F: include/linux/altera_jtaguart.h
AMAZON ETHERNET DRIVERS
-M: Netanel Belgazal <netanel@annapurnalabs.com>
-R: Saeed Bishara <saeed@annapurnalabs.com>
-R: Zorik Machulsky <zorik@annapurnalabs.com>
+M: Netanel Belgazal <netanel@amazon.com>
+R: Saeed Bishara <saeedb@amazon.com>
+R: Zorik Machulsky <zorik@amazon.com>
S: Supported
F: Documentation/networking/ena.txt
S: Supported
F: arch/x86/net/bpf_jit*
F: Documentation/networking/filter.txt
+F: Documentation/bpf/
F: include/linux/bpf*
F: include/linux/filter.h
F: include/uapi/linux/bpf*
F: net/sched/act_bpf.c
F: net/sched/cls_bpf.c
F: samples/bpf/
-F: tools/net/bpf*
+F: tools/bpf/
F: tools/testing/selftests/bpf/
BROADCOM B44 10/100 ETHERNET DRIVER
F: drivers/phy/broadcom/phy-brcm-usb*
BROADCOM GENET ETHERNET DRIVER
S: Supported
CA8210 IEEE-802.15.4 RADIO DRIVER
W: https://github.com/Cascoda/ca8210-linux.git
S: Maintained
F: drivers/auxdisplay/cfag12864bfb.c
F: include/linux/cfag12864b.h
-CFG80211 and NL80211
+802.11 (including CFG80211/NL80211)
W: http://wireless.kernel.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
S: Maintained
+F: net/wireless/
F: include/uapi/linux/nl80211.h
+F: include/linux/ieee80211.h
+F: include/net/wext.h
F: include/net/cfg80211.h
-F: net/wireless/*
-X: net/wireless/wext*
+F: include/net/iw_handler.h
+F: include/net/ieee80211_radiotap.h
+F: Documentation/driver-api/80211/cfg80211.rst
+F: Documentation/networking/regulatory.txt
CHAR and MISC DRIVERS
CISCO VIC ETHERNET NIC DRIVER
-M: Neel Patel <neepatel@cisco.com>
+M: Parvi Kaustubhi <pkaustub@cisco.com>
S: Supported
F: drivers/net/ethernet/cisco/enic/
S: Maintained
F: Documentation/cgroup-v1/cpusets.txt
F: include/linux/cpuset.h
-F: kernel/cpuset.c
+F: kernel/cgroup/cpuset.c
CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
INFINIBAND SUBSYSTEM
W: http://www.openfabrics.org/
Q: http://patchwork.kernel.org/project/linux-rdma/list/
F: include/linux/kgdb.h
F: kernel/debug/
- KMEMCHECK
- S: Maintained
- F: Documentation/dev-tools/kmemcheck.rst
- F: arch/x86/include/asm/kmemcheck.h
- F: arch/x86/mm/kmemcheck/
- F: include/linux/kmemcheck.h
- F: mm/kmemcheck.c
-
KMEMLEAK
S: Maintained
F: include/net/mac80211.h
F: net/mac80211/
F: drivers/net/wireless/mac80211_hwsim.[ch]
+F: Documentation/networking/mac80211_hwsim/README
MAILBOX API
S: Maintained
F: net/dsa/
F: include/net/dsa.h
+F: include/linux/dsa/
F: drivers/net/dsa/
NETWORKING [GENERAL]
F: include/uapi/linux/net.h
F: include/uapi/linux/netdevice.h
F: include/uapi/linux/net_namespace.h
-F: tools/net/
F: tools/testing/selftests/net/
+F: lib/net_utils.c
F: lib/random32.c
NETWORKING [IPSEC]
F: Documentation/devicetree/bindings/pci/pcie-kirin.txt
F: drivers/pci/dwc/pcie-kirin.c
+PCIE DRIVER FOR HISILICON STB
+S: Maintained
+F: Documentation/devicetree/bindings/pci/hisilicon-histb-pcie.txt
+F: drivers/pci/dwc/pcie-histb.c
+
PCIE DRIVER FOR MEDIATEK
F: Documentation/devicetree/bindings/pci/rockchip-pcie.txt
F: drivers/pci/host/pcie-rockchip.c
+PCI DRIVER FOR V3 SEMICONDUCTOR V360EPC
+S: Maintained
+F: Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt
+F: drivers/pci/host/pci-v3-semi.c
+
PCIE DRIVER FOR ST SPEAR13XX
QLOGIC QL4xxx RDMA DRIVER
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git
S: Maintained
F: Documentation/rfkill.txt
+F: Documentation/ABI/stable/sysfs-class-rfkill
F: net/rfkill/
RHASHTABLE
S: Maintained
F: drivers/thunderbolt/
+F: include/linux/thunderbolt.h
+
+THUNDERBOLT NETWORK DRIVER
+S: Maintained
+F: drivers/net/thunderbolt.c
THUNDERX GPIO DRIVER
F: include/linux/virtio_vsock.h
F: include/uapi/linux/virtio_vsock.h
F: include/uapi/linux/vsockmon.h
+F: include/uapi/linux/vm_sockets_diag.h
+F: net/vmw_vsock/diag.c
F: net/vmw_vsock/af_vsock_tap.c
F: net/vmw_vsock/virtio_transport_common.c
F: net/vmw_vsock/virtio_transport.c
F: drivers/net/vsockmon.c
F: drivers/vhost/vsock.c
F: drivers/vhost/vsock.h
+F: tools/testing/vsock/
VIRTIO CONSOLE DRIVER
S: Supported
W: http://wireless.kernel.org/en/users/Drivers/wil6210
F: drivers/net/wireless/ath/wil6210/
-F: include/uapi/linux/wil6210_uapi.h
WIMAX STACK
module_param_named(cc_table_size, qib_cc_table_size, uint, S_IRUGO);
MODULE_PARM_DESC(cc_table_size, "Congestion control table entries 0 (CCA disabled - default), min = 128, max = 1984");
-static void verify_interrupt(unsigned long);
+static void verify_interrupt(struct timer_list *);
static struct idr qib_unit_table;
u32 qib_cpulist_count;
spin_lock_init(&ppd->cc_shadow_lock);
init_waitqueue_head(&ppd->state_wait);
- setup_timer(&ppd->symerr_clear_timer, qib_clear_symerror_on_linkup,
- (unsigned long)ppd);
+ timer_setup(&ppd->symerr_clear_timer, qib_clear_symerror_on_linkup, 0);
ppd->qib_wq = NULL;
ppd->ibport_data.pmastats =
qib_get_eeprom_info(dd);
/* setup time (don't start yet) to verify we got interrupt */
- setup_timer(&dd->intrchk_timer, verify_interrupt,
- (unsigned long)dd);
+ timer_setup(&dd->intrchk_timer, verify_interrupt, 0);
done:
return ret;
}
}
}
-static void verify_interrupt(unsigned long opaque)
+static void verify_interrupt(struct timer_list *t)
{
- struct qib_devdata *dd = (struct qib_devdata *) opaque;
+ struct qib_devdata *dd = from_timer(dd, t, intrchk_timer);
u64 int_counter;
if (!dd)
continue;
if (dd->flags & QIB_HAS_SEND_DMA)
ret = qib_setup_sdma(ppd);
- setup_timer(&ppd->hol_timer, qib_hol_event,
- (unsigned long)ppd);
+ timer_setup(&ppd->hol_timer, qib_hol_event, 0);
ppd->hol_state = QIB_HOL_UP;
}
struct qib_pportdata *ppd;
int pidx;
- if (dd->stats_timer.data) {
+ if (dd->stats_timer.function)
del_timer_sync(&dd->stats_timer);
- dd->stats_timer.data = 0;
- }
- if (dd->intrchk_timer.data) {
+ if (dd->intrchk_timer.function)
del_timer_sync(&dd->intrchk_timer);
- dd->intrchk_timer.data = 0;
- }
for (pidx = 0; pidx < dd->num_pports; ++pidx) {
ppd = dd->pport + pidx;
- if (ppd->hol_timer.data)
+ if (ppd->hol_timer.function)
del_timer_sync(&ppd->hol_timer);
- if (ppd->led_override_timer.data) {
+ if (ppd->led_override_timer.function) {
del_timer_sync(&ppd->led_override_timer);
atomic_set(&ppd->led_override_timer_active, 0);
}
- if (ppd->symerr_clear_timer.data)
+ if (ppd->symerr_clear_timer.function)
del_timer_sync(&ppd->symerr_clear_timer);
}
}
}
if (!rcd->rcvegrbuf_phys) {
rcd->rcvegrbuf_phys =
- kmalloc_node(chunk * sizeof(rcd->rcvegrbuf_phys[0]),
- GFP_KERNEL, rcd->node_id);
+ kmalloc_array_node(chunk,
+ sizeof(rcd->rcvegrbuf_phys[0]),
+ GFP_KERNEL, rcd->node_id);
if (!rcd->rcvegrbuf_phys)
goto bail_rcvegrbuf;
}
#include "vt.h"
#include "trace.h"
-static void rvt_rc_timeout(unsigned long arg);
+static void rvt_rc_timeout(struct timer_list *t);
/*
* Convert the AETH RNR timeout code into the number of microseconds.
rdi->qp_dev->qp_table_size = rdi->dparms.qp_table_size;
rdi->qp_dev->qp_table_bits = ilog2(rdi->dparms.qp_table_size);
rdi->qp_dev->qp_table =
- kmalloc_node(rdi->qp_dev->qp_table_size *
+ kmalloc_array_node(rdi->qp_dev->qp_table_size,
sizeof(*rdi->qp_dev->qp_table),
GFP_KERNEL, rdi->dparms.node);
if (!rdi->qp_dev->qp_table)
/* take qp out the hash and wait for it to be unused */
rvt_remove_qp(rdi, qp);
- wait_event(qp->wait, !atomic_read(&qp->refcount));
/* grab the lock b/c it was locked at call time */
spin_lock_irq(&qp->r_lock);
if (init_attr->port_num == 0 ||
init_attr->port_num > ibpd->device->phys_port_cnt)
return ERR_PTR(-EINVAL);
+ /* fall through */
case IB_QPT_UC:
case IB_QPT_RC:
case IB_QPT_UD:
goto bail_qp;
}
/* initialize timers needed for rc qp */
- setup_timer(&qp->s_timer, rvt_rc_timeout, (unsigned long)qp);
+ timer_setup(&qp->s_timer, rvt_rc_timeout, 0);
hrtimer_init(&qp->s_rnr_timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL);
qp->s_rnr_timer.function = rvt_rc_rnr_retry;
atomic_set(&qp->refcount, 0);
atomic_set(&qp->local_ops_pending, 0);
init_waitqueue_head(&qp->wait);
- init_timer(&qp->s_timer);
- qp->s_timer.data = (unsigned long)qp;
INIT_LIST_HEAD(&qp->rspwait);
qp->state = IB_QPS_RESET;
qp->s_wq = swq;
spin_unlock(&qp->s_hlock);
spin_unlock_irq(&qp->r_lock);
+ wait_event(qp->wait, !atomic_read(&qp->refcount));
/* qpn is now available for use again */
rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
/**
* This is called from s_timer for missing responses.
*/
-static void rvt_rc_timeout(unsigned long arg)
+static void rvt_rc_timeout(struct timer_list *t)
{
- struct rvt_qp *qp = (struct rvt_qp *)arg;
+ struct rvt_qp *qp = from_timer(qp, t, s_timer);
struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
unsigned long flags;
rc = ena_alloc_rx_page(rx_ring, rx_info,
- __GFP_COLD | GFP_ATOMIC | __GFP_COMP);
+ GFP_ATOMIC | __GFP_COMP);
if (unlikely(rc < 0)) {
netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev,
"failed to alloc buffer for rx queue %d\n",
#endif /* CONFIG_NET_POLL_CONTROLLER */
};
-static void ena_device_io_suspend(struct work_struct *work)
-{
- struct ena_adapter *adapter =
- container_of(work, struct ena_adapter, suspend_io_task);
- struct net_device *netdev = adapter->netdev;
-
- /* ena_napi_disable_all disables only the IO handling.
- * We are still subject to AENQ keep alive watchdog.
- */
- u64_stats_update_begin(&adapter->syncp);
- adapter->dev_stats.io_suspend++;
- u64_stats_update_begin(&adapter->syncp);
- ena_napi_disable_all(adapter);
- netif_tx_lock(netdev);
- netif_device_detach(netdev);
- netif_tx_unlock(netdev);
-}
-
-static void ena_device_io_resume(struct work_struct *work)
-{
- struct ena_adapter *adapter =
- container_of(work, struct ena_adapter, resume_io_task);
- struct net_device *netdev = adapter->netdev;
-
- u64_stats_update_begin(&adapter->syncp);
- adapter->dev_stats.io_resume++;
- u64_stats_update_end(&adapter->syncp);
-
- netif_device_attach(netdev);
- ena_napi_enable_all(adapter);
-}
-
static int ena_device_validate_params(struct ena_adapter *adapter,
struct ena_com_dev_get_features_ctx *get_feat_ctx)
{
return rc;
}
-static void ena_fw_reset_device(struct work_struct *work)
+static void ena_destroy_device(struct ena_adapter *adapter)
{
- struct ena_com_dev_get_features_ctx get_feat_ctx;
- struct ena_adapter *adapter =
- container_of(work, struct ena_adapter, reset_task);
struct net_device *netdev = adapter->netdev;
struct ena_com_dev *ena_dev = adapter->ena_dev;
- struct pci_dev *pdev = adapter->pdev;
- bool dev_up, wd_state;
- int rc;
-
- if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
- dev_err(&pdev->dev,
- "device reset schedule while reset bit is off\n");
- return;
- }
+ bool dev_up;
netif_carrier_off(netdev);
del_timer_sync(&adapter->timer_service);
- rtnl_lock();
-
dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
+ adapter->dev_up_before_reset = dev_up;
+
ena_com_set_admin_running_state(ena_dev, false);
- /* After calling ena_close the tx queues and the napi
- * are disabled so no one can interfere or touch the
- * data structures
- */
ena_close(netdev);
+ /* Before releasing the ENA resources, a device reset is required.
+ * (to prevent the device from accessing them).
+ * In case the reset flag is set and the device is up, ena_close
+ * already perform the reset, so it can be skipped.
+ */
+ if (!(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags) && dev_up))
+ ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason);
+
ena_free_mgmnt_irq(adapter);
ena_disable_msix(adapter);
ena_com_mmio_reg_read_request_destroy(ena_dev);
adapter->reset_reason = ENA_REGS_RESET_NORMAL;
+
clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+}
- /* Finish with the destroy part. Start the init part */
+static int ena_restore_device(struct ena_adapter *adapter)
+{
+ struct ena_com_dev_get_features_ctx get_feat_ctx;
+ struct ena_com_dev *ena_dev = adapter->ena_dev;
+ struct pci_dev *pdev = adapter->pdev;
+ bool wd_state;
+ int rc;
rc = ena_device_init(ena_dev, adapter->pdev, &get_feat_ctx, &wd_state);
if (rc) {
goto err_device_destroy;
}
/* If the interface was up before the reset bring it up */
- if (dev_up) {
+ if (adapter->dev_up_before_reset) {
rc = ena_up(adapter);
if (rc) {
dev_err(&pdev->dev, "Failed to create I/O queues\n");
}
mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
-
- rtnl_unlock();
-
dev_err(&pdev->dev, "Device reset completed successfully\n");
- return;
+ return rc;
err_disable_msix:
ena_free_mgmnt_irq(adapter);
ena_disable_msix(adapter);
err_device_destroy:
ena_com_admin_destroy(ena_dev);
err:
- rtnl_unlock();
-
clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
dev_err(&pdev->dev,
"Reset attempt failed. Can not reset the device\n");
+
+ return rc;
+}
+
+static void ena_fw_reset_device(struct work_struct *work)
+{
+ struct ena_adapter *adapter =
+ container_of(work, struct ena_adapter, reset_task);
+ struct pci_dev *pdev = adapter->pdev;
+
+ if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+ dev_err(&pdev->dev,
+ "device reset schedule while reset bit is off\n");
+ return;
+ }
+ rtnl_lock();
+ ena_destroy_device(adapter);
+ ena_restore_device(adapter);
+ rtnl_unlock();
}
static int check_missing_comp_in_queue(struct ena_adapter *adapter,
struct ena_tx_buffer *tx_buf;
unsigned long last_jiffies;
u32 missed_tx = 0;
- int i;
+ int i, rc = 0;
for (i = 0; i < tx_ring->ring_size; i++) {
tx_buf = &tx_ring->tx_buffer_info[i];
tx_buf->print_once = 1;
missed_tx++;
-
- if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
- netif_err(adapter, tx_err, adapter->netdev,
- "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
- missed_tx,
- adapter->missing_tx_completion_threshold);
- adapter->reset_reason =
- ENA_REGS_RESET_MISS_TX_CMPL;
- set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
- return -EIO;
- }
}
}
- return 0;
+ if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
+ netif_err(adapter, tx_err, adapter->netdev,
+ "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
+ missed_tx,
+ adapter->missing_tx_completion_threshold);
+ adapter->reset_reason =
+ ENA_REGS_RESET_MISS_TX_CMPL;
+ set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+ rc = -EIO;
+ }
+
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->tx_stats.missed_tx = missed_tx;
+ u64_stats_update_end(&tx_ring->syncp);
+
+ return rc;
}
static void check_for_missing_tx_completions(struct ena_adapter *adapter)
goto err_rss;
}
- INIT_WORK(&adapter->suspend_io_task, ena_device_io_suspend);
- INIT_WORK(&adapter->resume_io_task, ena_device_io_resume);
INIT_WORK(&adapter->reset_task, ena_fw_reset_device);
adapter->last_keep_alive_jiffies = jiffies;
err_worker_destroy:
ena_com_destroy_interrupt_moderation(ena_dev);
del_timer(&adapter->timer_service);
- cancel_work_sync(&adapter->suspend_io_task);
- cancel_work_sync(&adapter->resume_io_task);
err_netdev_destroy:
free_netdev(netdev);
err_device_destroy:
cancel_work_sync(&adapter->reset_task);
- cancel_work_sync(&adapter->suspend_io_task);
-
- cancel_work_sync(&adapter->resume_io_task);
-
/* Reset the device only if the device is running. */
if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags))
ena_com_dev_reset(ena_dev, adapter->reset_reason);
vfree(ena_dev);
}
+#ifdef CONFIG_PM
+/* ena_suspend - PM suspend callback
+ * @pdev: PCI device information struct
+ * @state:power state
+ */
+static int ena_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct ena_adapter *adapter = pci_get_drvdata(pdev);
+
+ u64_stats_update_begin(&adapter->syncp);
+ adapter->dev_stats.suspend++;
+ u64_stats_update_end(&adapter->syncp);
+
+ rtnl_lock();
+ if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+ dev_err(&pdev->dev,
+ "ignoring device reset request as the device is being suspended\n");
+ clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+ }
+ ena_destroy_device(adapter);
+ rtnl_unlock();
+ return 0;
+}
+
+/* ena_resume - PM resume callback
+ * @pdev: PCI device information struct
+ *
+ */
+static int ena_resume(struct pci_dev *pdev)
+{
+ struct ena_adapter *adapter = pci_get_drvdata(pdev);
+ int rc;
+
+ u64_stats_update_begin(&adapter->syncp);
+ adapter->dev_stats.resume++;
+ u64_stats_update_end(&adapter->syncp);
+
+ rtnl_lock();
+ rc = ena_restore_device(adapter);
+ rtnl_unlock();
+ return rc;
+}
+#endif
+
static struct pci_driver ena_pci_driver = {
.name = DRV_MODULE_NAME,
.id_table = ena_pci_tbl,
.probe = ena_probe,
.remove = ena_remove,
+#ifdef CONFIG_PM
+ .suspend = ena_suspend,
+ .resume = ena_resume,
+#endif
.sriov_configure = ena_sriov_configure,
};
ENA_ADMIN_NOTIFICATION);
switch (aenq_e->aenq_common_desc.syndrom) {
- case ENA_ADMIN_SUSPEND:
- /* Suspend just the IO queues.
- * We deliberately don't suspend admin so the timer and
- * the keep_alive events should remain.
- */
- queue_work(ena_wq, &adapter->suspend_io_task);
- break;
- case ENA_ADMIN_RESUME:
- queue_work(ena_wq, &adapter->resume_io_task);
- break;
case ENA_ADMIN_UPDATE_HINTS:
hints = (struct ena_admin_ena_hw_hints *)
(&aenq_e->inline_data_w4);
/* work queue for link status */
struct cavium_wq link_status_wq;
+ /* work queue to regularly send local time to octeon firmware */
+ struct cavium_wq sync_octeon_time_wq;
+
int netdev_uc_count;
};
struct sk_buff *skb;
struct octeon_skb_page_info *skb_pg_info;
- page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ page = alloc_page(GFP_ATOMIC);
if (unlikely(!page))
return NULL;
if (mlx4_en_prepare_rx_desc(priv, ring,
ring->actual_size,
- GFP_KERNEL | __GFP_COLD)) {
+ GFP_KERNEL)) {
if (ring->actual_size < MLX4_EN_MIN_RX_SIZE) {
en_err(priv, "Failed to allocate enough rx buffers\n");
return -ENOMEM;
DEF_RX_RINGS));
num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS :
- min_t(int, num_of_eqs,
- netif_get_num_default_rss_queues());
+ min_t(int, num_of_eqs, num_online_cpus());
mdev->profile.prof[i].rx_ring_num =
rounddown_pow_of_two(num_rx_rings);
}
do {
if (mlx4_en_prepare_rx_desc(priv, ring,
ring->prod & ring->size_mask,
- GFP_ATOMIC | __GFP_COLD |
- __GFP_MEMALLOC))
+ GFP_ATOMIC | __GFP_MEMALLOC))
break;
ring->prod++;
} while (likely(--missing));
xdp.data_hard_start = va - frags[0].page_offset;
xdp.data = va;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + length;
orig_data = xdp.data;
case XDP_PASS:
break;
case XDP_TX:
- if (likely(!mlx4_en_xmit_frame(ring, frags, dev,
+ if (likely(!mlx4_en_xmit_frame(ring, frags, priv,
length, cq_ring,
&doorbell_pending))) {
frags[0].page = NULL;
return timed_out ? -EIO : 0;
}
-static void nfp_net_reconfig_timer(unsigned long data)
+static void nfp_net_reconfig_timer(struct timer_list *t)
{
- struct nfp_net *nn = (void *)data;
+ struct nfp_net *nn = from_timer(nn, t, reconfig_timer);
spin_lock_bh(&nn->reconfig_lock);
} else {
struct page *page;
- page = alloc_page(GFP_KERNEL | __GFP_COLD);
+ page = alloc_page(GFP_KERNEL);
frag = page ? page_address(page) : NULL;
}
if (!frag) {
if (!dp->xdp_prog) {
frag = napi_alloc_frag(dp->fl_bufsz);
+ if (unlikely(!frag))
+ return NULL;
} else {
struct page *page;
- page = alloc_page(GFP_ATOMIC);
- frag = page ? page_address(page) : NULL;
- }
- if (!frag) {
- nn_dp_warn(dp, "Failed to alloc receive page frag\n");
- return NULL;
+ page = dev_alloc_page();
+ if (unlikely(!page))
+ return NULL;
+ frag = page_address(page);
}
*dma_addr = nfp_net_dma_map_rx(dp, frag);
{
u64_stats_update_begin(&r_vec->rx_sync);
r_vec->rx_drops++;
+ /* If we have both skb and rxbuf the replacement buffer allocation
+ * must have failed, count this as an alloc failure.
+ */
+ if (skb && rxbuf)
+ r_vec->rx_replace_buf_alloc_fail++;
u64_stats_update_end(&r_vec->rx_sync);
/* skb is build based on the frag, free_skb() would free the frag
return true;
}
-static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start,
- unsigned int *off, unsigned int *len)
-{
- struct xdp_buff xdp;
- void *orig_data;
- int ret;
-
- xdp.data_hard_start = hard_start;
- xdp.data = data + *off;
- xdp.data_end = data + *off + *len;
-
- orig_data = xdp.data;
- ret = bpf_prog_run_xdp(prog, &xdp);
-
- *len -= xdp.data - orig_data;
- *off += xdp.data - orig_data;
-
- return ret;
-}
-
/**
* nfp_net_rx() - receive up to @budget packets on @rx_ring
* @rx_ring: RX ring to receive from
struct nfp_meta_parsed meta;
struct net_device *netdev;
dma_addr_t new_dma_addr;
+ u32 meta_len_xdp = 0;
void *new_frag;
idx = D_IDX(rx_ring, rx_ring->rd_p);
if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
dp->bpf_offload_xdp) && !meta.portid) {
+ void *orig_data = rxbuf->frag + pkt_off;
unsigned int dma_off;
- void *hard_start;
+ struct xdp_buff xdp;
int act;
- hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+ xdp.data_hard_start = rxbuf->frag + NFP_NET_RX_BUF_HEADROOM;
+ xdp.data = orig_data;
+ xdp.data_meta = orig_data;
+ xdp.data_end = orig_data + pkt_len;
+
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+ pkt_len -= xdp.data - orig_data;
+ pkt_off += xdp.data - orig_data;
- act = nfp_net_run_xdp(xdp_prog, rxbuf->frag, hard_start,
- &pkt_off, &pkt_len);
switch (act) {
case XDP_PASS:
+ meta_len_xdp = xdp.data - xdp.data_meta;
break;
case XDP_TX:
dma_off = pkt_off - NFP_NET_RX_BUF_HEADROOM;
if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
le16_to_cpu(rxd->rxd.vlan));
+ if (meta_len_xdp)
+ skb_metadata_set(skb, meta_len_xdp);
napi_gro_receive(&rx_ring->r_vec->napi, skb);
}
return 0;
}
-static int nfp_net_xdp(struct net_device *netdev, struct netdev_xdp *xdp)
+static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
{
struct nfp_net *nn = netdev_priv(netdev);
xdp->prog_attached = XDP_ATTACHED_HW;
xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
return 0;
+ case BPF_OFFLOAD_VERIFIER_PREP:
+ return nfp_app_bpf_verifier_prep(nn->app, nn, xdp);
+ case BPF_OFFLOAD_TRANSLATE:
+ return nfp_app_bpf_translate(nn->app, nn,
+ xdp->offload.prog);
+ case BPF_OFFLOAD_DESTROY:
+ return nfp_app_bpf_destroy(nn->app, nn,
+ xdp->offload.prog);
default:
return -EINVAL;
}
.ndo_get_phys_port_name = nfp_port_get_phys_port_name,
.ndo_udp_tunnel_add = nfp_net_add_vxlan_port,
.ndo_udp_tunnel_del = nfp_net_del_vxlan_port,
- .ndo_xdp = nfp_net_xdp,
+ .ndo_bpf = nfp_net_xdp,
};
/**
spin_lock_init(&nn->reconfig_lock);
spin_lock_init(&nn->link_status_lock);
- setup_timer(&nn->reconfig_timer,
- nfp_net_reconfig_timer, (unsigned long)nn);
+ timer_setup(&nn->reconfig_timer, nfp_net_reconfig_timer, 0);
return nn;
}
do {
page = ef4_reuse_page(rx_queue);
if (page == NULL) {
- page = alloc_pages(__GFP_COLD | __GFP_COMP |
+ page = alloc_pages(__GFP_COMP |
(atomic ? GFP_ATOMIC : GFP_KERNEL),
efx->rx_buffer_order);
if (unlikely(page == NULL))
ef4_nic_notify_rx_desc(rx_queue);
}
-void ef4_rx_slow_fill(unsigned long context)
+void ef4_rx_slow_fill(struct timer_list *t)
{
- struct ef4_rx_queue *rx_queue = (struct ef4_rx_queue *)context;
+ struct ef4_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
/* Post an event to cause NAPI to run and refill the queue */
ef4_nic_generate_fill_event(rx_queue);
do {
page = efx_reuse_page(rx_queue);
if (page == NULL) {
- page = alloc_pages(__GFP_COLD | __GFP_COMP |
+ page = alloc_pages(__GFP_COMP |
(atomic ? GFP_ATOMIC : GFP_KERNEL),
efx->rx_buffer_order);
if (unlikely(page == NULL))
efx_nic_notify_rx_desc(rx_queue);
}
-void efx_rx_slow_fill(unsigned long context)
+void efx_rx_slow_fill(struct timer_list *t)
{
- struct efx_rx_queue *rx_queue = (struct efx_rx_queue *)context;
+ struct efx_rx_queue *rx_queue = from_timer(rx_queue, t, slow_fill);
/* Post an event to cause NAPI to run and refill the queue */
efx_nic_generate_fill_event(rx_queue);
sw_data[0] = (u32)bufptr;
} else {
/* Allocate a secondary receive queue entry */
- page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD);
+ page = alloc_page(GFP_ATOMIC | GFP_DMA);
if (unlikely(!page)) {
dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n");
goto fail;
/* setup tc must be called under rtnl lock */
ASSERT_RTNL();
- if (type != TC_SETUP_MQPRIO)
+ if (type != TC_SETUP_QDISC_MQPRIO)
return -EOPNOTSUPP;
mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/average.h>
+#include <linux/filter.h>
#include <net/route.h>
static int napi_weight = NAPI_POLL_WEIGHT;
return skb;
}
-static bool virtnet_xdp_xmit(struct virtnet_info *vi,
- struct receive_queue *rq,
- struct xdp_buff *xdp)
+static void virtnet_xdp_flush(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct send_queue *sq;
+ unsigned int qp;
+
+ qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+ sq = &vi->sq[qp];
+
+ virtqueue_kick(sq->vq);
+}
+
+static bool __virtnet_xdp_xmit(struct virtnet_info *vi,
+ struct xdp_buff *xdp)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
unsigned int len;
return false;
}
- virtqueue_kick(sq->vq);
return true;
}
+static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ bool sent = __virtnet_xdp_xmit(vi, xdp);
+
+ if (!sent)
+ return -ENOSPC;
+ return 0;
+}
+
static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
{
return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
struct virtnet_info *vi,
struct receive_queue *rq,
void *buf, void *ctx,
- unsigned int len)
+ unsigned int len,
+ bool *xdp_xmit)
{
struct sk_buff *skb;
struct bpf_prog *xdp_prog;
unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
struct page *page = virt_to_head_page(buf);
- unsigned int delta = 0;
+ unsigned int delta = 0, err;
struct page *xdp_page;
len -= vi->hdr_len;
xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len;
xdp.data = xdp.data_hard_start + xdp_headroom;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + len;
orig_data = xdp.data;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
delta = orig_data - xdp.data;
break;
case XDP_TX:
- if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+ if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
+ else
+ *xdp_xmit = true;
+ rcu_read_unlock();
+ goto xdp_xmit;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(dev, &xdp, xdp_prog);
+ if (!err)
+ *xdp_xmit = true;
rcu_read_unlock();
goto xdp_xmit;
default:
struct receive_queue *rq,
void *buf,
void *ctx,
- unsigned int len)
+ unsigned int len,
+ bool *xdp_xmit)
{
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
struct bpf_prog *xdp_prog;
unsigned int truesize;
unsigned int headroom = mergeable_ctx_to_headroom(ctx);
+ int err;
head_skb = NULL;
data = page_address(xdp_page) + offset;
xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len;
xdp.data = data + vi->hdr_len;
+ xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + (len - vi->hdr_len);
act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ if (act != XDP_PASS)
+ ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+
switch (act) {
case XDP_PASS:
/* recalculate offset to account for any header
put_page(page);
head_skb = page_to_skb(vi, rq, xdp_page,
offset, len, PAGE_SIZE);
- ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
return head_skb;
}
break;
case XDP_TX:
- if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+ if (unlikely(!__virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
- ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
+ else
+ *xdp_xmit = true;
if (unlikely(xdp_page != page))
goto err_xdp;
rcu_read_unlock();
goto xdp_xmit;
+ case XDP_REDIRECT:
+ err = xdp_do_redirect(dev, &xdp, xdp_prog);
+ if (!err)
+ *xdp_xmit = true;
+ rcu_read_unlock();
+ goto xdp_xmit;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
case XDP_DROP:
if (unlikely(xdp_page != page))
__free_pages(xdp_page, 0);
- ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
goto err_xdp;
}
}
}
static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
- void *buf, unsigned int len, void **ctx)
+ void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
}
if (vi->mergeable_rx_bufs)
- skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
+ skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
else if (vi->big_packets)
skb = receive_big(dev, vi, rq, buf, len);
else
- skb = receive_small(dev, vi, rq, buf, ctx, len);
+ skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
if (unlikely(!skb))
return 0;
int err;
bool oom;
- gfp |= __GFP_COLD;
do {
if (vi->mergeable_rx_bufs)
err = add_recvbuf_mergeable(vi, rq, gfp);
}
}
-static int virtnet_receive(struct receive_queue *rq, int budget)
+static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
{
struct virtnet_info *vi = rq->vq->vdev->priv;
unsigned int len, received = 0, bytes = 0;
while (received < budget &&
(buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
- bytes += receive_buf(vi, rq, buf, len, ctx);
+ bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
received++;
}
} else {
while (received < budget &&
(buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
- bytes += receive_buf(vi, rq, buf, len, NULL);
+ bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
received++;
}
}
struct receive_queue *rq =
container_of(napi, struct receive_queue, napi);
unsigned int received;
+ bool xdp_xmit = false;
virtnet_poll_cleantx(rq);
- received = virtnet_receive(rq, budget);
+ received = virtnet_receive(rq, budget, &xdp_xmit);
/* Out of packets? */
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
+ if (xdp_xmit)
+ xdp_do_flush_map();
+
return received;
}
return 0;
}
-static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp)
+static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
switch (xdp->command) {
case XDP_SETUP_PROG:
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = virtnet_netpoll,
#endif
- .ndo_xdp = virtnet_xdp,
+ .ndo_bpf = virtnet_xdp,
+ .ndo_xdp_xmit = virtnet_xdp_xmit,
+ .ndo_xdp_flush = virtnet_xdp_flush,
.ndo_features_check = passthru_features_check,
};
struct list_head fuse_conn_list;
DEFINE_MUTEX(fuse_mutex);
-static int set_global_limit(const char *val, struct kernel_param *kp);
+static int set_global_limit(const char *val, const struct kernel_param *kp);
unsigned max_user_bgreq;
module_param_call(max_user_bgreq, set_global_limit, param_get_uint,
*limit = (1 << 16) - 1;
}
-static int set_global_limit(const char *val, struct kernel_param *kp)
+static int set_global_limit(const char *val, const struct kernel_param *kp)
{
int rv;
int err;
fuse_inode_cachep = kmem_cache_create("fuse_inode",
- sizeof(struct fuse_inode), 0,
- SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT,
- fuse_inode_init_once);
+ sizeof(struct fuse_inode), 0,
+ SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT|SLAB_RECLAIM_ACCOUNT,
+ fuse_inode_init_once);
err = -ENOMEM;
if (!fuse_inode_cachep)
goto out;
*/
#define DLMFS_CAPABILITIES "bast stackglue"
static int param_set_dlmfs_capabilities(const char *val,
- struct kernel_param *kp)
+ const struct kernel_param *kp)
{
printk(KERN_ERR "%s: readonly parameter\n", kp->name);
return -EINVAL;
}
static int param_get_dlmfs_capabilities(char *buffer,
- struct kernel_param *kp)
+ const struct kernel_param *kp)
{
return strlcpy(buffer, DLMFS_CAPABILITIES,
strlen(DLMFS_CAPABILITIES) + 1);
{
unregister_filesystem(&dlmfs_fs_type);
- flush_workqueue(user_dlm_worker);
destroy_workqueue(user_dlm_worker);
/*
struct bpf_prog {
u16 pages; /* Number of allocated pages */
- kmemcheck_bitfield_begin(meta);
u16 jited:1, /* Is our filter JIT'ed? */
locked:1, /* Program image locked? */
gpl_compatible:1, /* Is filter GPL compatible? */
cb_access:1, /* Is control block accessed? */
dst_needed:1; /* Do we need dst entry? */
- kmemcheck_bitfield_end(meta);
enum bpf_prog_type type; /* Type of BPF program */
u32 len; /* Number of filter blocks */
u32 jited_len; /* Size of jited insns in bytes */
struct bpf_prog *prog;
};
-#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi)
+#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi)
#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
struct bpf_skb_data_end {
struct qdisc_skb_cb qdisc_cb;
+ void *data_meta;
void *data_end;
};
struct xdp_buff {
void *data;
void *data_end;
+ void *data_meta;
void *data_hard_start;
};
-/* compute the linear packet data range [data, data_end) which
- * will be accessed by cls_bpf, act_bpf and lwt programs
+/* Compute the linear packet data range [data, data_end) which
+ * will be accessed by various program types (cls_bpf, act_bpf,
+ * lwt, ...). Subsystems allowing direct data access must (!)
+ * ensure that cb[] area can be written to when BPF program is
+ * invoked (otherwise cb[] save/restore is necessary).
*/
-static inline void bpf_compute_data_end(struct sk_buff *skb)
+static inline void bpf_compute_data_pointers(struct sk_buff *skb)
{
struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb));
- cb->data_end = skb->data + skb_headlen(skb);
+ cb->data_meta = skb->data - skb_metadata_len(skb);
+ cb->data_end = skb->data + skb_headlen(skb);
}
static inline u8 *bpf_skb_cb(struct sk_buff *skb)
struct bpf_prog *prog);
void xdp_do_flush_map(void);
+/* Drivers not supporting XDP metadata can use this helper, which
+ * rejects any room expansion for metadata as a result.
+ */
+static __always_inline void
+xdp_set_data_meta_invalid(struct xdp_buff *xdp)
+{
+ xdp->data_meta = xdp->data + 1;
+}
+
+static __always_inline bool
+xdp_data_meta_unsupported(const struct xdp_buff *xdp)
+{
+ return unlikely(xdp->data_meta > xdp->data);
+}
+
void bpf_warn_invalid_xdp_action(u32 act);
-void bpf_warn_invalid_xdp_redirect(u32 ifindex);
struct sock *do_sk_redirect_map(struct sk_buff *skb);
#define _LINUX_SKBUFF_H
#include <linux/kernel.h>
- #include <linux/kmemcheck.h>
#include <linux/compiler.h>
#include <linux/time.h>
#include <linux/bug.h>
* the end of the header data, ie. at skb->end.
*/
struct skb_shared_info {
- unsigned short _unused;
- unsigned char nr_frags;
+ __u8 __unused;
+ __u8 meta_len;
+ __u8 nr_frags;
__u8 tx_flags;
unsigned short gso_size;
/* Warning: this field is not always filled in (UFO)! */
struct skb_shared_hwtstamps hwtstamps;
unsigned int gso_type;
u32 tskey;
- __be32 ip6_frag_id;
/*
* Warning : all fields before dataref are cleared in __alloc_skb()
* @nf_trace: netfilter packet trace flag
* @protocol: Packet protocol from driver
* @destructor: Destruct function
+ * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
* @_nfct: Associated connection, if any (with nfctinfo bits)
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @skb_iif: ifindex of device we arrived on
struct sk_buff *prev;
union {
- ktime_t tstamp;
- u64 skb_mstamp;
+ struct net_device *dev;
+ /* Some protocols might use this space to store information,
+ * while device pointer would be NULL.
+ * UDP receive path is one user.
+ */
+ unsigned long dev_scratch;
};
};
struct rb_node rbnode; /* used in netem & tcp stack */
struct sock *sk;
union {
- struct net_device *dev;
- /* Some protocols might use this space to store information,
- * while device pointer would be NULL.
- * UDP receive path is one user.
- */
- unsigned long dev_scratch;
+ ktime_t tstamp;
+ u64 skb_mstamp;
};
/*
* This is the control buffer. It is free to use for every
*/
char cb[48] __aligned(8);
- unsigned long _skb_refdst;
- void (*destructor)(struct sk_buff *skb);
+ union {
+ struct {
+ unsigned long _skb_refdst;
+ void (*destructor)(struct sk_buff *skb);
+ };
+ struct list_head tcp_tsorted_anchor;
+ };
+
#ifdef CONFIG_XFRM
struct sec_path *sp;
#endif
/* Following fields are _not_ copied in __copy_skb_header()
* Note that queue_mapping is here mostly to fill a hole.
*/
- kmemcheck_bitfield_begin(flags1);
__u16 queue_mapping;
/* if you move cloned around you also must adapt those constants */
head_frag:1,
xmit_more:1,
__unused:1; /* one bit hole */
- kmemcheck_bitfield_end(flags1);
/* fields enclosed in headers_start/headers_end are copied
* using a single memcpy() in __copy_skb_header()
__u8 remcsum_offload:1;
#ifdef CONFIG_NET_SWITCHDEV
__u8 offload_fwd_mark:1;
+ __u8 offload_mr_fwd_mark:1;
#endif
#ifdef CONFIG_NET_CLS_ACT
__u8 tc_skip_classify:1;
return 0;
}
-/**
- * skb_header_release - release reference to header
- * @skb: buffer to operate on
- *
- * Drop a reference to the header part of the buffer. This is done
- * by acquiring a payload reference. You must not read from the header
- * part of skb->data after this.
- * Note : Check if you can use __skb_header_release() instead.
- */
-static inline void skb_header_release(struct sk_buff *skb)
-{
- BUG_ON(skb->nohdr);
- skb->nohdr = 1;
- atomic_add(1 << SKB_DATAREF_SHIFT, &skb_shinfo(skb)->dataref);
-}
-
/**
* __skb_header_release - release reference to header
* @skb: buffer to operate on
- *
- * Variant of skb_header_release() assuming skb is private to caller.
- * We can avoid one atomic operation.
*/
static inline void __skb_header_release(struct sk_buff *skb)
{
* 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to
* code in gfp_to_alloc_flags that should be enforcing this.
*/
- gfp_mask |= __GFP_COLD | __GFP_COMP | __GFP_MEMALLOC;
+ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC;
return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
}
return __skb_grow(skb, len);
}
+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+#define skb_rb_first(root) rb_to_skb(rb_first(root))
+#define skb_rb_last(root) rb_to_skb(rb_last(root))
+#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode))
+#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode))
+
#define skb_queue_walk(queue, skb) \
for (skb = (queue)->next; \
skb != (struct sk_buff *)(queue); \
for (; skb != (struct sk_buff *)(queue); \
skb = skb->next)
+#define skb_rbtree_walk(skb, root) \
+ for (skb = skb_rb_first(root); skb != NULL; \
+ skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from(skb) \
+ for (; skb != NULL; \
+ skb = skb_rb_next(skb))
+
+#define skb_rbtree_walk_from_safe(skb, tmp) \
+ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \
+ skb = tmp)
+
#define skb_queue_walk_from_safe(queue, skb, tmp) \
for (tmp = skb->next; \
skb != (struct sk_buff *)(queue); \
return 0;
}
+static inline u8 skb_metadata_len(const struct sk_buff *skb)
+{
+ return skb_shinfo(skb)->meta_len;
+}
+
+static inline void *skb_metadata_end(const struct sk_buff *skb)
+{
+ return skb_mac_header(skb);
+}
+
+static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
+ const struct sk_buff *skb_b,
+ u8 meta_len)
+{
+ const void *a = skb_metadata_end(skb_a);
+ const void *b = skb_metadata_end(skb_b);
+ /* Using more efficient varaiant than plain call to memcmp(). */
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+ u64 diffs = 0;
+
+ switch (meta_len) {
+#define __it(x, op) (x -= sizeof(u##op))
+#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
+ case 32: diffs |= __it_diff(a, b, 64);
+ case 24: diffs |= __it_diff(a, b, 64);
+ case 16: diffs |= __it_diff(a, b, 64);
+ case 8: diffs |= __it_diff(a, b, 64);
+ break;
+ case 28: diffs |= __it_diff(a, b, 64);
+ case 20: diffs |= __it_diff(a, b, 64);
+ case 12: diffs |= __it_diff(a, b, 64);
+ case 4: diffs |= __it_diff(a, b, 32);
+ break;
+ }
+ return diffs;
+#else
+ return memcmp(a - meta_len, b - meta_len, meta_len);
+#endif
+}
+
+static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
+ const struct sk_buff *skb_b)
+{
+ u8 len_a = skb_metadata_len(skb_a);
+ u8 len_b = skb_metadata_len(skb_b);
+
+ if (!(len_a | len_b))
+ return false;
+
+ return len_a != len_b ?
+ true : __skb_metadata_differs(skb_a, skb_b, len_a);
+}
+
+static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len)
+{
+ skb_shinfo(skb)->meta_len = meta_len;
+}
+
+static inline void skb_metadata_clear(struct sk_buff *skb)
+{
+ skb_metadata_set(skb, 0);
+}
+
struct sk_buff *skb_clone_sk(struct sk_buff *skb);
#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
#define _INET_SOCK_H
#include <linux/bitops.h>
- #include <linux/kmemcheck.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/jhash.h>
#define ireq_state req.__req_common.skc_state
#define ireq_family req.__req_common.skc_family
- kmemcheck_bitfield_begin(flags);
u16 snd_wscale : 4,
rcv_wscale : 4,
tstamp_ok : 1,
wscale_ok : 1,
ecn_ok : 1,
acked : 1,
- no_srccheck: 1;
+ no_srccheck: 1,
+ smc_ok : 1;
- kmemcheck_bitfield_end(flags);
u32 ir_mark;
union {
struct ip_options_rcu __rcu *ireq_opt;
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/cgroup-defs.h>
-
+#include <linux/rbtree.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include <linux/poll.h>
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
* @sk_gso_max_segs: Maximum number of GSO segments
+ * @sk_pacing_shift: scaling factor for TCP Small Queues
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
int sk_wmem_queued;
refcount_t sk_wmem_alloc;
unsigned long sk_tsq_flags;
- struct sk_buff *sk_send_head;
+ union {
+ struct sk_buff *sk_send_head;
+ struct rb_root tcp_rtx_queue;
+ };
struct sk_buff_head sk_write_queue;
__s32 sk_peek_off;
int sk_write_pending;
#define SK_FL_TYPE_MASK 0xffff0000
#endif
- kmemcheck_bitfield_begin(flags);
unsigned int sk_padding : 1,
sk_kern_sock : 1,
sk_no_check_tx : 1,
sk_protocol : 8,
sk_type : 16;
#define SK_PROTOCOL_MAX U8_MAX
- kmemcheck_bitfield_end(flags);
-
u16 sk_gso_max_segs;
+ u8 sk_pacing_shift;
unsigned long sk_lingertime;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
*
*/
#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \
- for (pos = rcu_dereference((head)->first); \
+ for (pos = rcu_dereference(hlist_first_rcu(head)); \
pos != NULL && \
({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \
- pos = rcu_dereference(pos->next))
+ pos = rcu_dereference(hlist_next_rcu(pos)))
static inline struct user_namespace *sk_user_ns(struct sock *sk)
{
*/
unsigned long *memory_pressure;
long *sysctl_mem;
+
int *sysctl_wmem;
int *sysctl_rmem;
+ u32 sysctl_wmem_offset;
+ u32 sysctl_rmem_offset;
+
int max_header;
bool no_autobind;
struct kmem_cache *slab;
unsigned int obj_size;
- int slab_flags;
+ slab_flags_t slab_flags;
struct percpu_counter *orphan_count;
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
+static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
+{
+ /* Does this proto have per netns sysctl_wmem ? */
+ if (proto->sysctl_wmem_offset)
+ return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+
+ return *proto->sysctl_wmem;
+}
+
+static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
+{
+ /* Does this proto have per netns sysctl_rmem ? */
+ if (proto->sysctl_rmem_offset)
+ return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+
+ return *proto->sysctl_rmem;
+}
+
#endif /* _SOCK_H */
Enable the userfaultfd() system call that allows to intercept and
handle page faults in userland.
-config PCI_QUIRKS
- default y
- bool "Enable PCI quirk workarounds" if EXPERT
- depends on PCI
- help
- This enables workarounds for various PCI chipset
- bugs/quirks. Disable this only if your target machine is
- unaffected by PCI quirks.
-
config MEMBARRIER
bool "Enable membarrier() system call" if EXPERT
default y
bool
default n
- config SLABINFO
- bool
- depends on PROC_FS
- depends on SLAB || SLUB_DEBUG
- default y
-
config RT_MUTEXES
bool
if (fp == NULL)
return NULL;
- kmemcheck_annotate_bitfield(fp, meta);
-
aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags);
if (aux == NULL) {
vfree(fp);
if (fp == NULL) {
__bpf_prog_uncharge(fp_old->aux->user, delta);
} else {
- kmemcheck_annotate_bitfield(fp, meta);
-
memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
fp->pages = pages;
fp->aux->prog = fp;
static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
{
+ const char *end = sym + KSYM_NAME_LEN;
+
BUILD_BUG_ON(sizeof("bpf_prog_") +
- sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN);
+ sizeof(prog->tag) * 2 +
+ /* name has been null terminated.
+ * We should need +1 for the '_' preceding
+ * the name. However, the null character
+ * is double counted between the name and the
+ * sizeof("bpf_prog_") above, so we omit
+ * the +1 here.
+ */
+ sizeof(prog->aux->name) > KSYM_NAME_LEN);
sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
- *sym = 0;
+ if (prog->aux->name[0])
+ snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
+ else
+ *sym = 0;
}
static __always_inline unsigned long
fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags, PAGE_KERNEL);
if (fp != NULL) {
- kmemcheck_annotate_bitfield(fp, meta);
-
/* aux->prog still points to the fp_other one, so
* when promoting the clone to the real program,
* this still needs to be adapted.
* valid program, which in this case would simply not
* be JITed, but falls back to the interpreter.
*/
- fp = bpf_int_jit_compile(fp);
+ if (!bpf_prog_is_dev_bound(fp->aux)) {
+ fp = bpf_int_jit_compile(fp);
+ } else {
+ *err = bpf_prog_offload_compile(fp);
+ if (*err)
+ return fp;
+ }
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
}
EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
+static unsigned int __bpf_prog_ret1(const void *ctx,
+ const struct bpf_insn *insn)
+{
+ return 1;
+}
+
+static struct bpf_prog_dummy {
+ struct bpf_prog prog;
+} dummy_bpf_prog = {
+ .prog = {
+ .bpf_func = __bpf_prog_ret1,
+ },
+};
+
+/* to avoid allocating empty bpf_prog_array for cgroups that
+ * don't have bpf program attached use one global 'empty_prog_array'
+ * It will not be modified the caller of bpf_prog_array_alloc()
+ * (since caller requested prog_cnt == 0)
+ * that pointer should be 'freed' by bpf_prog_array_free()
+ */
+static struct {
+ struct bpf_prog_array hdr;
+ struct bpf_prog *null_prog;
+} empty_prog_array = {
+ .null_prog = NULL,
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+{
+ if (prog_cnt)
+ return kzalloc(sizeof(struct bpf_prog_array) +
+ sizeof(struct bpf_prog *) * (prog_cnt + 1),
+ flags);
+
+ return &empty_prog_array.hdr;
+}
+
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+{
+ if (!progs ||
+ progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+ return;
+ kfree_rcu(progs, rcu);
+}
+
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+{
+ struct bpf_prog **prog;
+ u32 cnt = 0;
+
+ rcu_read_lock();
+ prog = rcu_dereference(progs)->progs;
+ for (; *prog; prog++)
+ cnt++;
+ rcu_read_unlock();
+ return cnt;
+}
+
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+ __u32 __user *prog_ids, u32 cnt)
+{
+ struct bpf_prog **prog;
+ u32 i = 0, id;
+
+ rcu_read_lock();
+ prog = rcu_dereference(progs)->progs;
+ for (; *prog; prog++) {
+ id = (*prog)->aux->id;
+ if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
+ rcu_read_unlock();
+ return -EFAULT;
+ }
+ if (++i == cnt) {
+ prog++;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ if (*prog)
+ return -ENOSPC;
+ return 0;
+}
+
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+ struct bpf_prog *old_prog)
+{
+ struct bpf_prog **prog = progs->progs;
+
+ for (; *prog; prog++)
+ if (*prog == old_prog) {
+ WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+ break;
+ }
+}
+
+int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
+ struct bpf_prog *exclude_prog,
+ struct bpf_prog *include_prog,
+ struct bpf_prog_array **new_array)
+{
+ int new_prog_cnt, carry_prog_cnt = 0;
+ struct bpf_prog **existing_prog;
+ struct bpf_prog_array *array;
+ int new_prog_idx = 0;
+
+ /* Figure out how many existing progs we need to carry over to
+ * the new array.
+ */
+ if (old_array) {
+ existing_prog = old_array->progs;
+ for (; *existing_prog; existing_prog++) {
+ if (*existing_prog != exclude_prog &&
+ *existing_prog != &dummy_bpf_prog.prog)
+ carry_prog_cnt++;
+ if (*existing_prog == include_prog)
+ return -EEXIST;
+ }
+ }
+
+ /* How many progs (not NULL) will be in the new array? */
+ new_prog_cnt = carry_prog_cnt;
+ if (include_prog)
+ new_prog_cnt += 1;
+
+ /* Do we have any prog (not NULL) in the new array? */
+ if (!new_prog_cnt) {
+ *new_array = NULL;
+ return 0;
+ }
+
+ /* +1 as the end of prog_array is marked with NULL */
+ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL);
+ if (!array)
+ return -ENOMEM;
+
+ /* Fill in the new prog array */
+ if (carry_prog_cnt) {
+ existing_prog = old_array->progs;
+ for (; *existing_prog; existing_prog++)
+ if (*existing_prog != exclude_prog &&
+ *existing_prog != &dummy_bpf_prog.prog)
+ array->progs[new_prog_idx++] = *existing_prog;
+ }
+ if (include_prog)
+ array->progs[new_prog_idx++] = include_prog;
+ array->progs[new_prog_idx] = NULL;
+ *new_array = array;
+ return 0;
+}
+
static void bpf_prog_free_deferred(struct work_struct *work)
{
struct bpf_prog_aux *aux;
aux = container_of(work, struct bpf_prog_aux, work);
+ if (bpf_prog_is_dev_bound(aux))
+ bpf_prog_offload_destroy(aux->prog);
bpf_jit_free(aux->prog);
}
EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
+/* These are only used within the BPF_SYSCALL code */
+#ifdef CONFIG_BPF_SYSCALL
EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type);
EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu);
+#endif
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
- #include <linux/kmemcheck.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/in.h>
shinfo = skb_shinfo(skb);
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
- kmemcheck_annotate_variable(shinfo->destructor_arg);
if (flags & SKB_ALLOC_FCLONE) {
struct sk_buff_fclones *fclones;
fclones = container_of(skb, struct sk_buff_fclones, skb1);
- kmemcheck_annotate_bitfield(&fclones->skb2, flags1);
skb->fclone = SKB_FCLONE_ORIG;
refcount_set(&fclones->fclone_ref, 1);
shinfo = skb_shinfo(skb);
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
- kmemcheck_annotate_variable(shinfo->destructor_arg);
return skb;
}
*/
void *netdev_alloc_frag(unsigned int fragsz)
{
- return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+ return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(netdev_alloc_frag);
void *napi_alloc_frag(unsigned int fragsz)
{
- return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+ return __napi_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(napi_alloc_frag);
if (!n)
return NULL;
- kmemcheck_annotate_bitfield(n, flags1);
n->fclone = SKB_FCLONE_UNAVAILABLE;
}
/* Set the tail pointer and length */
skb_put(n, skb->len);
- if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
copy_skb_header(n, skb);
return n;
BUG_ON(nhead < 0);
- if (skb_shared(skb))
- BUG();
+ BUG_ON(skb_shared(skb));
size = SKB_DATA_ALIGN(size);
skb->nohdr = 0;
atomic_set(&skb_shinfo(skb)->dataref, 1);
+ skb_metadata_clear(skb);
+
/* It is not generally safe to change skb->truesize.
* For the moment, we really care of rx path, or
* when skb is orphaned (not attached to a socket).
head_copy_off = newheadroom - head_copy_len;
/* Copy the linear header and data. */
- if (skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
- skb->len + head_copy_len))
- BUG();
+ BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off,
+ skb->len + head_copy_len));
copy_skb_header(n, skb);
return NULL;
}
- if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta))
- BUG();
+ BUG_ON(skb_copy_bits(skb, skb_headlen(skb),
+ skb_tail_pointer(skb), delta));
/* Optimization: no fragments, no reasons to preestimate
* size of pulled pages. Superb.
*/
void skb_rbtree_purge(struct rb_root *root)
{
- struct sk_buff *skb, *next;
+ struct rb_node *p = rb_first(root);
- rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode)
- kfree_skb(skb);
+ while (p) {
+ struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
- *root = RB_ROOT;
+ p = rb_next(p);
+ rb_erase(&skb->rbnode, root);
+ kfree_skb(skb);
+ }
}
/**
bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
bool *fragstolen, int *delta_truesize)
{
+ struct skb_shared_info *to_shinfo, *from_shinfo;
int i, delta, len = from->len;
*fragstolen = false;
return true;
}
- if (skb_has_frag_list(to) || skb_has_frag_list(from))
+ to_shinfo = skb_shinfo(to);
+ from_shinfo = skb_shinfo(from);
+ if (to_shinfo->frag_list || from_shinfo->frag_list)
return false;
if (skb_zcopy(to) || skb_zcopy(from))
return false;
struct page *page;
unsigned int offset;
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags >= MAX_SKB_FRAGS)
return false;
if (skb_head_is_locked(from))
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
- skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
+ skb_fill_page_desc(to, to_shinfo->nr_frags,
page, offset, skb_headlen(from));
*fragstolen = true;
} else {
- if (skb_shinfo(to)->nr_frags +
- skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
+ if (to_shinfo->nr_frags +
+ from_shinfo->nr_frags > MAX_SKB_FRAGS)
return false;
delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
WARN_ON_ONCE(delta < len);
- memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
- skb_shinfo(from)->frags,
- skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
- skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
+ memcpy(to_shinfo->frags + to_shinfo->nr_frags,
+ from_shinfo->frags,
+ from_shinfo->nr_frags * sizeof(skb_frag_t));
+ to_shinfo->nr_frags += from_shinfo->nr_frags;
if (!skb_cloned(from))
- skb_shinfo(from)->nr_frags = 0;
+ from_shinfo->nr_frags = 0;
/* if the skb is not cloned this does nothing
* since we set nr_frags to 0.
*/
- for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
- skb_frag_ref(from, i);
+ for (i = 0; i < from_shinfo->nr_frags; i++)
+ __skb_frag_ref(&from_shinfo->frags[i]);
to->truesize += delta;
to->len += len;
sk = kmalloc(prot->obj_size, priority);
if (sk != NULL) {
- kmemcheck_annotate_bitfield(sk, flags);
-
if (security_sk_alloc(sk, family, priority))
goto out_free;
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
- if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
+ if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot))
return 1;
} else { /* SK_MEM_SEND */
+ int wmem0 = sk_get_wmem0(sk, prot);
+
if (sk->sk_type == SOCK_STREAM) {
- if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
+ if (sk->sk_wmem_queued < wmem0)
return 1;
- } else if (refcount_read(&sk->sk_wmem_alloc) <
- prot->sysctl_wmem[0])
+ } else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) {
return 1;
+ }
}
if (sk_has_memory_pressure(sk)) {
sk_init_common(sk);
sk->sk_send_head = NULL;
- init_timer(&sk->sk_timer);
+ timer_setup(&sk->sk_timer, NULL, 0);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
+ sk->sk_pacing_shift = 10;
sk->sk_incoming_cpu = -1;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR);
-#ifdef CONFIG_NET_NS
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
__this_cpu_add(net->core.inuse->val[prot->inuse_idx], val);
}
core_initcall(net_inuse_init);
-#else
-static DEFINE_PER_CPU(struct prot_inuse, prot_inuse);
-
-void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
-{
- __this_cpu_add(prot_inuse.val[prot->inuse_idx], val);
-}
-EXPORT_SYMBOL_GPL(sock_prot_inuse_add);
-
-int sock_prot_inuse_get(struct net *net, struct proto *prot)
-{
- int cpu, idx = prot->inuse_idx;
- int res = 0;
-
- for_each_possible_cpu(cpu)
- res += per_cpu(prot_inuse, cpu).val[idx];
-
- return res >= 0 ? res : 0;
-}
-EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
-#endif
static void assign_proto_idx(struct proto *prot)
{
*/
#include <linux/kernel.h>
- #include <linux/kmemcheck.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <net/inet_hashtables.h>
}
EXPORT_SYMBOL_GPL(__inet_twsk_hashdance);
-static void tw_timer_handler(unsigned long data)
+static void tw_timer_handler(struct timer_list *t)
{
- struct inet_timewait_sock *tw = (struct inet_timewait_sock *)data;
+ struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
if (tw->tw_kill)
__NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
if (tw) {
const struct inet_sock *inet = inet_sk(sk);
- kmemcheck_annotate_bitfield(tw, flags);
-
tw->tw_dr = dr;
/* Give us an identity. */
tw->tw_daddr = inet->inet_daddr;
tw->tw_prot = sk->sk_prot_creator;
atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie));
twsk_net_set(tw, sock_net(sk));
- setup_pinned_timer(&tw->tw_timer, tw_timer_handler,
- (unsigned long)tw);
+ timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED);
/*
* Because we use RCU lookups, we should not set tw_refcnt
* to a non null value before everything is setup for this
#include <linux/ipsec.h>
#include <asm/unaligned.h>
#include <linux/errqueue.h>
+#include <trace/events/tcp.h>
+#include <linux/static_key.h>
-int sysctl_tcp_fack __read_mostly;
-int sysctl_tcp_max_reordering __read_mostly = 300;
-int sysctl_tcp_dsack __read_mostly = 1;
-int sysctl_tcp_app_win __read_mostly = 31;
-int sysctl_tcp_adv_win_scale __read_mostly = 1;
-EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-
-/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 1000;
-
-int sysctl_tcp_stdurg __read_mostly;
-int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
-int sysctl_tcp_frto __read_mostly = 2;
-int sysctl_tcp_min_rtt_wlen __read_mostly = 300;
-int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_early_retrans __read_mostly = 3;
-int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
sndmem *= nr_segs * per_mss;
if (sk->sk_sndbuf < sndmem)
- sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
+ sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
- int truesize = tcp_win_from_space(skb->truesize) >> 1;
- int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1;
+ int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
+ int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
/* Check #2. Increase window, if skb with such overhead
* will fit to rcvbuf in future.
*/
- if (tcp_win_from_space(skb->truesize) <= skb->len)
+ if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
incr = 2 * tp->advmss;
else
incr = __tcp_grow_window(sk, skb);
/* Dynamic Right Sizing (DRS) has 2 to 3 RTT latency
* Allow enough cushion so that sender is not limited by our window
*/
- if (sysctl_tcp_moderate_rcvbuf)
+ if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)
rcvmem <<= 2;
if (sk->sk_rcvbuf < rcvmem)
- sk->sk_rcvbuf = min(rcvmem, sysctl_tcp_rmem[2]);
+ sk->sk_rcvbuf = min(rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
}
/* 4. Try to fixup all. It is made immediately after connection enters
*/
void tcp_init_buffer_space(struct sock *sk)
{
+ int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
if (tp->window_clamp >= maxwin) {
tp->window_clamp = maxwin;
- if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss)
+ if (tcp_app_win && maxwin > 4 * tp->advmss)
tp->window_clamp = max(maxwin -
- (maxwin >> sysctl_tcp_app_win),
+ (maxwin >> tcp_app_win),
4 * tp->advmss);
}
/* Force reservation of one segment. */
- if (sysctl_tcp_app_win &&
+ if (tcp_app_win &&
tp->window_clamp > 2 * tp->advmss &&
tp->window_clamp + tp->advmss > maxwin)
tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct net *net = sock_net(sk);
icsk->icsk_ack.quick = 0;
- if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
+ if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
- sysctl_tcp_rmem[2]);
+ net->ipv4.sysctl_tcp_rmem[2]);
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sysctl_tcp_moderate_rcvbuf &&
+ if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvwin, rcvmem, rcvbuf;
}
rcvmem = SKB_TRUESIZE(tp->advmss + MAX_TCP_HEADER);
- while (tcp_win_from_space(rcvmem) < tp->advmss)
+ while (tcp_win_from_space(sk, rcvmem) < tp->advmss)
rcvmem += 128;
- rcvbuf = min(rcvwin / tp->advmss * rcvmem, sysctl_tcp_rmem[2]);
+ rcvbuf = min(rcvwin / tp->advmss * rcvmem,
+ sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
if (rcvbuf > sk->sk_rcvbuf) {
sk->sk_rcvbuf = rcvbuf;
tp->srtt_us = max(1U, srtt);
}
-/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
- * Note: TCP stack does not yet implement pacing.
- * FQ packet scheduler can be used to implement cheap but effective
- * TCP pacing, to smooth the burst on large writes when packets
- * in flight is significantly lower than cwnd (or rwin)
- */
-int sysctl_tcp_pacing_ss_ratio __read_mostly = 200;
-int sysctl_tcp_pacing_ca_ratio __read_mostly = 120;
-
static void tcp_update_pacing_rate(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
* end of slow start and should slow down.
*/
if (tp->snd_cwnd < tp->snd_ssthresh / 2)
- rate *= sysctl_tcp_pacing_ss_ratio;
+ rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
else
- rate *= sysctl_tcp_pacing_ca_ratio;
+ rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
rate *= max(tp->snd_cwnd, tp->packets_out);
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
-/*
- * Packet counting of FACK is based on in-order assumptions, therefore TCP
- * disables it when reordering is detected
- */
-void tcp_disable_fack(struct tcp_sock *tp)
-{
- /* RFC3517 uses different metric in lost marker => reset on change */
- if (tcp_is_fack(tp))
- tp->lost_skb_hint = NULL;
- tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED;
-}
-
/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
+ tp->rack.dsack_seen = 1;
}
-static void tcp_update_reordering(struct sock *sk, const int metric,
- const int ts)
+/* It's reordering when higher sequence was delivered (i.e. sacked) before
+ * some lower never-retransmitted sequence ("low_seq"). The maximum reordering
+ * distance is approximated in full-mss packet distance ("reordering").
+ */
+static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
+ const int ts)
{
struct tcp_sock *tp = tcp_sk(sk);
- int mib_idx;
+ const u32 mss = tp->mss_cache;
+ u32 fack, metric;
- if (WARN_ON_ONCE(metric < 0))
+ fack = tcp_highest_sack_seq(tp);
+ if (!before(low_seq, fack))
return;
- if (metric > tp->reordering) {
- tp->reordering = min(sysctl_tcp_max_reordering, metric);
-
+ metric = fack - low_seq;
+ if ((metric > tp->reordering * mss) && mss) {
#if FASTRETRANS_DEBUG > 1
pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
tp->reordering,
- tp->fackets_out,
+ 0,
tp->sacked_out,
tp->undo_marker ? tp->undo_retrans : 0);
#endif
- tcp_disable_fack(tp);
+ tp->reordering = min_t(u32, (metric + mss - 1) / mss,
+ sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
}
tp->rack.reord = 1;
-
/* This exciting event is worth to be remembered. 8) */
- if (ts)
- mib_idx = LINUX_MIB_TCPTSREORDER;
- else if (tcp_is_reno(tp))
- mib_idx = LINUX_MIB_TCPRENOREORDER;
- else if (tcp_is_fack(tp))
- mib_idx = LINUX_MIB_TCPFACKREORDER;
- else
- mib_idx = LINUX_MIB_TCPSACKREORDER;
-
- NET_INC_STATS(sock_net(sk), mib_idx);
+ NET_INC_STATS(sock_net(sk),
+ ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
}
/* This must be called before lost_out is incremented */
* 3. Loss detection event of two flavors:
* A. Scoreboard estimator decided the packet is lost.
* A'. Reno "three dupacks" marks head of queue lost.
- * A''. Its FACK modification, head until snd.fack is lost.
* B. SACK arrives sacking SND.NXT at the moment, when the
* segment was retransmitted.
* 4. D-SACK added new rule: D-SACK changes any tag to S.
}
struct tcp_sacktag_state {
- int reord;
- int fack_count;
+ u32 reord;
/* Timestamps for earliest and latest never-retransmitted segment
* that was SACKed. RTO needs the earliest RTT to stay conservative,
* but congestion control should still get an accurate delay signal.
u64 last_sackt;
struct rate_sample *rate;
int flag;
+ unsigned int mss_now;
};
/* Check if skb is fully within the SACK block. In presence of GSO skbs,
if (pkt_len >= skb->len && !in_sack)
return 0;
- err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
+ err = tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+ pkt_len, mss, GFP_ATOMIC);
if (err < 0)
return err;
}
u64 xmit_time)
{
struct tcp_sock *tp = tcp_sk(sk);
- int fack_count = state->fack_count;
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
if (tp->undo_marker && tp->undo_retrans > 0 &&
after(end_seq, tp->undo_marker))
tp->undo_retrans--;
- if (sacked & TCPCB_SACKED_ACKED)
- state->reord = min(fack_count, state->reord);
+ if ((sacked & TCPCB_SACKED_ACKED) &&
+ before(start_seq, state->reord))
+ state->reord = start_seq;
}
/* Nothing to do; acked frame is about to be dropped (was ACKed). */
* which was in hole. It is reordering.
*/
if (before(start_seq,
- tcp_highest_sack_seq(tp)))
- state->reord = min(fack_count,
- state->reord);
+ tcp_highest_sack_seq(tp)) &&
+ before(start_seq, state->reord))
+ state->reord = start_seq;
+
if (!after(end_seq, tp->high_seq))
state->flag |= FLAG_ORIG_SACK_ACKED;
if (state->first_sackt == 0)
tp->sacked_out += pcount;
tp->delivered += pcount; /* Out-of-order packets delivered */
- fack_count += pcount;
-
/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
- if (!tcp_is_fack(tp) && tp->lost_skb_hint &&
+ if (tp->lost_skb_hint &&
before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
tp->lost_cnt_hint += pcount;
-
- if (fack_count > tp->fackets_out)
- tp->fackets_out = fack_count;
}
/* D-SACK. We can detect redundant retransmission in S|R and plain R
/* Shift newly-SACKed bytes from this skb to the immediately previous
* already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
*/
-static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
+static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
+ struct sk_buff *skb,
struct tcp_sacktag_state *state,
unsigned int pcount, int shifted, int mss,
bool dup_sack)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */
u32 end_seq = start_seq + shifted; /* end of newly-SACKed */
if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp))
TCP_SKB_CB(prev)->tx.delivered_mstamp = 0;
- tcp_unlink_write_queue(skb, sk);
- sk_wmem_free_skb(sk, skb);
+ tcp_rtx_queue_unlink_and_free(skb, sk);
NET_INC_STATS(sock_net(sk), LINUX_MIB_SACKMERGED);
goto fallback;
/* Can only happen with delayed DSACK + discard craziness */
- if (unlikely(skb == tcp_write_queue_head(sk)))
+ prev = skb_rb_prev(skb);
+ if (!prev)
goto fallback;
- prev = tcp_write_queue_prev(sk, skb);
if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
goto fallback;
if (!skb_shift(prev, skb, len))
goto fallback;
- if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
+ if (!tcp_shifted_skb(sk, prev, skb, state, pcount, len, mss, dup_sack))
goto out;
/* Hole filled allows collapsing with the next as well, this is very
* useful when hole on every nth skb pattern happens
*/
- if (prev == tcp_write_queue_tail(sk))
+ skb = skb_rb_next(prev);
+ if (!skb)
goto out;
- skb = tcp_write_queue_next(sk, prev);
if (!skb_can_shift(skb) ||
- (skb == tcp_send_head(sk)) ||
((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) ||
(mss != tcp_skb_seglen(skb)))
goto out;
len = skb->len;
if (skb_shift(prev, skb, len)) {
pcount += tcp_skb_pcount(skb);
- tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
+ tcp_shifted_skb(sk, prev, skb, state, tcp_skb_pcount(skb),
+ len, mss, 0);
}
out:
- state->fack_count += pcount;
return prev;
noop:
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *tmp;
- tcp_for_write_queue_from(skb, sk) {
+ skb_rbtree_walk_from(skb) {
int in_sack = 0;
bool dup_sack = dup_sack_in;
- if (skb == tcp_send_head(sk))
- break;
-
/* queue is in-order => we can short-circuit the walk early */
if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
tcp_skb_pcount(skb),
skb->skb_mstamp);
tcp_rate_skb_delivered(sk, skb, state->rate);
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+ list_del_init(&skb->tcp_tsorted_anchor);
if (!before(TCP_SKB_CB(skb)->seq,
tcp_highest_sack_seq(tp)))
tcp_advance_highest_sack(sk, skb);
}
-
- state->fack_count += tcp_skb_pcount(skb);
}
return skb;
}
-/* Avoid all extra work that is being done by sacktag while walking in
- * a normal way
- */
+static struct sk_buff *tcp_sacktag_bsearch(struct sock *sk,
+ struct tcp_sacktag_state *state,
+ u32 seq)
+{
+ struct rb_node *parent, **p = &sk->tcp_rtx_queue.rb_node;
+ struct sk_buff *skb;
+
+ while (*p) {
+ parent = *p;
+ skb = rb_to_skb(parent);
+ if (before(seq, TCP_SKB_CB(skb)->seq)) {
+ p = &parent->rb_left;
+ continue;
+ }
+ if (!before(seq, TCP_SKB_CB(skb)->end_seq)) {
+ p = &parent->rb_right;
+ continue;
+ }
+ return skb;
+ }
+ return NULL;
+}
+
static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
struct tcp_sacktag_state *state,
u32 skip_to_seq)
{
- tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
-
- if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
- break;
+ if (skb && after(TCP_SKB_CB(skb)->seq, skip_to_seq))
+ return skb;
- state->fack_count += tcp_skb_pcount(skb);
- }
- return skb;
+ return tcp_sacktag_bsearch(sk, state, skip_to_seq);
}
static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
int first_sack_index;
state->flag = 0;
- state->reord = tp->packets_out;
+ state->reord = tp->snd_nxt;
- if (!tp->sacked_out) {
- if (WARN_ON(tp->fackets_out))
- tp->fackets_out = 0;
+ if (!tp->sacked_out)
tcp_highest_sack_reset(sk);
- }
found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
num_sacks, prior_snd_una);
}
}
- skb = tcp_write_queue_head(sk);
- state->fack_count = 0;
+ state->mss_now = tcp_current_mss(sk);
+ skb = NULL;
i = 0;
if (!tp->sacked_out) {
skb = tcp_highest_sack(sk);
if (!skb)
break;
- state->fack_count = tp->fackets_out;
cache++;
goto walk;
}
skb = tcp_highest_sack(sk);
if (!skb)
break;
- state->fack_count = tp->fackets_out;
}
skb = tcp_sacktag_skip(skb, sk, state, start_seq);
for (j = 0; j < used_sacks; j++)
tp->recv_sack_cache[i++] = sp[j];
- if ((state->reord < tp->fackets_out) &&
- ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker))
- tcp_update_reordering(sk, tp->fackets_out - state->reord, 0);
+ if (inet_csk(sk)->icsk_ca_state != TCP_CA_Loss || tp->undo_marker)
+ tcp_check_sack_reordering(sk, state->reord, 0);
tcp_verify_left_out(tp);
out:
static void tcp_check_reno_reordering(struct sock *sk, const int addend)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_limit_reno_sacked(tp))
- tcp_update_reordering(sk, tp->packets_out + addend, 0);
+
+ if (!tcp_limit_reno_sacked(tp))
+ return;
+
+ tp->reordering = min_t(u32, tp->packets_out + addend,
+ sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
}
/* Emulate SACKs for SACKless connection: account for a new dupack. */
tp->lost_out = 0;
tp->undo_marker = 0;
tp->undo_retrans = -1;
- tp->fackets_out = 0;
tp->sacked_out = 0;
}
if (tcp_is_reno(tp))
tcp_reset_reno_sack(tp);
- skb = tcp_write_queue_head(sk);
+ skb = tcp_rtx_queue_head(sk);
is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
if (is_reneg) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
- tp->fackets_out = 0;
}
tcp_clear_all_retrans_hints(tp);
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
-
+ skb_rbtree_walk_from(skb) {
mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
is_reneg);
if (mark_lost)
* falsely raise the receive window, which results in repeated
* timeouts and stop-and-go behavior.
*/
- tp->frto = sysctl_tcp_frto &&
+ tp->frto = net->ipv4.sysctl_tcp_frto &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
return false;
}
-static inline int tcp_fackets_out(const struct tcp_sock *tp)
-{
- return tcp_is_reno(tp) ? tp->sacked_out + 1 : tp->fackets_out;
-}
-
/* Heurestics to calculate number of duplicate ACKs. There's no dupACKs
* counter when SACK is enabled (without SACK, sacked_out is used for
* that purpose).
*
- * Instead, with FACK TCP uses fackets_out that includes both SACKed
- * segments up to the highest received SACK block so far and holes in
- * between them.
- *
* With reordering, holes may still be in flight, so RFC3517 recovery
* uses pure sacked_out (total number of SACKed segments) even though
* it violates the RFC that uses duplicate ACKs, often these are equal
*/
static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
{
- return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1;
+ return tp->sacked_out + 1;
}
-/* Linux NewReno/SACK/FACK/ECN state machine.
+/* Linux NewReno/SACK/ECN state machine.
* --------------------------------------
*
* "Open" Normal state, no dubious events, fast path.
* dynamically measured and adjusted. This is implemented in
* tcp_rack_mark_lost.
*
- * FACK (Disabled by default. Subsumbed by RACK):
- * It is the simplest heuristics. As soon as we decided
- * that something is lost, we decide that _all_ not SACKed
- * packets until the most forward SACK are lost. I.e.
- * lost_out = fackets_out - sacked_out and left_out = fackets_out.
- * It is absolutely correct estimate, if network does not reorder
- * packets. And it loses any connection to reality when reordering
- * takes place. We use FACK by default until reordering
- * is suspected on the path to this destination.
- *
* If the receiver does not support SACK:
*
* NewReno (RFC6582): in Recovery we assume that one segment
}
/* Detect loss in event "A" above by marking head of queue up as lost.
- * For FACK or non-SACK(Reno) senders, the first "packets" number of segments
+ * For non-SACK(Reno) senders, the first "packets" number of segments
* are considered lost. For RFC3517 SACK, a segment is considered lost if it
* has at least tp->reordering SACKed seqments above it; "packets" refers to
* the maximum SACKed segments to pass before reaching this limit.
const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq;
WARN_ON(packets > tp->packets_out);
- if (tp->lost_skb_hint) {
- skb = tp->lost_skb_hint;
- cnt = tp->lost_cnt_hint;
+ skb = tp->lost_skb_hint;
+ if (skb) {
/* Head already handled? */
- if (mark_head && skb != tcp_write_queue_head(sk))
+ if (mark_head && after(TCP_SKB_CB(skb)->seq, tp->snd_una))
return;
+ cnt = tp->lost_cnt_hint;
} else {
- skb = tcp_write_queue_head(sk);
+ skb = tcp_rtx_queue_head(sk);
cnt = 0;
}
- tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
+ skb_rbtree_walk_from(skb) {
/* TODO: do this better */
/* this is not the most efficient way to do this... */
tp->lost_skb_hint = skb;
break;
oldcnt = cnt;
- if (tcp_is_fack(tp) || tcp_is_reno(tp) ||
+ if (tcp_is_reno(tp) ||
(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
cnt += tcp_skb_pcount(skb);
if (cnt > packets) {
- if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
+ if (tcp_is_sack(tp) ||
(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
(oldcnt >= packets))
break;
/* If needed, chop off the prefix to mark as lost. */
lost = (packets - oldcnt) * mss;
if (lost < skb->len &&
- tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
+ tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
+ lost, mss, GFP_ATOMIC) < 0)
break;
cnt = packets;
}
if (tcp_is_reno(tp)) {
tcp_mark_head_lost(sk, 1, 1);
- } else if (tcp_is_fack(tp)) {
- int lost = tp->fackets_out - tp->reordering;
- if (lost <= 0)
- lost = 1;
- tcp_mark_head_lost(sk, lost, 0);
} else {
int sacked_upto = tp->sacked_out - tp->reordering;
if (sacked_upto >= 0)
if (tp->retrans_out)
return true;
- skb = tcp_write_queue_head(sk);
+ skb = tcp_rtx_queue_head(sk);
if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
return true;
return false;
}
-#if FASTRETRANS_DEBUG > 1
static void DBGUNDO(struct sock *sk, const char *msg)
{
+#if FASTRETRANS_DEBUG > 1
struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
tp->packets_out);
}
#endif
-}
-#else
-#define DBGUNDO(x...) do { } while (0)
#endif
+}
static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
if (unmark_loss) {
struct sk_buff *skb;
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
+ skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
}
tp->lost_out = 0;
mib_idx = LINUX_MIB_TCPFULLUNDO;
NET_INC_STATS(sock_net(sk), mib_idx);
+ } else if (tp->rack.reo_wnd_persist) {
+ tp->rack.reo_wnd_persist--;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && !tp->undo_retrans) {
+ tp->rack.reo_wnd_persist = min(TCP_RACK_RECOVERY_THRESH,
+ tp->rack.reo_wnd_persist + 1);
DBGUNDO(sk, "D-SACK");
tcp_undo_cwnd_reduction(sk, false);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
struct sk_buff *skb;
unsigned int mss = tcp_current_mss(sk);
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
+ skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
if (tcp_skb_seglen(skb) > mss &&
!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
* is updated in tcp_ack()). Otherwise fall back to
* the conventional recovery.
*/
- if (tcp_send_head(sk) &&
+ if (!tcp_write_queue_empty(sk) &&
after(tcp_wnd_end(tp), tp->snd_nxt)) {
*rexmit = REXMIT_NEW;
return;
}
/* Undo during fast recovery after partial ACK. */
-static bool tcp_try_undo_partial(struct sock *sk, const int acked)
+static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && tcp_packet_delayed(tp)) {
/* Plain luck! Hole if filled with delayed
- * packet, rather than with a retransmit.
+ * packet, rather than with a retransmit. Check reordering.
*/
- tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
+ tcp_check_sack_reordering(sk, prior_snd_una, 1);
/* We are getting evidence that the reordering degree is higher
* than we realized. If there are no retransmits out then we
struct tcp_sock *tp = tcp_sk(sk);
/* Use RACK to detect loss */
- if (sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+ if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
u32 prior_retrans = tp->retrans_out;
tcp_rack_mark_lost(sk);
}
}
+static bool tcp_force_fast_retransmit(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ return after(tcp_highest_sack_seq(tp),
+ tp->snd_una + tp->reordering * tp->mss_cache);
+}
+
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
-static void tcp_fastretrans_alert(struct sock *sk, const int acked,
+static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
bool is_dupack, int *ack_flag, int *rexmit)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int fast_rexmit = 0, flag = *ack_flag;
bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
- (tcp_fackets_out(tp) > tp->reordering));
+ tcp_force_fast_retransmit(sk));
- if (WARN_ON(!tp->packets_out && tp->sacked_out))
+ if (!tp->packets_out && tp->sacked_out)
tp->sacked_out = 0;
- if (WARN_ON(!tp->sacked_out && tp->fackets_out))
- tp->fackets_out = 0;
/* Now state machine starts.
* A. ECE, hence prohibit cwnd undoing, the reduction is required. */
if (tcp_is_reno(tp) && is_dupack)
tcp_add_reno_sack(sk);
} else {
- if (tcp_try_undo_partial(sk, acked))
+ if (tcp_try_undo_partial(sk, prior_snd_una))
return;
/* Partial ACK arrived. Force fast retransmit. */
do_lost = tcp_is_reno(tp) ||
- tcp_fackets_out(tp) > tp->reordering;
+ tcp_force_fast_retransmit(sk);
}
if (tcp_try_undo_dsack(sk)) {
tcp_try_keep_open(sk);
(*ack_flag & FLAG_LOST_RETRANS)))
return;
/* Change state if cwnd is undone or retransmits are lost */
+ /* fall through */
default:
if (tcp_is_reno(tp)) {
if (flag & FLAG_SND_UNA_ADVANCED)
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
{
+ u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
struct tcp_sock *tp = tcp_sk(sk);
- u32 wlen = sysctl_tcp_min_rtt_wlen * HZ;
minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32,
rtt_us ? : jiffies_to_usecs(1));
shinfo = skb_shinfo(skb);
if (!before(shinfo->tskey, prior_snd_una) &&
- before(shinfo->tskey, tcp_sk(sk)->snd_una))
- __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+ before(shinfo->tskey, tcp_sk(sk)->snd_una)) {
+ tcp_skb_tsorted_save(skb) {
+ __skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
+ } tcp_skb_tsorted_restore(skb);
+ }
}
/* Remove acknowledged frames from the retransmission queue. If our packet
* is before the ack sequence we can discard it as it's confirmed to have
* arrived at the other end.
*/
-static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
- u32 prior_snd_una, int *acked,
+static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
+ u32 prior_snd_una,
struct tcp_sacktag_state *sack)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
u64 first_ackt, last_ackt;
struct tcp_sock *tp = tcp_sk(sk);
u32 prior_sacked = tp->sacked_out;
- u32 reord = tp->packets_out;
+ u32 reord = tp->snd_nxt; /* lowest acked un-retx un-sacked seq */
+ struct sk_buff *skb, *next;
bool fully_acked = true;
long sack_rtt_us = -1L;
long seq_rtt_us = -1L;
long ca_rtt_us = -1L;
- struct sk_buff *skb;
u32 pkts_acked = 0;
u32 last_in_flight = 0;
bool rtt_update;
first_ackt = 0;
- while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
+ for (skb = skb_rb_first(&sk->tcp_rtx_queue); skb; skb = next) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+ const u32 start_seq = scb->seq;
u8 sacked = scb->sacked;
u32 acked_pcount;
break;
fully_acked = false;
} else {
- /* Speedup tcp_unlink_write_queue() and next loop */
- prefetchw(skb->next);
acked_pcount = tcp_skb_pcount(skb);
}
first_ackt = last_ackt;
last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
- reord = min(pkts_acked, reord);
+ if (before(start_seq, reord))
+ reord = start_seq;
if (!after(scb->end_seq, tp->high_seq))
flag |= FLAG_ORIG_SACK_ACKED;
}
if (!fully_acked)
break;
- tcp_unlink_write_queue(skb, sk);
- sk_wmem_free_skb(sk, skb);
+ next = skb_rb_next(skb);
if (unlikely(skb == tp->retransmit_skb_hint))
tp->retransmit_skb_hint = NULL;
if (unlikely(skb == tp->lost_skb_hint))
tp->lost_skb_hint = NULL;
+ tcp_rtx_queue_unlink_and_free(skb, sk);
}
if (!skb)
int delta;
/* Non-retransmitted hole got filled? That's reordering */
- if (reord < prior_fackets && reord <= tp->fackets_out)
- tcp_update_reordering(sk, tp->fackets_out - reord, 0);
+ if (before(reord, prior_fack))
+ tcp_check_sack_reordering(sk, reord, 0);
- delta = tcp_is_fack(tp) ? pkts_acked :
- prior_sacked - tp->sacked_out;
+ delta = prior_sacked - tp->sacked_out;
tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
}
-
- tp->fackets_out -= min(pkts_acked, tp->fackets_out);
-
} else if (skb && rtt_update && sack_rtt_us >= 0 &&
sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) {
/* Do not re-arm RTO if the sack RTT is measured from data sent
}
}
#endif
- *acked = pkts_acked;
return flag;
}
static void tcp_ack_probe(struct sock *sk)
{
- const struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct sk_buff *head = tcp_send_head(sk);
+ const struct tcp_sock *tp = tcp_sk(sk);
/* Was it a usable window open? */
-
- if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq, tcp_wnd_end(tp))) {
+ if (!head)
+ return;
+ if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
icsk->icsk_backoff = 0;
inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
/* Socket must be waked up by subsequent tcp_data_snd_check().
tp->pred_flags = 0;
tcp_fast_path_check(sk);
- if (tcp_send_head(sk))
+ if (!tcp_write_queue_empty(sk))
tcp_slow_start_after_idle_check(sk);
if (nwin > tp->max_window) {
if (*last_oow_ack_time) {
s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
- if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+ if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
static u32 challenge_timestamp;
static unsigned int challenge_count;
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
u32 count, now;
/* First check our per-socket dupack rate limit. */
- if (__tcp_oow_rate_limited(sock_net(sk),
+ if (__tcp_oow_rate_limited(net,
LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
&tp->last_oow_ack_time))
return;
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
if (now != challenge_timestamp) {
- u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+ u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ u32 half = (ack_limit + 1) >> 1;
challenge_timestamp = now;
- WRITE_ONCE(challenge_count, half +
- prandom_u32_max(sysctl_tcp_challenge_ack_limit));
+ WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
}
count = READ_ONCE(challenge_count);
if (count > 0) {
WRITE_ONCE(challenge_count, count - 1);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
+ NET_INC_STATS(net, LINUX_MIB_TCPCHALLENGEACK);
tcp_send_ack(sk);
}
}
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_fackets;
int prior_packets = tp->packets_out;
u32 delivered = tp->delivered;
u32 lost = tp->lost;
- int acked = 0; /* Number of packets newly acked */
int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */
+ u32 prior_fack;
sack_state.first_sackt = 0;
sack_state.rate = &rs;
- /* We very likely will need to access write queue head. */
- prefetchw(sk->sk_write_queue.next);
+ /* We very likely will need to access rtx queue. */
+ prefetch(sk->tcp_rtx_queue.rb_node);
/* If the ack is older than previous acks
* then we can probably ignore it.
icsk->icsk_retransmits = 0;
}
- prior_fackets = tp->fackets_out;
+ prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una;
rs.prior_in_flight = tcp_packets_in_flight(tp);
/* ts_recent update must be made after we are sure that the packet
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked,
- &sack_state);
+ flag |= tcp_clean_rtx_queue(sk, prior_fack, prior_snd_una, &sack_state);
+
+ tcp_rack_update_reo_wnd(sk, &rs);
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
if (tcp_ack_is_dubious(sk, flag)) {
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+ tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+ &rexmit);
}
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK)
- tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+ tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+ &rexmit);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
*/
- if (tcp_send_head(sk))
- tcp_ack_probe(sk);
+ tcp_ack_probe(sk);
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_state);
- tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+ tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag,
+ &rexmit);
tcp_xmit_recovery(sk, rexmit);
}
foc->exp = exp_opt;
}
+static void smc_parse_options(const struct tcphdr *th,
+ struct tcp_options_received *opt_rx,
+ const unsigned char *ptr,
+ int opsize)
+{
+#if IS_ENABLED(CONFIG_SMC)
+ if (static_branch_unlikely(&tcp_have_smc)) {
+ if (th->syn && !(opsize & 1) &&
+ opsize >= TCPOLEN_EXP_SMC_BASE &&
+ get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+ opt_rx->smc_ok = 1;
+ }
+#endif
+}
+
/* Look for tcp options. Normally only called on SYN and SYNACK packets.
* But, this can also be called on packets in the established flow when
* the fast version below fails.
tcp_parse_fastopen_option(opsize -
TCPOLEN_EXP_FASTOPEN_BASE,
ptr + 2, th->syn, foc, true);
+ else
+ smc_parse_options(th, opt_rx, ptr,
+ opsize);
break;
}
/* When we get a reset we do this. */
void tcp_reset(struct sock *sk)
{
+ trace_tcp_receive_reset(sk);
+
/* We want the right error as BSD sees it (and indeed as we do). */
switch (sk->sk_state) {
case TCP_SYN_SENT:
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
tp->rx_opt.num_sacks = num_sacks;
}
-enum tcp_queue {
- OOO_QUEUE,
- RCV_QUEUE,
-};
-
/**
* tcp_try_coalesce - try to merge skb to prior one
* @sk: socket
* Returns true if caller should free @from instead of queueing it
*/
static bool tcp_try_coalesce(struct sock *sk,
- enum tcp_queue dest,
struct sk_buff *to,
struct sk_buff *from,
bool *fragstolen)
if (TCP_SKB_CB(from)->has_rxtstamp) {
TCP_SKB_CB(to)->has_rxtstamp = true;
- if (dest == OOO_QUEUE)
- TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp;
- else
- to->tstamp = from->tstamp;
+ to->tstamp = from->tstamp;
}
return true;
p = rb_first(&tp->out_of_order_queue);
while (p) {
- skb = rb_entry(p, struct sk_buff, rbnode);
+ skb = rb_to_skb(p);
if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
break;
}
p = rb_next(p);
rb_erase(&skb->rbnode, &tp->out_of_order_queue);
- /* Replace tstamp which was stomped by rbnode */
- if (TCP_SKB_CB(skb)->has_rxtstamp)
- skb->tstamp = TCP_SKB_CB(skb)->swtstamp;
if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
SOCK_DEBUG(sk, "ofo packet was already received\n");
TCP_SKB_CB(skb)->end_seq);
tail = skb_peek_tail(&sk->sk_receive_queue);
- eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE,
- tail, skb, &fragstolen);
+ eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (!eaten)
static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct rb_node **p, *q, *parent;
+ struct rb_node **p, *parent;
struct sk_buff *skb1;
u32 seq, end_seq;
bool fragstolen;
return;
}
- /* Stash tstamp to avoid being stomped on by rbnode */
- if (TCP_SKB_CB(skb)->has_rxtstamp)
- TCP_SKB_CB(skb)->swtstamp = skb->tstamp;
-
/* Disable header prediction. */
tp->pred_flags = 0;
inet_csk_schedule_ack(sk);
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb,
+ if (tcp_try_coalesce(sk, tp->ooo_last_skb,
skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
parent = NULL;
while (*p) {
parent = *p;
- skb1 = rb_entry(parent, struct sk_buff, rbnode);
+ skb1 = rb_to_skb(parent);
if (before(seq, TCP_SKB_CB(skb1)->seq)) {
p = &parent->rb_left;
continue;
__kfree_skb(skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
+ } else if (tcp_try_coalesce(sk, skb1,
skb, &fragstolen)) {
goto coalesce_done;
}
merge_right:
/* Remove other segments covered by skb. */
- while ((q = rb_next(&skb->rbnode)) != NULL) {
- skb1 = rb_entry(q, struct sk_buff, rbnode);
-
+ while ((skb1 = skb_rb_next(skb)) != NULL) {
if (!after(end_seq, TCP_SKB_CB(skb1)->seq))
break;
if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
tcp_drop(sk, skb1);
}
/* If there is no skb after us, we are the last_skb ! */
- if (!q)
+ if (!skb1)
tp->ooo_last_skb = skb;
add_sack:
__skb_pull(skb, hdrlen);
eaten = (tail &&
- tcp_try_coalesce(sk, RCV_QUEUE, tail,
+ tcp_try_coalesce(sk, tail,
skb, fragstolen)) ? 1 : 0;
tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
if (!eaten) {
if (list)
return !skb_queue_is_last(list, skb) ? skb->next : NULL;
- return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode);
+ return skb_rb_next(skb);
}
static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb,
}
/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */
-static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
+void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
while (*p) {
parent = *p;
- skb1 = rb_entry(parent, struct sk_buff, rbnode);
+ skb1 = rb_to_skb(parent);
if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq))
p = &parent->rb_left;
else
* overlaps to the next one.
*/
if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
- (tcp_win_from_space(skb->truesize) > skb->len ||
+ (tcp_win_from_space(sk, skb->truesize) > skb->len ||
before(TCP_SKB_CB(skb)->seq, start))) {
end_of_skbs = false;
break;
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb, *head;
- struct rb_node *p;
u32 start, end;
- p = rb_first(&tp->out_of_order_queue);
- skb = rb_entry_safe(p, struct sk_buff, rbnode);
+ skb = skb_rb_first(&tp->out_of_order_queue);
new_range:
if (!skb) {
- p = rb_last(&tp->out_of_order_queue);
- /* Note: This is possible p is NULL here. We do not
- * use rb_entry_safe(), as ooo_last_skb is valid only
- * if rbtree is not empty.
- */
- tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode);
+ tp->ooo_last_skb = skb_rb_last(&tp->out_of_order_queue);
return;
}
start = TCP_SKB_CB(skb)->seq;
end = TCP_SKB_CB(skb)->end_seq;
for (head = skb;;) {
- skb = tcp_skb_next(skb, NULL);
+ skb = skb_rb_next(skb);
/* Range is terminated when we see a gap or when
* we are at the queue end.
do {
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
- tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
+ tcp_drop(sk, rb_to_skb(node));
sk_mem_reclaim(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
!tcp_under_memory_pressure(sk))
break;
node = prev;
} while (node);
- tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
+ tp->ooo_last_skb = rb_to_skb(prev);
/* Reset SACK state. A conforming SACK implementation will
* do the same at a timeout based retransmit. When a connection
struct tcp_sock *tp = tcp_sk(sk);
u32 ptr = ntohs(th->urg_ptr);
- if (ptr && !sysctl_tcp_stdurg)
+ if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
ptr--;
ptr += ntohl(th->seq);
security_inet_conn_established(sk, skb);
}
- /* Make sure socket is routed, for correct metrics. */
- icsk->icsk_af_ops->rebuild_header(sk);
-
- tcp_init_metrics(sk);
- tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
- tcp_init_congestion_control(sk);
+ tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
/* Prevent spurious tcp_cwnd_restart() on first data
* packet.
*/
tp->lsndtime = tcp_jiffies32;
- tcp_init_buffer_space(sk);
-
if (sock_flag(sk, SOCK_KEEPOPEN))
inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
struct tcp_fastopen_cookie *cookie)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
+ struct sk_buff *data = tp->syn_data ? tcp_rtx_queue_head(sk) : NULL;
u16 mss = tp->rx_opt.mss_clamp, try_exp = 0;
bool syn_drop = false;
tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp);
if (data) { /* Retransmit unacked data in SYN */
- tcp_for_write_queue_from(data, sk) {
- if (data == tcp_send_head(sk) ||
- __tcp_retransmit_skb(sk, data, 1))
+ skb_rbtree_walk_from(data) {
+ if (__tcp_retransmit_skb(sk, data, 1))
break;
}
tcp_rearm_rto(sk);
return false;
}
+static void smc_check_reset_syn(struct tcp_sock *tp)
+{
+#if IS_ENABLED(CONFIG_SMC)
+ if (static_branch_unlikely(&tcp_have_smc)) {
+ if (tp->syn_smc && !tp->rx_opt.smc_ok)
+ tp->syn_smc = 0;
+ }
+#endif
+}
+
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th)
{
tp->tcp_header_len = sizeof(struct tcphdr);
}
- if (tcp_is_sack(tp) && sysctl_tcp_fack)
- tcp_enable_fack(tp);
-
- tcp_mtup_init(sk);
tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
tcp_initialize_rcv_mss(sk);
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
+ smc_check_reset_syn(tp);
+
smp_mb();
tcp_finish_connect(sk, skb);
if (req) {
inet_csk(sk)->icsk_retransmits = 0;
reqsk_fastopen_remove(sk, req, false);
+ /* Re-arm the timer because data may have been sent out.
+ * This is similar to the regular data transmission case
+ * when new data has just been ack'ed.
+ *
+ * (TFO) - we could try to be more aggressive and
+ * retransmitting any data sooner based on when they
+ * are sent out.
+ */
+ tcp_rearm_rto(sk);
} else {
- /* Make sure socket is routed, for correct metrics. */
- icsk->icsk_af_ops->rebuild_header(sk);
- tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
- tcp_init_congestion_control(sk);
-
- tcp_mtup_init(sk);
+ tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
tp->copied_seq = tp->rcv_nxt;
- tcp_init_buffer_space(sk);
}
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
- if (req) {
- /* Re-arm the timer because data may have been sent out.
- * This is similar to the regular data transmission case
- * when new data has just been ack'ed.
- *
- * (TFO) - we could try to be more aggressive and
- * retransmitting any data sooner based on when they
- * are sent out.
- */
- tcp_rearm_rto(sk);
- } else
- tcp_init_metrics(sk);
-
if (!inet_csk(sk)->icsk_ca_ops->cong_control)
tcp_update_pacing_rate(sk);
case TCP_LAST_ACK:
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
break;
+ /* fall through */
case TCP_FIN_WAIT1:
case TCP_FIN_WAIT2:
/* RFC 793 says to queue data in these states,
ireq->ir_rmt_port = tcp_hdr(skb)->source;
ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
ireq->ir_mark = inet_request_mark(sk, skb);
+#if IS_ENABLED(CONFIG_SMC)
+ ireq->smc_ok = rx_opt->smc_ok;
+#endif
}
struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
if (req) {
struct inet_request_sock *ireq = inet_rsk(req);
- kmemcheck_annotate_bitfield(ireq, flags);
ireq->ireq_opt = NULL;
#if IS_ENABLED(CONFIG_IPV6)
ireq->pktopts = NULL;
tcp_openreq_init_rwin(req, sk, dst);
if (!want_cookie) {
tcp_reqsk_record_syn(sk, req, skb);
- fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc);
+ fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
}
if (fastopen_sk) {
af_ops->send_synack(fastopen_sk, dst, &fl, req,
projects / linux.git / commitdiff