summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--MAINTAINERS43
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_nic.c4
-rw-r--r--drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c16
-rw-r--r--drivers/net/ethernet/broadcom/tg3.c58
-rw-r--r--drivers/net/ethernet/intel/ice/devlink/devlink.c3
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.c150
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.h1
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx_lib.h43
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c35
-rw-r--r--drivers/net/tun.c14
-rw-r--r--drivers/net/vmxnet3/vmxnet3_xdp.c14
-rw-r--r--include/linux/netdevice.h2
-rw-r--r--include/net/sch_generic.h2
-rw-r--r--include/trace/events/rxrpc.h1
-rw-r--r--net/core/dev.c14
-rw-r--r--net/ethtool/ioctl.c2
-rw-r--r--net/ethtool/rss.c3
-rw-r--r--net/ipv4/udp.c4
-rw-r--r--net/ipv6/ioam6_iptunnel.c14
-rw-r--r--net/ipv6/rpl_iptunnel.c15
-rw-r--r--net/ipv6/seg6_iptunnel.c15
-rw-r--r--net/ipv6/udp.c4
-rw-r--r--net/rose/af_rose.c24
-rw-r--r--net/rxrpc/ar-internal.h2
-rw-r--r--net/rxrpc/call_object.c6
-rw-r--r--net/rxrpc/conn_event.c21
-rw-r--r--net/rxrpc/conn_object.c1
-rw-r--r--net/rxrpc/input.c12
-rw-r--r--net/rxrpc/sendmsg.c2
-rw-r--r--net/sched/sch_fifo.c3
-rw-r--r--net/sched/sch_netem.c2
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_ctx.py9
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c2
-rw-r--r--tools/testing/selftests/net/udpgso.c26
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json34
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json23
36 files changed, 446 insertions, 178 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 896a307fa065..873aa2cce4d7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16462,6 +16462,22 @@ F: include/net/dsa.h
F: net/dsa/
F: tools/testing/selftests/drivers/net/dsa/
+NETWORKING [ETHTOOL]
+M: Andrew Lunn <andrew@lunn.ch>
+M: Jakub Kicinski <kuba@kernel.org>
+F: Documentation/netlink/specs/ethtool.yaml
+F: Documentation/networking/ethtool-netlink.rst
+F: include/linux/ethtool*
+F: include/uapi/linux/ethtool*
+F: net/ethtool/
+F: tools/testing/selftests/drivers/net/*/ethtool*
+
+NETWORKING [ETHTOOL CABLE TEST]
+M: Andrew Lunn <andrew@lunn.ch>
+F: net/ethtool/cabletest.c
+F: tools/testing/selftests/drivers/net/*/ethtool*
+K: cable_test
+
NETWORKING [GENERAL]
M: "David S. Miller" <davem@davemloft.net>
M: Eric Dumazet <edumazet@google.com>
@@ -16621,6 +16637,7 @@ F: tools/testing/selftests/net/mptcp/
NETWORKING [TCP]
M: Eric Dumazet <edumazet@google.com>
M: Neal Cardwell <ncardwell@google.com>
+R: Kuniyuki Iwashima <kuniyu@amazon.com>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/networking/net_cachelines/tcp_sock.rst
@@ -16648,6 +16665,31 @@ F: include/net/tls.h
F: include/uapi/linux/tls.h
F: net/tls/*
+NETWORKING [SOCKETS]
+M: Eric Dumazet <edumazet@google.com>
+M: Kuniyuki Iwashima <kuniyu@amazon.com>
+M: Paolo Abeni <pabeni@redhat.com>
+M: Willem de Bruijn <willemb@google.com>
+S: Maintained
+F: include/linux/sock_diag.h
+F: include/linux/socket.h
+F: include/linux/sockptr.h
+F: include/net/sock.h
+F: include/net/sock_reuseport.h
+F: include/uapi/linux/socket.h
+F: net/core/*sock*
+F: net/core/scm.c
+F: net/socket.c
+
+NETWORKING [UNIX SOCKETS]
+M: Kuniyuki Iwashima <kuniyu@amazon.com>
+S: Maintained
+F: include/net/af_unix.h
+F: include/net/netns/unix.h
+F: include/uapi/linux/unix_diag.h
+F: net/unix/
+F: tools/testing/selftests/net/af_unix/
+
NETXEN (1/10) GbE SUPPORT
M: Manish Chopra <manishc@marvell.com>
M: Rahul Verma <rahulv@marvell.com>
@@ -17713,6 +17755,7 @@ L: netdev@vger.kernel.org
L: dev@openvswitch.org
S: Maintained
W: http://openvswitch.org
+F: Documentation/networking/openvswitch.rst
F: include/uapi/linux/openvswitch.h
F: net/openvswitch/
F: tools/testing/selftests/net/openvswitch/
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index fe0e3e2a8117..71e50fc65c14 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -1441,7 +1441,9 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
aq_ptp_ring_free(self);
aq_ptp_free(self);
- if (likely(self->aq_fw_ops->deinit) && link_down) {
+ /* May be invoked during hot unplug. */
+ if (pci_device_is_present(self->pdev) &&
+ likely(self->aq_fw_ops->deinit) && link_down) {
mutex_lock(&self->fwreq_mutex);
self->aq_fw_ops->deinit(self->aq_hw);
mutex_unlock(&self->fwreq_mutex);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 0715ea5bf13e..3b082114f2e5 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -41,9 +41,12 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
{
struct bcmgenet_priv *priv = netdev_priv(dev);
struct device *kdev = &priv->pdev->dev;
+ u32 phy_wolopts = 0;
- if (dev->phydev)
+ if (dev->phydev) {
phy_ethtool_get_wol(dev->phydev, wol);
+ phy_wolopts = wol->wolopts;
+ }
/* MAC is not wake-up capable, return what the PHY does */
if (!device_can_wakeup(kdev))
@@ -51,9 +54,14 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
/* Overlay MAC capabilities with that of the PHY queried before */
wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
- wol->wolopts = priv->wolopts;
- memset(wol->sopass, 0, sizeof(wol->sopass));
+ wol->wolopts |= priv->wolopts;
+ /* Return the PHY configured magic password */
+ if (phy_wolopts & WAKE_MAGICSECURE)
+ return;
+
+ /* Otherwise the MAC one */
+ memset(wol->sopass, 0, sizeof(wol->sopass));
if (wol->wolopts & WAKE_MAGICSECURE)
memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
}
@@ -70,7 +78,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
/* Try Wake-on-LAN from the PHY first */
if (dev->phydev) {
ret = phy_ethtool_set_wol(dev->phydev, wol);
- if (ret != -EOPNOTSUPP)
+ if (ret != -EOPNOTSUPP && wol->wolopts)
return ret;
}
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 1c94bf1db718..d9d675f1ebfe 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -55,6 +55,7 @@
#include <linux/hwmon.h>
#include <linux/hwmon-sysfs.h>
#include <linux/crc32poly.h>
+#include <linux/dmi.h>
#include <net/checksum.h>
#include <net/gso.h>
@@ -18212,6 +18213,50 @@ unlock:
static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
+/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal
+ * PCIe AER event on the tg3 device if the tg3 device is not, or cannot
+ * be, powered down.
+ */
+static const struct dmi_system_id tg3_restart_aer_quirk_table[] = {
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"),
+ },
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"),
+ },
+ },
+ {}
+};
+
static void tg3_shutdown(struct pci_dev *pdev)
{
struct net_device *dev = pci_get_drvdata(pdev);
@@ -18228,6 +18273,19 @@ static void tg3_shutdown(struct pci_dev *pdev)
if (system_state == SYSTEM_POWER_OFF)
tg3_power_down(tp);
+ else if (system_state == SYSTEM_RESTART &&
+ dmi_first_match(tg3_restart_aer_quirk_table) &&
+ pdev->current_state != PCI_D3cold &&
+ pdev->current_state != PCI_UNKNOWN) {
+ /* Disable PCIe AER on the tg3 to avoid a fatal
+ * error during this system restart.
+ */
+ pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL,
+ PCI_EXP_DEVCTL_CERE |
+ PCI_EXP_DEVCTL_NFERE |
+ PCI_EXP_DEVCTL_FERE |
+ PCI_EXP_DEVCTL_URRE);
+ }
rtnl_unlock();
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index d116e2b10bce..dbdb83567364 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -981,6 +981,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv
/* preallocate memory for ice_sched_node */
node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL);
+ if (!node)
+ return -ENOMEM;
+
*priv = node;
return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 5d2d7736fd5f..9c9ea4c1b93b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -527,15 +527,14 @@ err:
* @xdp: xdp_buff used as input to the XDP program
* @xdp_prog: XDP program to run
* @xdp_ring: ring to be used for XDP_TX action
- * @rx_buf: Rx buffer to store the XDP action
* @eop_desc: Last descriptor in packet to read metadata from
*
* Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
*/
-static void
+static u32
ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
- struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
+ union ice_32b_rx_flex_desc *eop_desc)
{
unsigned int ret = ICE_XDP_PASS;
u32 act;
@@ -574,7 +573,7 @@ out_failure:
ret = ICE_XDP_CONSUMED;
}
exit:
- ice_set_rx_bufs_act(xdp, rx_ring, ret);
+ return ret;
}
/**
@@ -860,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
xdp_buff_set_frags_flag(xdp);
}
- if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
- ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+ if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS))
return -ENOMEM;
- }
__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
rx_buf->page_offset, size);
@@ -924,7 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
struct ice_rx_buf *rx_buf;
rx_buf = &rx_ring->rx_buf[ntc];
- rx_buf->pgcnt = page_count(rx_buf->page);
prefetchw(rx_buf->page);
if (!size)
@@ -941,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
}
/**
+ * ice_get_pgcnts - grab page_count() for gathered fragments
+ * @rx_ring: Rx descriptor ring to store the page counts on
+ *
+ * This function is intended to be called right before running XDP
+ * program so that the page recycling mechanism will be able to take
+ * a correct decision regarding underlying pages; this is done in such
+ * way as XDP program can change the refcount of page
+ */
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+{
+ u32 nr_frags = rx_ring->nr_frags + 1;
+ u32 idx = rx_ring->first_desc;
+ struct ice_rx_buf *rx_buf;
+ u32 cnt = rx_ring->count;
+
+ for (int i = 0; i < nr_frags; i++) {
+ rx_buf = &rx_ring->rx_buf[idx];
+ rx_buf->pgcnt = page_count(rx_buf->page);
+
+ if (++idx == cnt)
+ idx = 0;
+ }
+}
+
+/**
* ice_build_skb - Build skb around an existing buffer
* @rx_ring: Rx descriptor ring to transact packets on
* @xdp: xdp_buff pointing to the data
@@ -1051,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
rx_buf->page_offset + headlen, size,
xdp->frame_sz);
} else {
- /* buffer is unused, change the act that should be taken later
- * on; data was copied onto skb's linear part so there's no
+ /* buffer is unused, restore biased page count in Rx buffer;
+ * data was copied onto skb's linear part so there's no
* need for adjusting page offset and we can reuse this buffer
* as-is
*/
- rx_buf->act = ICE_SKB_CONSUMED;
+ rx_buf->pagecnt_bias++;
}
if (unlikely(xdp_buff_has_frags(xdp))) {
@@ -1104,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
}
/**
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * @rx_ring: Rx ring with all the auxiliary data
+ * @xdp: XDP buffer carrying linear + frags part
+ * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
+ * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @verdict: return code from XDP program execution
+ *
+ * Walk through gathered fragments and satisfy internal page
+ * recycle mechanism; we take here an action related to verdict
+ * returned by XDP program;
+ */
+static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+ u32 *xdp_xmit, u32 ntc, u32 verdict)
+{
+ u32 nr_frags = rx_ring->nr_frags + 1;
+ u32 idx = rx_ring->first_desc;
+ u32 cnt = rx_ring->count;
+ u32 post_xdp_frags = 1;
+ struct ice_rx_buf *buf;
+ int i;
+
+ if (unlikely(xdp_buff_has_frags(xdp)))
+ post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+
+ for (i = 0; i < post_xdp_frags; i++) {
+ buf = &rx_ring->rx_buf[idx];
+
+ if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+ ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+ *xdp_xmit |= verdict;
+ } else if (verdict & ICE_XDP_CONSUMED) {
+ buf->pagecnt_bias++;
+ } else if (verdict == ICE_XDP_PASS) {
+ ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+ }
+
+ ice_put_rx_buf(rx_ring, buf);
+
+ if (++idx == cnt)
+ idx = 0;
+ }
+ /* handle buffers that represented frags released by XDP prog;
+ * for these we keep pagecnt_bias as-is; refcount from struct page
+ * has been decremented within XDP prog and we do not have to increase
+ * the biased refcnt
+ */
+ for (; i < nr_frags; i++) {
+ buf = &rx_ring->rx_buf[idx];
+ ice_put_rx_buf(rx_ring, buf);
+ if (++idx == cnt)
+ idx = 0;
+ }
+
+ xdp->data = NULL;
+ rx_ring->first_desc = ntc;
+ rx_ring->nr_frags = 0;
+}
+
+/**
* ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
* @rx_ring: Rx descriptor ring to transact packets on
* @budget: Total limit on number of packets to process
@@ -1120,15 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
unsigned int offset = rx_ring->rx_offset;
struct xdp_buff *xdp = &rx_ring->xdp;
- u32 cached_ntc = rx_ring->first_desc;
struct ice_tx_ring *xdp_ring = NULL;
struct bpf_prog *xdp_prog = NULL;
u32 ntc = rx_ring->next_to_clean;
+ u32 cached_ntu, xdp_verdict;
u32 cnt = rx_ring->count;
u32 xdp_xmit = 0;
- u32 cached_ntu;
bool failure;
- u32 first;
xdp_prog = READ_ONCE(rx_ring->xdp_prog);
if (xdp_prog) {
@@ -1190,6 +1268,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
xdp_buff_clear_frags_flag(xdp);
} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
+ ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
break;
}
if (++ntc == cnt)
@@ -1199,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
if (ice_is_non_eop(rx_ring, rx_desc))
continue;
- ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
- if (rx_buf->act == ICE_XDP_PASS)
+ ice_get_pgcnts(rx_ring);
+ xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
+ if (xdp_verdict == ICE_XDP_PASS)
goto construct_skb;
total_rx_bytes += xdp_get_buff_len(xdp);
total_rx_pkts++;
- xdp->data = NULL;
- rx_ring->first_desc = ntc;
- rx_ring->nr_frags = 0;
+ ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
continue;
construct_skb:
if (likely(ice_ring_uses_build_skb(rx_ring)))
@@ -1217,18 +1296,12 @@ construct_skb:
/* exit if we failed to retrieve a buffer */
if (!skb) {
rx_ring->ring_stats->rx_stats.alloc_page_failed++;
- rx_buf->act = ICE_XDP_CONSUMED;
- if (unlikely(xdp_buff_has_frags(xdp)))
- ice_set_rx_bufs_act(xdp, rx_ring,
- ICE_XDP_CONSUMED);
- xdp->data = NULL;
- rx_ring->first_desc = ntc;
- rx_ring->nr_frags = 0;
- break;
+ xdp_verdict = ICE_XDP_CONSUMED;
}
- xdp->data = NULL;
- rx_ring->first_desc = ntc;
- rx_ring->nr_frags = 0;
+ ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
+ if (!skb)
+ break;
stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
@@ -1257,23 +1330,6 @@ construct_skb:
total_rx_pkts++;
}
- first = rx_ring->first_desc;
- while (cached_ntc != first) {
- struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc];
-
- if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) {
- ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
- xdp_xmit |= buf->act;
- } else if (buf->act & ICE_XDP_CONSUMED) {
- buf->pagecnt_bias++;
- } else if (buf->act == ICE_XDP_PASS) {
- ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
- }
-
- ice_put_rx_buf(rx_ring, buf);
- if (++cached_ntc >= cnt)
- cached_ntc = 0;
- }
rx_ring->next_to_clean = ntc;
/* return up to cleaned_count buffers to hardware */
failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index cb347c852ba9..806bce701df3 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -201,7 +201,6 @@ struct ice_rx_buf {
struct page *page;
unsigned int page_offset;
unsigned int pgcnt;
- unsigned int act;
unsigned int pagecnt_bias;
};
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 79f960c6680d..6cf32b404127 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -6,49 +6,6 @@
#include "ice.h"
/**
- * ice_set_rx_bufs_act - propagate Rx buffer action to frags
- * @xdp: XDP buffer representing frame (linear and frags part)
- * @rx_ring: Rx ring struct
- * act: action to store onto Rx buffers related to XDP buffer parts
- *
- * Set action that should be taken before putting Rx buffer from first frag
- * to the last.
- */
-static inline void
-ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
- const unsigned int act)
-{
- u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
- u32 nr_frags = rx_ring->nr_frags + 1;
- u32 idx = rx_ring->first_desc;
- u32 cnt = rx_ring->count;
- struct ice_rx_buf *buf;
-
- for (int i = 0; i < nr_frags; i++) {
- buf = &rx_ring->rx_buf[idx];
- buf->act = act;
-
- if (++idx == cnt)
- idx = 0;
- }
-
- /* adjust pagecnt_bias on frags freed by XDP prog */
- if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
- u32 delta = rx_ring->nr_frags - sinfo_frags;
-
- while (delta) {
- if (idx == 0)
- idx = cnt - 1;
- else
- idx--;
- buf = &rx_ring->rx_buf[idx];
- buf->pagecnt_bias--;
- delta--;
- }
- }
-}
-
-/**
* ice_test_staterr - tests bits in Rx descriptor status and error fields
* @status_err_n: Rx descriptor status_error0 or status_error1 bits
* @stat_err_bits: value to mask
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d04543e5697b..b34ebb916b89 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2424,6 +2424,11 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
u32 chan = 0;
u8 qmode = 0;
+ if (rxfifosz == 0)
+ rxfifosz = priv->dma_cap.rx_fifo_size;
+ if (txfifosz == 0)
+ txfifosz = priv->dma_cap.tx_fifo_size;
+
/* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */
if (priv->plat->has_gmac4 || priv->plat->has_xgmac) {
rxfifosz /= rx_channels_count;
@@ -2892,6 +2897,11 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
int rxfifosz = priv->plat->rx_fifo_size;
int txfifosz = priv->plat->tx_fifo_size;
+ if (rxfifosz == 0)
+ rxfifosz = priv->dma_cap.rx_fifo_size;
+ if (txfifosz == 0)
+ txfifosz = priv->dma_cap.tx_fifo_size;
+
/* Adjust for real per queue fifo size */
rxfifosz /= rx_channels_count;
txfifosz /= tx_channels_count;
@@ -5868,6 +5878,9 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
const int mtu = new_mtu;
int ret;
+ if (txfifosz == 0)
+ txfifosz = priv->dma_cap.tx_fifo_size;
+
txfifosz /= priv->plat->tx_queues_to_use;
if (stmmac_xdp_is_enabled(priv) && new_mtu > ETH_DATA_LEN) {
@@ -7219,29 +7232,15 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
priv->plat->tx_queues_to_use = priv->dma_cap.number_tx_queues;
}
- if (!priv->plat->rx_fifo_size) {
- if (priv->dma_cap.rx_fifo_size) {
- priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size;
- } else {
- dev_err(priv->device, "Can't specify Rx FIFO size\n");
- return -ENODEV;
- }
- } else if (priv->dma_cap.rx_fifo_size &&
- priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) {
+ if (priv->dma_cap.rx_fifo_size &&
+ priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) {
dev_warn(priv->device,
"Rx FIFO size (%u) exceeds dma capability\n",
priv->plat->rx_fifo_size);
priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size;
}
- if (!priv->plat->tx_fifo_size) {
- if (priv->dma_cap.tx_fifo_size) {
- priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size;
- } else {
- dev_err(priv->device, "Can't specify Tx FIFO size\n");
- return -ENODEV;
- }
- } else if (priv->dma_cap.tx_fifo_size &&
- priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) {
+ if (priv->dma_cap.tx_fifo_size &&
+ priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) {
dev_warn(priv->device,
"Tx FIFO size (%u) exceeds dma capability\n",
priv->plat->tx_fifo_size);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 28624cca91f8..acf96f262488 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -574,18 +574,14 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
return ret;
}
-static inline bool tun_capable(struct tun_struct *tun)
+static inline bool tun_not_capable(struct tun_struct *tun)
{
const struct cred *cred = current_cred();
struct net *net = dev_net(tun->dev);
- if (ns_capable(net->user_ns, CAP_NET_ADMIN))
- return 1;
- if (uid_valid(tun->owner) && uid_eq(cred->euid, tun->owner))
- return 1;
- if (gid_valid(tun->group) && in_egroup_p(tun->group))
- return 1;
- return 0;
+ return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
+ (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
+ !ns_capable(net->user_ns, CAP_NET_ADMIN);
}
static void tun_set_real_num_queues(struct tun_struct *tun)
@@ -2782,7 +2778,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
!!(tun->flags & IFF_MULTI_QUEUE))
return -EINVAL;
- if (!tun_capable(tun))
+ if (tun_not_capable(tun))
return -EPERM;
err = security_tun_dev_open(tun->security);
if (err < 0)
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
index 1341374a4588..616ecc38d172 100644
--- a/drivers/net/vmxnet3/vmxnet3_xdp.c
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -28,7 +28,7 @@ vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter)
if (likely(cpu < tq_number))
tq = &adapter->tx_queue[cpu];
else
- tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)];
+ tq = &adapter->tx_queue[cpu % tq_number];
return tq;
}
@@ -124,6 +124,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
u32 buf_size;
u32 dw2;
+ spin_lock_irq(&tq->tx_lock);
dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
dw2 |= xdpf->len;
ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill;
@@ -134,6 +135,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) {
tq->stats.tx_ring_full++;
+ spin_unlock_irq(&tq->tx_lock);
return -ENOSPC;
}
@@ -142,8 +144,10 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
xdpf->data, buf_size,
DMA_TO_DEVICE);
- if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+ if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) {
+ spin_unlock_irq(&tq->tx_lock);
return -EFAULT;
+ }
tbi->map_type |= VMXNET3_MAP_SINGLE;
} else { /* XDP buffer from page pool */
page = virt_to_page(xdpf->data);
@@ -182,6 +186,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
dma_wmb();
gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
VMXNET3_TXD_GEN);
+ spin_unlock_irq(&tq->tx_lock);
/* No need to handle the case when tx_num_deferred doesn't reach
* threshold. Backend driver at hypervisor side will poll and reset
@@ -225,6 +230,7 @@ vmxnet3_xdp_xmit(struct net_device *dev,
{
struct vmxnet3_adapter *adapter = netdev_priv(dev);
struct vmxnet3_tx_queue *tq;
+ struct netdev_queue *nq;
int i;
if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)))
@@ -236,6 +242,9 @@ vmxnet3_xdp_xmit(struct net_device *dev,
if (tq->stopped)
return -ENETDOWN;
+ nq = netdev_get_tx_queue(adapter->netdev, tq->qid);
+
+ __netif_tx_lock(nq, smp_processor_id());
for (i = 0; i < n; i++) {
if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) {
tq->stats.xdp_xmit_err++;
@@ -243,6 +252,7 @@ vmxnet3_xdp_xmit(struct net_device *dev,
}
}
tq->stats.xdp_xmit += i;
+ __netif_tx_unlock(nq);
return i;
}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2a59034a5fa2..03bb584c62cf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2904,9 +2904,9 @@ struct pcpu_sw_netstats {
struct pcpu_dstats {
u64_stats_t rx_packets;
u64_stats_t rx_bytes;
- u64_stats_t rx_drops;
u64_stats_t tx_packets;
u64_stats_t tx_bytes;
+ u64_stats_t rx_drops;
u64_stats_t tx_drops;
struct u64_stats_sync syncp;
} __aligned(8 * sizeof(u64));
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d635c5b47eba..d48c657191cd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -851,7 +851,7 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
static inline void _bstats_update(struct gnet_stats_basic_sync *bstats,
- __u64 bytes, __u32 packets)
+ __u64 bytes, __u64 packets)
{
u64_stats_update_begin(&bstats->syncp);
u64_stats_add(&bstats->bytes, bytes);
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 2f119d18a061..cad50d91077e 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -219,6 +219,7 @@
EM(rxrpc_conn_get_conn_input, "GET inp-conn") \
EM(rxrpc_conn_get_idle, "GET idle ") \
EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \
+ EM(rxrpc_conn_get_poke_secured, "GET secured ") \
EM(rxrpc_conn_get_poke_timer, "GET poke ") \
EM(rxrpc_conn_get_service_conn, "GET svc-conn") \
EM(rxrpc_conn_new_client, "NEW client ") \
diff --git a/net/core/dev.c b/net/core/dev.c
index c0021cbd28fc..b91658e8aedb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11286,6 +11286,20 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
const struct net_device_ops *ops = dev->netdev_ops;
const struct net_device_core_stats __percpu *p;
+ /*
+ * IPv{4,6} and udp tunnels share common stat helpers and use
+ * different stat type (NETDEV_PCPU_STAT_TSTATS vs
+ * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent.
+ */
+ BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) !=
+ offsetof(struct pcpu_dstats, rx_bytes));
+ BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) !=
+ offsetof(struct pcpu_dstats, rx_packets));
+ BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) !=
+ offsetof(struct pcpu_dstats, tx_bytes));
+ BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) !=
+ offsetof(struct pcpu_dstats, tx_packets));
+
if (ops->ndo_get_stats64) {
memset(storage, 0, sizeof(*storage));
ops->ndo_get_stats64(dev, storage);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 34bee42e1247..7609ce2b2c5e 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -993,7 +993,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
return rc;
/* Nonzero ring with RSS only makes sense if NIC adds them together */
- if (cmd == ETHTOOL_SRXCLSRLINS && info.flow_type & FLOW_RSS &&
+ if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS &&
!ops->cap_rss_rxnfc_adds &&
ethtool_get_flow_spec_ring(info.fs.ring_cookie))
return -EINVAL;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 7cb106b590ab..58df9ad02ce8 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -107,6 +107,8 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev,
u32 total_size, indir_bytes;
u8 *rss_config;
+ data->no_key_fields = !dev->ethtool_ops->rxfh_per_ctx_key;
+
ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context);
if (!ctx)
return -ENOENT;
@@ -153,7 +155,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context)
return -EOPNOTSUPP;
- data->no_key_fields = !ops->rxfh_per_ctx_key;
return rss_prepare_ctx(request, dev, data, info);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c472c9a57cf6..a9bb9ce5438e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1141,9 +1141,9 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
- if (hlen + cork->gso_size > cork->fragsize) {
+ if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
kfree_skb(skb);
- return -EINVAL;
+ return -EMSGSIZE;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 28e5a89dc255..2c383c12a431 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -336,7 +336,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- struct dst_entry *dst = skb_dst(skb), *cache_dst;
+ struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
struct in6_addr orig_daddr;
struct ioam6_lwt *ilwt;
int err = -EINVAL;
@@ -407,13 +407,15 @@ do_encap:
cache_dst = ip6_route_output(net, NULL, &fl6);
if (cache_dst->error) {
err = cache_dst->error;
- dst_release(cache_dst);
goto drop;
}
- local_bh_disable();
- dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
- local_bh_enable();
+ /* cache only if we don't create a dst reference loop */
+ if (dst->lwtstate != cache_dst->lwtstate) {
+ local_bh_disable();
+ dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
+ local_bh_enable();
+ }
err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
if (unlikely(err))
@@ -426,8 +428,10 @@ do_encap:
return dst_output(net, sk, skb);
}
out:
+ dst_release(cache_dst);
return dst->lwtstate->orig_output(net, sk, skb);
drop:
+ dst_release(cache_dst);
kfree_skb(skb);
return err;
}
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 7ba22d2f2bfe..0ac4283acdf2 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -232,13 +232,15 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
err = dst->error;
- dst_release(dst);
goto drop;
}
- local_bh_disable();
- dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
- local_bh_enable();
+ /* cache only if we don't create a dst reference loop */
+ if (orig_dst->lwtstate != dst->lwtstate) {
+ local_bh_disable();
+ dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
+ local_bh_enable();
+ }
err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
if (unlikely(err))
@@ -251,6 +253,7 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
return dst_output(net, sk, skb);
drop:
+ dst_release(dst);
kfree_skb(skb);
return err;
}
@@ -269,8 +272,10 @@ static int rpl_input(struct sk_buff *skb)
local_bh_enable();
err = rpl_do_srh(skb, rlwt, dst);
- if (unlikely(err))
+ if (unlikely(err)) {
+ dst_release(dst);
goto drop;
+ }
if (!dst) {
ip6_route_input(skb);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 4bf937bfc263..33833b2064c0 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -482,8 +482,10 @@ static int seg6_input_core(struct net *net, struct sock *sk,
local_bh_enable();
err = seg6_do_srh(skb, dst);
- if (unlikely(err))
+ if (unlikely(err)) {
+ dst_release(dst);
goto drop;
+ }
if (!dst) {
ip6_route_input(skb);
@@ -571,13 +573,15 @@ static int seg6_output_core(struct net *net, struct sock *sk,
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
err = dst->error;
- dst_release(dst);
goto drop;
}
- local_bh_disable();
- dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
- local_bh_enable();
+ /* cache only if we don't create a dst reference loop */
+ if (orig_dst->lwtstate != dst->lwtstate) {
+ local_bh_disable();
+ dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+ local_bh_enable();
+ }
err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
if (unlikely(err))
@@ -593,6 +597,7 @@ static int seg6_output_core(struct net *net, struct sock *sk,
return dst_output(net, sk, skb);
drop:
+ dst_release(dst);
kfree_skb(skb);
return err;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6671daa67f4f..c6ea438b5c75 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1389,9 +1389,9 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
- if (hlen + cork->gso_size > cork->fragsize) {
+ if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
kfree_skb(skb);
- return -EINVAL;
+ return -EMSGSIZE;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 72c65d938a15..a4a668b88a8f 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -701,11 +701,9 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
struct net_device *dev;
ax25_address *source;
ax25_uid_assoc *user;
+ int err = -EINVAL;
int n;
- if (!sock_flag(sk, SOCK_ZAPPED))
- return -EINVAL;
-
if (addr_len != sizeof(struct sockaddr_rose) && addr_len != sizeof(struct full_sockaddr_rose))
return -EINVAL;
@@ -718,8 +716,15 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS)
return -EINVAL;
- if ((dev = rose_dev_get(&addr->srose_addr)) == NULL)
- return -EADDRNOTAVAIL;
+ lock_sock(sk);
+
+ if (!sock_flag(sk, SOCK_ZAPPED))
+ goto out_release;
+
+ err = -EADDRNOTAVAIL;
+ dev = rose_dev_get(&addr->srose_addr);
+ if (!dev)
+ goto out_release;
source = &addr->srose_call;
@@ -730,7 +735,8 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
} else {
if (ax25_uid_policy && !capable(CAP_NET_BIND_SERVICE)) {
dev_put(dev);
- return -EACCES;
+ err = -EACCES;
+ goto out_release;
}
rose->source_call = *source;
}
@@ -753,8 +759,10 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
rose_insert_socket(sk);
sock_reset_flag(sk, SOCK_ZAPPED);
-
- return 0;
+ err = 0;
+out_release:
+ release_sock(sk);
+ return err;
}
static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 718193df9d2e..f251845fe532 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -582,6 +582,7 @@ enum rxrpc_call_flag {
RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */
RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */
RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */
+ RXRPC_CALL_CONN_CHALLENGING, /* The connection is being challenged */
};
/*
@@ -602,7 +603,6 @@ enum rxrpc_call_state {
RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */
RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */
RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */
- RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */
RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */
RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */
RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 5a543c3f6fb0..c4c8b46a68c6 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -22,7 +22,6 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = {
[RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl",
[RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl",
[RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc",
- [RXRPC_CALL_SERVER_SECURING] = "SvSecure",
[RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq",
[RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq",
[RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl",
@@ -453,17 +452,16 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
call->cong_tstamp = skb->tstamp;
__set_bit(RXRPC_CALL_EXPOSED, &call->flags);
- rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
spin_lock(&conn->state_lock);
switch (conn->state) {
case RXRPC_CONN_SERVICE_UNSECURED:
case RXRPC_CONN_SERVICE_CHALLENGING:
- rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
+ __set_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags);
break;
case RXRPC_CONN_SERVICE:
- rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
break;
case RXRPC_CONN_ABORTED:
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 713e04394ceb..4d9c5e21ba78 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -228,10 +228,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn)
*/
static void rxrpc_call_is_secure(struct rxrpc_call *call)
{
- if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) {
- rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
+ if (call && __test_and_clear_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags))
rxrpc_notify_socket(call);
- }
}
/*
@@ -272,6 +270,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
* we've already received the packet, put it on the
* front of the queue.
*/
+ sp->conn = rxrpc_get_connection(conn, rxrpc_conn_get_poke_secured);
skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED;
rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured);
skb_queue_head(&conn->local->rx_queue, skb);
@@ -437,14 +436,16 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
rxrpc_abort_calls(conn);
- switch (skb->mark) {
- case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
- if (conn->state != RXRPC_CONN_SERVICE)
- break;
+ if (skb) {
+ switch (skb->mark) {
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ if (conn->state != RXRPC_CONN_SERVICE)
+ break;
- for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
- rxrpc_call_is_secure(conn->channels[loop].call);
- break;
+ for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
+ rxrpc_call_is_secure(conn->channels[loop].call);
+ break;
+ }
}
/* Process delayed ACKs whose time has come. */
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 7eba4d7d9a38..2f1fd1e2e7e4 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -67,6 +67,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet,
INIT_WORK(&conn->destructor, rxrpc_clean_up_connection);
INIT_LIST_HEAD(&conn->proc_link);
INIT_LIST_HEAD(&conn->link);
+ INIT_LIST_HEAD(&conn->attend_link);
mutex_init(&conn->security_lock);
mutex_init(&conn->tx_data_alloc_lock);
skb_queue_head_init(&conn->rx_queue);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 4974b5accafa..9047ba13bd31 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -448,11 +448,19 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
bool last = sp->hdr.flags & RXRPC_LAST_PACKET;
- skb_queue_tail(&call->recvmsg_queue, skb);
+ spin_lock_irq(&call->recvmsg_queue.lock);
+
+ __skb_queue_tail(&call->recvmsg_queue, skb);
rxrpc_input_update_ack_window(call, window, wtop);
trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq);
if (last)
+ /* Change the state inside the lock so that recvmsg syncs
+ * correctly with it and using sendmsg() to send a reply
+ * doesn't race.
+ */
rxrpc_end_rx_phase(call, sp->hdr.serial);
+
+ spin_unlock_irq(&call->recvmsg_queue.lock);
}
/*
@@ -657,7 +665,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb
rxrpc_propose_delay_ACK(call, sp->hdr.serial,
rxrpc_propose_ack_input_data);
}
- if (notify) {
+ if (notify && !test_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags)) {
trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial);
rxrpc_notify_socket(call);
}
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0e8da909d4f2..584397aba4a0 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -707,7 +707,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
} else {
switch (rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_AWAIT_CONN:
- case RXRPC_CALL_SERVER_SECURING:
+ case RXRPC_CALL_SERVER_RECV_REQUEST:
if (p.command == RXRPC_CMD_SEND_ABORT)
break;
fallthrough;
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index b50b2c2cc09b..e6bfd39ff339 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -40,6 +40,9 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
{
unsigned int prev_backlog;
+ if (unlikely(READ_ONCE(sch->limit) == 0))
+ return qdisc_drop(skb, sch, to_free);
+
if (likely(sch->q.qlen < READ_ONCE(sch->limit)))
return qdisc_enqueue_tail(skb, sch);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 71ec9986ed37..fdd79d3ccd8c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -749,9 +749,9 @@ deliver:
if (err != NET_XMIT_SUCCESS) {
if (net_xmit_drop_count(err))
qdisc_qstats_drop(sch);
- qdisc_tree_reduce_backlog(sch, 1, pkt_len);
sch->qstats.backlog -= pkt_len;
sch->q.qlen--;
+ qdisc_tree_reduce_backlog(sch, 1, pkt_len);
}
goto tfifo_dequeue;
}
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index ca8a7edff3dd..319aaa004c40 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -252,6 +252,7 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True):
try:
# this targets queue 4, which doesn't exist
ntuple2 = ethtool_create(cfg, "-N", flow)
+ defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}")
except CmdExitFailure:
pass
else:
@@ -259,7 +260,13 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True):
# change the table to target queues 0 and 2
ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0")
# ntuple rule therefore targets queues 1 and 3
- ntuple2 = ethtool_create(cfg, "-N", flow)
+ try:
+ ntuple2 = ethtool_create(cfg, "-N", flow)
+ except CmdExitFailure:
+ ksft_pr("Driver does not support rss + queue offset")
+ return
+
+ defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}")
# should replace existing filter
ksft_eq(ntuple, ntuple2)
_send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3),
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 414addef9a45..d240d02fa443 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -1302,7 +1302,7 @@ again:
return ret;
if (cfg_truncate > 0) {
- xdisconnect(fd);
+ shutdown(fd, SHUT_WR);
} else if (--cfg_repeat > 0) {
xdisconnect(fd);
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 3f2fca02fec5..36ff28af4b19 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -103,6 +103,19 @@ struct testcase testcases_v4[] = {
.r_num_mss = 1,
},
{
+ /* datalen <= MSS < gso_len: will fall back to no GSO */
+ .tlen = CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4 + 1,
+ .r_num_mss = 0,
+ .r_len_last = CONST_MSS_V4,
+ },
+ {
+ /* MSS < datalen < gso_len: fail */
+ .tlen = CONST_MSS_V4 + 1,
+ .gso_len = CONST_MSS_V4 + 2,
+ .tfail = true,
+ },
+ {
/* send a single MSS + 1B */
.tlen = CONST_MSS_V4 + 1,
.gso_len = CONST_MSS_V4,
@@ -206,6 +219,19 @@ struct testcase testcases_v6[] = {
.r_num_mss = 1,
},
{
+ /* datalen <= MSS < gso_len: will fall back to no GSO */
+ .tlen = CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6 + 1,
+ .r_num_mss = 0,
+ .r_len_last = CONST_MSS_V6,
+ },
+ {
+ /* MSS < datalen < gso_len: fail */
+ .tlen = CONST_MSS_V6 + 1,
+ .gso_len = CONST_MSS_V6 + 2,
+ .tfail = true
+ },
+ {
/* send a single MSS + 1B */
.tlen = CONST_MSS_V6 + 1,
.gso_len = CONST_MSS_V6,
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index d3dd65b05b5f..9044ac054167 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -94,5 +94,37 @@
"$TC qdisc del dev $DUMMY ingress",
"$IP addr del 10.10.10.10/24 dev $DUMMY"
]
- }
+ },
+ {
+ "id": "a4b9",
+ "name": "Test class qlen notification",
+ "category": [
+ "qdisc"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY root handle 1: drr",
+ "$TC filter add dev $DUMMY parent 1: basic classid 1:1",
+ "$TC class add dev $DUMMY parent 1: classid 1:1 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem",
+ "$TC qdisc add dev $DUMMY parent 2: handle 3: drr",
+ "$TC filter add dev $DUMMY parent 3: basic action drop",
+ "$TC class add dev $DUMMY parent 3: classid 3:1 drr",
+ "$TC class del dev $DUMMY classid 1:1",
+ "$TC class add dev $DUMMY parent 1: classid 1:1 drr"
+ ],
+ "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC qdisc ls dev $DUMMY",
+ "matchPattern": "drr 1: root",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY root handle 1: drr",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY"
+ ]
+ }
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
index ae3d286a32b2..6f20d033670d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
@@ -313,6 +313,29 @@
"matchPattern": "qdisc bfifo 1: root",
"matchCount": "0",
"teardown": [
+ ]
+ },
+ {
+ "id": "d774",
+ "name": "Check pfifo_head_drop qdisc enqueue behaviour when limit == 0",
+ "category": [
+ "qdisc",
+ "pfifo_head_drop"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY root handle 1: pfifo_head_drop limit 0",
+ "$IP link set dev $DUMMY up || true"
+ ],
+ "cmdUnderTest": "ping -c2 -W0.01 -I $DUMMY 10.10.10.1",
+ "expExitCode": "1",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+ "matchPattern": "dropped 2",
+ "matchCount": "1",
+ "teardown": [
]
}
]