Merge tag 'net-5.15-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from WiFi (mac80211), and BPF.
Current release - regressions:
- skb_expand_head: adjust skb->truesize to fix socket memory
accounting
- mptcp: fix corrupt receiver key in MPC + data + checksum
Previous releases - regressions:
- multicast: calculate csum of looped-back and forwarded packets
- cgroup: fix memory leak caused by missing cgroup_bpf_offline
- cfg80211: fix management registrations locking, prevent list
corruption
- cfg80211: correct false positive in bridge/4addr mode check
- tcp_bpf: fix race in the tcp_bpf_send_verdict resulting in reusing
previous verdict
Previous releases - always broken:
- sctp: enhancements for the verification tag, prevent attackers from
killing SCTP sessions
- tipc: fix size validations for the MSG_CRYPTO type
- mac80211: mesh: fix HE operation element length check, prevent out
of bound access
- tls: fix sign of socket errors, prevent positive error codes being
reported from read()/write()
- cfg80211: scan: extend RCU protection in
cfg80211_add_nontrans_list()
- implement ->sock_is_readable() for UDP and AF_UNIX, fix poll() for
sockets in a BPF sockmap
- bpf: fix potential race in tail call compatibility check resulting
in two operations which would make the map incompatible succeeding
- bpf: prevent increasing bpf_jit_limit above max
- bpf: fix error usage of map_fd and fdget() in generic batch update
- phy: ethtool: lock the phy for consistency of results
- prevent infinite while loop in skb_tx_hash() when Tx races with
driver reconfiguring the queue <> traffic class mapping
- usbnet: fixes for bad HW conjured by syzbot
- xen: stop tx queues during live migration, prevent UAF
- net-sysfs: initialize uid and gid before calling
net_ns_get_ownership
- mlxsw: prevent Rx stalls under memory pressure"
* tag 'net-5.15-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits)
Revert "net: hns3: fix pause config problem after autoneg disabled"
mptcp: fix corrupt receiver key in MPC + data + checksum
riscv, bpf: Fix potential NULL dereference
octeontx2-af: Fix possible null pointer dereference.
octeontx2-af: Display all enabled PF VF rsrc_alloc entries.
octeontx2-af: Check whether ipolicers exists
net: ethernet: microchip: lan743x: Fix skb allocation failure
net/tls: Fix flipped sign in async_wait.err assignment
net/tls: Fix flipped sign in tls_err_abort() calls
net/smc: Correct spelling mistake to TCPF_SYN_RECV
net/smc: Fix smc_link->llc_testlink_time overflow
nfp: bpf: relax prog rejection for mtu check through max_pkt_offset
vmxnet3: do not stop tx queues after netif_device_detach()
r8169: Add device 10ec:8162 to driver r8169
ptp: Document the PTP_CLK_MAGIC ioctl number
usbnet: fix error return code in usbnet_probe()
net: hns3: adjust string spaces of some parameters of tx bd info in debugfs
net: hns3: expand buffer len for some debugfs command
net: hns3: add more string spaces for dumping packets number of queue info in debugfs
net: hns3: fix data endian problem of some functions of debugfs
...
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2e81340..6655d92 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -104,6 +104,7 @@
'8' all SNP8023 advanced NIC card
<mailto:mcr@solidum.com>
';' 64-7F linux/vfio.h
+'=' 00-3f uapi/linux/ptp_clock.h <mailto:richardcochran@gmail.com>
'@' 00-0F linux/radeonfb.h conflict!
'@' 00-0F drivers/video/aty/aty128fb.c conflict!
'A' 00-1F linux/apm_bios.h conflict!
diff --git a/MAINTAINERS b/MAINTAINERS
index 80eebc1..c344865 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11291,7 +11291,6 @@
F: drivers/net/ethernet/marvell/octeontx2/af/
MARVELL PRESTERA ETHERNET SWITCH DRIVER
-M: Vadym Kochan <vkochan@marvell.com>
M: Taras Chornyi <tchornyi@marvell.com>
S: Supported
W: https://github.com/Marvell-switching/switchdev-prestera
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 41c23f4..803e777 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1136,6 +1136,11 @@
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index fed86f4..753d85b 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -125,7 +125,8 @@
if (i == NR_JIT_ITERATIONS) {
pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
- bpf_jit_binary_free(jit_data->header);
+ if (jit_data->header)
+ bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
@@ -166,6 +167,11 @@
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 2b66c59..e54f962 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -137,7 +137,7 @@
.name = "uc",
.cmd = HNAE3_DBG_CMD_MAC_UC,
.dentry = HNS3_DBG_DENTRY_MAC,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_128KB,
.init = hns3_dbg_common_file_init,
},
{
@@ -256,7 +256,7 @@
.name = "tqp",
.cmd = HNAE3_DBG_CMD_REG_TQP,
.dentry = HNS3_DBG_DENTRY_REG,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_128KB,
.init = hns3_dbg_common_file_init,
},
{
@@ -298,7 +298,7 @@
.name = "fd_tcam",
.cmd = HNAE3_DBG_CMD_FD_TCAM,
.dentry = HNS3_DBG_DENTRY_FD,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_1MB,
.init = hns3_dbg_common_file_init,
},
{
@@ -462,7 +462,7 @@
{ "TAIL", 2 },
{ "HEAD", 2 },
{ "FBDNUM", 2 },
- { "PKTNUM", 2 },
+ { "PKTNUM", 5 },
{ "COPYBREAK", 2 },
{ "RING_EN", 2 },
{ "RX_RING_EN", 2 },
@@ -565,7 +565,7 @@
{ "HEAD", 2 },
{ "FBDNUM", 2 },
{ "OFFSET", 2 },
- { "PKTNUM", 2 },
+ { "PKTNUM", 5 },
{ "RING_EN", 2 },
{ "TX_RING_EN", 2 },
{ "BASE_ADDR", 10 },
@@ -790,13 +790,13 @@
}
static const struct hns3_dbg_item tx_bd_info_items[] = {
- { "BD_IDX", 5 },
- { "ADDRESS", 2 },
+ { "BD_IDX", 2 },
+ { "ADDRESS", 13 },
{ "VLAN_TAG", 2 },
{ "SIZE", 2 },
{ "T_CS_VLAN_TSO", 2 },
{ "OT_VLAN_TAG", 3 },
- { "TV", 2 },
+ { "TV", 5 },
{ "OLT_VLAN_LEN", 2 },
{ "PAYLEN_OL4CS", 2 },
{ "BD_FE_SC_VLD", 2 },
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 32f62cd..9cda8b3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -391,7 +391,7 @@
static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u16 qset_id, qset_num;
int ret;
@@ -408,12 +408,12 @@
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%04u %#x %#x %#x %#x\n",
- qset_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2, bitmap->bit3);
+ qset_id, req.bit0, req.bit1, req.bit2,
+ req.bit3);
}
return 0;
@@ -422,7 +422,7 @@
static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 pri_id, pri_num;
int ret;
@@ -439,12 +439,11 @@
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%03u %#x %#x %#x\n",
- pri_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2);
+ pri_id, req.bit0, req.bit1, req.bit2);
}
return 0;
@@ -453,7 +452,7 @@
static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 pg_id;
int ret;
@@ -466,12 +465,11 @@
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%03u %#x %#x %#x\n",
- pg_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2);
+ pg_id, req.bit0, req.bit1, req.bit2);
}
return 0;
@@ -511,7 +509,7 @@
static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 port_id = 0;
int ret;
@@ -521,12 +519,12 @@
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n",
- bitmap->bit0);
+ req.bit0);
*pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n",
- bitmap->bit1);
+ req.bit1);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index dcd40cc..d891390 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2847,33 +2847,29 @@
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
static void hclge_reset_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
+ test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
static void hclge_errhand_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_bit(HCLGE_STATE_RST_FAIL, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task,
- delay_time);
+ mod_delayed_work(hclge_wq, &hdev->service_task, delay_time);
}
static int hclge_get_mac_link_status(struct hclge_dev *hdev, int *link_status)
@@ -3491,33 +3487,14 @@
hdev->num_msi_used += 1;
}
-static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify,
- const cpumask_t *mask)
-{
- struct hclge_dev *hdev = container_of(notify, struct hclge_dev,
- affinity_notify);
-
- cpumask_copy(&hdev->affinity_mask, mask);
-}
-
-static void hclge_irq_affinity_release(struct kref *ref)
-{
-}
-
static void hclge_misc_affinity_setup(struct hclge_dev *hdev)
{
irq_set_affinity_hint(hdev->misc_vector.vector_irq,
&hdev->affinity_mask);
-
- hdev->affinity_notify.notify = hclge_irq_affinity_notify;
- hdev->affinity_notify.release = hclge_irq_affinity_release;
- irq_set_affinity_notifier(hdev->misc_vector.vector_irq,
- &hdev->affinity_notify);
}
static void hclge_misc_affinity_teardown(struct hclge_dev *hdev)
{
- irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL);
irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL);
}
@@ -13052,7 +13029,7 @@
{
pr_info("%s is initializing\n", HCLGE_NAME);
- hclge_wq = alloc_workqueue("%s", 0, 0, HCLGE_NAME);
+ hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME);
if (!hclge_wq) {
pr_err("%s: failed to create workqueue\n", HCLGE_NAME);
return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index de6afbc..69cd8f8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -944,7 +944,6 @@
/* affinity mask and notify for misc interrupt */
cpumask_t affinity_mask;
- struct irq_affinity_notify affinity_notify;
struct hclge_ptp *ptp;
struct devlink *devlink;
};
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index bef6b98..cf00ad7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2232,6 +2232,7 @@
void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev)
{
if (!test_bit(HCLGEVF_STATE_REMOVING, &hdev->state) &&
+ test_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state) &&
!test_and_set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED,
&hdev->state))
mod_delayed_work(hclgevf_wq, &hdev->service_task, 0);
@@ -3449,6 +3450,8 @@
hclgevf_init_rxd_adv_layout(hdev);
+ set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state);
+
hdev->last_reset_time = jiffies;
dev_info(&hdev->pdev->dev, "finished initializing %s driver\n",
HCLGEVF_DRIVER_NAME);
@@ -3899,7 +3902,7 @@
{
pr_info("%s is initializing\n", HCLGEVF_NAME);
- hclgevf_wq = alloc_workqueue("%s", 0, 0, HCLGEVF_NAME);
+ hclgevf_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGEVF_NAME);
if (!hclgevf_wq) {
pr_err("%s: failed to create workqueue\n", HCLGEVF_NAME);
return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 883130a..28288d7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -146,6 +146,7 @@
HCLGEVF_STATE_REMOVING,
HCLGEVF_STATE_NIC_REGISTERED,
HCLGEVF_STATE_ROCE_REGISTERED,
+ HCLGEVF_STATE_SERVICE_INITED,
/* task states */
HCLGEVF_STATE_RST_SERVICE_SCHED,
HCLGEVF_STATE_RST_HANDLING,
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 37c18c6..e375ac8 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -100,9 +100,9 @@
*/
static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
{
- struct net_device *event_netdev, *netdev_tmp;
struct netdev_notifier_bonding_info *info;
struct netdev_bonding_info *bonding_info;
+ struct net_device *event_netdev;
const char *lag_netdev_name;
event_netdev = netdev_notifier_info_to_dev(ptr);
@@ -123,19 +123,6 @@
goto lag_out;
}
- rcu_read_lock();
- for_each_netdev_in_bond_rcu(lag->upper_netdev, netdev_tmp) {
- if (!netif_is_ice(netdev_tmp))
- continue;
-
- if (netdev_tmp && netdev_tmp != lag->netdev &&
- lag->peer_netdev != netdev_tmp) {
- dev_hold(netdev_tmp);
- lag->peer_netdev = netdev_tmp;
- }
- }
- rcu_read_unlock();
-
if (bonding_info->slave.state)
ice_lag_set_backup(lag);
else
@@ -319,6 +306,9 @@
case NETDEV_BONDING_INFO:
ice_lag_info_event(lag, ptr);
break;
+ case NETDEV_UNREGISTER:
+ ice_lag_unlink(lag, ptr);
+ break;
default:
break;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 80380ae..d1ef3d4 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1571,6 +1571,9 @@
*/
void ice_ptp_release(struct ice_pf *pf)
{
+ if (!test_bit(ICE_FLAG_PTP, pf->flags))
+ return;
+
/* Disable timestamping for both Tx and Rx */
ice_ptp_cfg_timestamp(pf, false);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 9338765..49d822a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -226,18 +226,85 @@
static void print_nix_qsize(struct seq_file *filp, struct rvu_pfvf *pfvf);
+static void get_lf_str_list(struct rvu_block block, int pcifunc,
+ char *lfs)
+{
+ int lf = 0, seq = 0, len = 0, prev_lf = block.lf.max;
+
+ for_each_set_bit(lf, block.lf.bmap, block.lf.max) {
+ if (lf >= block.lf.max)
+ break;
+
+ if (block.fn_map[lf] != pcifunc)
+ continue;
+
+ if (lf == prev_lf + 1) {
+ prev_lf = lf;
+ seq = 1;
+ continue;
+ }
+
+ if (seq)
+ len += sprintf(lfs + len, "-%d,%d", prev_lf, lf);
+ else
+ len += (len ? sprintf(lfs + len, ",%d", lf) :
+ sprintf(lfs + len, "%d", lf));
+
+ prev_lf = lf;
+ seq = 0;
+ }
+
+ if (seq)
+ len += sprintf(lfs + len, "-%d", prev_lf);
+
+ lfs[len] = '\0';
+}
+
+static int get_max_column_width(struct rvu *rvu)
+{
+ int index, pf, vf, lf_str_size = 12, buf_size = 256;
+ struct rvu_block block;
+ u16 pcifunc;
+ char *buf;
+
+ buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+ for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
+ pcifunc = pf << 10 | vf;
+ if (!pcifunc)
+ continue;
+
+ for (index = 0; index < BLK_COUNT; index++) {
+ block = rvu->hw->block[index];
+ if (!strlen(block.name))
+ continue;
+
+ get_lf_str_list(block, pcifunc, buf);
+ if (lf_str_size <= strlen(buf))
+ lf_str_size = strlen(buf) + 1;
+ }
+ }
+ }
+
+ kfree(buf);
+ return lf_str_size;
+}
+
/* Dumps current provisioning status of all RVU block LFs */
static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
char __user *buffer,
size_t count, loff_t *ppos)
{
- int index, off = 0, flag = 0, go_back = 0, len = 0;
+ int index, off = 0, flag = 0, len = 0, i = 0;
struct rvu *rvu = filp->private_data;
- int lf, pf, vf, pcifunc;
+ int bytes_not_copied = 0;
struct rvu_block block;
- int bytes_not_copied;
- int lf_str_size = 12;
+ int pf, vf, pcifunc;
int buf_size = 2048;
+ int lf_str_size;
char *lfs;
char *buf;
@@ -249,6 +316,9 @@
if (!buf)
return -ENOSPC;
+ /* Get the maximum width of a column */
+ lf_str_size = get_max_column_width(rvu);
+
lfs = kzalloc(lf_str_size, GFP_KERNEL);
if (!lfs) {
kfree(buf);
@@ -262,65 +332,69 @@
"%-*s", lf_str_size,
rvu->hw->block[index].name);
}
+
off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
+ bytes_not_copied = copy_to_user(buffer + (i * off), buf, off);
+ if (bytes_not_copied)
+ goto out;
+
+ i++;
+ *ppos += off;
for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
+ off = 0;
+ flag = 0;
pcifunc = pf << 10 | vf;
if (!pcifunc)
continue;
if (vf) {
sprintf(lfs, "PF%d:VF%d", pf, vf - 1);
- go_back = scnprintf(&buf[off],
- buf_size - 1 - off,
- "%-*s", lf_str_size, lfs);
+ off = scnprintf(&buf[off],
+ buf_size - 1 - off,
+ "%-*s", lf_str_size, lfs);
} else {
sprintf(lfs, "PF%d", pf);
- go_back = scnprintf(&buf[off],
- buf_size - 1 - off,
- "%-*s", lf_str_size, lfs);
+ off = scnprintf(&buf[off],
+ buf_size - 1 - off,
+ "%-*s", lf_str_size, lfs);
}
- off += go_back;
- for (index = 0; index < BLKTYPE_MAX; index++) {
+ for (index = 0; index < BLK_COUNT; index++) {
block = rvu->hw->block[index];
if (!strlen(block.name))
continue;
len = 0;
lfs[len] = '\0';
- for (lf = 0; lf < block.lf.max; lf++) {
- if (block.fn_map[lf] != pcifunc)
- continue;
+ get_lf_str_list(block, pcifunc, lfs);
+ if (strlen(lfs))
flag = 1;
- len += sprintf(&lfs[len], "%d,", lf);
- }
- if (flag)
- len--;
- lfs[len] = '\0';
off += scnprintf(&buf[off], buf_size - 1 - off,
"%-*s", lf_str_size, lfs);
- if (!strlen(lfs))
- go_back += lf_str_size;
}
- if (!flag)
- off -= go_back;
- else
- flag = 0;
- off--;
- off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
+ if (flag) {
+ off += scnprintf(&buf[off],
+ buf_size - 1 - off, "\n");
+ bytes_not_copied = copy_to_user(buffer +
+ (i * off),
+ buf, off);
+ if (bytes_not_copied)
+ goto out;
+
+ i++;
+ *ppos += off;
+ }
}
}
- bytes_not_copied = copy_to_user(buffer, buf, off);
+out:
kfree(lfs);
kfree(buf);
-
if (bytes_not_copied)
return -EFAULT;
- *ppos = off;
- return off;
+ return *ppos;
}
RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL);
@@ -504,7 +578,7 @@
if (cmd_buf)
ret = -EINVAL;
- if (!strncmp(subtoken, "help", 4) || ret < 0) {
+ if (ret < 0 || !strncmp(subtoken, "help", 4)) {
dev_info(rvu->dev, "Use echo <%s-lf > qsize\n", blk_string);
goto qsize_write_done;
}
@@ -1719,6 +1793,10 @@
u16 pcifunc;
char *str;
+ /* Ingress policers do not exist on all platforms */
+ if (!nix_hw->ipolicer)
+ return 0;
+
for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
if (layer == BAND_PROF_INVAL_LAYER)
continue;
@@ -1768,6 +1846,10 @@
int layer;
char *str;
+ /* Ingress policers do not exist on all platforms */
+ if (!nix_hw->ipolicer)
+ return 0;
+
seq_puts(m, "\nBandwidth profile resource free count\n");
seq_puts(m, "=====================================\n");
for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 9ef4e94..6970540 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2507,6 +2507,9 @@
return;
nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ if (!nix_hw)
+ return;
+
vlan = &nix_hw->txvlan;
mutex_lock(&vlan->rsrc_lock);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 13b0259..fcace73 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -353,13 +353,10 @@
struct sk_buff *skb;
int err;
- elem_info->u.rdq.skb = NULL;
skb = netdev_alloc_skb_ip_align(NULL, buf_len);
if (!skb)
return -ENOMEM;
- /* Assume that wqe was previously zeroed. */
-
err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data,
buf_len, DMA_FROM_DEVICE);
if (err)
@@ -597,21 +594,26 @@
struct pci_dev *pdev = mlxsw_pci->pdev;
struct mlxsw_pci_queue_elem_info *elem_info;
struct mlxsw_rx_info rx_info = {};
- char *wqe;
+ char wqe[MLXSW_PCI_WQE_SIZE];
struct sk_buff *skb;
u16 byte_count;
int err;
elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
- skb = elem_info->u.sdq.skb;
- if (!skb)
- return;
- wqe = elem_info->elem;
- mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+ skb = elem_info->u.rdq.skb;
+ memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE);
if (q->consumer_counter++ != consumer_counter_limit)
dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
+ err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
+ if (err) {
+ dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+ goto out;
+ }
+
+ mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+
if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
rx_info.is_lag = true;
rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe);
@@ -647,10 +649,7 @@
skb_put(skb, byte_count);
mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
- memset(wqe, 0, q->elem_size);
- err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
- if (err)
- dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+out:
/* Everything is set up, ring doorbell to pass elem to HW */
q->producer_counter++;
mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 9e8561c..4d5a5d6 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1743,6 +1743,16 @@
ret = -EINVAL;
goto cleanup;
}
+ if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev,
+ DMA_BIT_MASK(64))) {
+ if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev,
+ DMA_BIT_MASK(32))) {
+ dev_warn(&tx->adapter->pdev->dev,
+ "lan743x_: No suitable DMA available\n");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ }
ring_allocation_size = ALIGN(tx->ring_size *
sizeof(struct lan743x_tx_descriptor),
PAGE_SIZE);
@@ -1934,7 +1944,8 @@
index);
}
-static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index)
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+ gfp_t gfp)
{
struct net_device *netdev = rx->adapter->netdev;
struct device *dev = &rx->adapter->pdev->dev;
@@ -1948,7 +1959,7 @@
descriptor = &rx->ring_cpu_ptr[index];
buffer_info = &rx->buffer_info[index];
- skb = __netdev_alloc_skb(netdev, buffer_length, GFP_ATOMIC | GFP_DMA);
+ skb = __netdev_alloc_skb(netdev, buffer_length, gfp);
if (!skb)
return -ENOMEM;
dma_ptr = dma_map_single(dev, skb->data, buffer_length, DMA_FROM_DEVICE);
@@ -2110,7 +2121,8 @@
/* save existing skb, allocate new skb and map to dma */
skb = buffer_info->skb;
- if (lan743x_rx_init_ring_element(rx, rx->last_head)) {
+ if (lan743x_rx_init_ring_element(rx, rx->last_head,
+ GFP_ATOMIC | GFP_DMA)) {
/* failed to allocate next skb.
* Memory is very low.
* Drop this packet and reuse buffer.
@@ -2276,6 +2288,16 @@
ret = -EINVAL;
goto cleanup;
}
+ if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev,
+ DMA_BIT_MASK(64))) {
+ if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev,
+ DMA_BIT_MASK(32))) {
+ dev_warn(&rx->adapter->pdev->dev,
+ "lan743x_: No suitable DMA available\n");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ }
ring_allocation_size = ALIGN(rx->ring_size *
sizeof(struct lan743x_rx_descriptor),
PAGE_SIZE);
@@ -2315,13 +2337,16 @@
rx->last_head = 0;
for (index = 0; index < rx->ring_size; index++) {
- ret = lan743x_rx_init_ring_element(rx, index);
+ ret = lan743x_rx_init_ring_element(rx, index, GFP_KERNEL);
if (ret)
goto cleanup;
}
return 0;
cleanup:
+ netif_warn(rx->adapter, ifup, rx->adapter->netdev,
+ "Error allocating memory for LAN743x\n");
+
lan743x_rx_ring_cleanup(rx);
return ret;
}
@@ -3019,6 +3044,8 @@
if (ret) {
netif_err(adapter, probe, adapter->netdev,
"lan743x_hardware_init returned %d\n", ret);
+ lan743x_pci_cleanup(adapter);
+ return ret;
}
/* open netdev when netdev is at running state while resume.
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 11c83a9..f469950 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -182,15 +182,21 @@
nfp_bpf_check_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu)
{
struct nfp_net *nn = netdev_priv(netdev);
- unsigned int max_mtu;
+ struct nfp_bpf_vnic *bv;
+ struct bpf_prog *prog;
if (~nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
return 0;
- max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- if (new_mtu > max_mtu) {
- nn_info(nn, "BPF offload active, MTU over %u not supported\n",
- max_mtu);
+ if (nn->xdp_hw.prog) {
+ prog = nn->xdp_hw.prog;
+ } else {
+ bv = nn->app_priv;
+ prog = bv->tc_prog;
+ }
+
+ if (nfp_bpf_offload_check_mtu(nn, prog, new_mtu)) {
+ nn_info(nn, "BPF offload active, potential packet access beyond hardware packet boundary");
return -EBUSY;
}
return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index d0e17ee..16841bb7 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -560,6 +560,8 @@
void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog);
int nfp_bpf_jit(struct nfp_prog *prog);
bool nfp_bpf_supported_opcode(u8 code);
+bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog,
+ unsigned int mtu);
int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
int prev_insn_idx);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 5385185..9d97cd2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -481,19 +481,28 @@
return 0;
}
+bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog,
+ unsigned int mtu)
+{
+ unsigned int fw_mtu, pkt_off;
+
+ fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
+ pkt_off = min(prog->aux->max_pkt_offset, mtu);
+
+ return fw_mtu < pkt_off;
+}
+
static int
nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
- unsigned int fw_mtu, pkt_off, max_stack, max_prog_len;
+ unsigned int max_stack, max_prog_len;
dma_addr_t dma_addr;
void *img;
int err;
- fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu);
- if (fw_mtu < pkt_off) {
+ if (nfp_bpf_offload_check_mtu(nn, prog, nn->dp.netdev->mtu)) {
NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary");
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index d29fe56..c910fa2 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1015,9 +1015,6 @@
napi_disable(&pldat->napi);
netif_stop_queue(ndev);
- if (ndev->phydev)
- phy_stop(ndev->phydev);
-
spin_lock_irqsave(&pldat->lock, flags);
__lpc_eth_reset(pldat);
netif_carrier_off(ndev);
@@ -1025,6 +1022,8 @@
writel(0, LPC_ENET_MAC2(pldat->net_base));
spin_unlock_irqrestore(&pldat->lock, flags);
+ if (ndev->phydev)
+ phy_stop(ndev->phydev);
clk_disable_unprepare(pldat->clk);
return 0;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 46a6ff9..2918947 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -157,6 +157,7 @@
{ PCI_VDEVICE(REALTEK, 0x8129) },
{ PCI_VDEVICE(REALTEK, 0x8136), RTL_CFG_NO_GBIT },
{ PCI_VDEVICE(REALTEK, 0x8161) },
+ { PCI_VDEVICE(REALTEK, 0x8162) },
{ PCI_VDEVICE(REALTEK, 0x8167) },
{ PCI_VDEVICE(REALTEK, 0x8168) },
{ PCI_VDEVICE(NCUBE, 0x8168) },
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index f124a8a..a3bfb15 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -243,62 +243,10 @@
}
}
-int phy_ethtool_ksettings_set(struct phy_device *phydev,
- const struct ethtool_link_ksettings *cmd)
-{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
- u8 autoneg = cmd->base.autoneg;
- u8 duplex = cmd->base.duplex;
- u32 speed = cmd->base.speed;
-
- if (cmd->base.phy_address != phydev->mdio.addr)
- return -EINVAL;
-
- linkmode_copy(advertising, cmd->link_modes.advertising);
-
- /* We make sure that we don't pass unsupported values in to the PHY */
- linkmode_and(advertising, advertising, phydev->supported);
-
- /* Verify the settings we care about. */
- if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
- return -EINVAL;
-
- if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
- return -EINVAL;
-
- if (autoneg == AUTONEG_DISABLE &&
- ((speed != SPEED_1000 &&
- speed != SPEED_100 &&
- speed != SPEED_10) ||
- (duplex != DUPLEX_HALF &&
- duplex != DUPLEX_FULL)))
- return -EINVAL;
-
- phydev->autoneg = autoneg;
-
- if (autoneg == AUTONEG_DISABLE) {
- phydev->speed = speed;
- phydev->duplex = duplex;
- }
-
- linkmode_copy(phydev->advertising, advertising);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
- phydev->advertising, autoneg == AUTONEG_ENABLE);
-
- phydev->master_slave_set = cmd->base.master_slave_cfg;
- phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
-
- /* Restart the PHY */
- phy_start_aneg(phydev);
-
- return 0;
-}
-EXPORT_SYMBOL(phy_ethtool_ksettings_set);
-
void phy_ethtool_ksettings_get(struct phy_device *phydev,
struct ethtool_link_ksettings *cmd)
{
+ mutex_lock(&phydev->lock);
linkmode_copy(cmd->link_modes.supported, phydev->supported);
linkmode_copy(cmd->link_modes.advertising, phydev->advertising);
linkmode_copy(cmd->link_modes.lp_advertising, phydev->lp_advertising);
@@ -317,6 +265,7 @@
cmd->base.autoneg = phydev->autoneg;
cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl;
cmd->base.eth_tp_mdix = phydev->mdix;
+ mutex_unlock(&phydev->lock);
}
EXPORT_SYMBOL(phy_ethtool_ksettings_get);
@@ -751,6 +700,37 @@
}
/**
+ * _phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ * them), and then calls the driver's config_aneg function.
+ * If the PHYCONTROL Layer is operating, we change the state to
+ * reflect the beginning of Auto-negotiation or forcing.
+ */
+static int _phy_start_aneg(struct phy_device *phydev)
+{
+ int err;
+
+ lockdep_assert_held(&phydev->lock);
+
+ if (!phydev->drv)
+ return -EIO;
+
+ if (AUTONEG_DISABLE == phydev->autoneg)
+ phy_sanitize_settings(phydev);
+
+ err = phy_config_aneg(phydev);
+ if (err < 0)
+ return err;
+
+ if (phy_is_started(phydev))
+ err = phy_check_link_status(phydev);
+
+ return err;
+}
+
+/**
* phy_start_aneg - start auto-negotiation for this PHY device
* @phydev: the phy_device struct
*
@@ -763,21 +743,8 @@
{
int err;
- if (!phydev->drv)
- return -EIO;
-
mutex_lock(&phydev->lock);
-
- if (AUTONEG_DISABLE == phydev->autoneg)
- phy_sanitize_settings(phydev);
-
- err = phy_config_aneg(phydev);
- if (err < 0)
- goto out_unlock;
-
- if (phy_is_started(phydev))
- err = phy_check_link_status(phydev);
-out_unlock:
+ err = _phy_start_aneg(phydev);
mutex_unlock(&phydev->lock);
return err;
@@ -800,6 +767,61 @@
return ret < 0 ? ret : 0;
}
+int phy_ethtool_ksettings_set(struct phy_device *phydev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+ u8 autoneg = cmd->base.autoneg;
+ u8 duplex = cmd->base.duplex;
+ u32 speed = cmd->base.speed;
+
+ if (cmd->base.phy_address != phydev->mdio.addr)
+ return -EINVAL;
+
+ linkmode_copy(advertising, cmd->link_modes.advertising);
+
+ /* We make sure that we don't pass unsupported values in to the PHY */
+ linkmode_and(advertising, advertising, phydev->supported);
+
+ /* Verify the settings we care about. */
+ if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
+ return -EINVAL;
+
+ if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
+ return -EINVAL;
+
+ if (autoneg == AUTONEG_DISABLE &&
+ ((speed != SPEED_1000 &&
+ speed != SPEED_100 &&
+ speed != SPEED_10) ||
+ (duplex != DUPLEX_HALF &&
+ duplex != DUPLEX_FULL)))
+ return -EINVAL;
+
+ mutex_lock(&phydev->lock);
+ phydev->autoneg = autoneg;
+
+ if (autoneg == AUTONEG_DISABLE) {
+ phydev->speed = speed;
+ phydev->duplex = duplex;
+ }
+
+ linkmode_copy(phydev->advertising, advertising);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+ phydev->advertising, autoneg == AUTONEG_ENABLE);
+
+ phydev->master_slave_set = cmd->base.master_slave_cfg;
+ phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
+
+ /* Restart the PHY */
+ _phy_start_aneg(phydev);
+
+ mutex_unlock(&phydev->lock);
+ return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_ksettings_set);
+
/**
* phy_speed_down - set speed to lowest speed supported by both link partners
* @phydev: the phy_device struct
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 793f8fb..63cd72c 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4122,6 +4122,12 @@
dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out, 1);
+ /* Reject broken descriptors. */
+ if (dev->maxpacket == 0) {
+ ret = -ENODEV;
+ goto out4;
+ }
+
/* driver requires remote-wakeup capability during autosuspend. */
intf->needs_remote_wakeup = 1;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 80432ee..a33d7fb8 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1790,6 +1790,7 @@
dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1);
if (dev->maxpacket == 0) {
/* that is a broken device */
+ status = -ENODEV;
goto out4;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 142f706..8799854 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3833,7 +3833,6 @@
vmxnet3_free_intr_resources(adapter);
netif_device_detach(netdev);
- netif_tx_stop_all_queues(netdev);
/* Create wake-up filters. */
pmConf = adapter->pm_conf;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e31b984..fc41ba9 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1730,6 +1730,10 @@
dev_dbg(&dev->dev, "%s\n", dev->nodename);
+ netif_tx_lock_bh(info->netdev);
+ netif_device_detach(info->netdev);
+ netif_tx_unlock_bh(info->netdev);
+
xennet_disconnect_backend(info);
return 0;
}
@@ -2349,6 +2353,10 @@
* domain a kick because we've probably just requeued some
* packets.
*/
+ netif_tx_lock_bh(np->netdev);
+ netif_device_attach(np->netdev);
+ netif_tx_unlock_bh(np->netdev);
+
netif_carrier_on(np->netdev);
for (j = 0; j < num_queues; ++j) {
queue = &np->queues[j];
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index 517376c..16ceb76 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -1006,11 +1006,11 @@
skb = port100_alloc_skb(dev, 0);
if (!skb)
- return -ENOMEM;
+ return 0;
resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_COMMAND_TYPE, skb);
if (IS_ERR(resp))
- return PTR_ERR(resp);
+ return 0;
if (resp->len < 8)
mask = 0;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 020a7d5..3db6f6c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -929,8 +929,11 @@
* stored in the map to make sure that all callers and callees have
* the same prog type and JITed flag.
*/
- enum bpf_prog_type type;
- bool jited;
+ struct {
+ spinlock_t lock;
+ enum bpf_prog_type type;
+ bool jited;
+ } owner;
/* Programs with direct jumps into programs part of this array. */
struct list_head poke_progs;
struct bpf_map *map;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9c81724..bbe1eef 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -101,14 +101,14 @@
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
-#ifdef CONFIG_NET
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
#ifdef CONFIG_BPF_LSM
BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
+#ifdef CONFIG_NET
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4a93c12..ef03ff3 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1051,6 +1051,7 @@
extern int bpf_jit_harden;
extern int bpf_jit_kallsyms;
extern long bpf_jit_limit;
+extern long bpf_jit_limit_max;
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 14ab0c0..1ce9a9e 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -128,6 +128,7 @@
struct sk_msg *msg, u32 bytes);
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags);
+bool sk_msg_is_readable(struct sock *sk);
static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
{
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 62dd842..27336fc 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5376,7 +5376,6 @@
* netdev and may otherwise be used by driver read-only, will be update
* by cfg80211 on change_interface
* @mgmt_registrations: list of registrations for management frames
- * @mgmt_registrations_lock: lock for the list
* @mgmt_registrations_need_update: mgmt registrations were updated,
* need to propagate the update to the driver
* @mtx: mutex used to lock data in this struct, may be used by drivers
@@ -5423,7 +5422,6 @@
u32 identifier;
struct list_head mgmt_registrations;
- spinlock_t mgmt_registrations_lock;
u8 mgmt_registrations_need_update:1;
struct mutex mtx;
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 6026bbe..3214848 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -69,6 +69,10 @@
struct {
u64 sndr_key;
u64 rcvr_key;
+ u64 data_seq;
+ u32 subflow_seq;
+ u16 data_len;
+ __sum16 csum;
};
struct {
struct mptcp_addr_info addr;
diff --git a/include/net/sock.h b/include/net/sock.h
index ea6fbc8..463f390 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1208,7 +1208,7 @@
#endif
bool (*stream_memory_free)(const struct sock *sk, int wake);
- bool (*stream_memory_read)(const struct sock *sk);
+ bool (*sock_is_readable)(struct sock *sk);
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
void (*leave_memory_pressure)(struct sock *sk);
@@ -2820,4 +2820,10 @@
int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
+static inline bool sk_is_readable(struct sock *sk)
+{
+ if (sk->sk_prot->sock_is_readable)
+ return sk->sk_prot->sock_is_readable(sk);
+ return false;
+}
#endif /* _SOCK_H */
diff --git a/include/net/tls.h b/include/net/tls.h
index be4b3e1..1fffb20 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -358,6 +358,7 @@
int __user *optlen);
int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
+void tls_err_abort(struct sock *sk, int err);
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
@@ -375,7 +376,7 @@
void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
-bool tls_sw_stream_read(const struct sock *sk);
+bool tls_sw_sock_is_readable(struct sock *sk);
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
@@ -466,12 +467,6 @@
#endif
}
-static inline void tls_err_abort(struct sock *sk, int err)
-{
- sk->sk_err = err;
- sk_error_report(sk);
-}
-
static inline bool tls_bigint_increment(unsigned char *seq, int len)
{
int i;
@@ -512,7 +507,7 @@
struct cipher_context *ctx)
{
if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size))
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (prot->version != TLS_1_3_VERSION &&
prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
diff --git a/include/net/udp.h b/include/net/udp.h
index 360df45..909ecf4 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -494,8 +494,9 @@
* CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
* packets in udp_gro_complete_segment. As does UDP GSO, verified by
* udp_send_skb. But when those packets are looped in dev_loopback_xmit
- * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
- * specific case, where PARTIAL is both correct and required.
+ * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
+ * Reset in this specific case, where PARTIAL is both correct and
+ * required.
*/
if (skb->pkt_type == PACKET_LOOPBACK)
skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cebd4fb..447def5 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1072,6 +1072,7 @@
INIT_WORK(&aux->work, prog_array_map_clear_deferred);
INIT_LIST_HEAD(&aux->poke_progs);
mutex_init(&aux->poke_mutex);
+ spin_lock_init(&aux->owner.lock);
map = array_map_alloc(attr);
if (IS_ERR(map)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6b7dfd..6e3ae90 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -524,6 +524,7 @@
int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
long bpf_jit_limit __read_mostly;
+long bpf_jit_limit_max __read_mostly;
static void
bpf_prog_ksym_set_addr(struct bpf_prog *prog)
@@ -817,7 +818,8 @@
static int __init bpf_jit_charge_init(void)
{
/* Only used as heuristic here to derive limit. */
- bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+ bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
PAGE_SIZE), LONG_MAX);
return 0;
}
@@ -1821,20 +1823,26 @@
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
+ bool ret;
+
if (fp->kprobe_override)
return false;
- if (!array->aux->type) {
+ spin_lock(&array->aux->owner.lock);
+
+ if (!array->aux->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
- array->aux->type = fp->type;
- array->aux->jited = fp->jited;
- return true;
+ array->aux->owner.type = fp->type;
+ array->aux->owner.jited = fp->jited;
+ ret = true;
+ } else {
+ ret = array->aux->owner.type == fp->type &&
+ array->aux->owner.jited == fp->jited;
}
-
- return array->aux->type == fp->type &&
- array->aux->jited == fp->jited;
+ spin_unlock(&array->aux->owner.lock);
+ return ret;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4e50c0b..1cad697 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -543,8 +543,10 @@
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
array = container_of(map, struct bpf_array, map);
- type = array->aux->type;
- jited = array->aux->jited;
+ spin_lock(&array->aux->owner.lock);
+ type = array->aux->owner.type;
+ jited = array->aux->owner.jited;
+ spin_unlock(&array->aux->owner.lock);
}
seq_printf(m,
@@ -1337,12 +1339,11 @@
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
u32 value_size, cp, max_count;
- int ufd = attr->map_fd;
+ int ufd = attr->batch.map_fd;
void *key, *value;
struct fd f;
int err = 0;
- f = fdget(ufd);
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
@@ -1367,6 +1368,7 @@
return -ENOMEM;
}
+ f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
@@ -1386,6 +1388,7 @@
kvfree(value);
kvfree(key);
+ fdput(f);
return err;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 570b0c9..ea08f01 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2187,8 +2187,10 @@
* And don't kill the default root.
*/
if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
- !percpu_ref_is_dying(&root->cgrp.self.refcnt))
+ !percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+ cgroup_bpf_offline(&root->cgrp);
percpu_ref_kill(&root->cgrp.self.refcnt);
+ }
cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 1669744..1768784 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1560,11 +1560,15 @@
return 0;
bat_priv->bla.claim_hash = batadv_hash_new(128);
- bat_priv->bla.backbone_hash = batadv_hash_new(32);
-
- if (!bat_priv->bla.claim_hash || !bat_priv->bla.backbone_hash)
+ if (!bat_priv->bla.claim_hash)
return -ENOMEM;
+ bat_priv->bla.backbone_hash = batadv_hash_new(32);
+ if (!bat_priv->bla.backbone_hash) {
+ batadv_hash_destroy(bat_priv->bla.claim_hash);
+ return -ENOMEM;
+ }
+
batadv_hash_set_lock_class(bat_priv->bla.claim_hash,
&batadv_claim_hash_lock_class_key);
batadv_hash_set_lock_class(bat_priv->bla.backbone_hash,
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 3ddd66e..5207cd8 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -190,29 +190,41 @@
bat_priv->gw.generation = 0;
- ret = batadv_v_mesh_init(bat_priv);
- if (ret < 0)
- goto err;
-
ret = batadv_originator_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_orig;
+ }
ret = batadv_tt_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_tt;
+ }
+
+ ret = batadv_v_mesh_init(bat_priv);
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_v;
+ }
ret = batadv_bla_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_bla;
+ }
ret = batadv_dat_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_dat;
+ }
ret = batadv_nc_mesh_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_nc;
+ }
batadv_gw_init(bat_priv);
batadv_mcast_init(bat_priv);
@@ -222,8 +234,20 @@
return 0;
-err:
- batadv_mesh_free(soft_iface);
+err_nc:
+ batadv_dat_free(bat_priv);
+err_dat:
+ batadv_bla_free(bat_priv);
+err_bla:
+ batadv_v_mesh_free(bat_priv);
+err_v:
+ batadv_tt_free(bat_priv);
+err_tt:
+ batadv_originator_free(bat_priv);
+err_orig:
+ batadv_purge_outstanding_packets(bat_priv, NULL);
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE);
+
return ret;
}
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 9f06132..0a7f1d3 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -152,8 +152,10 @@
&batadv_nc_coding_hash_lock_class_key);
bat_priv->nc.decoding_hash = batadv_hash_new(128);
- if (!bat_priv->nc.decoding_hash)
+ if (!bat_priv->nc.decoding_hash) {
+ batadv_hash_destroy(bat_priv->nc.coding_hash);
goto err;
+ }
batadv_hash_set_lock_class(bat_priv->nc.decoding_hash,
&batadv_nc_decoding_hash_lock_class_key);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index e0b3dac..4b7ad66 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -4162,8 +4162,10 @@
return ret;
ret = batadv_tt_global_init(bat_priv);
- if (ret < 0)
+ if (ret < 0) {
+ batadv_tt_local_table_free(bat_priv);
return ret;
+ }
batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1,
batadv_tt_tvlv_unicast_handler_v1,
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ee9fec..eb3a366 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3163,6 +3163,12 @@
qoffset = sb_dev->tc_to_txq[tc].offset;
qcount = sb_dev->tc_to_txq[tc].count;
+ if (unlikely(!qcount)) {
+ net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n",
+ sb_dev->name, qoffset, tc);
+ qoffset = 0;
+ qcount = dev->real_num_tx_queues;
+ }
}
if (skb_rx_queue_recorded(skb)) {
@@ -3906,7 +3912,8 @@
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
skb->pkt_type = PACKET_LOOPBACK;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (skb->ip_summed == CHECKSUM_NONE)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(skb));
skb_dst_force(skb);
netif_rx_ni(skb);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f619777..b2e49eb 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1973,9 +1973,9 @@
int netdev_change_owner(struct net_device *ndev, const struct net *net_old,
const struct net *net_new)
{
+ kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID;
+ kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID;
struct device *dev = &ndev->dev;
- kuid_t old_uid, new_uid;
- kgid_t old_gid, new_gid;
int error;
net_ns_get_ownership(net_old, &old_uid, &old_gid);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2170bea..fe93584 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -80,6 +80,7 @@
#include <linux/indirect_call_wrapper.h>
#include "datagram.h"
+#include "sock_destructor.h"
struct kmem_cache *skbuff_head_cache __ro_after_init;
static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
@@ -1804,30 +1805,39 @@
struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
{
int delta = headroom - skb_headroom(skb);
+ int osize = skb_end_offset(skb);
+ struct sock *sk = skb->sk;
if (WARN_ONCE(delta <= 0,
"%s is expecting an increase in the headroom", __func__))
return skb;
- /* pskb_expand_head() might crash, if skb is shared */
- if (skb_shared(skb)) {
+ delta = SKB_DATA_ALIGN(delta);
+ /* pskb_expand_head() might crash, if skb is shared. */
+ if (skb_shared(skb) || !is_skb_wmem(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
- if (likely(nskb)) {
- if (skb->sk)
- skb_set_owner_w(nskb, skb->sk);
- consume_skb(skb);
- } else {
- kfree_skb(skb);
- }
+ if (unlikely(!nskb))
+ goto fail;
+
+ if (sk)
+ skb_set_owner_w(nskb, sk);
+ consume_skb(skb);
skb = nskb;
}
- if (skb &&
- pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
- kfree_skb(skb);
- skb = NULL;
+ if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
+ goto fail;
+
+ if (sk && is_skb_wmem(skb)) {
+ delta = skb_end_offset(skb) - osize;
+ refcount_add(delta, &sk->sk_wmem_alloc);
+ skb->truesize += delta;
}
return skb;
+
+fail:
+ kfree_skb(skb);
+ return NULL;
}
EXPORT_SYMBOL(skb_expand_head);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b..a86ef7e 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -474,6 +474,20 @@
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
+bool sk_msg_is_readable(struct sock *sk)
+{
+ struct sk_psock *psock;
+ bool empty = true;
+
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (likely(psock))
+ empty = list_empty(&psock->ingress_msg);
+ rcu_read_unlock();
+ return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
struct sk_buff *skb)
{
diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h
new file mode 100644
index 0000000..2f396e6
--- /dev/null
+++ b/net/core/sock_destructor.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _NET_CORE_SOCK_DESTRUCTOR_H
+#define _NET_CORE_SOCK_DESTRUCTOR_H
+#include <net/tcp.h>
+
+static inline bool is_skb_wmem(const struct sk_buff *skb)
+{
+ return skb->destructor == sock_wfree ||
+ skb->destructor == __sock_wfree ||
+ (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree);
+}
+#endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c8496c1..5f88526 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -419,7 +419,7 @@
.mode = 0600,
.proc_handler = proc_dolongvec_minmax_bpf_restricted,
.extra1 = &long_one,
- .extra2 = &long_max,
+ .extra2 = &bpf_jit_limit_max,
},
#endif
{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8b48df..f5c336f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -486,10 +486,7 @@
{
if (tcp_epollin_ready(sk, target))
return true;
-
- if (sk->sk_prot->stream_memory_read)
- return sk->sk_prot->stream_memory_read(sk);
- return false;
+ return sk_is_readable(sk);
}
/*
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386..5f4d6f4 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -150,19 +150,6 @@
EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
#ifdef CONFIG_BPF_SYSCALL
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
- struct sk_psock *psock;
- bool empty = true;
-
- rcu_read_lock();
- psock = sk_psock(sk);
- if (likely(psock))
- empty = list_empty(&psock->ingress_msg);
- rcu_read_unlock();
- return !empty;
-}
-
static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
long timeo)
{
@@ -232,6 +219,7 @@
bool cork = false, enospc = sk_msg_full(msg);
struct sock *sk_redir;
u32 tosend, delta = 0;
+ u32 eval = __SK_NONE;
int ret;
more_data:
@@ -275,13 +263,24 @@
case __SK_REDIRECT:
sk_redir = psock->sk_redir;
sk_msg_apply_bytes(psock, tosend);
+ if (!psock->apply_bytes) {
+ /* Clean up before releasing the sock lock. */
+ eval = psock->eval;
+ psock->eval = __SK_NONE;
+ psock->sk_redir = NULL;
+ }
if (psock->cork) {
cork = true;
psock->cork = NULL;
}
sk_msg_return(sk, msg, tosend);
release_sock(sk);
+
ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+ if (eval == __SK_REDIRECT)
+ sock_put(sk_redir);
+
lock_sock(sk);
if (unlikely(ret < 0)) {
int free = sk_msg_free_nocharge(sk, msg);
@@ -479,7 +478,7 @@
prot[TCP_BPF_BASE].unhash = sock_map_unhash;
prot[TCP_BPF_BASE].close = sock_map_close;
prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg;
- prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read;
+ prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable;
prot[TCP_BPF_TX] = prot[TCP_BPF_BASE];
prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8536b2a..2fffcf2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2867,6 +2867,9 @@
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
+ /* psock ingress_msg queue should not contain any bad checksum frames */
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a1d5f4..bbe6569 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -114,6 +114,7 @@
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = udp_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 97095b7..5dcfd53 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -672,7 +672,7 @@
u8 *ie, u8 ie_len)
{
struct ieee80211_supported_band *sband;
- const u8 *cap;
+ const struct element *cap;
const struct ieee80211_he_operation *he_oper = NULL;
sband = ieee80211_get_sband(sdata);
@@ -687,9 +687,10 @@
sdata->vif.bss_conf.he_support = true;
- cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
- if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3]))
- he_oper = (void *)(cap + 3);
+ cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
+ if (cap && cap->datalen >= 1 + sizeof(*he_oper) &&
+ cap->datalen >= 1 + ieee80211_he_oper_size(cap->data + 1))
+ he_oper = (void *)(cap->data + 1);
if (he_oper)
sdata->vif.bss_conf.he_oper.params =
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c41273c..f0f22eb 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -485,11 +485,11 @@
mpext = mptcp_get_ext(skb);
data_len = mpext ? mpext->data_len : 0;
- /* we will check ext_copy.data_len in mptcp_write_options() to
+ /* we will check ops->data_len in mptcp_write_options() to
* discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
* TCPOLEN_MPTCP_MPC_ACK
*/
- opts->ext_copy.data_len = data_len;
+ opts->data_len = data_len;
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
@@ -505,9 +505,9 @@
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd) {
/* we need to propagate more info to csum the pseudo hdr */
- opts->ext_copy.data_seq = mpext->data_seq;
- opts->ext_copy.subflow_seq = mpext->subflow_seq;
- opts->ext_copy.csum = mpext->csum;
+ opts->data_seq = mpext->data_seq;
+ opts->subflow_seq = mpext->subflow_seq;
+ opts->csum = mpext->csum;
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
}
*size = ALIGN(len, 4);
@@ -1227,7 +1227,7 @@
WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
-static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+static u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __sum16 sum)
{
struct csum_pseudo_header header;
__wsum csum;
@@ -1237,15 +1237,21 @@
* always the 64-bit value, irrespective of what length is used in the
* DSS option itself.
*/
- header.data_seq = cpu_to_be64(mpext->data_seq);
- header.subflow_seq = htonl(mpext->subflow_seq);
- header.data_len = htons(mpext->data_len);
+ header.data_seq = cpu_to_be64(data_seq);
+ header.subflow_seq = htonl(subflow_seq);
+ header.data_len = htons(data_len);
header.csum = 0;
- csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum));
+ csum = csum_partial(&header, sizeof(header), ~csum_unfold(sum));
return (__force u16)csum_fold(csum);
}
+static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+{
+ return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len,
+ mpext->csum);
+}
+
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
@@ -1337,7 +1343,7 @@
len = TCPOLEN_MPTCP_MPC_SYN;
} else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) {
len = TCPOLEN_MPTCP_MPC_SYNACK;
- } else if (opts->ext_copy.data_len) {
+ } else if (opts->data_len) {
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd)
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
@@ -1366,14 +1372,17 @@
put_unaligned_be64(opts->rcvr_key, ptr);
ptr += 2;
- if (!opts->ext_copy.data_len)
+ if (!opts->data_len)
goto mp_capable_done;
if (opts->csum_reqd) {
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
- mptcp_make_csum(&opts->ext_copy), ptr);
+ put_unaligned_be32(opts->data_len << 16 |
+ __mptcp_make_csum(opts->data_seq,
+ opts->subflow_seq,
+ opts->data_len,
+ opts->csum), ptr);
} else {
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
+ put_unaligned_be32(opts->data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
ptr += 1;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 32df65f..fb3da4d 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -156,6 +156,12 @@
void *arg,
struct sctp_cmd_seq *commands);
+static enum sctp_disposition
+__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands);
+
/* Small helper function that checks if the chunk length
* is of the appropriate length. The 'required_length' argument
* is set to be the size of a specific chunk we are testing.
@@ -337,6 +343,14 @@
if (!chunk->singleton)
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ /* Make sure that the INIT chunk has a valid length.
+ * Normally, this would cause an ABORT with a Protocol Violation
+ * error, but since we don't have an association, we'll
+ * just discard the packet.
+ */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* If the packet is an OOTB packet which is temporarily on the
* control endpoint, respond with an ABORT.
*/
@@ -351,14 +365,6 @@
if (chunk->sctp_hdr->vtag != 0)
return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
- /* Make sure that the INIT chunk has a valid length.
- * Normally, this would cause an ABORT with a Protocol Violation
- * error, but since we don't have an association, we'll
- * just discard the packet.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-
/* If the INIT is coming toward a closing socket, we'll send back
* and ABORT. Essentially, this catches the race of INIT being
* backloged to the socket at the same time as the user issues close().
@@ -704,6 +710,9 @@
struct sock *sk;
int error = 0;
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* If the packet is an OOTB packet which is temporarily on the
* control endpoint, respond with an ABORT.
*/
@@ -718,7 +727,8 @@
* in sctp_unpack_cookie().
*/
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
/* If the endpoint is not listening or if the number of associations
* on the TCP-style socket exceed the max backlog, respond with an
@@ -1524,20 +1534,16 @@
if (!chunk->singleton)
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ /* Make sure that the INIT chunk has a valid length. */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* 3.1 A packet containing an INIT chunk MUST have a zero Verification
* Tag.
*/
if (chunk->sctp_hdr->vtag != 0)
return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
- /* Make sure that the INIT chunk has a valid length.
- * In this case, we generate a protocol violation since we have
- * an association established.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
-
if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port)
return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands);
@@ -1882,9 +1888,9 @@
* its peer.
*/
if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) {
- disposition = sctp_sf_do_9_2_reshutack(net, ep, asoc,
- SCTP_ST_CHUNK(chunk->chunk_hdr->type),
- chunk, commands);
+ disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc,
+ SCTP_ST_CHUNK(chunk->chunk_hdr->type),
+ chunk, commands);
if (SCTP_DISPOSITION_NOMEM == disposition)
goto nomem;
@@ -2202,9 +2208,11 @@
* enough for the chunk header. Cookie length verification is
* done later.
*/
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) {
+ if (!sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands);
+ }
/* "Decode" the chunk. We have no optional parameters so we
* are in good shape.
@@ -2341,7 +2349,7 @@
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2387,7 +2395,7 @@
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2657,7 +2665,7 @@
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2970,13 +2978,11 @@
* that belong to this association, it should discard the INIT chunk and
* retransmit the SHUTDOWN ACK chunk.
*/
-enum sctp_disposition sctp_sf_do_9_2_reshutack(
- struct net *net,
- const struct sctp_endpoint *ep,
- const struct sctp_association *asoc,
- const union sctp_subtype type,
- void *arg,
- struct sctp_cmd_seq *commands)
+static enum sctp_disposition
+__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands)
{
struct sctp_chunk *chunk = arg;
struct sctp_chunk *reply;
@@ -3010,6 +3016,26 @@
return SCTP_DISPOSITION_NOMEM;
}
+enum sctp_disposition
+sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_chunk *chunk = arg;
+
+ if (!chunk->singleton)
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
+ if (chunk->sctp_hdr->vtag != 0)
+ return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
+
+ return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands);
+}
+
/*
* sctp_sf_do_ecn_cwr
*
@@ -3662,6 +3688,9 @@
SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES);
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+
ch = (struct sctp_chunkhdr *)chunk->chunk_hdr;
do {
/* Report violation if the chunk is less then minimal */
@@ -3777,12 +3806,6 @@
SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
- /* If the chunk length is invalid, we don't want to process
- * the reset of the packet.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-
/* We need to discard the rest of the packet to prevent
* potential boomming attacks from additional bundled chunks.
* This is documented in SCTP Threats ID.
@@ -3810,6 +3833,9 @@
{
struct sctp_chunk *chunk = arg;
+ if (!sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+
/* Make sure that the SHUTDOWN_ACK chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
@@ -3845,6 +3871,11 @@
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
+ /* Make sure that the ASCONF ADDIP chunk has a valid length. */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk)))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* ADD-IP: Section 4.1.1
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
@@ -3853,13 +3884,7 @@
*/
if (!asoc->peer.asconf_capable ||
(!net->sctp.addip_noauth && !chunk->auth))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg,
- commands);
-
- /* Make sure that the ASCONF ADDIP chunk has a valid length. */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
hdr = (struct sctp_addiphdr *)chunk->skb->data;
serial = ntohl(hdr->serial);
@@ -3988,6 +4013,12 @@
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
+ /* Make sure that the ADDIP chunk has a valid length. */
+ if (!sctp_chunk_length_valid(asconf_ack,
+ sizeof(struct sctp_addip_chunk)))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* ADD-IP, Section 4.1.2:
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
@@ -3996,14 +4027,7 @@
*/
if (!asoc->peer.asconf_capable ||
(!net->sctp.addip_noauth && !asconf_ack->auth))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg,
- commands);
-
- /* Make sure that the ADDIP chunk has a valid length. */
- if (!sctp_chunk_length_valid(asconf_ack,
- sizeof(struct sctp_addip_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data;
rcvd_serial = ntohl(addip_hdr->serial);
@@ -4575,6 +4599,9 @@
{
struct sctp_chunk *chunk = arg;
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Make sure that the chunk has a valid length.
* Since we don't know the chunk type, we use a general
* chunkhdr structure to make a comparison.
@@ -4642,6 +4669,9 @@
{
struct sctp_chunk *chunk = arg;
+ if (!sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Make sure that the chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
@@ -6348,6 +6378,7 @@
* yet.
*/
switch (chunk->chunk_hdr->type) {
+ case SCTP_CID_INIT:
case SCTP_CID_INIT_ACK:
{
struct sctp_initack_chunk *initack;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c038efc..78b663d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1057,7 +1057,7 @@
if (smc->clcsock->sk->sk_err) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
} else if ((1 << smc->clcsock->sk->sk_state) &
- (TCPF_SYN_SENT | TCP_SYN_RECV)) {
+ (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo);
if ((rc == -EPIPE) &&
((1 << smc->clcsock->sk->sk_state) &
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 72f4b72..f1d3234 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1822,7 +1822,7 @@
link->smcibdev->ibdev->name, link->ibport);
link->state = SMC_LNK_ACTIVE;
if (link->lgr->llc_testlink_time) {
- link->llc_testlink_time = link->lgr->llc_testlink_time * HZ;
+ link->llc_testlink_time = link->lgr->llc_testlink_time;
schedule_delayed_work(&link->llc_testlink_wrk,
link->llc_testlink_time);
}
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c9391d3..dc60c32 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -2285,43 +2285,53 @@
u16 key_gen = msg_key_gen(hdr);
u16 size = msg_data_sz(hdr);
u8 *data = msg_data(hdr);
+ unsigned int keylen;
+
+ /* Verify whether the size can exist in the packet */
+ if (unlikely(size < sizeof(struct tipc_aead_key) + TIPC_AEAD_KEYLEN_MIN)) {
+ pr_debug("%s: message data size is too small\n", rx->name);
+ goto exit;
+ }
+
+ keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+
+ /* Verify the supplied size values */
+ if (unlikely(size != keylen + sizeof(struct tipc_aead_key) ||
+ keylen > TIPC_AEAD_KEY_SIZE_MAX)) {
+ pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name);
+ goto exit;
+ }
spin_lock(&rx->lock);
if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) {
pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name,
rx->skey, key_gen, rx->key_gen);
- goto exit;
+ goto exit_unlock;
}
/* Allocate memory for the key */
skey = kmalloc(size, GFP_ATOMIC);
if (unlikely(!skey)) {
pr_err("%s: unable to allocate memory for skey\n", rx->name);
- goto exit;
+ goto exit_unlock;
}
/* Copy key from msg data */
- skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+ skey->keylen = keylen;
memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME);
memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32),
skey->keylen);
- /* Sanity check */
- if (unlikely(size != tipc_aead_key_size(skey))) {
- kfree(skey);
- skey = NULL;
- goto exit;
- }
-
rx->key_gen = key_gen;
rx->skey_mode = msg_key_mode(hdr);
rx->skey = skey;
rx->nokey = 0;
mb(); /* for nokey flag */
-exit:
+exit_unlock:
spin_unlock(&rx->lock);
+exit:
/* Schedule the key attaching on this crypto */
if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0)))
return true;
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index fde56ff..9ab81db 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -681,12 +681,12 @@
prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg;
- prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read;
+ prot[TLS_BASE][TLS_SW].sock_is_readable = tls_sw_sock_is_readable;
prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close;
prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg;
- prot[TLS_SW][TLS_SW].stream_memory_read = tls_sw_stream_read;
+ prot[TLS_SW][TLS_SW].sock_is_readable = tls_sw_sock_is_readable;
prot[TLS_SW][TLS_SW].close = tls_sk_proto_close;
#ifdef CONFIG_TLS_DEVICE
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4feb95e..1b08b87 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -35,6 +35,7 @@
* SOFTWARE.
*/
+#include <linux/bug.h>
#include <linux/sched/signal.h>
#include <linux/module.h>
#include <linux/splice.h>
@@ -43,6 +44,14 @@
#include <net/strparser.h>
#include <net/tls.h>
+noinline void tls_err_abort(struct sock *sk, int err)
+{
+ WARN_ON_ONCE(err >= 0);
+ /* sk->sk_err should contain a positive error code. */
+ sk->sk_err = -err;
+ sk_error_report(sk);
+}
+
static int __skb_nsg(struct sk_buff *skb, int offset, int len,
unsigned int recursion_level)
{
@@ -419,7 +428,7 @@
tx_err:
if (rc < 0 && rc != -EAGAIN)
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
return rc;
}
@@ -450,7 +459,7 @@
/* If err is already set on socket, return the same code */
if (sk->sk_err) {
- ctx->async_wait.err = sk->sk_err;
+ ctx->async_wait.err = -sk->sk_err;
} else {
ctx->async_wait.err = err;
tls_err_abort(sk, err);
@@ -763,7 +772,7 @@
msg_pl->sg.size + prot->tail_size, i);
if (rc < 0) {
if (rc != -EINPROGRESS) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (split) {
tls_ctx->pending_open_record_frags = true;
tls_merge_open_record(sk, rec, tmp, orig_end);
@@ -1827,7 +1836,7 @@
err = decrypt_skb_update(sk, skb, &msg->msg_iter,
&chunk, &zc, async_capable);
if (err < 0 && err != -EINPROGRESS) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
goto recv_end;
}
@@ -2007,7 +2016,7 @@
}
if (err < 0) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
goto splice_read_end;
}
ctx->decrypted = 1;
@@ -2026,7 +2035,7 @@
return copied ? : err;
}
-bool tls_sw_stream_read(const struct sock *sk)
+bool tls_sw_sock_is_readable(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 89f9e85..78e08e8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3052,6 +3052,8 @@
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
@@ -3091,6 +3093,8 @@
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (sk->sk_type == SOCK_SEQPACKET) {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b927e2b..452376c 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -102,6 +102,7 @@
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void unix_stream_bpf_rebuild_protos(struct proto *prot,
@@ -110,6 +111,7 @@
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
prot->unhash = sock_map_unhash;
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 0332312..aaba847 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -524,6 +524,7 @@
INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk);
INIT_WORK(&rdev->mgmt_registrations_update_wk,
cfg80211_mgmt_registrations_update_wk);
+ spin_lock_init(&rdev->mgmt_registrations_lock);
#ifdef CONFIG_CFG80211_DEFAULT_PS
rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -1279,7 +1280,6 @@
INIT_LIST_HEAD(&wdev->event_list);
spin_lock_init(&wdev->event_lock);
INIT_LIST_HEAD(&wdev->mgmt_registrations);
- spin_lock_init(&wdev->mgmt_registrations_lock);
INIT_LIST_HEAD(&wdev->pmsr_list);
spin_lock_init(&wdev->pmsr_lock);
INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index b35d0db..1720abf 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -100,6 +100,8 @@
struct work_struct propagate_cac_done_wk;
struct work_struct mgmt_registrations_update_wk;
+ /* lock for all wdev lists */
+ spinlock_t mgmt_registrations_lock;
/* must be last because of the way we do wiphy_priv(),
* and it should at least be aligned to NETDEV_ALIGN */
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 3aa69b3..783acd2 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -452,9 +452,9 @@
lockdep_assert_held(&rdev->wiphy.mtx);
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
if (!wdev->mgmt_registrations_need_update) {
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
return;
}
@@ -479,7 +479,7 @@
rcu_read_unlock();
wdev->mgmt_registrations_need_update = 0;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
rdev_update_mgmt_frame_registrations(rdev, wdev, &upd);
}
@@ -503,6 +503,7 @@
int match_len, bool multicast_rx,
struct netlink_ext_ack *extack)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_mgmt_registration *reg, *nreg;
int err = 0;
u16 mgmt_type;
@@ -548,7 +549,7 @@
if (!nreg)
return -ENOMEM;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry(reg, &wdev->mgmt_registrations, list) {
int mlen = min(match_len, reg->match_len);
@@ -583,7 +584,7 @@
list_add(&nreg->list, &wdev->mgmt_registrations);
}
wdev->mgmt_registrations_need_update = 1;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
cfg80211_mgmt_registrations_update(wdev);
@@ -591,7 +592,7 @@
out:
kfree(nreg);
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
return err;
}
@@ -602,7 +603,7 @@
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
struct cfg80211_mgmt_registration *reg, *tmp;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) {
if (reg->nlportid != nlportid)
@@ -615,7 +616,7 @@
schedule_work(&rdev->mgmt_registrations_update_wk);
}
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
if (nlportid && rdev->crit_proto_nlportid == nlportid) {
rdev->crit_proto_nlportid = 0;
@@ -628,15 +629,16 @@
void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_mgmt_registration *reg, *tmp;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) {
list_del(®->list);
kfree(reg);
}
wdev->mgmt_registrations_need_update = 1;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
cfg80211_mgmt_registrations_update(wdev);
}
@@ -784,7 +786,7 @@
data = buf + ieee80211_hdrlen(mgmt->frame_control);
data_len = len - ieee80211_hdrlen(mgmt->frame_control);
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry(reg, &wdev->mgmt_registrations, list) {
if (reg->frame_type != ftype)
@@ -808,7 +810,7 @@
break;
}
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
trace_cfg80211_return_bool(result);
return result;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 11c68b1..adc0d14 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -418,14 +418,17 @@
}
ssid_len = ssid[1];
ssid = ssid + 2;
- rcu_read_unlock();
/* check if nontrans_bss is in the list */
list_for_each_entry(bss, &trans_bss->nontrans_list, nontrans_list) {
- if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len))
+ if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) {
+ rcu_read_unlock();
return 0;
+ }
}
+ rcu_read_unlock();
+
/* add to the list */
list_add_tail(&nontrans_bss->nontrans_list, &trans_bss->nontrans_list);
return 0;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 18dba3d..a1a99a5 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1028,14 +1028,14 @@
!(rdev->wiphy.interface_modes & (1 << ntype)))
return -EOPNOTSUPP;
- /* if it's part of a bridge, reject changing type to station/ibss */
- if (netif_is_bridge_port(dev) &&
- (ntype == NL80211_IFTYPE_ADHOC ||
- ntype == NL80211_IFTYPE_STATION ||
- ntype == NL80211_IFTYPE_P2P_CLIENT))
- return -EBUSY;
-
if (ntype != otype) {
+ /* if it's part of a bridge, reject changing type to station/ibss */
+ if (netif_is_bridge_port(dev) &&
+ (ntype == NL80211_IFTYPE_ADHOC ||
+ ntype == NL80211_IFTYPE_STATION ||
+ ntype == NL80211_IFTYPE_P2P_CLIENT))
+ return -EBUSY;
+
dev->ieee80211_ptr->use_4addr = false;
dev->ieee80211_ptr->mesh_id_up_len = 0;
wdev_lock(dev->ieee80211_ptr);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 5c59790..d88bb65 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -949,7 +949,6 @@
int err, n;
u32 key;
char b;
- int retries = 100;
zero_verdict_count(verd_mapfd);
@@ -1002,17 +1001,11 @@
goto close_peer1;
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_peer1:
xclose(p1);
@@ -1571,7 +1564,6 @@
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
int sfd[2];
u32 key;
@@ -1606,17 +1598,11 @@
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close:
xclose(c1);
@@ -1748,7 +1734,6 @@
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
u32 key;
char b;
@@ -1781,17 +1766,11 @@
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_cli1:
xclose(c1);
@@ -1841,7 +1820,6 @@
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
int sfd[2];
u32 key;
@@ -1876,17 +1854,11 @@
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_cli1:
xclose(c1);
@@ -1932,7 +1904,6 @@
int sfd[2];
u32 key;
char b;
- int retries = 100;
zero_verdict_count(verd_mapfd);
@@ -1963,17 +1934,11 @@
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close:
xclose(c1);
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 8e67a25..3313566 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -445,10 +445,13 @@
ip -netns ${NSA} link set dev ${NSA_DEV} down
ip -netns ${NSA} link del dev ${NSA_DEV}
+ ip netns pids ${NSA} | xargs kill 2>/dev/null
ip netns del ${NSA}
fi
+ ip netns pids ${NSB} | xargs kill 2>/dev/null
ip netns del ${NSB}
+ ip netns pids ${NSC} | xargs kill 2>/dev/null
ip netns del ${NSC} >/dev/null 2>&1
}
