
}
EXPORT_SYMBOL_GPL(nft_data_init);
nft_trace_notify(info);
}
-static inline void nft_trace_packet(struct nft_traceinfo *info,
+static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
+ struct nft_traceinfo *info,
const struct nft_chain *chain,
const struct nft_rule_dp *rule,
enum nft_trace_types type)
{
if (static_branch_unlikely(&nft_trace_enabled)) {
- const struct nft_pktinfo *pkt = info->pkt;
-
info->nf_trace = pkt->skb->nf_trace;
info->rule = rule;
__nft_trace_packet(info, chain, type);
}
}
-static inline void nft_trace_copy_nftrace(struct nft_traceinfo *info)
+static inline void nft_trace_copy_nftrace(const struct nft_pktinfo *pkt,
+ struct nft_traceinfo *info)
{
if (static_branch_unlikely(&nft_trace_enabled)) {
- const struct nft_pktinfo *pkt = info->pkt;
-
if (info->trace)
info->nf_trace = pkt->skb->nf_trace;
}
const struct nft_chain *chain,
const struct nft_regs *regs)
{
- const struct nft_pktinfo *pkt = info->pkt;
enum nft_trace_types type;
switch (regs->verdict.code) {
break;
default:
type = NFT_TRACETYPE_RULE;
- info->nf_trace = pkt->skb->nf_trace;
+
+ if (info->trace)
+ info->nf_trace = info->pkt->skb->nf_trace;
break;
}
switch (regs.verdict.code) {
case NFT_BREAK:
regs.verdict.code = NFT_CONTINUE;
- nft_trace_copy_nftrace(&info);
+ nft_trace_copy_nftrace(pkt, &info);
continue;
case NFT_CONTINUE:
- nft_trace_packet(&info, chain, rule,
+ nft_trace_packet(pkt, &info, chain, rule,
NFT_TRACETYPE_RULE);
continue;
}
goto next_rule;
}
- nft_trace_packet(&info, basechain, NULL, NFT_TRACETYPE_POLICY);
+ nft_trace_packet(pkt, &info, basechain, NULL, NFT_TRACETYPE_POLICY);
if (static_branch_unlikely(&nft_counters_enabled))
nft_update_chain_stats(basechain, pkt);
static int nft_bitwise_init_bool(struct nft_bitwise *priv,
const struct nlattr *const tb[])
{
- struct nft_data_desc mask, xor;
+ struct nft_data_desc mask = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->mask),
+ .len = priv->len,
+ };
+ struct nft_data_desc xor = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->xor),
+ .len = priv->len,
+ };
int err;
if (tb[NFTA_BITWISE_DATA])
!tb[NFTA_BITWISE_XOR])
return -EINVAL;
- err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &mask,
- tb[NFTA_BITWISE_MASK]);
+ err = nft_data_init(NULL, &priv->mask, &mask, tb[NFTA_BITWISE_MASK]);
if (err < 0)
return err;
- if (mask.type != NFT_DATA_VALUE || mask.len != priv->len) {
- err = -EINVAL;
- goto err_mask_release;
- }
- err = nft_data_init(NULL, &priv->xor, sizeof(priv->xor), &xor,
- tb[NFTA_BITWISE_XOR]);
+ err = nft_data_init(NULL, &priv->xor, &xor, tb[NFTA_BITWISE_XOR]);
if (err < 0)
- goto err_mask_release;
- if (xor.type != NFT_DATA_VALUE || xor.len != priv->len) {
- err = -EINVAL;
- goto err_xor_release;
- }
+ goto err_xor_err;
return 0;
-err_xor_release:
- nft_data_release(&priv->xor, xor.type);
-err_mask_release:
+err_xor_err:
nft_data_release(&priv->mask, mask.type);
+
return err;
}
static int nft_bitwise_init_shift(struct nft_bitwise *priv,
const struct nlattr *const tb[])
{
- struct nft_data_desc d;
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->data),
+ .len = sizeof(u32),
+ };
int err;
if (tb[NFTA_BITWISE_MASK] ||
if (!tb[NFTA_BITWISE_DATA])
return -EINVAL;
- err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &d,
- tb[NFTA_BITWISE_DATA]);
+ err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_BITWISE_DATA]);
if (err < 0)
return err;
- if (d.type != NFT_DATA_VALUE || d.len != sizeof(u32) ||
- priv->data.data[0] >= BITS_PER_TYPE(u32)) {
- nft_data_release(&priv->data, d.type);
+
+ if (priv->data.data[0] >= BITS_PER_TYPE(u32)) {
+ nft_data_release(&priv->data, desc.type);
return -EINVAL;
}
static int
nft_bitwise_extract_u32_data(const struct nlattr * const tb, u32 *out)
{
- struct nft_data_desc desc;
struct nft_data data;
- int err = 0;
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(data),
+ .len = sizeof(u32),
+ };
+ int err;
- err = nft_data_init(NULL, &data, sizeof(data), &desc, tb);
+ err = nft_data_init(NULL, &data, &desc, tb);
if (err < 0)
return err;
- if (desc.type != NFT_DATA_VALUE || desc.len != sizeof(u32)) {
- err = -EINVAL;
- goto err;
- }
*out = data.data[0];
-err:
- nft_data_release(&data, desc.type);
- return err;
+
+ return 0;
}
static int nft_bitwise_fast_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_cmp_expr *priv = nft_expr_priv(expr);
- struct nft_data_desc desc;
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->data),
+ };
int err;
- err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc,
- tb[NFTA_CMP_DATA]);
+ err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
if (err < 0)
return err;
- if (desc.type != NFT_DATA_VALUE) {
- err = -EINVAL;
- nft_data_release(&priv->data, desc.type);
- return err;
- }
-
err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
if (err < 0)
return err;
const struct nlattr * const tb[])
{
struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
- struct nft_data_desc desc;
struct nft_data data;
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(data),
+ };
int err;
- err = nft_data_init(NULL, &data, sizeof(data), &desc,
- tb[NFTA_CMP_DATA]);
+ err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
if (err < 0)
return err;
const struct nlattr * const tb[])
{
struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr);
- struct nft_data_desc desc;
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->data),
+ };
int err;
- err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &desc,
- tb[NFTA_CMP_DATA]);
+ err = nft_data_init(NULL, &priv->data, &desc, tb[NFTA_CMP_DATA]);
if (err < 0)
return err;
static const struct nft_expr_ops *
nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
{
- struct nft_data_desc desc;
struct nft_data data;
+ struct nft_data_desc desc = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(data),
+ };
enum nft_cmp_ops op;
u8 sreg;
int err;
return ERR_PTR(-EINVAL);
}
- err = nft_data_init(NULL, &data, sizeof(data), &desc,
- tb[NFTA_CMP_DATA]);
+ err = nft_data_init(NULL, &data, &desc, tb[NFTA_CMP_DATA]);
if (err < 0)
return ERR_PTR(err);
- if (desc.type != NFT_DATA_VALUE)
- goto err1;
-
sreg = ntohl(nla_get_be32(tb[NFTA_CMP_SREG]));
if (op == NFT_CMP_EQ || op == NFT_CMP_NEQ) {
return &nft_cmp16_fast_ops;
}
return &nft_cmp_ops;
-err1:
- nft_data_release(&data, desc.type);
- return ERR_PTR(-EINVAL);
}
struct nft_expr_type nft_cmp_type __read_mostly = {
®s->data[priv->sreg_key], NULL,
®s->data[priv->sreg_data],
timeout, 0, GFP_ATOMIC);
- if (elem == NULL)
+ if (IS_ERR(elem))
goto err1;
ext = nft_set_elem_ext(set, elem);
[NFTA_IMMEDIATE_DATA] = { .type = NLA_NESTED },
};
+static enum nft_data_types nft_reg_to_type(const struct nlattr *nla)
+{
+ enum nft_data_types type;
+ u8 reg;
+
+ reg = ntohl(nla_get_be32(nla));
+ if (reg == NFT_REG_VERDICT)
+ type = NFT_DATA_VERDICT;
+ else
+ type = NFT_DATA_VALUE;
+
+ return type;
+}
+
static int nft_immediate_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
{
struct nft_immediate_expr *priv = nft_expr_priv(expr);
- struct nft_data_desc desc;
+ struct nft_data_desc desc = {
+ .size = sizeof(priv->data),
+ };
int err;
if (tb[NFTA_IMMEDIATE_DREG] == NULL ||
tb[NFTA_IMMEDIATE_DATA] == NULL)
return -EINVAL;
- err = nft_data_init(ctx, &priv->data, sizeof(priv->data), &desc,
- tb[NFTA_IMMEDIATE_DATA]);
+ desc.type = nft_reg_to_type(tb[NFTA_IMMEDIATE_DREG]);
+ err = nft_data_init(ctx, &priv->data, &desc, tb[NFTA_IMMEDIATE_DATA]);
if (err < 0)
return err;
const struct nlattr * const tb[])
{
struct nft_range_expr *priv = nft_expr_priv(expr);
- struct nft_data_desc desc_from, desc_to;
+ struct nft_data_desc desc_from = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->data_from),
+ };
+ struct nft_data_desc desc_to = {
+ .type = NFT_DATA_VALUE,
+ .size = sizeof(priv->data_to),
+ };
int err;
u32 op;
!tb[NFTA_RANGE_TO_DATA])
return -EINVAL;
- err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from),
- &desc_from, tb[NFTA_RANGE_FROM_DATA]);
+ err = nft_data_init(NULL, &priv->data_from, &desc_from,
+ tb[NFTA_RANGE_FROM_DATA]);
if (err < 0)
return err;
- if (desc_from.type != NFT_DATA_VALUE) {
- err = -EINVAL;
- goto err1;
- }
-
- err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to),
- &desc_to, tb[NFTA_RANGE_TO_DATA]);
+ err = nft_data_init(NULL, &priv->data_to, &desc_to,
+ tb[NFTA_RANGE_TO_DATA]);
if (err < 0)
goto err1;
- if (desc_to.type != NFT_DATA_VALUE) {
- err = -EINVAL;
- goto err2;
- }
-
if (desc_from.len != desc_to.len) {
err = -EINVAL;
goto err2;
/* Don't allow users to add both IPv4 and IPv6 addresses for a
* single entry. However, allow users to create two entries, one each
- * for IPv4 and IPv4, with the same LSM security context which should
+ * for IPv4 and IPv6, with the same LSM security context which should
* achieve the same result. */
if (!info->attrs[NLBL_UNLABEL_A_SECCTX] ||
!info->attrs[NLBL_UNLABEL_A_IFACE] ||
rcu_assign_pointer(f->next, f1);
rcu_assign_pointer(*fp, f);
- if (fold && fold->handle && f->handle != fold->handle) {
+ if (fold) {
th = to_hash(fold->handle);
h = from_hash(fold->handle >> 16);
b = rtnl_dereference(head->table[th]);
unsigned long dev_trans_start(struct net_device *dev)
{
- unsigned long val, res;
+ unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start);
+ unsigned long val;
unsigned int i;
- if (is_vlan_dev(dev))
- dev = vlan_dev_real_dev(dev);
- else if (netif_is_macvlan(dev))
- dev = macvlan_dev_real_dev(dev);
- res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start);
for (i = 1; i < dev->num_tx_queues; i++) {
val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start);
if (val && time_after(val, res))
struct tls_offload_context_tx *offload_ctx =
container_of(work, struct tls_offload_context_tx, destruct_work);
struct tls_context *ctx = offload_ctx->ctx;
- struct net_device *netdev = ctx->netdev;
+ struct net_device *netdev;
+
+ /* Safe, because this is the destroy flow, refcount is 0, so
+ * tls_device_down can't store this field in parallel.
+ */
+ netdev = rcu_dereference_protected(ctx->netdev,
+ !refcount_read(&ctx->refcount));
netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX);
dev_put(netdev);
static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
{
+ struct net_device *netdev;
unsigned long flags;
bool async_cleanup;
}
list_del(&ctx->list); /* Remove from tls_device_list / tls_device_down_list */
- async_cleanup = ctx->netdev && ctx->tx_conf == TLS_HW;
+
+ /* Safe, because this is the destroy flow, refcount is 0, so
+ * tls_device_down can't store this field in parallel.
+ */
+ netdev = rcu_dereference_protected(ctx->netdev,
+ !refcount_read(&ctx->refcount));
+
+ async_cleanup = netdev && ctx->tx_conf == TLS_HW;
if (async_cleanup) {
struct tls_offload_context_tx *offload_ctx = tls_offload_ctx_tx(ctx);
trace_tls_device_tx_resync_send(sk, seq, rcd_sn);
down_read(&device_offload_lock);
- netdev = tls_ctx->netdev;
+ netdev = rcu_dereference_protected(tls_ctx->netdev,
+ lockdep_is_held(&device_offload_lock));
if (netdev)
err = netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq,
rcd_sn,
trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type);
rcu_read_lock();
- netdev = READ_ONCE(tls_ctx->netdev);
+ netdev = rcu_dereference(tls_ctx->netdev);
if (netdev)
netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn,
TLS_OFFLOAD_CTX_DIR_RX);
int is_decrypted = skb->decrypted;
int is_encrypted = !is_decrypted;
struct sk_buff *skb_iter;
+ int left;
+ left = rxm->full_len - skb->len;
/* Check if all the data is decrypted already */
- skb_walk_frags(skb, skb_iter) {
+ skb_iter = skb_shinfo(skb)->frag_list;
+ while (skb_iter && left > 0) {
is_decrypted &= skb_iter->decrypted;
is_encrypted &= !skb_iter->decrypted;
+
+ left -= skb_iter->len;
+ skb_iter = skb_iter->next;
}
trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len,
if (sk->sk_destruct != tls_device_sk_destruct) {
refcount_set(&ctx->refcount, 1);
dev_hold(netdev);
- ctx->netdev = netdev;
+ RCU_INIT_POINTER(ctx->netdev, netdev);
spin_lock_irq(&tls_device_lock);
list_add_tail(&ctx->list, &tls_device_list);
spin_unlock_irq(&tls_device_lock);
struct net_device *netdev;
down_read(&device_offload_lock);
- netdev = tls_ctx->netdev;
+ netdev = rcu_dereference_protected(tls_ctx->netdev,
+ lockdep_is_held(&device_offload_lock));
if (!netdev)
goto out;
if (tls_ctx->tx_conf != TLS_HW) {
dev_put(netdev);
- tls_ctx->netdev = NULL;
+ rcu_assign_pointer(tls_ctx->netdev, NULL);
} else {
set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags);
}
spin_lock_irqsave(&tls_device_lock, flags);
list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) {
- if (ctx->netdev != netdev ||
+ struct net_device *ctx_netdev =
+ rcu_dereference_protected(ctx->netdev,
+ lockdep_is_held(&device_offload_lock));
+
+ if (ctx_netdev != netdev ||
!refcount_inc_not_zero(&ctx->refcount))
continue;
/* Stop the RX and TX resync.
* tls_dev_resync must not be called after tls_dev_del.
*/
- WRITE_ONCE(ctx->netdev, NULL);
+ rcu_assign_pointer(ctx->netdev, NULL);
/* Start skipping the RX resync logic completely. */
set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags);
struct net_device *dev,
struct sk_buff *skb)
{
- if (dev == tls_get_ctx(sk)->netdev || netif_is_bond_master(dev))
+ if (dev == rcu_dereference_bh(tls_get_ctx(sk)->netdev) ||
+ netif_is_bond_master(dev))
return skb;
return tls_sw_fallback(sk, skb);
struct sk_buff *skb;
int i, err, offset;
- skb = alloc_skb_with_frags(0, strp->anchor->len, TLS_PAGE_ORDER,
+ skb = alloc_skb_with_frags(0, strp->stm.full_len, TLS_PAGE_ORDER,
&err, strp->sk->sk_allocation);
if (!skb)
return NULL;
if (sk->sk_state == TCP_SYN_SENT &&
(sk->sk_shutdown != SHUTDOWN_MASK)) {
sk->sk_state = TCP_CLOSE;
+ sk->sk_socket->state = SS_UNCONNECTED;
sk->sk_err = ETIMEDOUT;
sk_error_report(sk);
vsock_transport_cancel_pkt(vsk);
* timeout fires.
*/
sock_hold(sk);
- schedule_delayed_work(&vsk->connect_work, timeout);
+
+ /* If the timeout function is already scheduled,
+ * reschedule it, then ungrab the socket refcount to
+ * keep it balanced.
+ */
+ if (mod_delayed_work(system_wq, &vsk->connect_work,
+ timeout))
+ sock_put(sk);
/* Skip ahead to preserve error code set above. */
goto out_wait;
#endif
if (cr->status == WLAN_STATUS_SUCCESS) {
- for_each_valid_link(cr, link) {
- if (WARN_ON_ONCE(!cr->links[link].bss))
- break;
+ if (!wiphy_to_rdev(wdev->wiphy)->ops->connect) {
+ for_each_valid_link(cr, link) {
+ if (WARN_ON_ONCE(!cr->links[link].bss))
+ break;
+ }
}
for_each_valid_link(cr, link) {
sk->sk_socket->state = SS_UNCONNECTED;
break;
}
+ rc = -ENOTCONN;
+ if (sk->sk_state == TCP_CLOSE) {
+ sk->sk_socket->state = SS_UNCONNECTED;
+ break;
+ }
rc = 0;
if (sk->sk_state != TCP_ESTABLISHED) {
release_sock(sk);
const char *errstr;
};
-long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
+long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size);
static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
unsigned int size)
{
#ifdef __KERNEL__
- return bpf_sys_bpf(cmd, attr, size);
+ return kern_sys_bpf(cmd, attr, size);
#else
return syscall(__NR_bpf, cmd, attr, size);
#endif
#include "bpf_iter_test_kern6.skel.h"
#include "bpf_iter_bpf_link.skel.h"
#include "bpf_iter_ksym.skel.h"
+#include "bpf_iter_sockmap.skel.h"
static int duration;
bpf_link__destroy(link);
}
+static void do_read_map_iter_fd(struct bpf_object_skeleton **skel, struct bpf_program *prog,
+ struct bpf_map *map)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ union bpf_iter_link_info linfo;
+ struct bpf_link *link;
+ char buf[16] = {};
+ int iter_fd, len;
+
+ memset(&linfo, 0, sizeof(linfo));
+ linfo.map.map_fd = bpf_map__fd(map);
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+ link = bpf_program__attach_iter(prog, &opts);
+ if (!ASSERT_OK_PTR(link, "attach_map_iter"))
+ return;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (!ASSERT_GE(iter_fd, 0, "create_map_iter")) {
+ bpf_link__destroy(link);
+ return;
+ }
+
+ /* Close link and map fd prematurely */
+ bpf_link__destroy(link);
+ bpf_object__destroy_skeleton(*skel);
+ *skel = NULL;
+
+ /* Try to let map free work to run first if map is freed */
+ usleep(100);
+ /* Memory used by both sock map and sock local storage map are
+ * freed after two synchronize_rcu() calls, so wait for it
+ */
+ kern_sync_rcu();
+ kern_sync_rcu();
+
+ /* Read after both map fd and link fd are closed */
+ while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+ ;
+ ASSERT_GE(len, 0, "read_iterator");
+
+ close(iter_fd);
+}
+
static int read_fd_into_buffer(int fd, char *buf, int size)
{
int bufleft = size;
goto out;
}
+ /* Sleepable program is prohibited for hash map iterator */
+ linfo.map.map_fd = map_fd;
+ link = bpf_program__attach_iter(skel->progs.sleepable_dummy_dump, &opts);
+ if (!ASSERT_ERR_PTR(link, "attach_sleepable_prog_to_iter"))
+ goto out;
+
linfo.map.map_fd = map_fd;
link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
if (!ASSERT_OK_PTR(link, "attach_iter"))
bpf_iter_bpf_array_map__destroy(skel);
}
+static void test_bpf_array_map_iter_fd(void)
+{
+ struct bpf_iter_bpf_array_map *skel;
+
+ skel = bpf_iter_bpf_array_map__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_array_map__open_and_load"))
+ return;
+
+ do_read_map_iter_fd(&skel->skeleton, skel->progs.dump_bpf_array_map,
+ skel->maps.arraymap1);
+
+ bpf_iter_bpf_array_map__destroy(skel);
+}
+
static void test_bpf_percpu_array_map(void)
{
DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
bpf_iter_bpf_sk_storage_helpers__destroy(skel);
}
+static void test_bpf_sk_stoarge_map_iter_fd(void)
+{
+ struct bpf_iter_bpf_sk_storage_map *skel;
+
+ skel = bpf_iter_bpf_sk_storage_map__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_sk_storage_map__open_and_load"))
+ return;
+
+ do_read_map_iter_fd(&skel->skeleton, skel->progs.rw_bpf_sk_storage_map,
+ skel->maps.sk_stg_map);
+
+ bpf_iter_bpf_sk_storage_map__destroy(skel);
+}
+
static void test_bpf_sk_storage_map(void)
{
DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
linfo.map.map_fd = map_fd;
opts.link_info = &linfo;
opts.link_info_len = sizeof(linfo);
- link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts);
+ link = bpf_program__attach_iter(skel->progs.oob_write_bpf_sk_storage_map, &opts);
+ err = libbpf_get_error(link);
+ if (!ASSERT_EQ(err, -EACCES, "attach_oob_write_iter")) {
+ if (!err)
+ bpf_link__destroy(link);
+ goto out;
+ }
+
+ link = bpf_program__attach_iter(skel->progs.rw_bpf_sk_storage_map, &opts);
if (!ASSERT_OK_PTR(link, "attach_iter"))
goto out;
if (!ASSERT_GE(iter_fd, 0, "create_iter"))
goto free_link;
+ skel->bss->to_add_val = time(NULL);
/* do some tests */
while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
;
if (!ASSERT_EQ(skel->bss->val_sum, expected_val, "val_sum"))
goto close_iter;
+ for (i = 0; i < num_sockets; i++) {
+ err = bpf_map_lookup_elem(map_fd, &sock_fd[i], &val);
+ if (!ASSERT_OK(err, "map_lookup") ||
+ !ASSERT_EQ(val, i + 1 + skel->bss->to_add_val, "check_map_value"))
+ break;
+ }
+
close_iter:
close(iter_fd);
free_link:
bpf_iter_task_vma__destroy(skel);
}
+void test_bpf_sockmap_map_iter_fd(void)
+{
+ struct bpf_iter_sockmap *skel;
+
+ skel = bpf_iter_sockmap__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "bpf_iter_sockmap__open_and_load"))
+ return;
+
+ do_read_map_iter_fd(&skel->skeleton, skel->progs.copy, skel->maps.sockmap);
+
+ bpf_iter_sockmap__destroy(skel);
+}
+
void test_bpf_iter(void)
{
if (test__start_subtest("btf_id_or_null"))
test_bpf_percpu_hash_map();
if (test__start_subtest("bpf_array_map"))
test_bpf_array_map();
+ if (test__start_subtest("bpf_array_map_iter_fd"))
+ test_bpf_array_map_iter_fd();
if (test__start_subtest("bpf_percpu_array_map"))
test_bpf_percpu_array_map();
if (test__start_subtest("bpf_sk_storage_map"))
test_bpf_sk_storage_map();
+ if (test__start_subtest("bpf_sk_storage_map_iter_fd"))
+ test_bpf_sk_stoarge_map_iter_fd();
if (test__start_subtest("bpf_sk_storage_delete"))
test_bpf_sk_storage_delete();
if (test__start_subtest("bpf_sk_storage_get"))
test_link_iter();
if (test__start_subtest("ksym"))
test_ksym_iter();
+ if (test__start_subtest("bpf_sockmap_map_iter_fd"))
+ test_bpf_sockmap_map_iter_fd();
}
#include <test_progs.h>
#include <network_helpers.h>
#include <bpf/btf.h>
+#include "bind4_prog.skel.h"
typedef int (*test_cb)(struct bpf_object *obj);
prog_name, false, NULL);
}
+static int find_prog_btf_id(const char *name, __u32 attach_prog_fd)
+{
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ struct btf *btf;
+ int ret;
+
+ ret = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
+ if (ret)
+ return ret;
+
+ if (!info.btf_id)
+ return -EINVAL;
+
+ btf = btf__load_from_kernel_by_id(info.btf_id);
+ ret = libbpf_get_error(btf);
+ if (ret)
+ return ret;
+
+ ret = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
+ btf__free(btf);
+ return ret;
+}
+
+static int load_fentry(int attach_prog_fd, int attach_btf_id)
+{
+ LIBBPF_OPTS(bpf_prog_load_opts, opts,
+ .expected_attach_type = BPF_TRACE_FENTRY,
+ .attach_prog_fd = attach_prog_fd,
+ .attach_btf_id = attach_btf_id,
+ );
+ struct bpf_insn insns[] = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+
+ return bpf_prog_load(BPF_PROG_TYPE_TRACING,
+ "bind4_fentry",
+ "GPL",
+ insns,
+ ARRAY_SIZE(insns),
+ &opts);
+}
+
+static void test_fentry_to_cgroup_bpf(void)
+{
+ struct bind4_prog *skel = NULL;
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ int cgroup_fd = -1;
+ int fentry_fd = -1;
+ int btf_id;
+
+ cgroup_fd = test__join_cgroup("/fentry_to_cgroup_bpf");
+ if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
+ return;
+
+ skel = bind4_prog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel"))
+ goto cleanup;
+
+ skel->links.bind_v4_prog = bpf_program__attach_cgroup(skel->progs.bind_v4_prog, cgroup_fd);
+ if (!ASSERT_OK_PTR(skel->links.bind_v4_prog, "bpf_program__attach_cgroup"))
+ goto cleanup;
+
+ btf_id = find_prog_btf_id("bind_v4_prog", bpf_program__fd(skel->progs.bind_v4_prog));
+ if (!ASSERT_GE(btf_id, 0, "find_prog_btf_id"))
+ goto cleanup;
+
+ fentry_fd = load_fentry(bpf_program__fd(skel->progs.bind_v4_prog), btf_id);
+ if (!ASSERT_GE(fentry_fd, 0, "load_fentry"))
+ goto cleanup;
+
+ /* Make sure bpf_obj_get_info_by_fd works correctly when attaching
+ * to another BPF program.
+ */
+
+ ASSERT_OK(bpf_obj_get_info_by_fd(fentry_fd, &info, &info_len),
+ "bpf_obj_get_info_by_fd");
+
+ ASSERT_EQ(info.btf_id, 0, "info.btf_id");
+ ASSERT_EQ(info.attach_btf_id, btf_id, "info.attach_btf_id");
+ ASSERT_GT(info.attach_btf_obj_id, 0, "info.attach_btf_obj_id");
+
+cleanup:
+ if (cgroup_fd >= 0)
+ close(cgroup_fd);
+ if (fentry_fd >= 0)
+ close(fentry_fd);
+ bind4_prog__destroy(skel);
+}
+
/* NOTE: affect other tests, must run in serial mode */
void serial_test_fexit_bpf2bpf(void)
{
test_fmod_ret_freplace();
if (test__start_subtest("func_replace_global_func"))
test_func_replace_global_func();
+ if (test__start_subtest("fentry_to_cgroup_bpf"))
+ test_fentry_to_cgroup_bpf();
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#include "lru_bug.skel.h"
+
+void test_lru_bug(void)
+{
+ struct lru_bug *skel;
+ int ret;
+
+ skel = lru_bug__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "lru_bug__open_and_load"))
+ return;
+ ret = lru_bug__attach(skel);
+ if (!ASSERT_OK(ret, "lru_bug__attach"))
+ goto end;
+ usleep(1);
+ ASSERT_OK(skel->data->result, "prealloc_lru_pop doesn't call check_and_init_map_value");
+end:
+ lru_bug__destroy(skel);
+}
return 0;
}
+
+SEC("iter.s/bpf_map_elem")
+int sleepable_dummy_dump(struct bpf_iter__bpf_map_elem *ctx)
+{
+ if (ctx->meta->seq_num == 0)
+ BPF_SEQ_PRINTF(ctx->meta->seq, "map dump starts\n");
+
+ return 0;
+}
__u32 val_sum = 0;
__u32 ipv6_sk_count = 0;
+__u32 to_add_val = 0;
SEC("iter/bpf_sk_storage_map")
-int dump_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+int rw_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
{
struct sock *sk = ctx->sk;
__u32 *val = ctx->value;
- if (sk == (void *)0 || val == (void *)0)
+ if (sk == NULL || val == NULL)
return 0;
if (sk->sk_family == AF_INET6)
ipv6_sk_count++;
val_sum += *val;
+
+ *val += to_add_val;
+
+ return 0;
+}
+
+SEC("iter/bpf_sk_storage_map")
+int oob_write_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+{
+ struct sock *sk = ctx->sk;
+ __u32 *val = ctx->value;
+
+ if (sk == NULL || val == NULL)
+ return 0;
+
+ *(val + 1) = 0xdeadbeef;
+
return 0;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct map_value {
+ struct task_struct __kptr *ptr;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_LRU_HASH);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_value);
+} lru_map SEC(".maps");
+
+int pid = 0;
+int result = 1;
+
+SEC("fentry/bpf_ktime_get_ns")
+int printk(void *ctx)
+{
+ struct map_value v = {};
+
+ if (pid == bpf_get_current_task_btf()->pid)
+ bpf_map_update_elem(&lru_map, &(int){0}, &v, 0);
+ return 0;
+}
+
+SEC("fentry/do_nanosleep")
+int nanosleep(void *ctx)
+{
+ struct map_value val = {}, *v;
+ struct task_struct *current;
+
+ bpf_map_update_elem(&lru_map, &(int){0}, &val, 0);
+ v = bpf_map_lookup_elem(&lru_map, &(int){0});
+ if (!v)
+ return 0;
+ bpf_map_delete_elem(&lru_map, &(int){0});
+ current = bpf_get_current_task_btf();
+ v->ptr = current;
+ pid = current->pid;
+ bpf_ktime_get_ns();
+ result = !v->ptr;
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
toeplitz
tun
cmsg_sender
-unix_connect
\ No newline at end of file
+unix_connect
+tap
\ No newline at end of file
TEST_GEN_FILES += ioam6_parser
TEST_GEN_FILES += gro
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap
TEST_GEN_FILES += toeplitz
TEST_GEN_FILES += cmsg_sender
TEST_GEN_FILES += stress_reuseport_listen
send_src_ipv4()
{
- $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_dst_ipv4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_src_udp4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B 203.0.113.2 \
-d 1msec -t udp "sp=0-32768,dp=30000"
}
send_dst_udp4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B 203.0.113.2 \
-d 1msec -t udp "sp=20000,dp=0-32768"
}
send_src_ipv6()
{
- $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_dst_ipv6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_src_udp6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B 2001:db8:4::2 \
-d 1msec -t udp "sp=0-32768,dp=30000"
}
send_dst_udp6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B 2001:db8:4::2 \
-d 1msec -t udp "sp=20000,dp=0-32768"
}
send_src_ipv4()
{
- $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_dst_ipv4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_src_udp4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B 203.0.113.2 \
-d 1msec -t udp "sp=0-32768,dp=30000"
}
send_dst_udp4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B 203.0.113.2 \
-d 1msec -t udp "sp=20000,dp=0-32768"
}
send_src_ipv6()
{
- $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_dst_ipv6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_src_udp6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B 2001:db8:2::2 \
-d 1msec -t udp "sp=0-32768,dp=30000"
}
send_dst_udp6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B 2001:db8:2::2 \
-d 1msec -t udp "sp=20000,dp=0-32768"
}
send_src_ipv4()
{
- $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_dst_ipv4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_src_udp4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B 203.0.113.2 \
-d 1msec -t udp "sp=0-32768,dp=30000"
}
send_dst_udp4()
{
- $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \
+ ip vrf exec v$h1 $MZ $h1 -q -p 64 \
+ -A 198.51.100.2 -B 203.0.113.2 \
-d 1msec -t udp "sp=20000,dp=0-32768"
}
send_src_ipv6()
{
- $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_dst_ipv6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \
-d 1msec -c 50 -t udp "sp=20000,dp=30000"
}
send_src_udp6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B 2001:db8:2::2 \
-d 1msec -t udp "sp=0-32768,dp=30000"
}
send_dst_udp6()
{
- $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
+ ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \
+ -A 2001:db8:1::2 -B 2001:db8:2::2 \
-d 1msec -t udp "sp=20000,dp=0-32768"
}
fcntl(fd, F_SETFL, flags & ~O_NONBLOCK);
}
+static void shut_wr(int fd)
+{
+ /* Close our write side, ev. give some time
+ * for address notification and/or checking
+ * the current status
+ */
+ if (cfg_wait)
+ usleep(cfg_wait);
+
+ shutdown(fd, SHUT_WR);
+}
+
static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after_out)
{
struct pollfd fds = {
/* ... and peer also closed already */
break;
- /* ... but we still receive.
- * Close our write side, ev. give some time
- * for address notification and/or checking
- * the current status
- */
- if (cfg_wait)
- usleep(cfg_wait);
- shutdown(peerfd, SHUT_WR);
+ shut_wr(peerfd);
} else {
if (errno == EINTR)
continue;
if (err)
return err;
- shutdown(peerfd, SHUT_WR);
+ shut_wr(peerfd);
err = do_recvfile(peerfd, outfd);
*in_closed_after_out = true;
err = do_sendfile(infd, peerfd, size);
if (err)
return err;
+
+ shut_wr(peerfd);
+
err = do_recvfile(peerfd, outfd);
*in_closed_after_out = true;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <net/if.h>
+#include <linux/if_tun.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <linux/virtio_net.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+#include "../kselftest_harness.h"
+
+static const char param_dev_tap_name[] = "xmacvtap0";
+static const char param_dev_dummy_name[] = "xdummy0";
+static unsigned char param_hwaddr_src[] = { 0x00, 0xfe, 0x98, 0x14, 0x22, 0x42 };
+static unsigned char param_hwaddr_dest[] = {
+ 0x00, 0xfe, 0x98, 0x94, 0xd2, 0x43
+};
+
+#define MAX_RTNL_PAYLOAD (2048)
+#define PKT_DATA 0xCB
+#define TEST_PACKET_SZ (sizeof(struct virtio_net_hdr) + ETH_HLEN + ETH_MAX_MTU)
+
+static struct rtattr *rtattr_add(struct nlmsghdr *nh, unsigned short type,
+ unsigned short len)
+{
+ struct rtattr *rta =
+ (struct rtattr *)((uint8_t *)nh + RTA_ALIGN(nh->nlmsg_len));
+ rta->rta_type = type;
+ rta->rta_len = RTA_LENGTH(len);
+ nh->nlmsg_len = RTA_ALIGN(nh->nlmsg_len) + RTA_ALIGN(rta->rta_len);
+ return rta;
+}
+
+static struct rtattr *rtattr_begin(struct nlmsghdr *nh, unsigned short type)
+{
+ return rtattr_add(nh, type, 0);
+}
+
+static void rtattr_end(struct nlmsghdr *nh, struct rtattr *attr)
+{
+ uint8_t *end = (uint8_t *)nh + nh->nlmsg_len;
+
+ attr->rta_len = end - (uint8_t *)attr;
+}
+
+static struct rtattr *rtattr_add_str(struct nlmsghdr *nh, unsigned short type,
+ const char *s)
+{
+ struct rtattr *rta = rtattr_add(nh, type, strlen(s));
+
+ memcpy(RTA_DATA(rta), s, strlen(s));
+ return rta;
+}
+
+static struct rtattr *rtattr_add_strsz(struct nlmsghdr *nh, unsigned short type,
+ const char *s)
+{
+ struct rtattr *rta = rtattr_add(nh, type, strlen(s) + 1);
+
+ strcpy(RTA_DATA(rta), s);
+ return rta;
+}
+
+static struct rtattr *rtattr_add_any(struct nlmsghdr *nh, unsigned short type,
+ const void *arr, size_t len)
+{
+ struct rtattr *rta = rtattr_add(nh, type, len);
+
+ memcpy(RTA_DATA(rta), arr, len);
+ return rta;
+}
+
+static int dev_create(const char *dev, const char *link_type,
+ int (*fill_rtattr)(struct nlmsghdr *nh),
+ int (*fill_info_data)(struct nlmsghdr *nh))
+{
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg info;
+ unsigned char data[MAX_RTNL_PAYLOAD];
+ } req;
+ struct rtattr *link_info, *info_data;
+ int ret, rtnl;
+
+ rtnl = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+ if (rtnl < 0) {
+ fprintf(stderr, "%s: socket %s\n", __func__, strerror(errno));
+ return 1;
+ }
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.info));
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE;
+ req.nh.nlmsg_type = RTM_NEWLINK;
+
+ req.info.ifi_family = AF_UNSPEC;
+ req.info.ifi_type = 1;
+ req.info.ifi_index = 0;
+ req.info.ifi_flags = IFF_BROADCAST | IFF_UP;
+ req.info.ifi_change = 0xffffffff;
+
+ rtattr_add_str(&req.nh, IFLA_IFNAME, dev);
+
+ if (fill_rtattr) {
+ ret = fill_rtattr(&req.nh);
+ if (ret)
+ return ret;
+ }
+
+ link_info = rtattr_begin(&req.nh, IFLA_LINKINFO);
+
+ rtattr_add_strsz(&req.nh, IFLA_INFO_KIND, link_type);
+
+ if (fill_info_data) {
+ info_data = rtattr_begin(&req.nh, IFLA_INFO_DATA);
+ ret = fill_info_data(&req.nh);
+ if (ret)
+ return ret;
+ rtattr_end(&req.nh, info_data);
+ }
+
+ rtattr_end(&req.nh, link_info);
+
+ ret = send(rtnl, &req, req.nh.nlmsg_len, 0);
+ if (ret < 0)
+ fprintf(stderr, "%s: send %s\n", __func__, strerror(errno));
+ ret = (unsigned int)ret != req.nh.nlmsg_len;
+
+ close(rtnl);
+ return ret;
+}
+
+static int dev_delete(const char *dev)
+{
+ struct {
+ struct nlmsghdr nh;
+ struct ifinfomsg info;
+ unsigned char data[MAX_RTNL_PAYLOAD];
+ } req;
+ int ret, rtnl;
+
+ rtnl = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+ if (rtnl < 0) {
+ fprintf(stderr, "%s: socket %s\n", __func__, strerror(errno));
+ return 1;
+ }
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.info));
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_type = RTM_DELLINK;
+
+ req.info.ifi_family = AF_UNSPEC;
+
+ rtattr_add_str(&req.nh, IFLA_IFNAME, dev);
+
+ ret = send(rtnl, &req, req.nh.nlmsg_len, 0);
+ if (ret < 0)
+ fprintf(stderr, "%s: send %s\n", __func__, strerror(errno));
+
+ ret = (unsigned int)ret != req.nh.nlmsg_len;
+
+ close(rtnl);
+ return ret;
+}
+
+static int macvtap_fill_rtattr(struct nlmsghdr *nh)
+{
+ int ifindex;
+
+ ifindex = if_nametoindex(param_dev_dummy_name);
+ if (ifindex == 0) {
+ fprintf(stderr, "%s: ifindex %s\n", __func__, strerror(errno));
+ return -errno;
+ }
+
+ rtattr_add_any(nh, IFLA_LINK, &ifindex, sizeof(ifindex));
+ rtattr_add_any(nh, IFLA_ADDRESS, param_hwaddr_src, ETH_ALEN);
+
+ return 0;
+}
+
+static int opentap(const char *devname)
+{
+ int ifindex;
+ char buf[256];
+ int fd;
+ struct ifreq ifr;
+
+ ifindex = if_nametoindex(devname);
+ if (ifindex == 0) {
+ fprintf(stderr, "%s: ifindex %s\n", __func__, strerror(errno));
+ return -errno;
+ }
+
+ sprintf(buf, "/dev/tap%d", ifindex);
+ fd = open(buf, O_RDWR | O_NONBLOCK);
+ if (fd < 0) {
+ fprintf(stderr, "%s: open %s\n", __func__, strerror(errno));
+ return -errno;
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ strcpy(ifr.ifr_name, devname);
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR | IFF_MULTI_QUEUE;
+ if (ioctl(fd, TUNSETIFF, &ifr, sizeof(ifr)) < 0)
+ return -errno;
+ return fd;
+}
+
+size_t build_eth(uint8_t *buf, uint16_t proto)
+{
+ struct ethhdr *eth = (struct ethhdr *)buf;
+
+ eth->h_proto = htons(proto);
+ memcpy(eth->h_source, param_hwaddr_src, ETH_ALEN);
+ memcpy(eth->h_dest, param_hwaddr_dest, ETH_ALEN);
+
+ return ETH_HLEN;
+}
+
+static uint32_t add_csum(const uint8_t *buf, int len)
+{
+ uint32_t sum = 0;
+ uint16_t *sbuf = (uint16_t *)buf;
+
+ while (len > 1) {
+ sum += *sbuf++;
+ len -= 2;
+ }
+
+ if (len)
+ sum += *(uint8_t *)sbuf;
+
+ return sum;
+}
+
+static uint16_t finish_ip_csum(uint32_t sum)
+{
+ uint16_t lo = sum & 0xffff;
+ uint16_t hi = sum >> 16;
+
+ return ~(lo + hi);
+
+}
+
+static uint16_t build_ip_csum(const uint8_t *buf, int len,
+ uint32_t sum)
+{
+ sum += add_csum(buf, len);
+ return finish_ip_csum(sum);
+}
+
+static int build_ipv4_header(uint8_t *buf, int payload_len)
+{
+ struct iphdr *iph = (struct iphdr *)buf;
+
+ iph->ihl = 5;
+ iph->version = 4;
+ iph->ttl = 8;
+ iph->tot_len =
+ htons(sizeof(*iph) + sizeof(struct udphdr) + payload_len);
+ iph->id = htons(1337);
+ iph->protocol = IPPROTO_UDP;
+ iph->saddr = htonl((172 << 24) | (17 << 16) | 2);
+ iph->daddr = htonl((172 << 24) | (17 << 16) | 1);
+ iph->check = build_ip_csum(buf, iph->ihl << 2, 0);
+
+ return iph->ihl << 2;
+}
+
+static int build_udp_packet(uint8_t *buf, int payload_len, bool csum_off)
+{
+ const int ip4alen = sizeof(uint32_t);
+ struct udphdr *udph = (struct udphdr *)buf;
+ int len = sizeof(*udph) + payload_len;
+ uint32_t sum = 0;
+
+ udph->source = htons(22);
+ udph->dest = htons(58822);
+ udph->len = htons(len);
+
+ memset(buf + sizeof(struct udphdr), PKT_DATA, payload_len);
+
+ sum = add_csum(buf - 2 * ip4alen, 2 * ip4alen);
+ sum += htons(IPPROTO_UDP) + udph->len;
+
+ if (!csum_off)
+ sum += add_csum(buf, len);
+
+ udph->check = finish_ip_csum(sum);
+
+ return sizeof(*udph) + payload_len;
+}
+
+size_t build_test_packet_valid_udp_gso(uint8_t *buf, size_t payload_len)
+{
+ uint8_t *cur = buf;
+ struct virtio_net_hdr *vh = (struct virtio_net_hdr *)buf;
+
+ vh->hdr_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct udphdr);
+ vh->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ vh->csum_start = ETH_HLEN + sizeof(struct iphdr);
+ vh->csum_offset = __builtin_offsetof(struct udphdr, check);
+ vh->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ vh->gso_size = ETH_DATA_LEN - sizeof(struct iphdr);
+ cur += sizeof(*vh);
+
+ cur += build_eth(cur, ETH_P_IP);
+ cur += build_ipv4_header(cur, payload_len);
+ cur += build_udp_packet(cur, payload_len, true);
+
+ return cur - buf;
+}
+
+size_t build_test_packet_valid_udp_csum(uint8_t *buf, size_t payload_len)
+{
+ uint8_t *cur = buf;
+ struct virtio_net_hdr *vh = (struct virtio_net_hdr *)buf;
+
+ vh->flags = VIRTIO_NET_HDR_F_DATA_VALID;
+ vh->gso_type = VIRTIO_NET_HDR_GSO_NONE;
+ cur += sizeof(*vh);
+
+ cur += build_eth(cur, ETH_P_IP);
+ cur += build_ipv4_header(cur, payload_len);
+ cur += build_udp_packet(cur, payload_len, false);
+
+ return cur - buf;
+}
+
+size_t build_test_packet_crash_tap_invalid_eth_proto(uint8_t *buf,
+ size_t payload_len)
+{
+ uint8_t *cur = buf;
+ struct virtio_net_hdr *vh = (struct virtio_net_hdr *)buf;
+
+ vh->hdr_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct udphdr);
+ vh->flags = 0;
+ vh->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ vh->gso_size = ETH_DATA_LEN - sizeof(struct iphdr);
+ cur += sizeof(*vh);
+
+ cur += build_eth(cur, 0);
+ cur += sizeof(struct iphdr) + sizeof(struct udphdr);
+ cur += build_ipv4_header(cur, payload_len);
+ cur += build_udp_packet(cur, payload_len, true);
+ cur += payload_len;
+
+ return cur - buf;
+}
+
+FIXTURE(tap)
+{
+ int fd;
+};
+
+FIXTURE_SETUP(tap)
+{
+ int ret;
+
+ ret = dev_create(param_dev_dummy_name, "dummy", NULL, NULL);
+ EXPECT_EQ(ret, 0);
+
+ ret = dev_create(param_dev_tap_name, "macvtap", macvtap_fill_rtattr,
+ NULL);
+ EXPECT_EQ(ret, 0);
+
+ self->fd = opentap(param_dev_tap_name);
+ ASSERT_GE(self->fd, 0);
+}
+
+FIXTURE_TEARDOWN(tap)
+{
+ int ret;
+
+ if (self->fd != -1)
+ close(self->fd);
+
+ ret = dev_delete(param_dev_tap_name);
+ EXPECT_EQ(ret, 0);
+
+ ret = dev_delete(param_dev_dummy_name);
+ EXPECT_EQ(ret, 0);
+}
+
+TEST_F(tap, test_packet_valid_udp_gso)
+{
+ uint8_t pkt[TEST_PACKET_SZ];
+ size_t off;
+ int ret;
+
+ memset(pkt, 0, sizeof(pkt));
+ off = build_test_packet_valid_udp_gso(pkt, 1021);
+ ret = write(self->fd, pkt, off);
+ ASSERT_EQ(ret, off);
+}
+
+TEST_F(tap, test_packet_valid_udp_csum)
+{
+ uint8_t pkt[TEST_PACKET_SZ];
+ size_t off;
+ int ret;
+
+ memset(pkt, 0, sizeof(pkt));
+ off = build_test_packet_valid_udp_csum(pkt, 1024);
+ ret = write(self->fd, pkt, off);
+ ASSERT_EQ(ret, off);
+}
+
+TEST_F(tap, test_packet_crash_tap_invalid_eth_proto)
+{
+ uint8_t pkt[TEST_PACKET_SZ];
+ size_t off;
+ int ret;
+
+ memset(pkt, 0, sizeof(pkt));
+ off = build_test_packet_crash_tap_invalid_eth_proto(pkt, 1024);
+ ret = write(self->fd, pkt, off);
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EINVAL);
+}
+
+TEST_HARNESS_MAIN
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
-testns=testns1
+testns=testns-$(mktemp -u "XXXXXXXX")
+
tables="foo bar baz quux"
+global_ret=0
+eret=0
+lret=0
+
+check_result()
+{
+ local r=$1
+ local OK="PASS"
+
+ if [ $r -ne 0 ] ;then
+ OK="FAIL"
+ global_ret=$r
+ fi
+
+ echo "$OK: nft $2 test returned $r"
+
+ eret=0
+}
nft --version > /dev/null 2>&1
if [ $? -ne 0 ];then
sleep 1
+ip netns exec "$testns" nft -f "$tmp"
for i in $(seq 1 10) ; do ip netns exec "$testns" nft -f "$tmp" & done
for table in $tables;do
- randsleep=$((RANDOM%10))
+ randsleep=$((RANDOM%2))
sleep $randsleep
- ip netns exec "$testns" nft delete table inet $table 2>/dev/null
+ ip netns exec "$testns" nft delete table inet $table
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ eret=$lret
+ fi
done
-randsleep=$((RANDOM%10))
-sleep $randsleep
+check_result $eret "add/delete"
+
+for i in $(seq 1 10) ; do
+ (echo "flush ruleset"; cat "$tmp") | ip netns exec "$testns" nft -f /dev/stdin
+
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ eret=$lret
+ fi
+done
+
+check_result $eret "reload"
+
+for i in $(seq 1 10) ; do
+ (echo "flush ruleset"; cat "$tmp"
+ echo "insert rule inet foo INPUT meta nftrace set 1"
+ echo "insert rule inet foo OUTPUT meta nftrace set 1"
+ ) | ip netns exec "$testns" nft -f /dev/stdin
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ eret=$lret
+ fi
+
+ (echo "flush ruleset"; cat "$tmp"
+ ) | ip netns exec "$testns" nft -f /dev/stdin
+
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ eret=$lret
+ fi
+done
+
+check_result $eret "add/delete with nftrace enabled"
+
+echo "insert rule inet foo INPUT meta nftrace set 1" >> $tmp
+echo "insert rule inet foo OUTPUT meta nftrace set 1" >> $tmp
+
+for i in $(seq 1 10) ; do
+ (echo "flush ruleset"; cat "$tmp") | ip netns exec "$testns" nft -f /dev/stdin
+
+ lret=$?
+ if [ $lret -ne 0 ]; then
+ eret=1
+ fi
+done
+
+check_result $lret "add/delete with nftrace enabled"
pkill -9 ping
rm -f "$tmp"
ip netns del "$testns"
+
+exit $global_ret