[linux-next] LinuxNextTracking branch, master, updated. next-20220304

The following commit has been merged in the master branch: commit 80901bff812984624918d9d03f9286e3245ee9a5 Merge: 25bf4df4d18b4546a5821d77b5fac149a3a4961f b949c21fc23ecaccef89582f251e6281cad1f81e Author: Jakub Kicinski kuba@kernel.org Date: Thu Mar 3 11:55:12 2022 -0800

Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

net/batman-adv/hard-interface.c commit 690bb6fb64f5 ("batman-adv: Request iflink once in batadv-on-batadv check") commit 6ee3c393eeb7 ("batman-adv: Demote batadv-on-batadv skip error message") https://lore.kernel.org/all/20220302163049.101957-1-sw@simonwunderlich.de/

net/smc/af_smc.c commit 4d08b7b57ece ("net/smc: Fix cleanup when register ULP fails") commit 462791bbfa35 ("net/smc: add sysctl interface for SMC") https://lore.kernel.org/all/20220302112209.355def40@canb.auug.org.au/

Signed-off-by: Jakub Kicinski kuba@kernel.org

diff --combined MAINTAINERS index ceb907b773eb,d2b39f444abf..cb75c5d6d78b --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -2254,7 -2254,7 +2254,7 @@@ F: drivers/phy/mediatek ARM/Microchip (AT91) SoC support M: Nicolas Ferre nicolas.ferre@microchip.com M: Alexandre Belloni alexandre.belloni@bootlin.com - M: Ludovic Desroches ludovic.desroches@microchip.com + M: Claudiu Beznea claudiu.beznea@microchip.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported W: http://www.linux4sam.org @@@ -3527,8 -3527,6 +3527,8 @@@ F: net/sched/act_bpf. F: net/sched/cls_bpf.c F: samples/bpf/ F: scripts/bpf_doc.py +F: scripts/pahole-flags.sh +F: scripts/pahole-version.sh F: tools/bpf/ F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ @@@ -4915,7 -4913,8 +4915,8 @@@ F: kernel/cgroup/cpuset. CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG) M: Johannes Weiner hannes@cmpxchg.org M: Michal Hocko mhocko@kernel.org - M: Vladimir Davydov vdavydov.dev@gmail.com + M: Roman Gushchin roman.gushchin@linux.dev + M: Shakeel Butt shakeelb@google.com L: cgroups@vger.kernel.org L: linux-mm@kvack.org S: Maintained @@@ -7745,8 -7744,7 +7746,7 @@@ M: Qiang Zhao <qiang.zhao@nxp.com L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/soc/fsl/qe/ - F: include/soc/fsl/*qe*.h - F: include/soc/fsl/*ucc*.h + F: include/soc/fsl/qe/

FREESCALE QUICC ENGINE UCC ETHERNET DRIVER M: Li Yang leoyang.li@nxp.com @@@ -7777,6 -7775,7 +7777,7 @@@ F: Documentation/devicetree/bindings/mi F: Documentation/devicetree/bindings/soc/fsl/ F: drivers/soc/fsl/ F: include/linux/fsl/ + F: include/soc/fsl/

FREESCALE SOC FS_ENET DRIVER M: Pantelis Antoniou pantelis.antoniou@gmail.com @@@ -7931,12 -7930,6 +7932,12 @@@ L: platform-driver-x86@vger.kernel.or S: Maintained F: drivers/platform/x86/fujitsu-tablet.c

+FUNGIBLE ETHERNET DRIVERS +M: Dimitris Michailidis dmichail@fungible.com +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/fungible/ + FUSE: FILESYSTEM IN USERSPACE M: Miklos Szeredi miklos@szeredi.hu L: linux-fsdevel@vger.kernel.org @@@ -13706,7 -13699,7 +13707,7 @@@ F: scripts/nsdep NTB AMD DRIVER M: Sanjay R Mehta sanju.mehta@amd.com M: Shyam Sundar S K Shyam-sundar.S-k@amd.com - L: linux-ntb@googlegroups.com + L: ntb@lists.linux.dev S: Supported F: drivers/ntb/hw/amd/

@@@ -13714,7 -13707,7 +13715,7 @@@ NTB DRIVER COR M: Jon Mason jdmason@kudzu.us M: Dave Jiang dave.jiang@intel.com M: Allen Hubbe allenbh@gmail.com - L: linux-ntb@googlegroups.com + L: ntb@lists.linux.dev S: Supported W: https://github.com/jonmason/ntb/wiki T: git git://github.com/jonmason/ntb.git @@@ -13726,13 -13719,13 +13727,13 @@@ F: tools/testing/selftests/ntb

NTB IDT DRIVER M: Serge Semin fancer.lancer@gmail.com - L: linux-ntb@googlegroups.com + L: ntb@lists.linux.dev S: Supported F: drivers/ntb/hw/idt/

NTB INTEL DRIVER M: Dave Jiang dave.jiang@intel.com - L: linux-ntb@googlegroups.com + L: ntb@lists.linux.dev S: Supported W: https://github.com/davejiang/linux/wiki T: git https://github.com/davejiang/linux.git @@@ -15575,6 -15568,7 +15576,7 @@@ M: Iurii Zaikin <yzaikin@google.com L: linux-kernel@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Maintained + T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git sysctl-next F: fs/proc/proc_sysctl.c F: include/linux/sysctl.h F: kernel/sysctl-test.c @@@ -16377,7 -16371,8 +16379,7 @@@ M: Linus Walleij <linus.walleij@linaro. M: Alvin ��ipraga alsi@bang-olufsen.dk S: Maintained F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt -F: drivers/net/dsa/realtek-smi* -F: drivers/net/dsa/rtl83* +F: drivers/net/dsa/realtek/*

REALTEK WIRELESS DRIVER (rtlwifi family) M: Ping-Ke Shih pkshih@realtek.com @@@ -17767,8 -17762,10 +17769,10 @@@ M: David Rientjes <rientjes@google.com M: Joonsoo Kim iamjoonsoo.kim@lge.com M: Andrew Morton akpm@linux-foundation.org M: Vlastimil Babka vbabka@suse.cz + R: Roman Gushchin roman.gushchin@linux.dev L: linux-mm@kvack.org S: Maintained + T: git git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git F: include/linux/sl?b*.h F: mm/sl?b*

diff --combined drivers/net/ethernet/ibm/ibmvnic.c index 916aa91d5a6f,b423e94956f1..869a4fe17c7c --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@@ -60,7 -60,6 +60,7 @@@ #include <asm/hvcall.h> #include <linux/atomic.h> #include <asm/vio.h> +#include <asm/xive.h> #include <asm/iommu.h> #include <linux/uaccess.h> #include <asm/firmware.h> @@@ -2213,6 -2212,19 +2213,19 @@@ static const char *reset_reason_to_stri return "UNKNOWN"; }

+ /* + * Initialize the init_done completion and return code values. We + * can get a transport event just after registering the CRQ and the + * tasklet will use this to communicate the transport event. To ensure + * we don't miss the notification/error, initialize these _before_ + * regisering the CRQ. + */ + static inline void reinit_init_done(struct ibmvnic_adapter *adapter) + { + reinit_completion(&adapter->init_done); + adapter->init_done_rc = 0; + } + /* * do_reset returns zero if we are able to keep processing reset events, or * non-zero if we hit a fatal error and must halt. @@@ -2319,6 -2331,8 +2332,8 @@@ static int do_reset(struct ibmvnic_adap */ adapter->state = VNIC_PROBED;

+ reinit_init_done(adapter); + if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM) { rc = init_crq_queue(adapter); } else if (adapter->reset_reason == VNIC_RESET_MOBILITY) { @@@ -2462,7 -2476,8 +2477,8 @@@ static int do_hard_reset(struct ibmvnic */ adapter->state = VNIC_PROBED;

- reinit_completion(&adapter->init_done); + reinit_init_done(adapter); + rc = init_crq_queue(adapter); if (rc) { netdev_err(adapter->netdev, @@@ -2603,23 -2618,82 +2619,82 @@@ out static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_adapter *adapter; - bool saved_state = false; + unsigned int timeout = 5000; struct ibmvnic_rwi *tmprwi; + bool saved_state = false; struct ibmvnic_rwi *rwi; unsigned long flags; - u32 reset_state; + struct device *dev; + bool need_reset; int num_fails = 0; + u32 reset_state; int rc = 0;

adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset); + dev = &adapter->vdev->dev;

- if (test_and_set_bit_lock(0, &adapter->resetting)) { + /* Wait for ibmvnic_probe() to complete. If probe is taking too long + * or if another reset is in progress, defer work for now. If probe + * eventually fails it will flush and terminate our work. + * + * Three possibilities here: + * 1. Adpater being removed - just return + * 2. Timed out on probe or another reset in progress - delay the work + * 3. Completed probe - perform any resets in queue + */ + if (adapter->state == VNIC_PROBING && + !wait_for_completion_timeout(&adapter->probe_done, timeout)) { + dev_err(dev, "Reset thread timed out on probe"); queue_delayed_work(system_long_wq, &adapter->ibmvnic_delayed_reset, IBMVNIC_RESET_DELAY); return; }

+ /* adapter is done with probe (i.e state is never VNIC_PROBING now) */ + if (adapter->state == VNIC_REMOVING) + return; + + /* ->rwi_list is stable now (no one else is removing entries) */ + + /* ibmvnic_probe() may have purged the reset queue after we were + * scheduled to process a reset so there maybe no resets to process. + * Before setting the ->resetting bit though, we have to make sure + * that there is infact a reset to process. Otherwise we may race + * with ibmvnic_open() and end up leaving the vnic down: + * + * __ibmvnic_reset() ibmvnic_open() + * ----------------- -------------- + * + * set ->resetting bit + * find ->resetting bit is set + * set ->state to IBMVNIC_OPEN (i.e + * assume reset will open device) + * return + * find reset queue empty + * return + * + * Neither performed vnic login/open and vnic stays down + * + * If we hold the lock and conditionally set the bit, either we + * or ibmvnic_open() will complete the open. + */ + need_reset = false; + spin_lock(&adapter->rwi_lock); + if (!list_empty(&adapter->rwi_list)) { + if (test_and_set_bit_lock(0, &adapter->resetting)) { + queue_delayed_work(system_long_wq, + &adapter->ibmvnic_delayed_reset, + IBMVNIC_RESET_DELAY); + } else { + need_reset = true; + } + } + spin_unlock(&adapter->rwi_lock); + + if (!need_reset) + return; + rwi = get_next_rwi(adapter); while (rwi) { spin_lock_irqsave(&adapter->state_lock, flags); @@@ -2736,12 -2810,23 +2811,23 @@@ static void __ibmvnic_delayed_reset(str __ibmvnic_reset(&adapter->ibmvnic_reset); }

+ static void flush_reset_queue(struct ibmvnic_adapter *adapter) + { + struct list_head *entry, *tmp_entry; + + if (!list_empty(&adapter->rwi_list)) { + list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) { + list_del(entry); + kfree(list_entry(entry, struct ibmvnic_rwi, list)); + } + } + } + static int ibmvnic_reset(struct ibmvnic_adapter *adapter, enum ibmvnic_reset_reason reason) { - struct list_head *entry, *tmp_entry; - struct ibmvnic_rwi *rwi, *tmp; struct net_device *netdev = adapter->netdev; + struct ibmvnic_rwi *rwi, *tmp; unsigned long flags; int ret;

@@@ -2760,13 -2845,6 +2846,6 @@@ goto err; }

- if (adapter->state == VNIC_PROBING) { - netdev_warn(netdev, "Adapter reset during probe\n"); - adapter->init_done_rc = -EAGAIN; - ret = EAGAIN; - goto err; - } - list_for_each_entry(tmp, &adapter->rwi_list, list) { if (tmp->reset_reason == reason) { netdev_dbg(netdev, "Skipping matching reset, reason=%s\n", @@@ -2784,10 -2862,9 +2863,9 @@@ /* if we just received a transport event, * flush reset queue and process this reset */ - if (adapter->force_reset_recovery && !list_empty(&adapter->rwi_list)) { - list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) - list_del(entry); - } + if (adapter->force_reset_recovery) + flush_reset_queue(adapter); + rwi->reset_reason = reason; list_add_tail(&rwi->list, &adapter->rwi_list); netdev_dbg(adapter->netdev, "Scheduling reset (reason %s)\n", @@@ -3563,30 -3640,6 +3641,30 @@@ static int disable_scrq_irq(struct ibmv return rc; }

+/* We can not use the IRQ chip EOI handler because that has the + * unintended effect of changing the interrupt priority. + */ +static void ibmvnic_xics_eoi(struct device *dev, struct ibmvnic_sub_crq_queue *scrq) +{ + u64 val = 0xff000000 | scrq->hw_irq; + unsigned long rc; + + rc = plpar_hcall_norets(H_EOI, val); + if (rc) + dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", val, rc); +} + +/* Due to a firmware bug, the hypervisor can send an interrupt to a + * transmit or receive queue just prior to a partition migration. + * Force an EOI after migration. + */ +static void ibmvnic_clear_pending_interrupt(struct device *dev, + struct ibmvnic_sub_crq_queue *scrq) +{ + if (!xive_enabled()) + ibmvnic_xics_eoi(dev, scrq); +} + static int enable_scrq_irq(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *scrq) { @@@ -3600,7 -3653,15 +3678,7 @@@

if (test_bit(0, &adapter->resetting) && adapter->reset_reason == VNIC_RESET_MOBILITY) { - u64 val = (0xff000000) | scrq->hw_irq; - - rc = plpar_hcall_norets(H_EOI, val); - /* H_EOI would fail with rc = H_FUNCTION when running - * in XIVE mode which is expected, but not an error. - */ - if (rc && (rc != H_FUNCTION)) - dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", - val, rc); + ibmvnic_clear_pending_interrupt(dev, scrq); }

rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, @@@ -5338,9 -5399,9 +5416,9 @@@ static void ibmvnic_handle_crq(union ib }

if (!completion_done(&adapter->init_done)) { - complete(&adapter->init_done); if (!adapter->init_done_rc) adapter->init_done_rc = -EAGAIN; + complete(&adapter->init_done); }

break; @@@ -5363,6 -5424,13 +5441,13 @@@ adapter->fw_done_rc = -EIO; complete(&adapter->fw_done); } + + /* if we got here during crq-init, retry crq-init */ + if (!completion_done(&adapter->init_done)) { + adapter->init_done_rc = -EAGAIN; + complete(&adapter->init_done); + } + if (!completion_done(&adapter->stats_done)) complete(&adapter->stats_done); if (test_bit(0, &adapter->resetting)) @@@ -5679,10 -5747,6 +5764,6 @@@ static int ibmvnic_reset_init(struct ib

adapter->from_passive_init = false;

- if (reset) - reinit_completion(&adapter->init_done); - - adapter->init_done_rc = 0; rc = ibmvnic_send_crq_init(adapter); if (rc) { dev_err(dev, "Send crq init failed with error %d\n", rc); @@@ -5696,12 -5760,14 +5777,14 @@@

if (adapter->init_done_rc) { release_crq_queue(adapter); + dev_err(dev, "CRQ-init failed, %d\n", adapter->init_done_rc); return adapter->init_done_rc; }

if (adapter->from_passive_init) { adapter->state = VNIC_OPEN; adapter->from_passive_init = false; + dev_err(dev, "CRQ-init failed, passive-init\n"); return -EINVAL; }

@@@ -5741,6 -5807,7 +5824,7 @@@ static int ibmvnic_probe(struct vio_de struct ibmvnic_adapter *adapter; struct net_device *netdev; unsigned char *mac_addr_p; + unsigned long flags; bool init_success; int rc;

@@@ -5785,6 -5852,7 +5869,7 @@@ spin_lock_init(&adapter->rwi_lock); spin_lock_init(&adapter->state_lock); mutex_init(&adapter->fw_lock); + init_completion(&adapter->probe_done); init_completion(&adapter->init_done); init_completion(&adapter->fw_done); init_completion(&adapter->reset_done); @@@ -5795,6 -5863,33 +5880,33 @@@

init_success = false; do { + reinit_init_done(adapter); + + /* clear any failovers we got in the previous pass + * since we are reinitializing the CRQ + */ + adapter->failover_pending = false; + + /* If we had already initialized CRQ, we may have one or + * more resets queued already. Discard those and release + * the CRQ before initializing the CRQ again. + */ + release_crq_queue(adapter); + + /* Since we are still in PROBING state, __ibmvnic_reset() + * will not access the ->rwi_list and since we released CRQ, + * we won't get _new_ transport events. But there maybe an + * ongoing ibmvnic_reset() call. So serialize access to + * rwi_list. If we win the race, ibvmnic_reset() could add + * a reset after we purged but thats ok - we just may end + * up with an extra reset (i.e similar to having two or more + * resets in the queue at once). + * CHECK. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, flags); + rc = init_crq_queue(adapter); if (rc) { dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", @@@ -5826,12 -5921,6 +5938,6 @@@ goto ibmvnic_dev_file_err;

netif_carrier_off(netdev); - rc = register_netdev(netdev); - if (rc) { - dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - goto ibmvnic_register_fail; - } - dev_info(&dev->dev, "ibmvnic registered\n");

if (init_success) { adapter->state = VNIC_PROBED; @@@ -5844,6 -5933,16 +5950,16 @@@

adapter->wait_for_reset = false; adapter->last_reset_time = jiffies; + + rc = register_netdev(netdev); + if (rc) { + dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); + goto ibmvnic_register_fail; + } + dev_info(&dev->dev, "ibmvnic registered\n"); + + complete(&adapter->probe_done); + return 0;

ibmvnic_register_fail: @@@ -5858,6 -5957,17 +5974,17 @@@ ibmvnic_stats_fail ibmvnic_init_fail: release_sub_crqs(adapter, 1); release_crq_queue(adapter); + + /* cleanup worker thread after releasing CRQ so we don't get + * transport events (i.e new work items for the worker thread). + */ + adapter->state = VNIC_REMOVING; + complete(&adapter->probe_done); + flush_work(&adapter->ibmvnic_reset); + flush_delayed_work(&adapter->ibmvnic_delayed_reset); + + flush_reset_queue(adapter); + mutex_destroy(&adapter->fw_lock); free_netdev(netdev);

diff --combined drivers/net/ethernet/intel/e1000e/netdev.c index 6fb3437f68e0,c5bdef3ffe26..fa06f68c8c80 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@@ -6987,8 -6987,21 +6987,21 @@@ static __maybe_unused int e1000e_pm_sus struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); + struct e1000_hw *hw = &adapter->hw; + u16 phy_data; int rc;

+ if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { + /* Mask OEM Bits / Gig Disable / Restart AN (772_26[12] = 1) */ + e1e_rphy(hw, I217_MEMPWR, &phy_data); + phy_data |= I217_MEMPWR_MOEM; + e1e_wphy(hw, I217_MEMPWR, phy_data); + + /* Disable LCD reset */ + hw->phy.reset_disable = true; + } + e1000e_flush_lpic(pdev);

e1000e_pm_freeze(dev); @@@ -7010,6 -7023,8 +7023,8 @@@ static __maybe_unused int e1000e_pm_res struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); + struct e1000_hw *hw = &adapter->hw; + u16 phy_data; int rc;

/* Introduce S0ix implementation */ @@@ -7020,6 -7035,17 +7035,17 @@@ if (rc) return rc;

+ if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { + /* Unmask OEM Bits / Gig Disable / Restart AN 772_26[12] = 0 */ + e1e_rphy(hw, I217_MEMPWR, &phy_data); + phy_data &= ~I217_MEMPWR_MOEM; + e1e_wphy(hw, I217_MEMPWR, phy_data); + + /* Enable LCD reset */ + hw->phy.reset_disable = false; + } + return e1000e_pm_thaw(dev); }

@@@ -7388,9 -7414,9 +7414,9 @@@ static int e1000_probe(struct pci_dev * resource_size_t flash_start, flash_len; static int cards_found; u16 aspm_disable_flag = 0; - int bars, i, err, pci_using_dac; u16 eeprom_data = 0; u16 eeprom_apme_mask = E1000_EEPROM_APME; + int bars, i, err; s32 ret_val = 0;

if (ei->flags2 & FLAG2_DISABLE_ASPM_L0S) @@@ -7404,11 -7430,17 +7430,11 @@@ if (err) return err;

- pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; }

bars = pci_select_bars(pdev, IORESOURCE_MEM); @@@ -7544,8 -7576,10 +7570,8 @@@

netdev->priv_flags |= IFF_UNICAST_FLT;

- if (pci_using_dac) { - netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= NETIF_F_HIGHDMA; - } + netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= NETIF_F_HIGHDMA;

/* MTU range: 68 - max_hw_frame_size */ netdev->min_mtu = ETH_MIN_MTU; diff --combined drivers/net/ethernet/intel/iavf/iavf.h index 25c986034319,89423947ee65..bed2ebf15627 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@@ -44,9 -44,6 +44,9 @@@ #define DEFAULT_DEBUG_LEVEL_SHIFT 3 #define PFX "iavf: "

+int iavf_status_to_errno(enum iavf_status status); +int virtchnl_status_to_errno(enum virtchnl_status_code v_status); + /* VSI state flags shared with common code */ enum iavf_vsi_state_t { __IAVF_VSI_DOWN, @@@ -191,7 -188,7 +191,7 @@@ enum iavf_state_t __IAVF_REMOVE, /* driver is being unloaded */ __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ - __IAVF_INIT_GET_OFFLOAD_VLAN_V2_CAPS, + __IAVF_INIT_EXTENDED_CAPS, /* process extended caps which require aq msg exchange */ __IAVF_INIT_CONFIG_ADAPTER, __IAVF_INIT_SW, /* got resources, setting up structs */ __IAVF_INIT_FAILED, /* init failed, restarting procedure */ @@@ -204,6 -201,10 +204,10 @@@ __IAVF_RUNNING, /* opened, working */ };

+ enum iavf_critical_section_t { + __IAVF_IN_REMOVE_TASK, /* device being removed */ + }; + #define IAVF_CLOUD_FIELD_OMAC 0x01 #define IAVF_CLOUD_FIELD_IMAC 0x02 #define IAVF_CLOUD_FIELD_IVLAN 0x04 @@@ -249,7 -250,6 +253,6 @@@ struct iavf_adapter struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; - struct mutex remove_lock; /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; @@@ -287,6 -287,7 +290,7 @@@ #define IAVF_FLAG_LEGACY_RX BIT(15) #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) #define IAVF_FLAG_QUEUES_DISABLED BIT(17) + #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ @@@ -332,21 -333,6 +336,21 @@@ #define IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION BIT_ULL(37) #define IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION BIT_ULL(38)

+ /* flags for processing extended capability messages during + * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires + * both a SEND and a RECV step, which must be processed in sequence. + * + * During the __IAVF_INIT_EXTENDED_CAPS state, the driver will + * process one flag at a time during each state loop. + */ + u64 extended_caps; +#define IAVF_EXTENDED_CAP_SEND_VLAN_V2 BIT_ULL(0) +#define IAVF_EXTENDED_CAP_RECV_VLAN_V2 BIT_ULL(1) + +#define IAVF_EXTENDED_CAPS \ + (IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \ + IAVF_EXTENDED_CAP_RECV_VLAN_V2) + /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; @@@ -528,7 -514,7 +532,7 @@@ void iavf_add_vlans(struct iavf_adapte void iavf_del_vlans(struct iavf_adapter *adapter); void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags); void iavf_request_stats(struct iavf_adapter *adapter); -void iavf_request_reset(struct iavf_adapter *adapter); +int iavf_request_reset(struct iavf_adapter *adapter); void iavf_get_hena(struct iavf_adapter *adapter); void iavf_set_hena(struct iavf_adapter *adapter); void iavf_set_rss_key(struct iavf_adapter *adapter); diff --combined drivers/net/ethernet/intel/iavf/iavf_main.c index 56387cec024f,dcf24264c7ea..45a1e88c9276 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@@ -51,113 -51,6 +51,113 @@@ MODULE_LICENSE("GPL v2") static const struct net_device_ops iavf_netdev_ops; struct workqueue_struct *iavf_wq;

+int iavf_status_to_errno(enum iavf_status status) +{ + switch (status) { + case IAVF_SUCCESS: + return 0; + case IAVF_ERR_PARAM: + case IAVF_ERR_MAC_TYPE: + case IAVF_ERR_INVALID_MAC_ADDR: + case IAVF_ERR_INVALID_LINK_SETTINGS: + case IAVF_ERR_INVALID_PD_ID: + case IAVF_ERR_INVALID_QP_ID: + case IAVF_ERR_INVALID_CQ_ID: + case IAVF_ERR_INVALID_CEQ_ID: + case IAVF_ERR_INVALID_AEQ_ID: + case IAVF_ERR_INVALID_SIZE: + case IAVF_ERR_INVALID_ARP_INDEX: + case IAVF_ERR_INVALID_FPM_FUNC_ID: + case IAVF_ERR_QP_INVALID_MSG_SIZE: + case IAVF_ERR_INVALID_FRAG_COUNT: + case IAVF_ERR_INVALID_ALIGNMENT: + case IAVF_ERR_INVALID_PUSH_PAGE_INDEX: + case IAVF_ERR_INVALID_IMM_DATA_SIZE: + case IAVF_ERR_INVALID_VF_ID: + case IAVF_ERR_INVALID_HMCFN_ID: + case IAVF_ERR_INVALID_PBLE_INDEX: + case IAVF_ERR_INVALID_SD_INDEX: + case IAVF_ERR_INVALID_PAGE_DESC_INDEX: + case IAVF_ERR_INVALID_SD_TYPE: + case IAVF_ERR_INVALID_HMC_OBJ_INDEX: + case IAVF_ERR_INVALID_HMC_OBJ_COUNT: + case IAVF_ERR_INVALID_SRQ_ARM_LIMIT: + return -EINVAL; + case IAVF_ERR_NVM: + case IAVF_ERR_NVM_CHECKSUM: + case IAVF_ERR_PHY: + case IAVF_ERR_CONFIG: + case IAVF_ERR_UNKNOWN_PHY: + case IAVF_ERR_LINK_SETUP: + case IAVF_ERR_ADAPTER_STOPPED: + case IAVF_ERR_PRIMARY_REQUESTS_PENDING: + case IAVF_ERR_AUTONEG_NOT_COMPLETE: + case IAVF_ERR_RESET_FAILED: + case IAVF_ERR_BAD_PTR: + case IAVF_ERR_SWFW_SYNC: + case IAVF_ERR_QP_TOOMANY_WRS_POSTED: + case IAVF_ERR_QUEUE_EMPTY: + case IAVF_ERR_FLUSHED_QUEUE: + case IAVF_ERR_OPCODE_MISMATCH: + case IAVF_ERR_CQP_COMPL_ERROR: + case IAVF_ERR_BACKING_PAGE_ERROR: + case IAVF_ERR_NO_PBLCHUNKS_AVAILABLE: + case IAVF_ERR_MEMCPY_FAILED: + case IAVF_ERR_SRQ_ENABLED: + case IAVF_ERR_ADMIN_QUEUE_ERROR: + case IAVF_ERR_ADMIN_QUEUE_FULL: + case IAVF_ERR_BAD_IWARP_CQE: + case IAVF_ERR_NVM_BLANK_MODE: + case IAVF_ERR_PE_DOORBELL_NOT_ENABLED: + case IAVF_ERR_DIAG_TEST_FAILED: + case IAVF_ERR_FIRMWARE_API_VERSION: + case IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return -EIO; + case IAVF_ERR_DEVICE_NOT_SUPPORTED: + return -ENODEV; + case IAVF_ERR_NO_AVAILABLE_VSI: + case IAVF_ERR_RING_FULL: + return -ENOSPC; + case IAVF_ERR_NO_MEMORY: + return -ENOMEM; + case IAVF_ERR_TIMEOUT: + case IAVF_ERR_ADMIN_QUEUE_TIMEOUT: + return -ETIMEDOUT; + case IAVF_ERR_NOT_IMPLEMENTED: + case IAVF_NOT_SUPPORTED: + return -EOPNOTSUPP; + case IAVF_ERR_ADMIN_QUEUE_NO_WORK: + return -EALREADY; + case IAVF_ERR_NOT_READY: + return -EBUSY; + case IAVF_ERR_BUF_TOO_SHORT: + return -EMSGSIZE; + } + + return -EIO; +} + +int virtchnl_status_to_errno(enum virtchnl_status_code v_status) +{ + switch (v_status) { + case VIRTCHNL_STATUS_SUCCESS: + return 0; + case VIRTCHNL_STATUS_ERR_PARAM: + case VIRTCHNL_STATUS_ERR_INVALID_VF_ID: + return -EINVAL; + case VIRTCHNL_STATUS_ERR_NO_MEMORY: + return -ENOMEM; + case VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH: + case VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR: + case VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR: + return -EIO; + case VIRTCHNL_STATUS_ERR_NOT_SUPPORTED: + return -EOPNOTSUPP; + } + + return -EIO; +} + /** * iavf_pdev_to_adapter - go from pci_dev to adapter * @pdev: pci_dev pointer @@@ -409,8 -302,9 +409,9 @@@ static irqreturn_t iavf_msix_aq(int irq rd32(hw, IAVF_VFINT_ICR01); rd32(hw, IAVF_VFINT_ICR0_ENA1);

- /* schedule work on the private workqueue */ - queue_work(iavf_wq, &adapter->adminq_task); + if (adapter->state != __IAVF_REMOVE) + /* schedule work on the private workqueue */ + queue_work(iavf_wq, &adapter->adminq_task);

return IRQ_HANDLED; } @@@ -983,7 -877,6 +984,7 @@@ struct iavf_mac_filter *iavf_add_filter list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; f->is_new_mac = true; + f->is_primary = false; adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; } else { f->remove = false; @@@ -1017,22 -910,17 +1018,22 @@@ static int iavf_set_mac(struct net_devi f = iavf_find_filter(adapter, hw->mac.addr); if (f) { f->remove = true; + f->is_primary = true; adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; }

f = iavf_add_filter(adapter, addr->sa_data); - - spin_unlock_bh(&adapter->mac_vlan_list_lock); - if (f) { + f->is_primary = true; ether_addr_copy(hw->mac.addr, addr->sa_data); }

+ spin_unlock_bh(&adapter->mac_vlan_list_lock); + + /* schedule the watchdog task to immediately process the request */ + if (f) + queue_work(iavf_wq, &adapter->watchdog_task.work); + return (f == NULL) ? -ENOMEM : 0; }

@@@ -1249,8 -1137,7 +1250,7 @@@ void iavf_down(struct iavf_adapter *ada rss->state = IAVF_ADV_RSS_DEL_REQUEST; spin_unlock_bh(&adapter->adv_rss_lock);

- if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && - adapter->state != __IAVF_RESETTING) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait @@@ -1534,7 -1421,7 +1534,7 @@@ static int iavf_config_rss_aq(struct ia struct iavf_aqc_get_set_rss_key_data *rss_key = (struct iavf_aqc_get_set_rss_key_data *)adapter->rss_key; struct iavf_hw *hw = &adapter->hw; - int ret = 0; + enum iavf_status status;

if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@@ -1543,25 -1430,24 +1543,25 @@@ return -EBUSY; }

- ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); - if (ret) { + status = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); + if (status) { dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n", - iavf_stat_str(hw, ret), + iavf_stat_str(hw, status), iavf_aq_str(hw, hw->aq.asq_last_status)); - return ret; + return iavf_status_to_errno(status);

}

- ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, - adapter->rss_lut, adapter->rss_lut_size); - if (ret) { + status = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, + adapter->rss_lut, adapter->rss_lut_size); + if (status) { dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n", - iavf_stat_str(hw, ret), + iavf_stat_str(hw, status), iavf_aq_str(hw, hw->aq.asq_last_status)); + return iavf_status_to_errno(status); }

- return ret; + return 0;

}

@@@ -1631,6 -1517,7 +1631,6 @@@ static void iavf_fill_rss_lut(struct ia static int iavf_init_rss(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; - int ret;

if (!RSS_PF(adapter)) { /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ @@@ -1646,8 -1533,9 +1646,8 @@@

iavf_fill_rss_lut(adapter); netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size); - ret = iavf_config_rss(adapter);

- return ret; + return iavf_config_rss(adapter); }

/** @@@ -2115,24 -2003,23 +2115,24 @@@ static void iavf_startup(struct iavf_ad { struct pci_dev *pdev = adapter->pdev; struct iavf_hw *hw = &adapter->hw; - int err; + enum iavf_status status; + int ret;

WARN_ON(adapter->state != __IAVF_STARTUP);

/* driver loaded, probe complete */ adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - err = iavf_set_mac_type(hw); - if (err) { - dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", err); + status = iavf_set_mac_type(hw); + if (status) { + dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", status); goto err; }

- err = iavf_check_reset_complete(hw); - if (err) { + ret = iavf_check_reset_complete(hw); + if (ret) { dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n", - err); + ret); goto err; } hw->aq.num_arq_entries = IAVF_AQ_LEN; @@@ -2140,15 -2027,14 +2140,15 @@@ hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE; hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE;

- err = iavf_init_adminq(hw); - if (err) { - dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", err); + status = iavf_init_adminq(hw); + if (status) { + dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", + status); goto err; } - err = iavf_send_api_ver(adapter); - if (err) { - dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err); + ret = iavf_send_api_ver(adapter); + if (ret) { + dev_err(&pdev->dev, "Unable to send to PF (%d)\n", ret); iavf_shutdown_adminq(hw); goto err; } @@@ -2184,7 -2070,7 +2184,7 @@@ static void iavf_init_version_check(str /* aq msg sent, awaiting reply */ err = iavf_verify_api_ver(adapter); if (err) { - if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK) + if (err == -EALREADY) err = iavf_send_api_ver(adapter); else dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n", @@@ -2285,11 -2171,11 +2285,11 @@@ static void iavf_init_get_resources(str } } err = iavf_get_vf_config(adapter); - if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK) { + if (err == -EALREADY) { err = iavf_send_vf_config_msg(adapter); goto err_alloc; - } else if (err == IAVF_ERR_PARAM) { - /* We only get ERR_PARAM if the device is in a very bad + } else if (err == -EINVAL) { + /* We only get -EINVAL if the device is in a very bad * state or if we've been disabled for previous bad * behavior. Either way, we're done now. */ @@@ -2303,18 -2189,26 +2303,18 @@@ }

err = iavf_parse_vf_resource_msg(adapter); - if (err) - goto err_alloc; - - err = iavf_send_vf_offload_vlan_v2_msg(adapter); - if (err == -EOPNOTSUPP) { - /* underlying PF doesn't support VIRTCHNL_VF_OFFLOAD_VLAN_V2, so - * go directly to finishing initialization - */ - iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); - return; - } else if (err) { - dev_err(&pdev->dev, "Unable to send offload vlan v2 request (%d)\n", + if (err) { + dev_err(&pdev->dev, "Failed to parse VF resource message from PF (%d)\n", err); goto err_alloc; } - - /* underlying PF supports VIRTCHNL_VF_OFFLOAD_VLAN_V2, so update the - * state accordingly + /* Some features require additional messages to negotiate extended + * capabilities. These are processed in sequence by the + * __IAVF_INIT_EXTENDED_CAPS driver state. */ - iavf_change_state(adapter, __IAVF_INIT_GET_OFFLOAD_VLAN_V2_CAPS); + adapter->extended_caps = IAVF_EXTENDED_CAPS; + + iavf_change_state(adapter, __IAVF_INIT_EXTENDED_CAPS); return;

err_alloc: @@@ -2325,92 -2219,34 +2325,92 @@@ err }

/** - * iavf_init_get_offload_vlan_v2_caps - part of driver startup + * iavf_init_send_offload_vlan_v2_caps - part of initializing VLAN V2 caps * @adapter: board private structure * - * Function processes __IAVF_INIT_GET_OFFLOAD_VLAN_V2_CAPS driver state if the - * VF negotiates VIRTCHNL_VF_OFFLOAD_VLAN_V2. If VIRTCHNL_VF_OFFLOAD_VLAN_V2 is - * not negotiated, then this state will never be entered. + * Function processes send of the extended VLAN V2 capability message to the + * PF. Must clear IAVF_EXTENDED_CAP_RECV_VLAN_V2 if the message is not sent, + * e.g. due to PF not negotiating VIRTCHNL_VF_OFFLOAD_VLAN_V2. + */ +static void iavf_init_send_offload_vlan_v2_caps(struct iavf_adapter *adapter) +{ + int ret; + + WARN_ON(!(adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_VLAN_V2)); + + ret = iavf_send_vf_offload_vlan_v2_msg(adapter); + if (ret && ret == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_OFFLOAD_V2. In this case, + * we did not send the capability exchange message and do not + * expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_VLAN_V2; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_VLAN_V2; +} + +/** + * iavf_init_recv_offload_vlan_v2_caps - part of initializing VLAN V2 caps + * @adapter: board private structure + * + * Function processes receipt of the extended VLAN V2 capability message from + * the PF. **/ -static void iavf_init_get_offload_vlan_v2_caps(struct iavf_adapter *adapter) +static void iavf_init_recv_offload_vlan_v2_caps(struct iavf_adapter *adapter) { int ret;

- WARN_ON(adapter->state != __IAVF_INIT_GET_OFFLOAD_VLAN_V2_CAPS); + WARN_ON(!(adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_VLAN_V2));

memset(&adapter->vlan_v2_caps, 0, sizeof(adapter->vlan_v2_caps));

ret = iavf_get_vf_vlan_v2_caps(adapter); - if (ret) { - if (ret == IAVF_ERR_ADMIN_QUEUE_NO_WORK) - iavf_send_vf_offload_vlan_v2_msg(adapter); + if (ret) goto err; - }

- iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); + /* We've processed receipt of the VLAN V2 caps message */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_VLAN_V2; return; err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_VLAN_V2; iavf_change_state(adapter, __IAVF_INIT_FAILED); }

+/** + * iavf_init_process_extended_caps - Part of driver startup + * @adapter: board private structure + * + * Function processes __IAVF_INIT_EXTENDED_CAPS driver state. This state + * handles negotiating capabilities for features which require an additional + * message. + * + * Once all extended capabilities exchanges are finished, the driver will + * transition into __IAVF_INIT_CONFIG_ADAPTER. + */ +static void iavf_init_process_extended_caps(struct iavf_adapter *adapter) +{ + WARN_ON(adapter->state != __IAVF_INIT_EXTENDED_CAPS); + + /* Process capability exchange for VLAN V2 */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_VLAN_V2) { + iavf_init_send_offload_vlan_v2_caps(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_VLAN_V2) { + iavf_init_recv_offload_vlan_v2_caps(adapter); + return; + } + + /* When we reach here, no further extended capabilities exchanges are + * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER + */ + iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); +} + /** * iavf_init_config_adapter - last part of driver startup * @adapter: board private structure @@@ -2538,17 -2374,22 +2538,22 @@@ static void iavf_watchdog_task(struct w struct iavf_hw *hw = &adapter->hw; u32 reg_val;

- if (!mutex_trylock(&adapter->crit_lock)) + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state == __IAVF_REMOVE) + return; + goto restart_watchdog; + }

if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) iavf_change_state(adapter, __IAVF_COMM_FAILED);

- if (adapter->flags & IAVF_FLAG_RESET_NEEDED && - adapter->state != __IAVF_RESETTING) { - iavf_change_state(adapter, __IAVF_RESETTING); + if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); + queue_work(iavf_wq, &adapter->reset_task); + return; }

switch (adapter->state) { @@@ -2570,8 -2411,8 +2575,8 @@@ queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; - case __IAVF_INIT_GET_OFFLOAD_VLAN_V2_CAPS: - iavf_init_get_offload_vlan_v2_caps(adapter); + case __IAVF_INIT_EXTENDED_CAPS: + iavf_init_process_extended_caps(adapter); mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(1)); @@@ -2583,6 -2424,15 +2588,15 @@@ msecs_to_jiffies(1)); return; case __IAVF_INIT_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Do not update the state and do not reschedule + * watchdog task, iavf_remove should handle this state + * as it can loop forever + */ + mutex_unlock(&adapter->crit_lock); + return; + } if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { dev_err(&adapter->pdev->dev, "Failed to communicate with PF; waiting before retry\n"); @@@ -2599,6 -2449,17 +2613,17 @@@ queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Set state to __IAVF_INIT_FAILED and perform remove + * steps. Remove IAVF_FLAG_PF_COMMS_FAILED so the task + * doesn't bring the state back to __IAVF_COMM_FAILED. + */ + iavf_change_state(adapter, __IAVF_INIT_FAILED); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + mutex_unlock(&adapter->crit_lock); + return; + } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if (reg_val == VIRTCHNL_VFR_VFACTIVE || @@@ -2671,7 -2532,8 +2696,8 @@@ schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); mutex_unlock(&adapter->crit_lock); restart_watchdog: - queue_work(iavf_wq, &adapter->adminq_task); + if (adapter->state >= __IAVF_DOWN) + queue_work(iavf_wq, &adapter->adminq_task); if (adapter->aq_required) queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(20)); @@@ -2758,7 -2620,6 +2784,7 @@@ static void iavf_reset_task(struct work struct iavf_hw *hw = &adapter->hw; struct iavf_mac_filter *f, *ftmp; struct iavf_cloud_filter *cf; + enum iavf_status status; u32 reg_val; int i = 0, err; bool running; @@@ -2766,13 -2627,13 +2792,13 @@@ /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - if (mutex_is_locked(&adapter->remove_lock)) - return; + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state != __IAVF_REMOVE) + queue_work(iavf_wq, &adapter->reset_task);

- if (iavf_lock_timeout(&adapter->crit_lock, 200)) { - schedule_work(&adapter->reset_task); return; } + while (!mutex_trylock(&adapter->client_lock)) usleep_range(500, 1000); if (CLIENT_ENABLED(adapter)) { @@@ -2827,6 -2688,7 +2853,7 @@@ reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); + mutex_unlock(&adapter->crit_lock); return; /* Do not attempt to reinit. It's dead, Jim. */ }

@@@ -2835,8 -2697,7 +2862,7 @@@ continue_reset * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - running = ((adapter->state == __IAVF_RUNNING) || - (adapter->state == __IAVF_RESETTING)); + running = adapter->state == __IAVF_RUNNING;

if (running) { netdev->flags &= ~IFF_UP; @@@ -2860,12 -2721,10 +2886,12 @@@ /* kill and reinit the admin queue */ iavf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; - err = iavf_init_adminq(hw); - if (err) + status = iavf_init_adminq(hw); + if (status) { dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", - err); + status); + goto reset_err; + } adapter->aq_required = 0;

if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { @@@ -2993,13 -2852,19 +3019,19 @@@ static void iavf_adminq_task(struct wor if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) goto out;

+ if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state == __IAVF_REMOVE) + return; + + queue_work(iavf_wq, &adapter->adminq_task); + goto out; + } + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) goto out;

- if (iavf_lock_timeout(&adapter->crit_lock, 200)) - goto freedom; do { ret = iavf_clean_arq_element(hw, &event, &pending); v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); @@@ -3015,6 -2880,24 +3047,24 @@@ } while (pending); mutex_unlock(&adapter->crit_lock);

+ if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES)) { + if (adapter->netdev_registered || + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { + struct net_device *netdev = adapter->netdev; + + rtnl_lock(); + netdev_update_features(netdev); + rtnl_unlock(); + /* Request VLAN offload settings */ + if (VLAN_V2_ALLOWED(adapter)) + iavf_set_vlan_offload_features + (adapter, 0, netdev->features); + + iavf_set_queue_vlan_tag_loc(adapter); + } + + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; + } if ((adapter->flags & (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || adapter->state == __IAVF_RESETTING) @@@ -3967,11 -3850,12 +4017,12 @@@ static int iavf_close(struct net_devic struct iavf_adapter *adapter = netdev_priv(netdev); int status;

- if (adapter->state <= __IAVF_DOWN_PENDING) - return 0; + mutex_lock(&adapter->crit_lock);

- while (!mutex_trylock(&adapter->crit_lock)) - usleep_range(500, 1000); + if (adapter->state <= __IAVF_DOWN_PENDING) { + mutex_unlock(&adapter->crit_lock); + return 0; + }

set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); if (CLIENT_ENABLED(adapter)) @@@ -4020,8 -3904,11 +4071,11 @@@ static int iavf_change_mtu(struct net_d iavf_notify_client_l2_params(&adapter->vsi); adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + queue_work(iavf_wq, &adapter->reset_task); + }

return 0; } @@@ -4535,9 -4422,12 +4589,9 @@@ static int iavf_probe(struct pci_dev *p

err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; }

err = pci_request_regions(pdev, iavf_driver_name); @@@ -4595,7 -4485,6 +4649,6 @@@ */ mutex_init(&adapter->crit_lock); mutex_init(&adapter->client_lock); - mutex_init(&adapter->remove_lock); mutex_init(&hw->aq.asq_mutex); mutex_init(&hw->aq.arq_mutex);

@@@ -4711,7 -4600,6 +4764,6 @@@ static int __maybe_unused iavf_resume(s static void iavf_remove(struct pci_dev *pdev) { struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - enum iavf_state_t prev_state = adapter->last_state; struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; @@@ -4720,14 -4608,30 +4772,30 @@@ struct iavf_cloud_filter *cf, *cftmp; struct iavf_hw *hw = &adapter->hw; int err; - /* Indicate we are in remove and not to run reset_task */ - mutex_lock(&adapter->remove_lock); - cancel_work_sync(&adapter->reset_task); + + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); + /* Wait until port initialization is complete. + * There are flows where register/unregister netdev may race. + */ + while (1) { + mutex_lock(&adapter->crit_lock); + if (adapter->state == __IAVF_RUNNING || + adapter->state == __IAVF_DOWN || + adapter->state == __IAVF_INIT_FAILED) { + mutex_unlock(&adapter->crit_lock); + break; + } + + mutex_unlock(&adapter->crit_lock); + usleep_range(500, 1000); + } cancel_delayed_work_sync(&adapter->watchdog_task); - cancel_delayed_work_sync(&adapter->client_task); + if (adapter->netdev_registered) { - unregister_netdev(netdev); + rtnl_lock(); + unregister_netdevice(netdev); adapter->netdev_registered = false; + rtnl_unlock(); } if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_del_device(adapter); @@@ -4736,6 -4640,10 +4804,10 @@@ err); }

+ mutex_lock(&adapter->crit_lock); + dev_info(&adapter->pdev->dev, "Remove device\n"); + iavf_change_state(adapter, __IAVF_REMOVE); + iavf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@@ -4743,37 -4651,24 +4815,24 @@@ iavf_request_reset(adapter); msleep(50); } - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__);

- dev_info(&adapter->pdev->dev, "Removing device\n"); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ - iavf_change_state(adapter, __IAVF_REMOVE); + cancel_work_sync(&adapter->reset_task); + cancel_delayed_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->adminq_task); + cancel_delayed_work_sync(&adapter->client_task); + adapter->aq_required = 0; adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;

iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); - iavf_misc_irq_disable(adapter); iavf_free_misc_irq(adapter);

- /* In case we enter iavf_remove from erroneous state, free traffic irqs - * here, so as to not cause a kernel crash, when calling - * iavf_reset_interrupt_capability. - */ - if ((adapter->last_state == __IAVF_RESETTING && - prev_state != __IAVF_DOWN) || - (adapter->last_state == __IAVF_RUNNING && - !(netdev->flags & IFF_UP))) - iavf_free_traffic_irqs(adapter); - iavf_reset_interrupt_capability(adapter); iavf_free_q_vectors(adapter);

- cancel_delayed_work_sync(&adapter->watchdog_task); - - cancel_work_sync(&adapter->adminq_task); - iavf_free_rss(adapter);

if (hw->aq.asq.count) @@@ -4785,8 -4680,6 +4844,6 @@@ mutex_destroy(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); - mutex_unlock(&adapter->remove_lock); - mutex_destroy(&adapter->remove_lock);

iounmap(hw->hw_addr); pci_release_regions(pdev); @@@ -4856,6 -4749,8 +4913,6 @@@ static struct pci_driver iavf_driver = **/ static int __init iavf_init_module(void) { - int ret; - pr_info("iavf: %s\n", iavf_driver_string);

pr_info("%s\n", iavf_copyright); @@@ -4866,7 -4761,8 +4923,7 @@@ pr_err("%s: Failed to create workqueue\n", iavf_driver_name); return -ENOMEM; } - ret = pci_register_driver(&iavf_driver); - return ret; + return pci_register_driver(&iavf_driver); }

module_init(iavf_init_module); diff --combined drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 814c62e0851a,88844d68e150..c6f52f8ef678 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@@ -22,17 -22,17 +22,17 @@@ static int iavf_send_pf_msg(struct iavf enum virtchnl_ops op, u8 *msg, u16 len) { struct iavf_hw *hw = &adapter->hw; - enum iavf_status err; + enum iavf_status status;

if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) return 0; /* nothing to see here, move along */

- err = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); - if (err) - dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", - op, iavf_stat_str(hw, err), + status = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); + if (status) + dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, status %s, aq_err %s\n", + op, iavf_stat_str(hw, status), iavf_aq_str(hw, hw->aq.asq_last_status)); - return err; + return iavf_status_to_errno(status); }

/** @@@ -54,41 -54,6 +54,41 @@@ int iavf_send_api_ver(struct iavf_adapt sizeof(vvi)); }

+/** + * iavf_poll_virtchnl_msg + * @hw: HW configuration structure + * @event: event to populate on success + * @op_to_poll: requested virtchnl op to poll for + * + * Initialize poll for virtchnl msg matching the requested_op. Returns 0 + * if a message of the correct opcode is in the queue or an error code + * if no message matching the op code is waiting and other failures. + */ +static int +iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event, + enum virtchnl_ops op_to_poll) +{ + enum virtchnl_ops received_op; + enum iavf_status status; + u32 v_retval; + + while (1) { + /* When the AQ is empty, iavf_clean_arq_element will return + * nonzero and this loop will terminate. + */ + status = iavf_clean_arq_element(hw, event, NULL); + if (status != IAVF_SUCCESS) + return iavf_status_to_errno(status); + received_op = + (enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high); + if (op_to_poll == received_op) + break; + } + + v_retval = le32_to_cpu(event->desc.cookie_low); + return virtchnl_status_to_errno((enum virtchnl_status_code)v_retval); +} + /** * iavf_verify_api_ver * @adapter: adapter structure @@@ -100,28 -65,55 +100,28 @@@ **/ int iavf_verify_api_ver(struct iavf_adapter *adapter) { - struct virtchnl_version_info *pf_vvi; - struct iavf_hw *hw = &adapter->hw; struct iavf_arq_event_info event; - enum virtchnl_ops op; - enum iavf_status err; + int err;

event.buf_len = IAVF_MAX_AQ_BUF_SIZE; - event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); - if (!event.msg_buf) { - err = -ENOMEM; - goto out; - } - - while (1) { - err = iavf_clean_arq_element(hw, &event, NULL); - /* When the AQ is empty, iavf_clean_arq_element will return - * nonzero and this loop will terminate. - */ - if (err) - goto out_alloc; - op = - (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); - if (op == VIRTCHNL_OP_VERSION) - break; - } - + event.msg_buf = kzalloc(IAVF_MAX_AQ_BUF_SIZE, GFP_KERNEL); + if (!event.msg_buf) + return -ENOMEM;

- err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low); - if (err) - goto out_alloc; + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, VIRTCHNL_OP_VERSION); + if (!err) { + struct virtchnl_version_info *pf_vvi = + (struct virtchnl_version_info *)event.msg_buf; + adapter->pf_version = *pf_vvi;

- if (op != VIRTCHNL_OP_VERSION) { - dev_info(&adapter->pdev->dev, "Invalid reply type %d from PF\n", - op); - err = -EIO; - goto out_alloc; + if (pf_vvi->major > VIRTCHNL_VERSION_MAJOR || + (pf_vvi->major == VIRTCHNL_VERSION_MAJOR && + pf_vvi->minor > VIRTCHNL_VERSION_MINOR)) + err = -EIO; }

- pf_vvi = (struct virtchnl_version_info *)event.msg_buf; - adapter->pf_version = *pf_vvi; - - if ((pf_vvi->major > VIRTCHNL_VERSION_MAJOR) || - ((pf_vvi->major == VIRTCHNL_VERSION_MAJOR) && - (pf_vvi->minor > VIRTCHNL_VERSION_MINOR))) - err = -EIO; - -out_alloc: kfree(event.msg_buf); -out: + return err; }

@@@ -216,17 -208,33 +216,17 @@@ int iavf_get_vf_config(struct iavf_adap { struct iavf_hw *hw = &adapter->hw; struct iavf_arq_event_info event; - enum virtchnl_ops op; - enum iavf_status err; u16 len; + int err;

- len = sizeof(struct virtchnl_vf_resource) + + len = sizeof(struct virtchnl_vf_resource) + IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); event.buf_len = len; - event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); - if (!event.msg_buf) { - err = -ENOMEM; - goto out; - } - - while (1) { - /* When the AQ is empty, iavf_clean_arq_element will return - * nonzero and this loop will terminate. - */ - err = iavf_clean_arq_element(hw, &event, NULL); - if (err) - goto out_alloc; - op = - (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); - if (op == VIRTCHNL_OP_GET_VF_RESOURCES) - break; - } + event.msg_buf = kzalloc(len, GFP_KERNEL); + if (!event.msg_buf) + return -ENOMEM;

- err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low); + err = iavf_poll_virtchnl_msg(hw, &event, VIRTCHNL_OP_GET_VF_RESOURCES); memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len));

/* some PFs send more queues than we should have so validate that @@@ -235,32 -243,48 +235,32 @@@ if (!err) iavf_validate_num_queues(adapter); iavf_vf_parse_hw_config(hw, adapter->vf_res); -out_alloc: + kfree(event.msg_buf); -out: + return err; }

int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) { - struct iavf_hw *hw = &adapter->hw; struct iavf_arq_event_info event; - enum virtchnl_ops op; - enum iavf_status err; + int err; u16 len;

- len = sizeof(struct virtchnl_vlan_caps); + len = sizeof(struct virtchnl_vlan_caps); event.buf_len = len; - event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); - if (!event.msg_buf) { - err = -ENOMEM; - goto out; - } - - while (1) { - /* When the AQ is empty, iavf_clean_arq_element will return - * nonzero and this loop will terminate. - */ - err = iavf_clean_arq_element(hw, &event, NULL); - if (err) - goto out_alloc; - op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); - if (op == VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS) - break; - } + event.msg_buf = kzalloc(len, GFP_KERNEL); + if (!event.msg_buf) + return -ENOMEM;

- err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low); - if (err) - goto out_alloc; + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS); + if (!err) + memcpy(&adapter->vlan_v2_caps, event.msg_buf, + min(event.msg_len, len));

- memcpy(&adapter->vlan_v2_caps, event.msg_buf, min(event.msg_len, len)); -out_alloc: kfree(event.msg_buf); -out: + return err; }

@@@ -429,20 -453,6 +429,20 @@@ void iavf_map_queues(struct iavf_adapte kfree(vimi); }

+/** + * iavf_set_mac_addr_type - Set the correct request type from the filter type + * @virtchnl_ether_addr: pointer to requested list element + * @filter: pointer to requested filter + **/ +static void +iavf_set_mac_addr_type(struct virtchnl_ether_addr *virtchnl_ether_addr, + const struct iavf_mac_filter *filter) +{ + virtchnl_ether_addr->type = filter->is_primary ? + VIRTCHNL_ETHER_ADDR_PRIMARY : + VIRTCHNL_ETHER_ADDR_EXTRA; +} + /** * iavf_add_ether_addrs * @adapter: adapter structure @@@ -498,7 -508,6 +498,7 @@@ void iavf_add_ether_addrs(struct iavf_a list_for_each_entry(f, &adapter->mac_filter_list, list) { if (f->add) { ether_addr_copy(veal->list[i].addr, f->macaddr); + iavf_set_mac_addr_type(&veal->list[i], f); i++; f->add = false; if (i == count) @@@ -568,7 -577,6 +568,7 @@@ void iavf_del_ether_addrs(struct iavf_a list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { if (f->remove) { ether_addr_copy(veal->list[i].addr, f->macaddr); + iavf_set_mac_addr_type(&veal->list[i], f); i++; list_del(&f->list); kfree(f); @@@ -1819,13 -1827,11 +1819,13 @@@ void iavf_del_adv_rss_cfg(struct iavf_a * * Request that the PF reset this VF. No response is expected. **/ -void iavf_request_reset(struct iavf_adapter *adapter) +int iavf_request_reset(struct iavf_adapter *adapter) { + int err; /* Don't check CURRENT_OP - this is always higher priority */ - iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); + err = iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); adapter->current_op = VIRTCHNL_OP_UNKNOWN; + return err; }

/** @@@ -2140,29 -2146,7 +2140,7 @@@ void iavf_virtchnl_completion(struct ia sizeof(adapter->vlan_v2_caps)));

iavf_process_config(adapter); - - /* unlock crit_lock before acquiring rtnl_lock as other - * processes holding rtnl_lock could be waiting for the same - * crit_lock - */ - mutex_unlock(&adapter->crit_lock); - /* VLAN capabilities can change during VFR, so make sure to - * update the netdev features with the new capabilities - */ - rtnl_lock(); - netdev_update_features(netdev); - rtnl_unlock(); - if (iavf_lock_timeout(&adapter->crit_lock, 10000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", - __FUNCTION__); - - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - - iavf_set_queue_vlan_tag_loc(adapter); - + adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; } break; case VIRTCHNL_OP_ENABLE_QUEUES: diff --combined drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index ee28929b9c5f,6a5e9cf6b5da..dd7ff66d422f --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@@ -207,28 -207,26 +207,28 @@@ bool ixgbe_alloc_rx_buffers_zc(struct i }

static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi) + const struct xdp_buff *xdp) { - unsigned int metasize = bi->xdp->data - bi->xdp->data_meta; - unsigned int datasize = bi->xdp->data_end - bi->xdp->data; + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb;

+ net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - bi->xdp->data_end - bi->xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL;

- skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + }

- xsk_buff_free(bi->xdp); - bi->xdp = NULL; return skb; }

@@@ -319,15 -317,12 +319,15 @@@ int ixgbe_clean_rx_irq_zc(struct ixgbe_ }

/* XDP_PASS path */ - skb = ixgbe_construct_skb_zc(rx_ring, bi); + skb = ixgbe_construct_skb_zc(rx_ring, bi->xdp); if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; break; }

+ xsk_buff_free(bi->xdp); + bi->xdp = NULL; + cleaned_count++; ixgbe_inc_ntc(rx_ring);

@@@ -395,12 -390,14 +395,14 @@@ static bool ixgbe_xmit_zc(struct ixgbe_ u32 cmd_type;

while (budget-- > 0) { - if (unlikely(!ixgbe_desc_unused(xdp_ring)) || - !netif_carrier_ok(xdp_ring->netdev)) { + if (unlikely(!ixgbe_desc_unused(xdp_ring))) { work_done = false; break; }

+ if (!netif_carrier_ok(xdp_ring->netdev)) + break; + if (!xsk_tx_peek_desc(pool, &desc)) break;

diff --combined drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 77a0d9d7e65a,2881f5b2b5f4..407a1f8e3059 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@@ -127,7 -127,7 +127,7 @@@ bool sxgbe_eee_init(struct sxgbe_priv_d /* MAC core supports the EEE feature. */ if (priv->hw_cap.eee) { /* Check if the PHY supports EEE */ - if (phy_init_eee(ndev->phydev, 1)) + if (phy_init_eee(ndev->phydev, true)) return false;

priv->eee_active = 1; @@@ -2285,18 -2285,18 +2285,18 @@@ static int __init sxgbe_cmdline_opt(cha char *opt;

if (!str || !*str) - return -EINVAL; + return 1; while ((opt = strsep(&str, ",")) != NULL) { if (!strncmp(opt, "eee_timer:", 10)) { if (kstrtoint(opt + 10, 0, &eee_timer)) goto err; } } - return 0; + return 1;

err: pr_err("%s: ERROR broken module parameter conversion\n", __func__); - return -EINVAL; + return 1; }

__setup("sxgbeeth=", sxgbe_cmdline_opt); diff --combined drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b745d624b2cb,422e3225f476..cf4e077d21ff --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@@ -938,15 -938,105 +938,15 @@@ static void stmmac_mac_flow_ctrl(struc priv->pause, tx_cnt); }

-static void stmmac_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - __ETHTOOL_DECLARE_LINK_MODE_MASK(mac_supported) = { 0, }; - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - int tx_cnt = priv->plat->tx_queues_to_use; - int max_speed = priv->plat->max_speed; - - phylink_set(mac_supported, 10baseT_Half); - phylink_set(mac_supported, 10baseT_Full); - phylink_set(mac_supported, 100baseT_Half); - phylink_set(mac_supported, 100baseT_Full); - phylink_set(mac_supported, 1000baseT_Half); - phylink_set(mac_supported, 1000baseT_Full); - phylink_set(mac_supported, 1000baseKX_Full); - - phylink_set(mac_supported, Autoneg); - phylink_set(mac_supported, Pause); - phylink_set(mac_supported, Asym_Pause); - phylink_set_port_modes(mac_supported); - - /* Cut down 1G if asked to */ - if ((max_speed > 0) && (max_speed < 1000)) { - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); - } else if (priv->plat->has_gmac4) { - if (!max_speed || max_speed >= 2500) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 2500baseX_Full); - } - } else if (priv->plat->has_xgmac) { - if (!max_speed || (max_speed >= 2500)) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 2500baseX_Full); - } - if (!max_speed || (max_speed >= 5000)) { - phylink_set(mac_supported, 5000baseT_Full); - } - if (!max_speed || (max_speed >= 10000)) { - phylink_set(mac_supported, 10000baseSR_Full); - phylink_set(mac_supported, 10000baseLR_Full); - phylink_set(mac_supported, 10000baseER_Full); - phylink_set(mac_supported, 10000baseLRM_Full); - phylink_set(mac_supported, 10000baseT_Full); - phylink_set(mac_supported, 10000baseKX4_Full); - phylink_set(mac_supported, 10000baseKR_Full); - } - if (!max_speed || (max_speed >= 25000)) { - phylink_set(mac_supported, 25000baseCR_Full); - phylink_set(mac_supported, 25000baseKR_Full); - phylink_set(mac_supported, 25000baseSR_Full); - } - if (!max_speed || (max_speed >= 40000)) { - phylink_set(mac_supported, 40000baseKR4_Full); - phylink_set(mac_supported, 40000baseCR4_Full); - phylink_set(mac_supported, 40000baseSR4_Full); - phylink_set(mac_supported, 40000baseLR4_Full); - } - if (!max_speed || (max_speed >= 50000)) { - phylink_set(mac_supported, 50000baseCR2_Full); - phylink_set(mac_supported, 50000baseKR2_Full); - phylink_set(mac_supported, 50000baseSR2_Full); - phylink_set(mac_supported, 50000baseKR_Full); - phylink_set(mac_supported, 50000baseSR_Full); - phylink_set(mac_supported, 50000baseCR_Full); - phylink_set(mac_supported, 50000baseLR_ER_FR_Full); - phylink_set(mac_supported, 50000baseDR_Full); - } - if (!max_speed || (max_speed >= 100000)) { - phylink_set(mac_supported, 100000baseKR4_Full); - phylink_set(mac_supported, 100000baseSR4_Full); - phylink_set(mac_supported, 100000baseCR4_Full); - phylink_set(mac_supported, 100000baseLR4_ER4_Full); - phylink_set(mac_supported, 100000baseKR2_Full); - phylink_set(mac_supported, 100000baseSR2_Full); - phylink_set(mac_supported, 100000baseCR2_Full); - phylink_set(mac_supported, 100000baseLR2_ER2_FR2_Full); - phylink_set(mac_supported, 100000baseDR2_Full); - } - } - - /* Half-Duplex can only work with single queue */ - if (tx_cnt > 1) { - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 1000baseT_Half); - }

- linkmode_and(supported, supported, mac_supported); - linkmode_andnot(supported, supported, mask); + if (!priv->hw->xpcs) + return NULL;

- linkmode_and(state->advertising, state->advertising, mac_supported); - linkmode_andnot(state->advertising, state->advertising, mask); - - /* If PCS is supported, check which modes it supports. */ - if (priv->hw->xpcs) - xpcs_validate(priv->hw->xpcs, supported, state); + return &priv->hw->xpcs->pcs; }

static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@@ -1085,8 -1175,7 +1085,8 @@@ static void stmmac_mac_link_up(struct p }

static const struct phylink_mac_ops stmmac_phylink_mac_ops = { - .validate = stmmac_validate, + .validate = phylink_generic_validate, + .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, @@@ -1166,12 -1255,12 +1166,12 @@@ static int stmmac_phy_setup(struct stmm { struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); + int max_speed = priv->plat->max_speed; int mode = priv->plat->phy_interface; struct phylink *phylink;

priv->phylink_config.dev = &priv->dev->dev; priv->phylink_config.type = PHYLINK_NETDEV; - priv->phylink_config.pcs_poll = true; if (priv->plat->mdio_bus_data) priv->phylink_config.ovr_an_inband = mdio_bus_data->xpcs_an_inband; @@@ -1179,50 -1268,14 +1179,50 @@@ if (!fwnode) fwnode = dev_fwnode(priv->device);

+ /* Set the platform/firmware specified interface mode */ + __set_bit(mode, priv->phylink_config.supported_interfaces); + + /* If we have an xpcs, it defines which PHY interfaces are supported. */ + if (priv->hw->xpcs) + xpcs_get_interfaces(priv->hw->xpcs, + priv->phylink_config.supported_interfaces); + + priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; + + if (!max_speed || max_speed >= 1000) + priv->phylink_config.mac_capabilities |= MAC_1000; + + if (priv->plat->has_gmac4) { + if (!max_speed || max_speed >= 2500) + priv->phylink_config.mac_capabilities |= MAC_2500FD; + } else if (priv->plat->has_xgmac) { + if (!max_speed || max_speed >= 2500) + priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (!max_speed || max_speed >= 5000) + priv->phylink_config.mac_capabilities |= MAC_5000FD; + if (!max_speed || max_speed >= 10000) + priv->phylink_config.mac_capabilities |= MAC_10000FD; + if (!max_speed || max_speed >= 25000) + priv->phylink_config.mac_capabilities |= MAC_25000FD; + if (!max_speed || max_speed >= 40000) + priv->phylink_config.mac_capabilities |= MAC_40000FD; + if (!max_speed || max_speed >= 50000) + priv->phylink_config.mac_capabilities |= MAC_50000FD; + if (!max_speed || max_speed >= 100000) + priv->phylink_config.mac_capabilities |= MAC_100000FD; + } + + /* Half-Duplex can only work with single queue */ + if (priv->plat->tx_queues_to_use > 1) + priv->phylink_config.mac_capabilities &= + ~(MAC_10HD | MAC_100HD | MAC_1000HD); + phylink = phylink_create(&priv->phylink_config, fwnode, mode, &stmmac_phylink_mac_ops); if (IS_ERR(phylink)) return PTR_ERR(phylink);

- if (priv->hw->xpcs) - phylink_set_pcs(phylink, &priv->hw->xpcs->pcs); - priv->phylink = phylink; return 0; } @@@ -2209,6 -2262,23 +2209,23 @@@ static void stmmac_stop_tx_dma(struct s stmmac_stop_tx(priv, priv->ioaddr, chan); }

+ static void stmmac_enable_all_dma_irq(struct stmmac_priv *priv) + { + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 dma_csr_ch = max(rx_channels_count, tx_channels_count); + u32 chan; + + for (chan = 0; chan < dma_csr_ch; chan++) { + struct stmmac_channel *ch = &priv->channel[chan]; + unsigned long flags; + + spin_lock_irqsave(&ch->lock, flags); + stmmac_enable_dma_irq(priv, priv->ioaddr, chan, 1, 1); + spin_unlock_irqrestore(&ch->lock, flags); + } + } + /** * stmmac_start_all_dma - start all RX and TX DMA channels * @priv: driver private structure @@@ -2851,8 -2921,10 +2868,10 @@@ static int stmmac_init_dma_engine(struc stmmac_axi(priv, priv->ioaddr, priv->plat->axi);

/* DMA CSR Channel configuration */ - for (chan = 0; chan < dma_csr_ch; chan++) + for (chan = 0; chan < dma_csr_ch; chan++) { stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); + stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 1, 1); + }

/* DMA RX Channel Configuration */ for (chan = 0; chan < rx_channels_count; chan++) { @@@ -3708,6 -3780,7 +3727,7 @@@ static int stmmac_open(struct net_devic

stmmac_enable_all_queues(priv); netif_tx_start_all_queues(priv->dev); + stmmac_enable_all_dma_irq(priv);

return 0;

@@@ -6457,8 -6530,10 +6477,10 @@@ int stmmac_xdp_open(struct net_device * }

/* DMA CSR Channel configuration */ - for (chan = 0; chan < dma_csr_ch; chan++) + for (chan = 0; chan < dma_csr_ch; chan++) { stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); + stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 1, 1); + }

/* Adjust Split header */ sph_en = (priv->hw->rx_csum > 0) && priv->sph; @@@ -6519,6 -6594,7 +6541,7 @@@ stmmac_enable_all_queues(priv); netif_carrier_on(dev); netif_tx_start_all_queues(dev); + stmmac_enable_all_dma_irq(priv);

return 0;

@@@ -7398,6 -7474,7 +7421,7 @@@ int stmmac_resume(struct device *dev stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw);

stmmac_enable_all_queues(priv); + stmmac_enable_all_dma_irq(priv);

mutex_unlock(&priv->lock); rtnl_unlock(); @@@ -7414,7 -7491,7 +7438,7 @@@ static int __init stmmac_cmdline_opt(ch char *opt;

if (!str || !*str) - return -EINVAL; + return 1; while ((opt = strsep(&str, ",")) != NULL) { if (!strncmp(opt, "debug:", 6)) { if (kstrtoint(opt + 6, 0, &debug)) @@@ -7445,11 -7522,11 +7469,11 @@@ goto err; } } - return 0; + return 1;

err: pr_err("%s: ERROR broken module parameter conversion", __func__); - return -EINVAL; + return 1; }

__setup("stmmaceth=", stmmac_cmdline_opt); diff --combined drivers/ptp/ptp_ocp.c index 50982623aafa,17ad5f0d13b2..608d1a0eb141 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@@ -52,8 -52,6 +52,8 @@@ struct ocp_reg u32 servo_offset_i; u32 servo_drift_p; u32 servo_drift_i; + u32 status_offset; + u32 status_drift; };

#define OCP_CTRL_ENABLE BIT(0) @@@ -90,10 -88,9 +90,10 @@@ struct tod_reg #define TOD_CTRL_GNSS_MASK ((1U << 4) - 1) #define TOD_CTRL_GNSS_SHIFT 24

-#define TOD_STATUS_UTC_MASK 0xff -#define TOD_STATUS_UTC_VALID BIT(8) -#define TOD_STATUS_LEAP_VALID BIT(16) +#define TOD_STATUS_UTC_MASK 0xff +#define TOD_STATUS_UTC_VALID BIT(8) +#define TOD_STATUS_LEAP_ANNOUNCE BIT(12) +#define TOD_STATUS_LEAP_VALID BIT(16)

struct ts_reg { u32 enable; @@@ -610,7 -607,7 +610,7 @@@ ptp_ocp_settime(struct ptp_clock_info * }

static void - __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u64 adj_val) + __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u32 adj_val) { u32 select, ctrl;

@@@ -618,7 -615,7 +618,7 @@@ iowrite32(OCP_SELECT_CLK_REG, &bp->reg->select);

iowrite32(adj_val, &bp->reg->offset_ns); - iowrite32(adj_val & 0x7f, &bp->reg->offset_window_ns); + iowrite32(NSEC_PER_SEC, &bp->reg->offset_window_ns);

ctrl = OCP_CTRL_ADJUST_OFFSET | OCP_CTRL_ENABLE; iowrite32(ctrl, &bp->reg->ctrl); @@@ -627,6 -624,22 +627,22 @@@ iowrite32(select >> 16, &bp->reg->select); }

+ static void + ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) + { + struct timespec64 ts; + unsigned long flags; + int err; + + spin_lock_irqsave(&bp->lock, flags); + err = __ptp_ocp_gettime_locked(bp, &ts, NULL); + if (likely(!err)) { + timespec64_add_ns(&ts, delta_ns); + __ptp_ocp_settime_locked(bp, &ts); + } + spin_unlock_irqrestore(&bp->lock, flags); + } + static int ptp_ocp_adjtime(struct ptp_clock_info *ptp_info, s64 delta_ns) { @@@ -634,6 -647,11 +650,11 @@@ unsigned long flags; u32 adj_ns, sign;

+ if (delta_ns > NSEC_PER_SEC || -delta_ns > NSEC_PER_SEC) { + ptp_ocp_adjtime_coarse(bp, delta_ns); + return 0; + } + sign = delta_ns < 0 ? BIT(31) : 0; adj_ns = sign ? -delta_ns : delta_ns;

@@@ -741,31 -759,12 +762,31 @@@ __ptp_ocp_clear_drift_locked(struct ptp iowrite32(select >> 16, &bp->reg->select); }

+static void +ptp_ocp_utc_distribute(struct ptp_ocp *bp, u32 val) +{ + unsigned long flags; + + spin_lock_irqsave(&bp->lock, flags); + + bp->utc_tai_offset = val; + + if (bp->irig_out) + iowrite32(val, &bp->irig_out->adj_sec); + if (bp->dcf_out) + iowrite32(val, &bp->dcf_out->adj_sec); + if (bp->nmea_out) + iowrite32(val, &bp->nmea_out->adj_sec); + + spin_unlock_irqrestore(&bp->lock, flags); +} + static void ptp_ocp_watchdog(struct timer_list *t) { struct ptp_ocp *bp = from_timer(bp, t, watchdog); unsigned long flags; - u32 status; + u32 status, utc_offset;

status = ioread32(&bp->pps_to_clk->status);

@@@ -782,17 -781,6 +803,17 @@@ bp->gnss_lost = 0; }

+ /* if GNSS provides correct data we can rely on + * it to get leap second information + */ + if (bp->tod) { + status = ioread32(&bp->tod->utc_status); + utc_offset = status & TOD_STATUS_UTC_MASK; + if (status & TOD_STATUS_UTC_VALID && + utc_offset != bp->utc_tai_offset) + ptp_ocp_utc_distribute(bp, utc_offset); + } + mod_timer(&bp->watchdog, jiffies + HZ); }

@@@ -861,6 -849,25 +882,6 @@@ ptp_ocp_init_clock(struct ptp_ocp *bp return 0; }

-static void -ptp_ocp_utc_distribute(struct ptp_ocp *bp, u32 val) -{ - unsigned long flags; - - spin_lock_irqsave(&bp->lock, flags); - - bp->utc_tai_offset = val; - - if (bp->irig_out) - iowrite32(val, &bp->irig_out->adj_sec); - if (bp->dcf_out) - iowrite32(val, &bp->dcf_out->adj_sec); - if (bp->nmea_out) - iowrite32(val, &bp->nmea_out->adj_sec); - - spin_unlock_irqrestore(&bp->lock, flags); -} - static void ptp_ocp_tod_init(struct ptp_ocp *bp) { @@@ -876,26 -883,45 +897,26 @@@ ptp_ocp_utc_distribute(bp, reg & TOD_STATUS_UTC_MASK); }

-static void -ptp_ocp_tod_info(struct ptp_ocp *bp) +static const char * +ptp_ocp_tod_proto_name(const int idx) { static const char * const proto_name[] = { "NMEA", "NMEA_ZDA", "NMEA_RMC", "NMEA_none", "UBX", "UBX_UTC", "UBX_LS", "UBX_none" }; + return proto_name[idx]; +} + +static const char * +ptp_ocp_tod_gnss_name(int idx) +{ static const char * const gnss_name[] = { "ALL", "COMBINED", "GPS", "GLONASS", "GALILEO", "BEIDOU", + "Unknown" }; - u32 version, ctrl, reg; - int idx; - - version = ioread32(&bp->tod->version); - dev_info(&bp->pdev->dev, "TOD Version %d.%d.%d\n", - version >> 24, (version >> 16) & 0xff, version & 0xffff); - - ctrl = ioread32(&bp->tod->ctrl); - idx = ctrl & TOD_CTRL_PROTOCOL ? 4 : 0; - idx += (ctrl >> 16) & 3; - dev_info(&bp->pdev->dev, "control: %x\n", ctrl); - dev_info(&bp->pdev->dev, "TOD Protocol %s %s\n", proto_name[idx], - ctrl & TOD_CTRL_ENABLE ? "enabled" : ""); - - idx = (ctrl >> TOD_CTRL_GNSS_SHIFT) & TOD_CTRL_GNSS_MASK; - if (idx < ARRAY_SIZE(gnss_name)) - dev_info(&bp->pdev->dev, "GNSS %s\n", gnss_name[idx]); - - reg = ioread32(&bp->tod->status); - dev_info(&bp->pdev->dev, "status: %x\n", reg); - - reg = ioread32(&bp->tod->adj_sec); - dev_info(&bp->pdev->dev, "correction: %d\n", reg); - - reg = ioread32(&bp->tod->utc_status); - dev_info(&bp->pdev->dev, "utc_status: %x\n", reg); - dev_info(&bp->pdev->dev, "utc_offset: %d valid:%d leap_valid:%d\n", - reg & TOD_STATUS_UTC_MASK, reg & TOD_STATUS_UTC_VALID ? 1 : 0, - reg & TOD_STATUS_LEAP_VALID ? 1 : 0); + if (idx > ARRAY_SIZE(gnss_name)) + idx = ARRAY_SIZE(gnss_name) - 1; + return gnss_name[idx]; }

static int @@@ -1948,76 -1974,6 +1969,76 @@@ available_clock_sources_show(struct dev } static DEVICE_ATTR_RO(available_clock_sources);

+static ssize_t +clock_status_drift_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + int res; + + val = ioread32(&bp->reg->status_drift); + res = (val & ~INT_MAX) ? -1 : 1; + res *= (val & INT_MAX); + return sysfs_emit(buf, "%d\n", res); +} +static DEVICE_ATTR_RO(clock_status_drift); + +static ssize_t +clock_status_offset_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + int res; + + val = ioread32(&bp->reg->status_offset); + res = (val & ~INT_MAX) ? -1 : 1; + res *= (val & INT_MAX); + return sysfs_emit(buf, "%d\n", res); +} +static DEVICE_ATTR_RO(clock_status_offset); + +static ssize_t +tod_correction_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + int res; + + val = ioread32(&bp->tod->adj_sec); + res = (val & ~INT_MAX) ? -1 : 1; + res *= (val & INT_MAX); + return sysfs_emit(buf, "%d\n", res); +} + +static ssize_t +tod_correction_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + unsigned long flags; + int err, res; + u32 val = 0; + + err = kstrtos32(buf, 0, &res); + if (err) + return err; + if (res < 0) { + res *= -1; + val |= BIT(31); + } + val |= res; + + spin_lock_irqsave(&bp->lock, flags); + iowrite32(val, &bp->tod->adj_sec); + spin_unlock_irqrestore(&bp->lock, flags); + + return count; +} +static DEVICE_ATTR_RW(tod_correction); + static struct attribute *timecard_attrs[] = { &dev_attr_serialnum.attr, &dev_attr_gnss_sync.attr, @@@ -2029,12 -1985,9 +2050,12 @@@ &dev_attr_sma4.attr, &dev_attr_available_sma_inputs.attr, &dev_attr_available_sma_outputs.attr, + &dev_attr_clock_status_drift.attr, + &dev_attr_clock_status_offset.attr, &dev_attr_irig_b_mode.attr, &dev_attr_utc_tai_offset.attr, &dev_attr_ts_window_adjust.attr, + &dev_attr_tod_correction.attr, NULL, }; ATTRIBUTE_GROUPS(timecard); @@@ -2247,57 -2200,6 +2268,57 @@@ ptp_ocp_summary_show(struct seq_file *s } DEFINE_SHOW_ATTRIBUTE(ptp_ocp_summary);

+static int +ptp_ocp_tod_status_show(struct seq_file *s, void *data) +{ + struct device *dev = s->private; + struct ptp_ocp *bp; + u32 val; + int idx; + + bp = dev_get_drvdata(dev); + + val = ioread32(&bp->tod->ctrl); + if (!(val & TOD_CTRL_ENABLE)) { + seq_printf(s, "TOD Slave disabled\n"); + return 0; + } + seq_printf(s, "TOD Slave enabled, Control Register 0x%08X\n", val); + + idx = val & TOD_CTRL_PROTOCOL ? 4 : 0; + idx += (val >> 16) & 3; + seq_printf(s, "Protocol %s\n", ptp_ocp_tod_proto_name(idx)); + + idx = (val >> TOD_CTRL_GNSS_SHIFT) & TOD_CTRL_GNSS_MASK; + seq_printf(s, "GNSS %s\n", ptp_ocp_tod_gnss_name(idx)); + + val = ioread32(&bp->tod->version); + seq_printf(s, "TOD Version %d.%d.%d\n", + val >> 24, (val >> 16) & 0xff, val & 0xffff); + + val = ioread32(&bp->tod->status); + seq_printf(s, "Status register: 0x%08X\n", val); + + val = ioread32(&bp->tod->adj_sec); + idx = (val & ~INT_MAX) ? -1 : 1; + idx *= (val & INT_MAX); + seq_printf(s, "Correction seconds: %d\n", idx); + + val = ioread32(&bp->tod->utc_status); + seq_printf(s, "UTC status register: 0x%08X\n", val); + seq_printf(s, "UTC offset: %d valid:%d\n", + val & TOD_STATUS_UTC_MASK, val & TOD_STATUS_UTC_VALID ? 1 : 0); + seq_printf(s, "Leap second info valid:%d, Leap second announce %d\n", + val & TOD_STATUS_LEAP_VALID ? 1 : 0, + val & TOD_STATUS_LEAP_ANNOUNCE ? 1 : 0); + + val = ioread32(&bp->tod->leap); + seq_printf(s, "Time to next leap second (in sec): %d\n", (s32) val); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(ptp_ocp_tod_status); + static struct dentry *ptp_ocp_debugfs_root;

static void @@@ -2309,9 -2211,6 +2330,9 @@@ ptp_ocp_debugfs_add_device(struct ptp_o bp->debug_root = d; debugfs_create_file("summary", 0444, bp->debug_root, &bp->dev, &ptp_ocp_summary_fops); + if (bp->tod) + debugfs_create_file("tod_status", 0444, bp->debug_root, + &bp->dev, &ptp_ocp_tod_status_fops); }

static void @@@ -2490,6 -2389,8 +2511,6 @@@ ptp_ocp_info(struct ptp_ocp *bp u32 reg;

ptp_ocp_phc_info(bp); - if (bp->tod) - ptp_ocp_tod_info(bp);

if (bp->image) { u32 ver = ioread32(&bp->image->version); diff --combined drivers/tty/serial/sc16is7xx.c index 25d67b8c4db7,38d1c0748533..3a6c68e19c80 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@@ -734,12 -734,15 +734,15 @@@ static irqreturn_t sc16is7xx_irq(int ir static void sc16is7xx_tx_proc(struct kthread_work *ws) { struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port); + struct sc16is7xx_port *s = dev_get_drvdata(port->dev);

if ((port->rs485.flags & SER_RS485_ENABLED) && (port->rs485.delay_rts_before_send > 0)) msleep(port->rs485.delay_rts_before_send);

+ mutex_lock(&s->efr_lock); sc16is7xx_handle_tx(port); + mutex_unlock(&s->efr_lock); }

static void sc16is7xx_reconf_rs485(struct uart_port *port) @@@ -1440,9 -1443,11 +1443,9 @@@ static int sc16is7xx_spi_probe(struct s return sc16is7xx_probe(&spi->dev, devtype, regmap, spi->irq); }

-static int sc16is7xx_spi_remove(struct spi_device *spi) +static void sc16is7xx_spi_remove(struct spi_device *spi) { sc16is7xx_remove(&spi->dev); - - return 0; }

static const struct spi_device_id sc16is7xx_spi_id_table[] = { diff --combined include/net/bluetooth/hci_core.h index f5caff1ddb29,e336e9c1dda4..d5377740e99c --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@@ -258,15 -258,6 +258,15 @@@ struct adv_info

#define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F

+struct monitored_device { + struct list_head list; + + bdaddr_t bdaddr; + __u8 addr_type; + __u16 handle; + bool notified; +}; + struct adv_pattern { struct list_head list; __u8 ad_type; @@@ -303,9 -294,6 +303,9 @@@ struct adv_monitor

#define HCI_MAX_SHORT_NAME_LENGTH 10

+#define HCI_CONN_HANDLE_UNSET 0xffff +#define HCI_CONN_HANDLE_MAX 0x0eff + /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7

@@@ -603,9 -591,6 +603,9 @@@ struct hci_dev

struct delayed_work interleave_scan;

+ struct list_head monitored_devices; + bool advmon_pend_notify; + #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif @@@ -1504,6 -1489,14 +1504,14 @@@ void hci_conn_del_sysfs(struct hci_con /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV))

+ /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: + * + * C24: Mandatory if the LE Controller supports Connection State and either + * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported + */ + #define use_enhanced_conn_complete(dev) (ll_privacy_capable(dev) || \ + ext_adv_capable(dev)) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01

@@@ -1862,8 -1855,6 +1870,8 @@@ void mgmt_adv_monitor_removed(struct hc int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type);

u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --combined include/net/ndisc.h index aac3a42de432,47ffb360ddfa..da7eec8669ec --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@@ -447,15 -447,10 +447,15 @@@ void ndisc_cleanup(void)

int ndisc_rcv(struct sk_buff *skb);

+struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, + const struct in6_addr *saddr, u64 nonce); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce);

+void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, + const struct in6_addr *saddr); + void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, @@@ -480,9 -475,9 +480,9 @@@ int igmp6_late_init(void) void igmp6_cleanup(void); void igmp6_late_cleanup(void);

- int igmp6_event_query(struct sk_buff *skb); + void igmp6_event_query(struct sk_buff *skb);

- int igmp6_event_report(struct sk_buff *skb); + void igmp6_event_report(struct sk_buff *skb);

#ifdef CONFIG_SYSCTL diff --combined net/batman-adv/hard-interface.c index b25afc7ff59c,35fadb924849..83fb51b6e299 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@@ -9,11 -9,11 +9,11 @@@

#include <linux/atomic.h> #include <linux/byteorder/generic.h> +#include <linux/container_of.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> -#include <linux/kernel.h> #include <linux/kref.h> #include <linux/limits.h> #include <linux/list.h> @@@ -149,25 -149,28 +149,28 @@@ static bool batadv_is_on_batman_iface(c struct net *net = dev_net(net_dev); struct net_device *parent_dev; struct net *parent_net; + int iflink; bool ret;

/* check if this is a batman-adv mesh interface */ if (batadv_softif_is_valid(net_dev)) return true;

- /* no more parents..stop recursion */ - if (dev_get_iflink(net_dev) == 0 || - dev_get_iflink(net_dev) == net_dev->ifindex) + iflink = dev_get_iflink(net_dev); + if (iflink == 0) return false;

parent_net = batadv_getlink_net(net_dev, net);

+ /* iflink to itself, most likely physical device */ + if (net == parent_net && iflink == net_dev->ifindex) + return false; + /* recurse over the parent device */ - parent_dev = __dev_get_by_index((struct net *)parent_net, - dev_get_iflink(net_dev)); + parent_dev = __dev_get_by_index((struct net *)parent_net, iflink); - /* if we got a NULL parent_dev there is something broken.. */ if (!parent_dev) { - pr_err("Cannot find parent device\n"); + pr_warn("Cannot find parent device. Skipping batadv-on-batadv check for %s\n", + net_dev->name); return false; }

@@@ -214,14 -217,15 +217,15 @@@ static struct net_device *batadv_get_re struct net_device *real_netdev = NULL; struct net *real_net; struct net *net; - int ifindex; + int iflink;

ASSERT_RTNL();

if (!netdev) return NULL;

- if (netdev->ifindex == dev_get_iflink(netdev)) { + iflink = dev_get_iflink(netdev); + if (iflink == 0) { dev_hold(netdev); return netdev; } @@@ -231,9 -235,16 +235,16 @@@ goto out;

net = dev_net(hard_iface->soft_iface); - ifindex = dev_get_iflink(netdev); real_net = batadv_getlink_net(netdev, net); - real_netdev = dev_get_by_index(real_net, ifindex); + + /* iflink to itself, most likely physical device */ + if (net == real_net && netdev->ifindex == iflink) { + real_netdev = netdev; + dev_hold(real_netdev); + goto out; + } + + real_netdev = dev_get_by_index(real_net, iflink);

out: batadv_hardif_put(hard_iface); diff --combined net/bluetooth/hci_core.c index 5bde0ec41177,2882bc7d79d7..b4782a6c1025 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@@ -2503,7 -2503,6 +2503,7 @@@ struct hci_dev *hci_alloc_dev_priv(int INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); INIT_LIST_HEAD(&hdev->blocked_keys); + INIT_LIST_HEAD(&hdev->monitored_devices);

INIT_LIST_HEAD(&hdev->local_codecs); INIT_WORK(&hdev->rx_work, hci_rx_work); @@@ -2739,6 -2738,7 +2739,7 @@@ void hci_release_dev(struct hci_dev *hd hci_dev_unlock(hdev);

ida_simple_remove(&hci_index_ida, hdev->id); + kfree_skb(hdev->sent_cmd); kfree(hdev); } EXPORT_SYMBOL(hci_release_dev); @@@ -3667,8 -3667,8 +3668,8 @@@ static void hci_scodata_packet(struct h sco_recv_scodata(conn, skb); return; } else { - bt_dev_err(hdev, "SCO packet for unknown connection handle %d", - handle); + bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", + handle); }

kfree_skb(skb); diff --combined net/bluetooth/hci_sync.c index 6e71aa6b6fea,9ba2a1a7d481..8fa57ef0bbc9 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@@ -382,9 -382,6 +382,9 @@@ int hci_cmd_sync_queue(struct hci_dev * { struct hci_cmd_sync_work_entry *entry;

+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return -ENODEV; + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; @@@ -1844,6 -1841,7 +1844,7 @@@ static u8 hci_update_accept_list_sync(s struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; + u8 filter_policy; int err;

/* Pause advertising if resolving list can be used as controllers are @@@ -1930,6 -1928,8 +1931,8 @@@ err = -EINVAL;

done: + filter_policy = err ? 0x00 : 0x01; + /* Enable address resolution when LL Privacy is enabled. */ err = hci_le_set_addr_resolution_enable_sync(hdev, 0x01); if (err) @@@ -1940,7 -1940,7 +1943,7 @@@ hci_resume_advertising_sync(hdev);

/* Select filter policy to use accept list */ - return err ? 0x00 : 0x01; + return filter_policy; }

/* Returns true if an le connection is in the scanning state */ @@@ -3265,10 -3265,10 +3268,10 @@@ static int hci_le_set_event_mask_sync(s if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) events[0] |= 0x40; /* LE Data Length Change */

- /* If the controller supports LL Privacy feature, enable - * the corresponding event. + /* If the controller supports LL Privacy feature or LE Extended Adv, + * enable the corresponding event. */ - if (hdev->le_features[0] & HCI_LE_LL_PRIVACY) + if (use_enhanced_conn_complete(hdev)) events[1] |= 0x02; /* LE Enhanced Connection Complete */

/* If the controller supports Extended Scanner Filter @@@ -4109,9 -4109,9 +4112,9 @@@ int hci_dev_close_sync(struct hci_dev * hci_inquiry_cache_flush(hdev); hci_pend_le_actions_clear(hdev); hci_conn_hash_flush(hdev); - hci_dev_unlock(hdev); - + /* Prevent data races on hdev->smp_data or hdev->smp_bredr_data */ smp_unregister(hdev); + hci_dev_unlock(hdev);

hci_sock_dev_event(hdev, HCI_DEV_DOWN);

@@@ -5143,8 -5143,8 +5146,8 @@@ static void set_ext_conn_params(struct p->max_ce_len = cpu_to_le16(0x0000); }

-int hci_le_ext_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, - u8 own_addr_type) +static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn, u8 own_addr_type) { struct hci_cp_le_ext_create_conn *cp; struct hci_cp_le_ext_conn_param *p; @@@ -5188,7 -5188,7 +5191,7 @@@ return __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_EXT_CREATE_CONN, plen, data, HCI_EV_LE_ENHANCED_CONN_COMPLETE, - HCI_CMD_TIMEOUT, NULL); + conn->conn_timeout, NULL); }

int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) @@@ -5273,9 -5273,18 +5276,18 @@@ cp.min_ce_len = cpu_to_le16(0x0000); cp.max_ce_len = cpu_to_le16(0x0000);

+ /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 2261: + * + * If this event is unmasked and the HCI_LE_Connection_Complete event + * is unmasked, only the HCI_LE_Enhanced_Connection_Complete event is + * sent when a new connection has been created. + */ err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CREATE_CONN, - sizeof(cp), &cp, HCI_EV_LE_CONN_COMPLETE, - HCI_CMD_TIMEOUT, NULL); + sizeof(cp), &cp, + use_enhanced_conn_complete(hdev) ? + HCI_EV_LE_ENHANCED_CONN_COMPLETE : + HCI_EV_LE_CONN_COMPLETE, + conn->conn_timeout, NULL);

done: /* Re-enable advertising after the connection attempt is finished. */ diff --combined net/bluetooth/mgmt.c index 5dd684e0b259,533cf60673a3..71aff6e65e7c --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@@ -42,7 -42,7 +42,7 @@@ #include "aosp.h"

#define MGMT_VERSION 1 -#define MGMT_REVISION 21 +#define MGMT_REVISION 22

static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@@ -174,8 -174,6 +174,8 @@@ static const u16 mgmt_events[] = MGMT_EV_ADV_MONITOR_REMOVED, MGMT_EV_CONTROLLER_SUSPEND, MGMT_EV_CONTROLLER_RESUME, + MGMT_EV_ADV_MONITOR_DEVICE_FOUND, + MGMT_EV_ADV_MONITOR_DEVICE_LOST, };

static const u16 mgmt_untrusted_commands[] = { @@@ -1220,7 -1218,13 +1220,13 @@@ static int new_settings(struct hci_dev static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp = cmd->param; + struct mgmt_mode *cp; + + /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + + cp = cmd->param;

bt_dev_dbg(hdev, "err %d", err);

@@@ -1244,7 -1248,7 +1250,7 @@@ mgmt_status(err)); }

- mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); }

static int set_powered_sync(struct hci_dev *hdev, void *data) @@@ -1283,7 -1287,7 +1289,7 @@@ static int set_powered(struct sock *sk goto failed; }

- cmd = mgmt_pending_new(sk, MGMT_OP_SET_POWERED, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_SET_POWERED, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@@ -1292,6 -1296,9 +1298,9 @@@ err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, mgmt_set_powered_complete);

+ if (err < 0) + mgmt_pending_remove(cmd); + failed: hci_dev_unlock(hdev); return err; @@@ -1385,6 -1392,10 +1394,10 @@@ static void mgmt_set_discoverable_compl

bt_dev_dbg(hdev, "err %d", err);

+ /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) + return; + hci_dev_lock(hdev);

if (err) { @@@ -1404,7 -1415,7 +1417,7 @@@ new_settings(hdev, cmd->sk);

done: - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); hci_dev_unlock(hdev); }

@@@ -1513,7 -1524,7 +1526,7 @@@ static int set_discoverable(struct soc goto failed; }

- cmd = mgmt_pending_new(sk, MGMT_OP_SET_DISCOVERABLE, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_SET_DISCOVERABLE, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@@ -1540,6 -1551,9 +1553,9 @@@ err = hci_cmd_sync_queue(hdev, set_discoverable_sync, cmd, mgmt_set_discoverable_complete);

+ if (err < 0) + mgmt_pending_remove(cmd); + failed: hci_dev_unlock(hdev); return err; @@@ -1552,6 -1566,10 +1568,10 @@@ static void mgmt_set_connectable_comple

bt_dev_dbg(hdev, "err %d", err);

+ /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) + return; + hci_dev_lock(hdev);

if (err) { @@@ -1564,7 -1582,9 +1584,9 @@@ new_settings(hdev, cmd->sk);

done: - mgmt_pending_free(cmd); + if (cmd) + mgmt_pending_remove(cmd); + hci_dev_unlock(hdev); }

@@@ -1636,7 -1656,7 +1658,7 @@@ static int set_connectable(struct sock goto failed; }

- cmd = mgmt_pending_new(sk, MGMT_OP_SET_CONNECTABLE, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_SET_CONNECTABLE, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@@ -1656,6 -1676,9 +1678,9 @@@ err = hci_cmd_sync_queue(hdev, set_connectable_sync, cmd, mgmt_set_connectable_complete);

+ if (err < 0) + mgmt_pending_remove(cmd); + failed: hci_dev_unlock(hdev); return err; @@@ -1776,6 -1799,10 +1801,10 @@@ static void set_ssp_complete(struct hci u8 enable = cp->val; bool changed;

+ /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_SSP, hdev)) + return; + if (err) { u8 mgmt_err = mgmt_status(err);

@@@ -3323,6 -3350,9 +3352,9 @@@ static void set_name_complete(struct hc

bt_dev_dbg(hdev, "err %d", err);

+ if (cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev)) + return; + if (status) { mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, status); @@@ -3495,6 -3525,9 +3527,9 @@@ static void set_default_phy_complete(st struct sk_buff *skb = cmd->skb; u8 status = mgmt_status(err);

+ if (cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) + return; + if (!status) { if (!skb) status = MGMT_STATUS_FAILED; @@@ -3761,13 -3794,6 +3796,6 @@@ static int set_wideband_speech(struct s

hci_dev_lock(hdev);

- if (pending_find(MGMT_OP_SET_WIDEBAND_SPEECH, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, - MGMT_OP_SET_WIDEBAND_SPEECH, - MGMT_STATUS_BUSY); - goto unlock; - } - if (hdev_is_powered(hdev) && !!cp->val != hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) { @@@ -5038,12 -5064,6 +5066,6 @@@ static int read_local_oob_data(struct s goto unlock; }

- if (pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - MGMT_STATUS_BUSY); - goto unlock; - } - cmd = mgmt_pending_new(sk, MGMT_OP_READ_LOCAL_OOB_DATA, hdev, NULL, 0); if (!cmd) err = -ENOMEM; @@@ -5263,11 -5283,16 +5285,16 @@@ static void start_discovery_complete(st { struct mgmt_pending_cmd *cmd = data;

+ if (cmd != pending_find(MGMT_OP_START_DISCOVERY, hdev) && + cmd != pending_find(MGMT_OP_START_LIMITED_DISCOVERY, hdev) && + cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev)) + return; + bt_dev_dbg(hdev, "err %d", err);

mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), cmd->param, 1); - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd);

hci_discovery_set_state(hdev, err ? DISCOVERY_STOPPED: DISCOVERY_FINDING); @@@ -5329,7 -5354,7 +5356,7 @@@ static int start_discovery_internal(str else hdev->discovery.limited = false;

- cmd = mgmt_pending_new(sk, op, hdev, data, len); + cmd = mgmt_pending_add(sk, op, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@@ -5338,7 -5363,7 +5365,7 @@@ err = hci_cmd_sync_queue(hdev, start_discovery_sync, cmd, start_discovery_complete); if (err < 0) { - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); goto failed; }

@@@ -5432,7 -5457,7 +5459,7 @@@ static int start_service_discovery(stru goto failed; }

- cmd = mgmt_pending_new(sk, MGMT_OP_START_SERVICE_DISCOVERY, + cmd = mgmt_pending_add(sk, MGMT_OP_START_SERVICE_DISCOVERY, hdev, data, len); if (!cmd) { err = -ENOMEM; @@@ -5465,7 -5490,7 +5492,7 @@@ err = hci_cmd_sync_queue(hdev, start_discovery_sync, cmd, start_discovery_complete); if (err < 0) { - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); goto failed; }

@@@ -5497,11 -5522,14 +5524,14 @@@ static void stop_discovery_complete(str { struct mgmt_pending_cmd *cmd = data;

+ if (cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev)) + return; + bt_dev_dbg(hdev, "err %d", err);

mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), cmd->param, 1); - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd);

if (!err) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); @@@ -5537,7 -5565,7 +5567,7 @@@ static int stop_discovery(struct sock * goto unlock; }

- cmd = mgmt_pending_new(sk, MGMT_OP_STOP_DISCOVERY, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_STOP_DISCOVERY, hdev, data, len); if (!cmd) { err = -ENOMEM; goto unlock; @@@ -5546,7 -5574,7 +5576,7 @@@ err = hci_cmd_sync_queue(hdev, stop_discovery_sync, cmd, stop_discovery_complete); if (err < 0) { - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); goto unlock; }

@@@ -7476,6 -7504,9 +7506,9 @@@ static void read_local_oob_ext_data_com u8 status = mgmt_status(err); u16 eir_len;

+ if (cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev)) + return; + if (!status) { if (!skb) status = MGMT_STATUS_FAILED; @@@ -7971,11 -8002,7 +8004,7 @@@ static bool requested_adv_flags_are_val

static bool adv_busy(struct hci_dev *hdev) { - return (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) || - pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) || - pending_find(MGMT_OP_SET_LE, hdev) || - pending_find(MGMT_OP_ADD_EXT_ADV_PARAMS, hdev) || - pending_find(MGMT_OP_ADD_EXT_ADV_DATA, hdev)); + return pending_find(MGMT_OP_SET_LE, hdev); }

static void add_adv_complete(struct hci_dev *hdev, struct sock *sk, u8 instance, @@@ -8565,9 -8592,7 +8594,7 @@@ static int remove_advertising(struct so goto unlock; }

- if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) || - pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) || - pending_find(MGMT_OP_SET_LE, hdev)) { + if (pending_find(MGMT_OP_SET_LE, hdev)) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, MGMT_STATUS_BUSY); goto unlock; @@@ -9591,116 -9616,12 +9618,116 @@@ static bool is_filter_match(struct hci_ return true; }

+void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type) +{ + struct mgmt_ev_adv_monitor_device_lost ev; + + ev.monitor_handle = cpu_to_le16(handle); + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = addr_type; + + mgmt_event(MGMT_EV_ADV_MONITOR_DEVICE_LOST, hdev, &ev, sizeof(ev), + NULL); +} + +static void mgmt_adv_monitor_device_found(struct hci_dev *hdev, + bdaddr_t *bdaddr, bool report_device, + struct sk_buff *skb, + struct sock *skip_sk) +{ + struct sk_buff *advmon_skb; + size_t advmon_skb_len; + __le16 *monitor_handle; + struct monitored_device *dev, *tmp; + bool matched = false; + bool notify = false; + + /* We have received the Advertisement Report because: + * 1. the kernel has initiated active discovery + * 2. if not, we have pend_le_reports > 0 in which case we are doing + * passive scanning + * 3. if none of the above is true, we have one or more active + * Advertisement Monitor + * + * For case 1 and 2, report all advertisements via MGMT_EV_DEVICE_FOUND + * and report ONLY one advertisement per device for the matched Monitor + * via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event. + * + * For case 3, since we are not active scanning and all advertisements + * received are due to a matched Advertisement Monitor, report all + * advertisements ONLY via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event. + */ + if (report_device && !hdev->advmon_pend_notify) { + mgmt_event_skb(skb, skip_sk); + return; + } + + advmon_skb_len = (sizeof(struct mgmt_ev_adv_monitor_device_found) - + sizeof(struct mgmt_ev_device_found)) + skb->len; + advmon_skb = mgmt_alloc_skb(hdev, MGMT_EV_ADV_MONITOR_DEVICE_FOUND, + advmon_skb_len); + if (!advmon_skb) { + if (report_device) + mgmt_event_skb(skb, skip_sk); + else + kfree_skb(skb); + return; + } + + /* ADV_MONITOR_DEVICE_FOUND is similar to DEVICE_FOUND event except + * that it also has 'monitor_handle'. Make a copy of DEVICE_FOUND and + * store monitor_handle of the matched monitor. + */ + monitor_handle = skb_put(advmon_skb, sizeof(*monitor_handle)); + skb_put_data(advmon_skb, skb->data, skb->len); + + hdev->advmon_pend_notify = false; + + list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) { + if (!bacmp(&dev->bdaddr, bdaddr)) { + matched = true; + + if (!dev->notified) { + *monitor_handle = cpu_to_le16(dev->handle); + notify = true; + dev->notified = true; + } + } + + if (!dev->notified) + hdev->advmon_pend_notify = true; + } + + if (!report_device && + ((matched && !notify) || !msft_monitor_supported(hdev))) { + /* Handle 0 indicates that we are not active scanning and this + * is a subsequent advertisement report for an already matched + * Advertisement Monitor or the controller offloading support + * is not available. + */ + *monitor_handle = 0; + notify = true; + } + + if (report_device) + mgmt_event_skb(skb, skip_sk); + else + kfree_skb(skb); + + if (notify) + mgmt_event_skb(advmon_skb, skip_sk); + else + kfree_skb(advmon_skb); +} + void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len) { struct sk_buff *skb; struct mgmt_ev_device_found *ev; + bool report_device = hci_discovery_active(hdev);

/* Don't send events for a non-kernel initiated discovery. With * LE one exception is if we have pend_le_reports > 0 in which @@@ -9709,10 -9630,11 +9736,10 @@@ if (!hci_discovery_active(hdev)) { if (link_type == ACL_LINK) return; - if (link_type == LE_LINK && - list_empty(&hdev->pend_le_reports) && - !hci_is_adv_monitoring(hdev)) { + if (link_type == LE_LINK && !list_empty(&hdev->pend_le_reports)) + report_device = true; + else if (!hci_is_adv_monitoring(hdev)) return; - } }

if (hdev->discovery.result_filtering) { @@@ -9777,7 -9699,7 +9804,7 @@@

ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len);

- mgmt_event_skb(skb, NULL); + mgmt_adv_monitor_device_found(hdev, bdaddr, report_device, skb, NULL); }

void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, diff --combined net/core/skbuff.c index e5082836295b,ea51e23e9247..23f3ba343661 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@@ -201,7 -201,7 +201,7 @@@ static void __build_skb_around(struct s skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); - skb->end = skb->tail + size; + skb_set_end_offset(skb, size); skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U;

@@@ -1736,10 -1736,11 +1736,10 @@@ int pskb_expand_head(struct sk_buff *sk skb->head = data; skb->head_frag = 0; skb->data += off; + + skb_set_end_offset(skb, size); #ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->end = size; off = nhead; -#else - skb->end = skb->head + size; #endif skb->tail += off; skb_headers_offset_update(skb, nhead); @@@ -1787,38 -1788,6 +1787,38 @@@ struct sk_buff *skb_realloc_headroom(st } EXPORT_SYMBOL(skb_realloc_headroom);

+int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) +{ + unsigned int saved_end_offset, saved_truesize; + struct skb_shared_info *shinfo; + int res; + + saved_end_offset = skb_end_offset(skb); + saved_truesize = skb->truesize; + + res = pskb_expand_head(skb, 0, 0, pri); + if (res) + return res; + + skb->truesize = saved_truesize; + + if (likely(skb_end_offset(skb) == saved_end_offset)) + return 0; + + shinfo = skb_shinfo(skb); + + /* We are about to change back skb->end, + * we need to move skb_shinfo() to its new location. + */ + memmove(skb->head + saved_end_offset, + shinfo, + offsetof(struct skb_shared_info, frags[shinfo->nr_frags])); + + skb_set_end_offset(skb, saved_end_offset); + + return 0; +} + /** * skb_expand_head - reallocate header of &sk_buff * @skb: buffer to reallocate @@@ -3907,6 -3876,7 +3907,7 @@@ struct sk_buff *skb_segment_list(struc list_skb = list_skb->next;

err = 0; + delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { @@@ -3931,7 -3901,6 +3932,6 @@@ tail = nskb;

delta_len += nskb->len; - delta_truesize += nskb->truesize;

skb_push(nskb, -skb_network_offset(nskb) + offset);

@@@ -4851,7 -4820,7 +4851,7 @@@ void __skb_tstamp_tx(struct sk_buff *or if (hwtstamps) *skb_hwtstamps(skb) = *hwtstamps; else - skb->tstamp = ktime_get_real(); + __net_timestamp(skb);

__skb_complete_tx_timestamp(skb, sk, tstype, opt_stats); } @@@ -5381,7 -5350,7 +5381,7 @@@ void skb_scrub_packet(struct sk_buff *s

ipvs_reset(skb); skb->mark = 0; - skb->tstamp = 0; + skb_clear_tstamp(skb); } EXPORT_SYMBOL_GPL(skb_scrub_packet);

@@@ -6075,7 -6044,11 +6075,7 @@@ static int pskb_carve_inside_header(str skb->head = data; skb->data = data; skb->head_frag = 0; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->end = size; -#else - skb->end = skb->head + size; -#endif + skb_set_end_offset(skb, size); skb_set_tail_pointer(skb, skb_headlen(skb)); skb_headers_offset_update(skb, 0); skb->cloned = 0; @@@ -6213,7 -6186,11 +6213,7 @@@ static int pskb_carve_inside_nonlinear( skb->head = data; skb->head_frag = 0; skb->data = data; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->end = size; -#else - skb->end = skb->head + size; -#endif + skb_set_end_offset(skb, size); skb_reset_tail_pointer(skb); skb_headers_offset_update(skb, 0); skb->cloned = 0; diff --combined net/dsa/dsa2.c index 030d5f26715a,b4e67758e104..d5f21a770689 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@@ -15,7 -15,6 +15,7 @@@ #include <linux/of.h> #include <linux/of_net.h> #include <net/devlink.h> +#include <net/sch_generic.h>

#include "dsa_priv.h"

@@@ -72,24 -71,27 +72,24 @@@ int dsa_broadcast(unsigned long e, voi }

/** - * dsa_lag_map() - Map LAG netdev to a linear LAG ID + * dsa_lag_map() - Map LAG structure to a linear LAG array * @dst: Tree in which to record the mapping. - * @lag: Netdev that is to be mapped to an ID. + * @lag: LAG structure that is to be mapped to the tree's array. * - * dsa_lag_id/dsa_lag_dev can then be used to translate between the + * dsa_lag_id/dsa_lag_by_id can then be used to translate between the * two spaces. The size of the mapping space is determined by the * driver by setting ds->num_lag_ids. It is perfectly legal to leave * it unset if it is not needed, in which case these functions become * no-ops. */ -void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag) +void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag) { unsigned int id;

- if (dsa_lag_id(dst, lag) >= 0) - /* Already mapped */ - return; - - for (id = 0; id < dst->lags_len; id++) { - if (!dsa_lag_dev(dst, id)) { - dst->lags[id] = lag; + for (id = 1; id <= dst->lags_len; id++) { + if (!dsa_lag_by_id(dst, id)) { + dst->lags[id - 1] = lag; + lag->id = id; return; } } @@@ -105,36 -107,28 +105,36 @@@ /** * dsa_lag_unmap() - Remove a LAG ID mapping * @dst: Tree in which the mapping is recorded. - * @lag: Netdev that was mapped. + * @lag: LAG structure that was mapped. * * As there may be multiple users of the mapping, it is only removed * if there are no other references to it. */ -void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag) +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag) { - struct dsa_port *dp; unsigned int id;

- dsa_lag_foreach_port(dp, dst, lag) - /* There are remaining users of this mapping */ - return; - dsa_lags_foreach_id(id, dst) { - if (dsa_lag_dev(dst, id) == lag) { - dst->lags[id] = NULL; + if (dsa_lag_by_id(dst, id) == lag) { + dst->lags[id - 1] = NULL; + lag->id = 0; break; } } }

+struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, + const struct net_device *lag_dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_lag_dev_get(dp) == lag_dev) + return dp->lag; + + return NULL; +} + struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, const struct net_device *br) { @@@ -458,10 -452,8 +458,10 @@@ static int dsa_port_setup(struct dsa_po return 0;

mutex_init(&dp->addr_lists_lock); + mutex_init(&dp->vlans_lock); INIT_LIST_HEAD(&dp->fdbs); INIT_LIST_HEAD(&dp->mdbs); + INIT_LIST_HEAD(&dp->vlans);

if (ds->ops->port_setup) { err = ds->ops->port_setup(ds, dp->index); @@@ -570,7 -562,6 +570,7 @@@ static void dsa_port_teardown(struct ds struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a, *tmp; struct net_device *slave; + struct dsa_vlan *v, *n;

if (!dp->setup) return; @@@ -611,11 -602,6 +611,11 @@@ kfree(a); }

+ list_for_each_entry_safe(v, n, &dp->vlans, list) { + list_del(&v->list); + kfree(v); + } + dp->setup = false; }

@@@ -1078,18 -1064,9 +1078,18 @@@ static int dsa_tree_setup_master(struc

list_for_each_entry(dp, &dst->ports, list) { if (dsa_port_is_cpu(dp)) { - err = dsa_master_setup(dp->master, dp); + struct net_device *master = dp->master; + bool admin_up = (master->flags & IFF_UP) && + !qdisc_tx_is_noop(master); + + err = dsa_master_setup(master, dp); if (err) return err; + + /* Replay master state event */ + dsa_tree_master_admin_state_change(dst, master, admin_up); + dsa_tree_master_oper_state_change(dst, master, + netif_oper_up(master)); } }

@@@ -1104,19 -1081,9 +1104,19 @@@ static void dsa_tree_teardown_master(st

rtnl_lock();

- list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_cpu(dp)) - dsa_master_teardown(dp->master); + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_cpu(dp)) { + struct net_device *master = dp->master; + + /* Synthesizing an "admin down" state is sufficient for + * the switches to get a notification if the master is + * currently up and running. + */ + dsa_tree_master_admin_state_change(dst, master, false); + + dsa_master_teardown(master); + } + }

rtnl_unlock(); } @@@ -1294,7 -1261,7 +1294,7 @@@ int dsa_tree_change_tag_proto(struct ds info.tag_ops = tag_ops; err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); if (err) - return err; + goto out_unwind_tagger;

err = dsa_tree_bind_tag_proto(dst, tag_ops); if (err) @@@ -1312,52 -1279,6 +1312,52 @@@ out_unlock return err; }

+static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, + struct net_device *master) +{ + struct dsa_notifier_master_state_info info; + struct dsa_port *cpu_dp = master->dsa_ptr; + + info.master = master; + info.operational = dsa_port_master_is_operational(cpu_dp); + + dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); +} + +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (up && cpu_dp->master_oper_up)) + notify = true; + + cpu_dp->master_admin_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (cpu_dp->master_admin_up && up)) + notify = true; + + cpu_dp->master_oper_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) { struct dsa_switch_tree *dst = ds->dst; diff --combined net/ipv4/tcp.c index 68f1236b2858,28ff2a820f7c..33f20134e3f1 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@@ -894,7 -894,8 +894,7 @@@ static unsigned int tcp_xmit_size_goal( return mss_now;

/* Note : tcp_tso_autosize() will eventually split this later */ - new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER; - new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal); + new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size);

/* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; @@@ -1683,11 -1684,13 +1683,13 @@@ int tcp_read_sock(struct sock *sk, read if (!copied) copied = used; break; - } else if (used <= len) { - seq += used; - copied += used; - offset += used; } + if (WARN_ON_ONCE(used > len)) + used = len; + seq += used; + copied += used; + offset += used; + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it @@@ -4431,76 -4434,6 +4433,76 @@@ int tcp_md5_hash_key(struct tcp_md5sig_ } EXPORT_SYMBOL(tcp_md5_hash_key);

+/* Called with rcu_read_lock() */ +bool tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, + enum skb_drop_reason *reason, + const void *saddr, const void *daddr, + int family, int dif, int sdif) +{ + /* + * This gets called for each TCP segment that arrives + * so we want to be efficient. + * We have 3 drop cases: + * o No MD5 hash and one expected. + * o MD5 hash and we're not expecting one. + * o MD5 hash and its wrong. + */ + const __u8 *hash_location = NULL; + struct tcp_md5sig_key *hash_expected; + const struct tcphdr *th = tcp_hdr(skb); + struct tcp_sock *tp = tcp_sk(sk); + int genhash, l3index; + u8 newhash[16]; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + hash_expected = tcp_md5_do_lookup(sk, l3index, saddr, family); + hash_location = tcp_parse_md5sig_option(th); + + /* We've parsed the options - do we have a hash? */ + if (!hash_expected && !hash_location) + return false; + + if (hash_expected && !hash_location) { + *reason = SKB_DROP_REASON_TCP_MD5NOTFOUND; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + return true; + } + + if (!hash_expected && hash_location) { + *reason = SKB_DROP_REASON_TCP_MD5UNEXPECTED; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); + return true; + } + + /* check the signature */ + genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected, + NULL, skb); + + if (genhash || memcmp(hash_location, newhash, 16) != 0) { + *reason = SKB_DROP_REASON_TCP_MD5FAILURE; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); + if (family == AF_INET) { + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", + saddr, ntohs(th->source), + daddr, ntohs(th->dest), + genhash ? " tcp_v4_calc_md5_hash failed" + : "", l3index); + } else { + net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n", + genhash ? "failed" : "mismatch", + saddr, ntohs(th->source), + daddr, ntohs(th->dest), l3index); + } + return true; + } + return false; +} +EXPORT_SYMBOL(tcp_inbound_md5_hash); + #endif

void tcp_done(struct sock *sk) diff --combined net/ipv6/addrconf.c index 63aea19004a6,f908e2fd30b2..b22504176588 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@@ -146,11 -146,18 +146,11 @@@ static int ipv6_generate_stable_address

#define IN6_ADDR_HSIZE_SHIFT 8 #define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) -/* - * Configured unicast address hash table - */ -static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; -static DEFINE_SPINLOCK(addrconf_hash_lock);

-static void addrconf_verify(void); -static void addrconf_verify_rtnl(void); -static void addrconf_verify_work(struct work_struct *); +static void addrconf_verify(struct net *net); +static void addrconf_verify_rtnl(struct net *net);

static struct workqueue_struct *addrconf_wq; -static DECLARE_DELAYED_WORK(addr_chk_work, addrconf_verify_work);

static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); @@@ -372,7 -379,7 +372,7 @@@ static struct inet6_dev *ipv6_add_dev(s

ASSERT_RTNL();

- if (dev->mtu < IPV6_MIN_MTU) + if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev) return ERR_PTR(-EINVAL);

ndev = kzalloc(sizeof(struct inet6_dev), GFP_KERNEL); @@@ -409,13 -416,12 +409,13 @@@ return ERR_PTR(err); }

- if (snmp6_register_dev(ndev) < 0) { - netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", - __func__, dev->name); - goto err_release; + if (dev != blackhole_netdev) { + if (snmp6_register_dev(ndev) < 0) { + netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", + __func__, dev->name); + goto err_release; + } } - /* One reference from device. */ refcount_set(&ndev->refcnt, 1);

@@@ -446,28 -452,25 +446,28 @@@

ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; - err = addrconf_sysctl_register(ndev); - if (err) { - ipv6_mc_destroy_dev(ndev); - snmp6_unregister_dev(ndev); - goto err_release; + if (dev != blackhole_netdev) { + err = addrconf_sysctl_register(ndev); + if (err) { + ipv6_mc_destroy_dev(ndev); + snmp6_unregister_dev(ndev); + goto err_release; + } } /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev);

- /* Join interface-local all-node multicast group */ - ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); - - /* Join all-node multicast group */ - ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); + if (dev != blackhole_netdev) { + /* Join interface-local all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes);

- /* Join all-router multicast group if forwarding is set */ - if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) - ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + /* Join all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes);

+ /* Join all-router multicast group if forwarding is set */ + if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) + ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); + } return ndev;

err_release: @@@ -551,7 -554,7 +551,7 @@@ static int inet6_netconf_fill_devconf(s #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - devconf->mc_forwarding) < 0) + atomic_read(&devconf->mc_forwarding)) < 0) goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && @@@ -1008,7 -1011,9 +1008,7 @@@ static bool ipv6_chk_same_addr(struct n { struct inet6_ifaddr *ifp;

- hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev) return true; @@@ -1019,21 -1024,20 +1019,21 @@@

static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) { - unsigned int hash = inet6_addr_hash(dev_net(dev), &ifa->addr); + struct net *net = dev_net(dev); + unsigned int hash = inet6_addr_hash(net, &ifa->addr); int err = 0;

- spin_lock(&addrconf_hash_lock); + spin_lock(&net->ipv6.addrconf_hash_lock);

/* Ignore adding duplicate addresses on an interface */ - if (ipv6_chk_same_addr(dev_net(dev), &ifa->addr, dev, hash)) { + if (ipv6_chk_same_addr(net, &ifa->addr, dev, hash)) { netdev_dbg(dev, "ipv6_add_addr: already assigned\n"); err = -EEXIST; } else { - hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); + hlist_add_head_rcu(&ifa->addr_lst, &net->ipv6.inet6_addr_lst[hash]); }

- spin_unlock(&addrconf_hash_lock); + spin_unlock(&net->ipv6.addrconf_hash_lock);

return err; } @@@ -1115,7 -1119,6 +1115,7 @@@ ipv6_add_addr(struct inet6_dev *idev, s ifa->prefix_len = cfg->plen; ifa->rt_priority = cfg->rt_priority; ifa->flags = cfg->ifa_flags; + ifa->ifa_proto = cfg->ifa_proto; /* No need to add the TENTATIVE flag for addresses with NODAD */ if (!(cfg->ifa_flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; @@@ -1258,10 -1261,9 +1258,10 @@@ cleanup_prefix_route(struct inet6_ifadd

static void ipv6_del_addr(struct inet6_ifaddr *ifp) { - int state; enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; + struct net *net = dev_net(ifp->idev->dev); unsigned long expires; + int state;

ASSERT_RTNL();

@@@ -1273,9 -1275,9 +1273,9 @@@ if (state == INET6_IFADDR_STATE_DEAD) goto out;

- spin_lock_bh(&addrconf_hash_lock); + spin_lock_bh(&net->ipv6.addrconf_hash_lock); hlist_del_init_rcu(&ifp->addr_lst); - spin_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&net->ipv6.addrconf_hash_lock);

write_lock_bh(&ifp->idev->lock);

@@@ -1918,8 -1920,10 +1918,8 @@@ __ipv6_chk_addr_and_flags(struct net *n if (skip_dev_check) dev = NULL;

- hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { ndev = ifp->idev->dev; - if (!net_eq(dev_net(ndev), net)) - continue;

if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; @@@ -2023,7 -2027,9 +2023,7 @@@ struct inet6_ifaddr *ipv6_get_ifaddr(st struct inet6_ifaddr *ifp, *result = NULL;

rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { @@@ -2090,7 -2096,7 +2090,7 @@@ static int addrconf_dad_end(struct inet void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; - struct net *net = dev_net(ifp->idev->dev); + struct net *net = dev_net(idev->dev);

if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@@ -2594,7 -2600,6 +2594,7 @@@ int addrconf_prefix_rcv_add_addr(struc .valid_lft = valid_lft, .preferred_lft = prefered_lft, .scope = addr_type & IPV6_ADDR_SCOPE_MASK, + .ifa_proto = IFAPROT_KERNEL_RA };

#ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@@ -2670,7 -2675,7 +2670,7 @@@ create, now);

in6_ifa_put(ifp); - addrconf_verify(); + addrconf_verify(net); }

return 0; @@@ -2982,7 -2987,7 +2982,7 @@@ static int inet6_addr_add(struct net *n manage_tempaddrs(idev, ifp, cfg->valid_lft, cfg->preferred_lft, true, jiffies); in6_ifa_put(ifp); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); return 0; } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, @@@ -3022,7 -3027,7 +3022,7 @@@ static int inet6_addr_del(struct net *n manage_tempaddrs(idev, ifp, 0, 0, false, jiffies); ipv6_del_addr(ifp); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, pfx, dev->ifindex); @@@ -3079,7 -3084,7 +3079,7 @@@ int addrconf_del_ifaddr(struct net *net }

static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, - int plen, int scope) + int plen, int scope, u8 proto) { struct inet6_ifaddr *ifp; struct ifa6_config cfg = { @@@ -3088,8 -3093,7 +3088,8 @@@ .ifa_flags = IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, - .scope = scope + .scope = scope, + .ifa_proto = proto };

ifp = ipv6_add_addr(idev, &cfg, true, NULL); @@@ -3134,7 -3138,7 +3134,7 @@@ static void add_v4_addrs(struct inet6_d }

if (addr.s6_addr32[3]) { - add_addr(idev, &addr, plen, scope); + add_addr(idev, &addr, plen, scope, IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); return; @@@ -3157,8 -3161,7 +3157,8 @@@ flag |= IFA_HOST; }

- add_addr(idev, &addr, plen, flag); + add_addr(idev, &addr, plen, flag, + IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); } @@@ -3181,7 -3184,7 +3181,7 @@@ static void init_loopback(struct net_de return; }

- add_addr(idev, &in6addr_loopback, 128, IFA_HOST); + add_addr(idev, &in6addr_loopback, 128, IFA_HOST, IFAPROT_KERNEL_LO); }

void addrconf_add_linklocal(struct inet6_dev *idev, @@@ -3193,8 -3196,7 +3193,8 @@@ .ifa_flags = flags | IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, - .scope = IFA_LINK + .scope = IFA_LINK, + .ifa_proto = IFAPROT_KERNEL_LL }; struct inet6_ifaddr *ifp;

@@@ -3730,6 -3732,7 +3730,7 @@@ static int addrconf_ifdown(struct net_d struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; bool keep_addr = false; + bool was_ready; int state, i;

ASSERT_RTNL(); @@@ -3770,9 -3773,9 +3771,9 @@@

/* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { - struct hlist_head *h = &inet6_addr_lst[i]; + struct hlist_head *h = &net->ipv6.inet6_addr_lst[i];

- spin_lock_bh(&addrconf_hash_lock); + spin_lock_bh(&net->ipv6.addrconf_hash_lock); restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { @@@ -3788,14 -3791,17 +3789,17 @@@ } } } - spin_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&net->ipv6.addrconf_hash_lock); }

write_lock_bh(&idev->lock);

addrconf_del_rs_timer(idev);

- /* Step 2: clear flags for stateless addrconf */ + /* Step 2: clear flags for stateless addrconf, repeated down + * detection + */ + was_ready = idev->if_flags & IF_READY; if (!unregister) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);

@@@ -3869,7 -3875,7 +3873,7 @@@ if (unregister) { ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); - } else { + } else if (was_ready) { ipv6_mc_down(idev); }

@@@ -4244,7 -4250,7 +4248,7 @@@ static void addrconf_dad_completed(stru * before this temporary address becomes deprecated. */ if (ifp->flags & IFA_F_TEMPORARY) - addrconf_verify_rtnl(); + addrconf_verify_rtnl(dev_net(dev)); }

static void addrconf_dad_run(struct inet6_dev *idev, bool restart) @@@ -4286,8 -4292,10 +4290,8 @@@ static struct inet6_ifaddr *if6_get_fir }

for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - hlist_for_each_entry_rcu(ifa, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { - if (!net_eq(dev_net(ifa->idev->dev), net)) - continue; /* sync with offset */ if (p < state->offset) { p++; @@@ -4310,6 -4318,8 +4314,6 @@@ static struct inet6_ifaddr *if6_get_nex struct net *net = seq_file_net(seq);

hlist_for_each_entry_continue_rcu(ifa, addr_lst) { - if (!net_eq(dev_net(ifa->idev->dev), net)) - continue; state->offset++; return ifa; } @@@ -4317,7 -4327,9 +4321,7 @@@ state->offset = 0; while (++state->bucket < IN6_ADDR_HSIZE) { hlist_for_each_entry_rcu(ifa, - &inet6_addr_lst[state->bucket], addr_lst) { - if (!net_eq(dev_net(ifa->idev->dev), net)) - continue; + &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { return ifa; } } @@@ -4405,7 -4417,9 +4409,7 @@@ int ipv6_chk_home_addr(struct net *net int ret = 0;

rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr) && (ifp->flags & IFA_F_HOMEADDRESS)) { ret = 1; @@@ -4443,7 -4457,9 +4447,7 @@@ int ipv6_chk_rpl_srh_loop(struct net *n hash = inet6_addr_hash(net, addr);

hash_found = false; - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) - continue; + hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) {

if (ipv6_addr_equal(&ifp->addr, addr)) { hash_found = true; @@@ -4472,7 -4488,7 +4476,7 @@@ * Periodic address status verification */

-static void addrconf_verify_rtnl(void) +static void addrconf_verify_rtnl(struct net *net) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; @@@ -4484,11 -4500,11 +4488,11 @@@ now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);

- cancel_delayed_work(&addr_chk_work); + cancel_delayed_work(&net->ipv6.addr_chk_work);

for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &net->ipv6.inet6_addr_lst[i], addr_lst) { unsigned long age;

/* When setting preferred_lft to a value not zero or @@@ -4587,23 -4603,20 +4591,23 @@@

pr_debug("now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", now, next, next_sec, next_sched); - mod_delayed_work(addrconf_wq, &addr_chk_work, next_sched - now); + mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, next_sched - now); rcu_read_unlock_bh(); }

static void addrconf_verify_work(struct work_struct *w) { + struct net *net = container_of(to_delayed_work(w), struct net, + ipv6.addr_chk_work); + rtnl_lock(); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(net); rtnl_unlock(); }

-static void addrconf_verify(void) +static void addrconf_verify(struct net *net) { - mod_delayed_work(addrconf_wq, &addr_chk_work, 0); + mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, 0); }

static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, @@@ -4632,7 -4645,6 +4636,7 @@@ static const struct nla_policy ifa_ipv6 [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, + [IFA_PROTO] = { .type = NLA_U8 }, };

static int @@@ -4700,8 -4712,7 +4704,8 @@@ static int modify_prefix_route(struct i return 0; }

-static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) +static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, + struct ifa6_config *cfg) { u32 flags; clock_t expires; @@@ -4758,7 -4769,6 +4762,7 @@@ ifp->tstamp = jiffies; ifp->valid_lft = cfg->valid_lft; ifp->prefered_lft = cfg->preferred_lft; + ifp->ifa_proto = cfg->ifa_proto;

if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) ifp->rt_priority = cfg->rt_priority; @@@ -4816,7 -4826,7 +4820,7 @@@ jiffies); }

- addrconf_verify_rtnl(); + addrconf_verify_rtnl(net);

return 0; } @@@ -4852,9 -4862,6 +4856,9 @@@ inet6_rtm_newaddr(struct sk_buff *skb, if (tb[IFA_RT_PRIORITY]) cfg.rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]);

+ if (tb[IFA_PROTO]) + cfg.ifa_proto = nla_get_u8(tb[IFA_PROTO]); + cfg.valid_lft = INFINITY_LIFE_TIME; cfg.preferred_lft = INFINITY_LIFE_TIME;

@@@ -4906,7 -4913,7 +4910,7 @@@ !(nlh->nlmsg_flags & NLM_F_REPLACE)) err = -EEXIST; else - err = inet6_addr_modify(ifa, &cfg); + err = inet6_addr_modify(net, ifa, &cfg);

in6_ifa_put(ifa);

@@@ -4958,7 -4965,6 +4962,7 @@@ static inline int inet6_ifaddr_msgsize( + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)) + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */; }

@@@ -5038,10 -5044,6 +5042,10 @@@ static int inet6_fill_ifaddr(struct sk_ if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) goto error;

+ if (ifa->ifa_proto && + nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) + goto error; + nlmsg_end(skb, nlh); return 0;

@@@ -5537,7 -5539,7 +5541,7 @@@ static inline void ipv6_store_devconf(s array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding; + array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; @@@ -5798,7 -5800,7 +5802,7 @@@ update_lft

write_unlock_bh(&idev->lock); inet6_ifinfo_notify(RTM_NEWLINK, idev); - addrconf_verify_rtnl(); + addrconf_verify_rtnl(dev_net(dev)); return 0; }

@@@ -7115,14 -7117,6 +7119,14 @@@ static int __net_init addrconf_init_net int err = -ENOMEM; struct ipv6_devconf *all, *dflt;

+ spin_lock_init(&net->ipv6.addrconf_hash_lock); + INIT_DEFERRABLE_WORK(&net->ipv6.addr_chk_work, addrconf_verify_work); + net->ipv6.inet6_addr_lst = kcalloc(IN6_ADDR_HSIZE, + sizeof(struct hlist_head), + GFP_KERNEL); + if (!net->ipv6.inet6_addr_lst) + goto err_alloc_addr; + all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; @@@ -7184,15 -7178,11 +7188,15 @@@ err_reg_all err_alloc_dflt: kfree(all); err_alloc_all: + kfree(net->ipv6.inet6_addr_lst); +err_alloc_addr: return err; }

static void __net_exit addrconf_exit_net(struct net *net) { + int i; + #ifdef CONFIG_SYSCTL __addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); @@@ -7200,19 -7190,7 +7204,19 @@@ NETCONFA_IFINDEX_ALL); #endif kfree(net->ipv6.devconf_dflt); + net->ipv6.devconf_dflt = NULL; kfree(net->ipv6.devconf_all); + net->ipv6.devconf_all = NULL; + + cancel_delayed_work_sync(&net->ipv6.addr_chk_work); + /* + * Check hash table, then free it. + */ + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON_ONCE(!hlist_empty(&net->ipv6.inet6_addr_lst[i])); + + kfree(net->ipv6.inet6_addr_lst); + net->ipv6.inet6_addr_lst = NULL; }

static struct pernet_operations addrconf_ops = { @@@ -7235,7 -7213,7 +7239,7 @@@ static struct rtnl_af_ops inet6_ops __r int __init addrconf_init(void) { struct inet6_dev *idev; - int i, err; + int err;

err = ipv6_addr_label_init(); if (err < 0) { @@@ -7254,8 -7232,26 +7258,8 @@@ goto out_nowq; }

- /* The addrconf netdev notifier requires that loopback_dev - * has it's ipv6 private information allocated and setup - * before it can bring up and give link-local addresses - * to other devices which are up. - * - * Unfortunately, loopback_dev is not necessarily the first - * entry in the global dev_base list of net devices. In fact, - * it is likely to be the very last entry on that list. - * So this causes the notifier registry below to try and - * give link-local addresses to all devices besides loopback_dev - * first, then loopback_dev, which cases all the non-loopback_dev - * devices to fail to get a link-local address. - * - * So, as a temporary fix, allocate the ipv6 structure for - * loopback_dev first by hand. - * Longer term, all of the dependencies ipv6 has upon the loopback - * device and it being up should be removed. - */ rtnl_lock(); - idev = ipv6_add_dev(init_net.loopback_dev); + idev = ipv6_add_dev(blackhole_netdev); rtnl_unlock(); if (IS_ERR(idev)) { err = PTR_ERR(idev); @@@ -7264,9 -7260,12 +7268,9 @@@

ip6_route_init_special_entries();

- for (i = 0; i < IN6_ADDR_HSIZE; i++) - INIT_HLIST_HEAD(&inet6_addr_lst[i]); - register_netdevice_notifier(&ipv6_dev_notf);

- addrconf_verify(); + addrconf_verify(&init_net);

rtnl_af_register(&inet6_ops);

@@@ -7324,6 -7323,7 +7328,6 @@@ out void addrconf_cleanup(void) { struct net_device *dev; - int i;

unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); @@@ -7341,6 -7341,14 +7345,6 @@@ } addrconf_ifdown(init_net.loopback_dev, true);

- /* - * Check hash table. - */ - spin_lock_bh(&addrconf_hash_lock); - for (i = 0; i < IN6_ADDR_HSIZE; i++) - WARN_ON(!hlist_empty(&inet6_addr_lst[i])); - spin_unlock_bh(&addrconf_hash_lock); - cancel_delayed_work(&addr_chk_work); rtnl_unlock();

destroy_workqueue(addrconf_wq); diff --combined net/ipv6/ip6_output.c index 50db9b20d746,4788f6b37053..e69fac576970 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@@ -130,7 -130,7 +130,7 @@@ static int ip6_finish_output2(struct ne rcu_read_unlock_bh();

IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return -EINVAL; }

@@@ -202,7 -202,7 +202,7 @@@ static int ip6_finish_output(struct ne case NET_XMIT_CN: return __ip6_finish_output(net, sk, skb) ? : ret; default: - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } @@@ -217,7 -217,7 +217,7 @@@ int ip6_output(struct net *net, struct

if (unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; }

@@@ -440,7 -440,7 +440,7 @@@ static inline int ip6_forward_finish(st } #endif

- skb->tstamp = 0; + skb_clear_tstamp(skb); return dst_output(net, sk, skb); }

@@@ -813,7 -813,6 +813,7 @@@ int ip6_fragment(struct net *net, struc struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; + bool mono_delivery_time = skb->mono_delivery_time; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; @@@ -904,7 -903,7 +904,7 @@@ if (iter.frag) ip6_fraglist_prepare(skb, &iter);

- skb->tstamp = tstamp; + skb_set_delivery_time(skb, tstamp, mono_delivery_time); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), @@@ -963,7 -962,7 +963,7 @@@ slow_path /* * Put this fragment into the sending queue. */ - frag->tstamp = tstamp; + skb_set_delivery_time(frag, tstamp, mono_delivery_time); err = output(net, sk, frag); if (err) goto fail; @@@ -1351,16 -1350,11 +1351,16 @@@ static void ip6_append_data_mtu(unsigne

static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, - struct rt6_info *rt, struct flowi6 *fl6) + struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu; - struct ipv6_txoptions *opt = ipc6->opt; + struct ipv6_txoptions *nopt, *opt = ipc6->opt; + + /* callers pass dst together with a reference, set it first so + * ip6_cork_release() can put it down even in case of an error. + */ + cork->base.dst = &rt->dst;

/* * setup for corking @@@ -1369,32 -1363,39 +1369,32 @@@ if (WARN_ON(v6_cork->opt)) return -EINVAL;

- v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); - if (unlikely(!v6_cork->opt)) + nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); + if (unlikely(!nopt)) return -ENOBUFS;

- v6_cork->opt->tot_len = sizeof(*opt); - v6_cork->opt->opt_flen = opt->opt_flen; - v6_cork->opt->opt_nflen = opt->opt_nflen; + nopt->tot_len = sizeof(*opt); + nopt->opt_flen = opt->opt_flen; + nopt->opt_nflen = opt->opt_nflen;

- v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt, - sk->sk_allocation); - if (opt->dst0opt && !v6_cork->opt->dst0opt) + nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); + if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS;

- v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt, - sk->sk_allocation); - if (opt->dst1opt && !v6_cork->opt->dst1opt) + nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); + if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS;

- v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt, - sk->sk_allocation); - if (opt->hopopt && !v6_cork->opt->hopopt) + nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); + if (opt->hopopt && !nopt->hopopt) return -ENOBUFS;

- v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt, - sk->sk_allocation); - if (opt->srcrt && !v6_cork->opt->srcrt) + nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); + if (opt->srcrt && !nopt->srcrt) return -ENOBUFS;

/* need source address above miyazawa*/ } - dst_hold(&rt->dst); - cork->base.dst = &rt->dst; - cork->fl.u.ip6 = *fl6; v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) @@@ -1407,8 -1408,6 +1407,6 @@@ if (np->frag_size) mtu = np->frag_size; } - if (mtu < IPV6_MIN_MTU) - return -EINVAL; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; @@@ -1425,8 -1424,9 +1423,8 @@@ }

static int __ip6_append_data(struct sock *sk, - struct flowi6 *fl6, struct sk_buff_head *queue, - struct inet_cork *cork, + struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, @@@ -1435,8 -1435,6 +1433,8 @@@ unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; + struct inet_cork *cork = &cork_full->base; + struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; @@@ -1471,8 -1469,6 +1469,6 @@@

fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - - sizeof(struct frag_hdr);

headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + @@@ -1480,6 -1476,13 +1476,13 @@@ sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len;

+ if (mtu < fragheaderlen || + ((mtu - fragheaderlen) & ~7) + fragheaderlen < sizeof(struct frag_hdr)) + goto emsgsize; + + maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - + sizeof(struct frag_hdr); + /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ @@@ -1488,7 -1491,6 +1491,7 @@@

if (cork->length + length > mtu - headersize && ipc6->dontfrag && (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); @@@ -1789,46 -1791,34 +1792,46 @@@ int ip6_append_data(struct sock *sk /* * setup for corking */ + dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, - ipc6, rt, fl6); + ipc6, rt); if (err) return err;

+ inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { - fl6 = &inet->cork.fl.u.ip6; transhdrlen = 0; }

- return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base, + return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data);

+static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) +{ + struct dst_entry *dst = cork->base.dst; + + cork->base.dst = NULL; + cork->base.flags &= ~IPCORK_ALLFRAG; + skb_dst_set(skb, dst); +} + static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { - kfree(v6_cork->opt->dst0opt); - kfree(v6_cork->opt->dst1opt); - kfree(v6_cork->opt->hopopt); - kfree(v6_cork->opt->srcrt); - kfree(v6_cork->opt); + struct ipv6_txoptions *opt = v6_cork->opt; + + kfree(opt->dst0opt); + kfree(opt->dst1opt); + kfree(opt->hopopt); + kfree(opt->srcrt); + kfree(opt); v6_cork->opt = NULL; }

@@@ -1837,6 -1827,7 +1840,6 @@@ cork->base.dst = NULL; cork->base.flags &= ~IPCORK_ALLFRAG; } - memset(&cork->fl, 0, sizeof(cork->fl)); }

struct sk_buff *__ip6_make_skb(struct sock *sk, @@@ -1846,7 -1837,7 +1849,7 @@@ { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; - struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; + struct in6_addr *final_dst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; @@@ -1876,9 -1867,9 +1879,9 @@@

/* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); - - *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); + + final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) @@@ -1898,9 -1889,10 +1901,9 @@@

skb->priority = sk->sk_priority; skb->mark = cork->base.mark; - skb->tstamp = cork->base.transmit_time;

- skb_dst_set(skb, dst_clone(&rt->dst)); + ip6_cork_steal_dst(skb, cork); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@@ -1972,26 -1964,26 +1975,26 @@@ struct sk_buff *ip6_make_skb(struct soc int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, - struct inet_cork_full *cork) + struct ipcm6_cookie *ipc6, struct rt6_info *rt, + unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err;

- if (flags & MSG_PROBE) + if (flags & MSG_PROBE) { + dst_release(&rt->dst); return NULL; + }

__skb_queue_head_init(&queue);

cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; - cork->base.dst = NULL; v6_cork.opt = NULL; - err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6); + err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); @@@ -1999,7 -1991,7 +2002,7 @@@ if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag;

- err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork, + err = __ip6_append_data(sk, &queue, cork, &v6_cork, &current->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6); diff --combined net/mac80211/ieee80211_i.h index da35791b8378,e87bccaab561..95aaf00c876c --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@@ -376,7 -376,7 +376,7 @@@ struct ieee80211_mgd_auth_data

u8 key[WLAN_KEY_LEN_WEP104]; u8 key_len, key_idx; - bool done; + bool done, waiting; bool peer_confirmed; bool timeout_started;

@@@ -2380,7 -2380,7 +2380,7 @@@ u8 *ieee80211_ie_build_vht_cap(u8 *pos u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef); u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype); -u8 *ieee80211_ie_build_he_cap(u8 *pos, +u8 *ieee80211_ie_build_he_cap(u32 disable_flags, u8 *pos, const struct ieee80211_sta_he_cap *he_cap, u8 *end); void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, diff --combined net/mac80211/mlme.c index 20b57ddf149c,744842c4513b..950be0f43b53 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@@ -37,6 -37,7 +37,7 @@@ #define IEEE80211_AUTH_TIMEOUT_SAE (HZ * 2) #define IEEE80211_AUTH_MAX_TRIES 3 #define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5) + #define IEEE80211_AUTH_WAIT_SAE_RETRY (HZ * 2) #define IEEE80211_ASSOC_TIMEOUT (HZ / 5) #define IEEE80211_ASSOC_TIMEOUT_LONG (HZ / 2) #define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10) @@@ -635,7 -636,7 +636,7 @@@ static void ieee80211_add_he_ie(struct struct sk_buff *skb, struct ieee80211_supported_band *sband) { - u8 *pos; + u8 *pos, *pre_he_pos; const struct ieee80211_sta_he_cap *he_cap = NULL; struct ieee80211_chanctx_conf *chanctx_conf; u8 he_cap_size; @@@ -652,21 -653,16 +653,21 @@@

he_cap = ieee80211_get_he_iftype_cap(sband, ieee80211_vif_type_p2p(&sdata->vif)); - if (!he_cap || !reg_cap) + if (!he_cap || !chanctx_conf || !reg_cap) return;

+ /* get a max size estimate */ he_cap_size = 2 + 1 + sizeof(he_cap->he_cap_elem) + ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) + ieee80211_he_ppe_size(he_cap->ppe_thres[0], he_cap->he_cap_elem.phy_cap_info); pos = skb_put(skb, he_cap_size); - ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size); + pre_he_pos = pos; + pos = ieee80211_ie_build_he_cap(sdata->u.mgd.flags, + pos, he_cap, pos + he_cap_size); + /* trim excess if any */ + skb_trim(skb, skb->len - (pre_he_pos + he_cap_size - pos));

ieee80211_ie_build_he_6ghz_cap(sdata, skb); } @@@ -3016,8 -3012,15 +3017,15 @@@ static void ieee80211_rx_mgmt_auth(stru (status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED || (auth_transaction == 1 && (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT || - status_code == WLAN_STATUS_SAE_PK)))) + status_code == WLAN_STATUS_SAE_PK)))) { + /* waiting for userspace now */ + ifmgd->auth_data->waiting = true; + ifmgd->auth_data->timeout = + jiffies + IEEE80211_AUTH_WAIT_SAE_RETRY; + ifmgd->auth_data->timeout_started = true; + run_again(sdata, ifmgd->auth_data->timeout); goto notify_driver; + }

sdata_info(sdata, "%pM denied authentication (status %d)\n", mgmt->sa, status_code); @@@ -4608,10 -4611,10 +4616,10 @@@ void ieee80211_sta_work(struct ieee8021

if (ifmgd->auth_data && ifmgd->auth_data->timeout_started && time_after(jiffies, ifmgd->auth_data->timeout)) { - if (ifmgd->auth_data->done) { + if (ifmgd->auth_data->done || ifmgd->auth_data->waiting) { /* - * ok ... we waited for assoc but userspace didn't, - * so let's just kill the auth data + * ok ... we waited for assoc or continuation but + * userspace didn't do it, so kill the auth data */ ieee80211_destroy_auth_data(sdata, false); } else if (ieee80211_auth(sdata)) { @@@ -4920,20 -4923,13 +4928,20 @@@ void ieee80211_mlme_notify_scan_complet rcu_read_unlock(); }

-static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, - struct cfg80211_bss *cbss) +static u8 ieee80211_max_rx_chains(struct ieee80211_sub_if_data *sdata, + struct cfg80211_bss *cbss) { + struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; const struct element *ht_cap_elem, *vht_cap_elem; + const struct cfg80211_bss_ies *ies; const struct ieee80211_ht_cap *ht_cap; const struct ieee80211_vht_cap *vht_cap; + const struct ieee80211_he_cap_elem *he_cap; + const struct element *he_cap_elem; + u16 mcs_80_map, mcs_160_map; + int i, mcs_nss_size; + bool support_160; u8 chains = 1;

if (ifmgd->flags & IEEE80211_STA_DISABLE_HT) @@@ -4968,155 -4964,9 +4976,155 @@@ chains = max(chains, nss); }

+ if (ifmgd->flags & IEEE80211_STA_DISABLE_HE) + return chains; + + ies = rcu_dereference(cbss->ies); + he_cap_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, + ies->data, ies->len); + + if (!he_cap_elem || he_cap_elem->datalen < sizeof(*he_cap)) + return chains; + + /* skip one byte ext_tag_id */ + he_cap = (void *)(he_cap_elem->data + 1); + mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap); + + /* invalid HE IE */ + if (he_cap_elem->datalen < 1 + mcs_nss_size + sizeof(*he_cap)) + return chains; + + /* mcs_nss is right after he_cap info */ + he_mcs_nss_supp = (void *)(he_cap + 1); + + mcs_80_map = le16_to_cpu(he_mcs_nss_supp->tx_mcs_80); + + for (i = 7; i >= 0; i--) { + u8 mcs_80 = mcs_80_map >> (2 * i) & 3; + + if (mcs_80 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + chains = max_t(u8, chains, i + 1); + break; + } + } + + support_160 = he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + + if (!support_160) + return chains; + + mcs_160_map = le16_to_cpu(he_mcs_nss_supp->tx_mcs_160); + for (i = 7; i >= 0; i--) { + u8 mcs_160 = mcs_160_map >> (2 * i) & 3; + + if (mcs_160 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + chains = max_t(u8, chains, i + 1); + break; + } + } + return chains; }

+static bool +ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, + const struct cfg80211_bss_ies *ies, + const struct ieee80211_he_operation *he_op) +{ + const struct element *he_cap_elem; + const struct ieee80211_he_cap_elem *he_cap; + struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp; + u16 mcs_80_map_tx, mcs_80_map_rx; + u16 ap_min_req_set; + int mcs_nss_size; + int nss; + + he_cap_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, + ies->data, ies->len); + + /* invalid HE IE */ + if (!he_cap_elem || he_cap_elem->datalen < 1 + sizeof(*he_cap)) { + sdata_info(sdata, + "Invalid HE elem, Disable HE\n"); + return false; + } + + /* skip one byte ext_tag_id */ + he_cap = (void *)(he_cap_elem->data + 1); + mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap); + + /* invalid HE IE */ + if (he_cap_elem->datalen < 1 + sizeof(*he_cap) + mcs_nss_size) { + sdata_info(sdata, + "Invalid HE elem with nss size, Disable HE\n"); + return false; + } + + /* mcs_nss is right after he_cap info */ + he_mcs_nss_supp = (void *)(he_cap + 1); + + mcs_80_map_tx = le16_to_cpu(he_mcs_nss_supp->tx_mcs_80); + mcs_80_map_rx = le16_to_cpu(he_mcs_nss_supp->rx_mcs_80); + + /* P802.11-REVme/D0.3 + * 27.1.1 Introduction to the HE PHY + * ... + * An HE STA shall support the following features: + * ... + * Single spatial stream HE-MCSs 0 to 7 (transmit and receive) in all + * supported channel widths for HE SU PPDUs + */ + if ((mcs_80_map_tx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED || + (mcs_80_map_rx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED) { + sdata_info(sdata, + "Missing mandatory rates for 1 Nss, rx 0x%x, tx 0x%x, disable HE\n", + mcs_80_map_tx, mcs_80_map_rx); + return false; + } + + if (!he_op) + return true; + + ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); + + /* make sure the AP is consistent with itself + * + * P802.11-REVme/D0.3 + * 26.17.1 Basic HE BSS operation + * + * A STA that is operating in an HE BSS shall be able to receive and + * transmit at each of the <HE-MCS, NSS> tuple values indicated by the + * Basic HE-MCS And NSS Set field of the HE Operation parameter of the + * MLME-START.request primitive and shall be able to receive at each of + * the <HE-MCS, NSS> tuple values indicated by the Supported HE-MCS and + * NSS Set field in the HE Capabilities parameter of the MLMESTART.request + * primitive + */ + for (nss = 8; nss > 0; nss--) { + u8 ap_op_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + u8 ap_rx_val; + u8 ap_tx_val; + + if (ap_op_val == IEEE80211_HE_MCS_NOT_SUPPORTED) + continue; + + ap_rx_val = (mcs_80_map_rx >> (2 * (nss - 1))) & 3; + ap_tx_val = (mcs_80_map_tx >> (2 * (nss - 1))) & 3; + + if (ap_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + ap_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + ap_rx_val < ap_op_val || ap_tx_val < ap_op_val) { + sdata_info(sdata, + "Invalid rates for %d Nss, rx %d, tx %d oper %d, disable HE\n", + nss, ap_rx_val, ap_rx_val, ap_op_val); + return false; + } + } + + return true; +} + static bool ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, @@@ -5163,15 -5013,7 +5171,15 @@@

/* * Make sure the HE AP doesn't require MCSs that aren't - * supported by the client + * supported by the client as required by spec + * + * P802.11-REVme/D0.3 + * 26.17.1 Basic HE BSS operation + * + * An HE STA shall not attempt to join * (MLME-JOIN.request primitive) + * a BSS, unless it supports (i.e., is able to both transmit and + * receive using) all of the <HE-MCS, NSS> tuples in the basic + * HE-MCS and NSS set. */ if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || @@@ -5302,8 -5144,7 +5310,8 @@@ static int ieee80211_prep_channel(struc } }

- if (!ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) + if (!ieee80211_verify_peer_he_mcs_support(sdata, ies, he_oper) || + !ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; }

@@@ -5337,7 -5178,7 +5345,7 @@@ s1g_oper, &chandef, false);

- sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss), + sdata->needed_rx_chains = min(ieee80211_max_rx_chains(sdata, cbss), local->rx_chains);

rcu_read_unlock(); diff --combined net/mac80211/rx.c index d54a4d98c648,48d9553dafe3..beb6b92eb780 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@@ -2607,7 -2607,8 +2607,8 @@@ static void ieee80211_deliver_skb_to_lo * address, so that the authenticator (e.g. hostapd) will see * the frame, but bridge won't forward it anywhere else. Note * that due to earlier filtering, the only other address can - * be the PAE group address. + * be the PAE group address, unless the hardware allowed them + * through in 802.3 offloaded mode. */ if (unlikely(skb->protocol == sdata->control_port_protocol && !ether_addr_equal(ehdr->h_dest, sdata->vif.addr))) @@@ -2922,13 -2923,13 +2923,13 @@@ ieee80211_rx_h_mesh_fwding(struct ieee8 ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE;

- ac = ieee80211_select_queue_80211(sdata, skb, hdr); + ac = ieee802_1d_to_ac[skb->priority]; q = sdata->vif.hw_queue[ac]; if (ieee80211_queue_stopped(&local->hw, q)) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion); return RX_DROP_MONITOR; } - skb_set_queue_mapping(skb, q); + skb_set_queue_mapping(skb, ac);

if (!--mesh_hdr->ttl) { if (!is_multicast_ether_addr(hdr->addr1)) @@@ -4514,12 -4515,7 +4515,7 @@@ static void ieee80211_rx_8023(struct ie

/* deliver to local stack */ skb->protocol = eth_type_trans(skb, fast_rx->dev); - memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->list) - list_add_tail(&skb->list, rx->list); - else - netif_receive_skb(skb); - + ieee80211_deliver_skb_to_local_stack(skb, rx); }

static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, @@@ -4629,8 -4625,6 +4625,8 @@@ /* do the header conversion - first grab the addresses */ ether_addr_copy(addrs.da, skb->data + fast_rx->da_offs); ether_addr_copy(addrs.sa, skb->data + fast_rx->sa_offs); + skb_postpull_rcsum(skb, skb->data + snap_offs, + sizeof(rfc1042_header) + 2); /* remove the SNAP but leave the ethertype */ skb_pull(skb, snap_offs + sizeof(rfc1042_header)); /* push the addresses in front */ diff --combined net/netfilter/core.c index d1c9dfbb11fa,8a77a3fd69bc..9a4feb922cf6 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@@ -428,14 -428,15 +428,15 @@@ static int __nf_register_net_hook(struc p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg);

- if (!IS_ERR(new_hooks)) + if (!IS_ERR(new_hooks)) { + hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); + }

mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks);

- hooks_validate(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); @@@ -621,8 -622,7 +622,8 @@@ int nf_hook_slow(struct sk_buff *skb, s case NF_ACCEPT: break; case NF_DROP: - kfree_skb(skb); + kfree_skb_reason(skb, + SKB_DROP_REASON_NETFILTER_DROP); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; diff --combined net/netfilter/nfnetlink_queue.c index db9b5357f2ca,64a6acb6aeae..a364f8e5e698 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@@ -392,7 -392,6 +392,7 @@@ nfqnl_build_packet_message(struct net * bool csum_verify; char *secdata = NULL; u32 seclen = 0; + ktime_t tstamp;

size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) @@@ -403,13 -402,11 +403,13 @@@ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + + nla_total_size(sizeof(u_int32_t)) /* priority */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) + nla_total_size(sizeof(u_int32_t)) /* skbinfo */ + nla_total_size(sizeof(u_int32_t)); /* cap_len */

- if (entskb->tstamp) + tstamp = skb_tstamp_cond(entskb, false); + if (tstamp) size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));

size += nfqnl_get_bridge_size(entry); @@@ -562,10 -559,6 +562,10 @@@ nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) goto nla_put_failure;

+ if (entskb->priority && + nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority))) + goto nla_put_failure; + if (indev && entskb->dev && skb_mac_header_was_set(entskb) && skb_mac_header_len(entskb) != 0) { @@@ -584,9 -577,9 +584,9 @@@ if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure;

- if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) { + if (entry->state.hook <= NF_INET_FORWARD && tstamp) { struct nfqnl_msg_packet_timestamp ts; - struct timespec64 kts = ktime_to_timespec64(entskb->tstamp); + struct timespec64 kts = ktime_to_timespec64(tstamp);

ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); @@@ -717,9 -710,15 +717,15 @@@ static struct nf_queue_entry nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); - if (entry) - nf_queue_entry_get_refs(entry); - return entry; + + if (!entry) + return NULL; + + if (nf_queue_entry_get_refs(entry)) + return entry; + + kfree(entry); + return NULL; }

#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) @@@ -1021,13 -1020,11 +1027,13 @@@ static const struct nla_policy nfqa_ver [NFQA_CT] = { .type = NLA_UNSPEC }, [NFQA_EXP] = { .type = NLA_UNSPEC }, [NFQA_VLAN] = { .type = NLA_NESTED }, + [NFQA_PRIORITY] = { .type = NLA_U32 }, };

static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, + [NFQA_PRIORITY] = { .type = NLA_U32 }, };

static struct nfqnl_instance * @@@ -1108,9 -1105,6 +1114,9 @@@ static int nfqnl_recv_verdict_batch(str if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));

+ if (nfqa[NFQA_PRIORITY]) + entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); + nfqnl_reinject(entry, verdict); } return 0; @@@ -1237,9 -1231,6 +1243,9 @@@ static int nfqnl_recv_verdict(struct sk if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));

+ if (nfqa[NFQA_PRIORITY]) + entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); + nfqnl_reinject(entry, verdict); return 0; } diff --combined net/sched/act_ct.c index 5234e8bcc764,ec19f625863a..89e46f66e3d9 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@@ -57,6 -57,12 +57,6 @@@ static const struct rhashtable_params z .automatic_shrinking = true, };

-static struct nf_ct_ext_type act_ct_extend __read_mostly = { - .len = sizeof(struct nf_conn_act_ct_ext), - .align = __alignof__(struct nf_conn_act_ct_ext), - .id = NF_CT_EXT_ACT_CT, -}; - static struct flow_action_entry * tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) { @@@ -355,6 -361,13 +355,13 @@@ static void tcf_ct_flow_table_put(struc } }

+ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, + struct nf_conn_act_ct_ext *act_ct_ext, u8 dir) + { + entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC; + entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; + } + static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, bool tcp) @@@ -379,10 -392,8 +386,8 @@@

act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { - entry->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx = - act_ct_ext->ifindex[IP_CT_DIR_ORIGINAL]; - entry->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx = - act_ct_ext->ifindex[IP_CT_DIR_REPLY]; + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); }

err = flow_offload_add(&ct_ft->nf_ft, entry); @@@ -1597,10 -1608,16 +1602,10 @@@ static int __init ct_init_module(void if (err) goto err_register;

- err = nf_ct_extend_register(&act_ct_extend); - if (err) - goto err_register_extend; - static_branch_inc(&tcf_frag_xmit_count);

return 0;

-err_register_extend: - tcf_unregister_action(&act_ct_ops, &ct_net_ops); err_register: tcf_ct_flow_tables_uninit(); err_tbl_init: @@@ -1611,6 -1628,7 +1616,6 @@@ static void __exit ct_cleanup_module(void) { static_branch_dec(&tcf_frag_xmit_count); - nf_ct_extend_unregister(&act_ct_extend); tcf_unregister_action(&act_ct_ops, &ct_net_ops); tcf_ct_flow_tables_uninit(); destroy_workqueue(act_ct_wq); diff --combined net/smc/af_smc.c index 6447607675fa,284befa90967..e508e4f3a073 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@@ -51,7 -51,6 +51,7 @@@ #include "smc_close.h" #include "smc_stats.h" #include "smc_tracepoint.h" +#include "smc_sysctl.h"

static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@@ -60,52 -59,12 +60,52 @@@ static DEFINE_MUTEX(smc_client_lgr_pend * creation on client */

+static struct workqueue_struct *smc_tcp_ls_wq; /* wq for tcp listen work */ struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ struct workqueue_struct *smc_close_wq; /* wq for close work */

static void smc_tcp_listen_work(struct work_struct *); static void smc_connect_work(struct work_struct *);

+int smc_nl_dump_hs_limitation(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + void *hdr; + + if (cb_ctx->pos[0]) + goto out; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_DUMP_HS_LIMITATION); + if (!hdr) + return -ENOMEM; + + if (nla_put_u8(skb, SMC_NLA_HS_LIMITATION_ENABLED, + sock_net(skb->sk)->smc.limit_smc_hs)) + goto err; + + genlmsg_end(skb, hdr); + cb_ctx->pos[0] = 1; +out: + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info) +{ + sock_net(skb->sk)->smc.limit_smc_hs = true; + return 0; +} + +int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info) +{ + sock_net(skb->sk)->smc.limit_smc_hs = false; + return 0; +} + static void smc_set_keepalive(struct sock *sk, int val) { struct smc_sock *smc = smc_sk(sk); @@@ -113,51 -72,6 +113,51 @@@ smc->clcsock->sk->sk_prot->keepalive(smc->clcsock->sk, val); }

+static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, + struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst, + struct request_sock *req_unhash, + bool *own_req) +{ + struct smc_sock *smc; + + smc = smc_clcsock_user_data(sk); + + if (READ_ONCE(sk->sk_ack_backlog) + atomic_read(&smc->queued_smc_hs) > + sk->sk_max_ack_backlog) + goto drop; + + if (sk_acceptq_is_full(&smc->sk)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + goto drop; + } + + /* passthrough to original syn recv sock fct */ + return smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, + own_req); + +drop: + dst_release(dst); + tcp_listendrop(sk); + return NULL; +} + +static bool smc_hs_congested(const struct sock *sk) +{ + const struct smc_sock *smc; + + smc = smc_clcsock_user_data(sk); + + if (!smc) + return true; + + if (workqueue_congested(WORK_CPU_UNBOUND, smc_hs_wq)) + return true; + + return false; +} + static struct smc_hashinfo smc_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; @@@ -193,27 -107,12 +193,27 @@@ void smc_unhash_sk(struct sock *sk } EXPORT_SYMBOL_GPL(smc_unhash_sk);

+/* This will be called before user really release sock_lock. So do the + * work which we didn't do because of user hold the sock_lock in the + * BH context + */ +static void smc_release_cb(struct sock *sk) +{ + struct smc_sock *smc = smc_sk(sk); + + if (smc->conn.tx_in_release_sock) { + smc_tx_pending(&smc->conn); + smc->conn.tx_in_release_sock = false; + } +} + struct proto smc_proto = { .name = "SMC", .owner = THIS_MODULE, .keepalive = smc_set_keepalive, .hash = smc_hash_sk, .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, .obj_size = sizeof(struct smc_sock), .h.smc_hash = &smc_v4_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, @@@ -226,7 -125,6 +226,7 @@@ struct proto smc_proto6 = .keepalive = smc_set_keepalive, .hash = smc_hash_sk, .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, .obj_size = sizeof(struct smc_sock), .h.smc_hash = &smc_v6_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, @@@ -285,7 -183,7 +285,7 @@@ static int smc_release(struct socket *s { struct sock *sk = sock->sk; struct smc_sock *smc; - int rc = 0; + int old_state, rc = 0;

if (!sk) goto out; @@@ -293,8 -191,10 +293,10 @@@ sock_hold(sk); /* sock_put below */ smc = smc_sk(sk);

+ old_state = sk->sk_state; + /* cleanup for a dangling non-blocking connect */ - if (smc->connect_nonblock && sk->sk_state == SMC_INIT) + if (smc->connect_nonblock && old_state == SMC_INIT) tcp_abort(smc->clcsock->sk, ECONNABORTED);

if (cancel_work_sync(&smc->connect_work)) @@@ -308,6 -208,10 +310,10 @@@ else lock_sock(sk);

+ if (old_state == SMC_INIT && sk->sk_state == SMC_ACTIVE && + !smc->use_fallback) + smc_close_active_abort(smc); + rc = __smc_release(smc);

/* detach socket */ @@@ -1393,14 -1297,8 +1399,14 @@@ static int __smc_connect(struct smc_soc

/* perform CLC handshake */ rc = smc_connect_clc(smc, aclc2, ini); - if (rc) + if (rc) { + /* -EAGAIN on timeout, see tcp_recvmsg() */ + if (rc == -EAGAIN) { + rc = -ETIMEDOUT; + smc->sk.sk_err = ETIMEDOUT; + } goto vlan_cleanup; + }

/* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); @@@ -1706,9 -1604,6 +1712,9 @@@ static void smc_listen_out(struct smc_s struct smc_sock *lsmc = new_smc->listen_smc; struct sock *newsmcsk = &new_smc->sk;

+ if (tcp_sk(new_smc->clcsock->sk)->syn_smc) + atomic_dec(&lsmc->queued_smc_hs); + if (lsmc->sk.sk_state == SMC_LISTEN) { lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); @@@ -2314,9 -2209,6 +2320,9 @@@ static void smc_tcp_listen_work(struct if (!new_smc) continue;

+ if (tcp_sk(new_smc->clcsock->sk)->syn_smc) + atomic_inc(&lsmc->queued_smc_hs); + new_smc->listen_smc = lsmc; new_smc->use_fallback = lsmc->use_fallback; new_smc->fallback_rsn = lsmc->fallback_rsn; @@@ -2345,7 -2237,7 +2351,7 @@@ static void smc_clcsock_data_ready(stru lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ - if (!queue_work(smc_hs_wq, &lsmc->tcp_listen_work)) + if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } } @@@ -2383,18 -2275,6 +2389,18 @@@ static int smc_listen(struct socket *so smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + /* save original ops */ + smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; + + smc->af_ops = *smc->ori_af_ops; + smc->af_ops.syn_recv_sock = smc_tcp_syn_recv_sock; + + inet_csk(smc->clcsock->sk)->icsk_af_ops = &smc->af_ops; + + if (smc->limit_smc_hs) + tcp_sk(smc->clcsock->sk)->smc_hs_congested = smc_hs_congested; + rc = kernel_listen(smc->clcsock, backlog); if (rc) { smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; @@@ -2688,71 -2568,6 +2694,71 @@@ out return rc ? rc : rc1; }

+static int __smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct smc_sock *smc; + int val, len; + + smc = smc_sk(sock->sk); + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(int, len, sizeof(int)); + + if (len < 0) + return -EINVAL; + + switch (optname) { + case SMC_LIMIT_HS: + val = smc->limit_smc_hs; + break; + default: + return -EOPNOTSUPP; + } + + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; +} + +static int __smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct smc_sock *smc; + int val, rc; + + smc = smc_sk(sk); + + lock_sock(sk); + switch (optname) { + case SMC_LIMIT_HS: + if (optlen < sizeof(int)) { + rc = -EINVAL; + break; + } + if (copy_from_sockptr(&val, optval, sizeof(int))) { + rc = -EFAULT; + break; + } + + smc->limit_smc_hs = !!val; + rc = 0; + break; + default: + rc = -EOPNOTSUPP; + break; + } + release_sock(sk); + + return rc; +} + static int smc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@@ -2762,8 -2577,6 +2768,8 @@@

if (level == SOL_TCP && optname == TCP_ULP) return -EOPNOTSUPP; + else if (level == SOL_SMC) + return __smc_setsockopt(sock, level, optname, optval, optlen);

smc = smc_sk(sk);

@@@ -2812,8 -2625,8 +2818,8 @@@ sk->sk_state != SMC_CLOSED) { if (val) { SMC_STAT_INC(smc, ndly_cnt); - mod_delayed_work(smc->conn.lgr->tx_wq, - &smc->conn.tx_work, 0); + smc_tx_pending(&smc->conn); + cancel_delayed_work(&smc->conn.tx_work); } } break; @@@ -2823,8 -2636,8 +2829,8 @@@ sk->sk_state != SMC_CLOSED) { if (!val) { SMC_STAT_INC(smc, cork_cnt); - mod_delayed_work(smc->conn.lgr->tx_wq, - &smc->conn.tx_work, 0); + smc_tx_pending(&smc->conn); + cancel_delayed_work(&smc->conn.tx_work); } } break; @@@ -2846,9 -2659,6 +2852,9 @@@ static int smc_getsockopt(struct socke struct smc_sock *smc; int rc;

+ if (level == SOL_SMC) + return __smc_getsockopt(sock, level, optname, optval, optlen); + smc = smc_sk(sock->sk); mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { @@@ -2965,10 -2775,8 +2971,10 @@@ static ssize_t smc_sendpage(struct sock rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); } else { + lock_sock(sk); + rc = smc_tx_sendpage(smc, page, offset, size, flags); + release_sock(sk); SMC_STAT_INC(smc, sendpage_cnt); - rc = sock_no_sendpage(sock, page, offset, size, flags); }

out: @@@ -3077,9 -2885,6 +3083,9 @@@ static int __smc_create(struct net *net smc->use_fallback = false; /* assume rdma capability first */ smc->fallback_rsn = 0;

+ /* default behavior from limit_smc_hs in every net namespace */ + smc->limit_smc_hs = net->smc.limit_smc_hs; + rc = 0; if (!clcsock) { rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, @@@ -3227,14 -3032,9 +3233,14 @@@ static int __init smc_init(void goto out_nl;

rc = -ENOMEM; + + smc_tcp_ls_wq = alloc_workqueue("smc_tcp_ls_wq", 0, 0); + if (!smc_tcp_ls_wq) + goto out_pnet; + smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0); if (!smc_hs_wq) - goto out_pnet; + goto out_alloc_tcp_ls_wq;

smc_close_wq = alloc_workqueue("smc_close_wq", 0, 0); if (!smc_close_wq) @@@ -3287,20 -3087,14 +3293,22 @@@ rc = tcp_register_ulp(&smc_ulp_ops); if (rc) { pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); - goto out_sock; + goto out_ib; }

+ rc = smc_sysctl_init(); + if (rc) { + pr_err("%s: sysctl_init fails with %d\n", __func__, rc); + goto out_ulp; + } + static_branch_enable(&tcp_have_smc); return 0;

+out_ulp: + tcp_unregister_ulp(&smc_ulp_ops); + out_ib: + smc_ib_unregister_client(); out_sock: sock_unregister(PF_SMC); out_proto6: @@@ -3313,8 -3107,6 +3321,8 @@@ out_alloc_wqs destroy_workqueue(smc_close_wq); out_alloc_hs_wq: destroy_workqueue(smc_hs_wq); +out_alloc_tcp_ls_wq: + destroy_workqueue(smc_tcp_ls_wq); out_pnet: smc_pnet_exit(); out_nl: @@@ -3328,13 -3120,11 +3336,13 @@@ out_pernet_subsys static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); + smc_sysctl_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); smc_ib_unregister_client(); destroy_workqueue(smc_close_wq); + destroy_workqueue(smc_tcp_ls_wq); destroy_workqueue(smc_hs_wq); proto_unregister(&smc_proto6); proto_unregister(&smc_proto); diff --combined net/smc/smc_core.c index 1674b2549f8b,be7d704976ff..f40f6ed0fbdb --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@@ -1161,8 -1161,8 +1161,8 @@@ void smc_conn_free(struct smc_connectio cancel_work_sync(&conn->abort_work); } if (!list_empty(&lgr->list)) { - smc_lgr_unregister_conn(conn); smc_buf_unuse(conn, lgr); /* allow buffer reuse */ + smc_lgr_unregister_conn(conn); }

if (!lgr->conns_num) @@@ -1864,7 -1864,8 +1864,8 @@@ int smc_conn_create(struct smc_sock *sm (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || - lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { + (lgr->conns_num < SMC_RMBS_PER_LGR_MAX && + !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) { /* link group found */ ini->first_contact_local = 0; conn->lgr = lgr; @@@ -1988,7 -1989,7 +1989,7 @@@ static struct smc_buf_desc *smc_buf_get */ static inline int smc_rmb_wnd_update_limit(int rmbe_size) { - return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); + return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); }

/* map an rmb buf to a link */ diff --combined net/xfrm/xfrm_interface.c index 4991e99ced9a,4e3c62d1ad9e..daec1fb08bf5 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@@ -190,7 -190,7 +190,7 @@@ static void xfrmi_dev_uninit(struct net

static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) { - skb->tstamp = 0; + skb_clear_tstamp(skb); skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; @@@ -673,12 -673,12 +673,12 @@@ static int xfrmi_changelink(struct net_ struct net *net = xi->net; struct xfrm_if_parms p = {};

+ xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; }

- xfrmi_netlink_parms(data, &p); xi = xfrmi_locate(net, &p); if (!xi) { xi = netdev_priv(dev); diff --combined tools/testing/selftests/net/mptcp/mptcp_connect.sh index 5b7a40d73253,f0f4ab96b8f3..621af6895f4d --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@@ -432,8 -432,6 +432,8 @@@ do_transfer( local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr")

timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@@ -526,23 -524,6 +526,23 @@@ fi fi

+ if $checksum; then + local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + + local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) + if [ $csum_err_s_nr -gt 0 ]; then + printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + rets=1 + fi + + local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) + if [ $csum_err_c_nr -gt 0 ]; then + printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + retc=1 + fi + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then printf "[ OK ]" fi @@@ -782,8 -763,8 +782,8 @@@ run_tests_disconnect( run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin"

# restore previous status - cout=$old_cout - cout_disconnect="$cout".disconnect + sin=$old_sin + sin_disconnect="$cout".disconnect cin=$old_cin cin_disconnect="$cin".disconnect connect_per_transfer=1