diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c index ddf0b9ff9e15c..435d0e2658a42 100644 --- a/drivers/firmware/arm_scpi.c +++ b/drivers/firmware/arm_scpi.c @@ -815,7 +815,7 @@ static int scpi_init_versions(struct scpi_drvinfo *info) info->firmware_version = le32_to_cpu(caps.platform_version); } /* Ignore error if not implemented */ - if (scpi_info->is_legacy && ret == -EOPNOTSUPP) + if (info->is_legacy && ret == -EOPNOTSUPP) return 0; return ret; @@ -913,13 +913,14 @@ static int scpi_probe(struct platform_device *pdev) struct resource res; struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; + struct scpi_drvinfo *scpi_drvinfo; - scpi_info = devm_kzalloc(dev, sizeof(*scpi_info), GFP_KERNEL); - if (!scpi_info) + scpi_drvinfo = devm_kzalloc(dev, sizeof(*scpi_drvinfo), GFP_KERNEL); + if (!scpi_drvinfo) return -ENOMEM; if (of_match_device(legacy_scpi_of_match, &pdev->dev)) - scpi_info->is_legacy = true; + scpi_drvinfo->is_legacy = true; count = of_count_phandle_with_args(np, "mboxes", "#mbox-cells"); if (count < 0) { @@ -927,19 +928,19 @@ static int scpi_probe(struct platform_device *pdev) return -ENODEV; } - scpi_info->channels = devm_kcalloc(dev, count, sizeof(struct scpi_chan), - GFP_KERNEL); - if (!scpi_info->channels) + scpi_drvinfo->channels = + devm_kcalloc(dev, count, sizeof(struct scpi_chan), GFP_KERNEL); + if (!scpi_drvinfo->channels) return -ENOMEM; - ret = devm_add_action(dev, scpi_free_channels, scpi_info); + ret = devm_add_action(dev, scpi_free_channels, scpi_drvinfo); if (ret) return ret; - for (; scpi_info->num_chans < count; scpi_info->num_chans++) { + for (; scpi_drvinfo->num_chans < count; scpi_drvinfo->num_chans++) { resource_size_t size; - int idx = scpi_info->num_chans; - struct scpi_chan *pchan = scpi_info->channels + idx; + int idx = scpi_drvinfo->num_chans; + struct scpi_chan *pchan = scpi_drvinfo->channels + idx; struct mbox_client *cl = &pchan->cl; struct device_node *shmem = of_parse_phandle(np, "shmem", idx); @@ -986,45 +987,53 @@ static int scpi_probe(struct platform_device *pdev) return ret; } - scpi_info->commands = scpi_std_commands; + scpi_drvinfo->commands = scpi_std_commands; - platform_set_drvdata(pdev, scpi_info); + platform_set_drvdata(pdev, scpi_drvinfo); - if (scpi_info->is_legacy) { + if (scpi_drvinfo->is_legacy) { /* Replace with legacy variants */ scpi_ops.clk_set_val = legacy_scpi_clk_set_val; - scpi_info->commands = scpi_legacy_commands; + scpi_drvinfo->commands = scpi_legacy_commands; /* Fill priority bitmap */ for (idx = 0; idx < ARRAY_SIZE(legacy_hpriority_cmds); idx++) set_bit(legacy_hpriority_cmds[idx], - scpi_info->cmd_priority); + scpi_drvinfo->cmd_priority); } - ret = scpi_init_versions(scpi_info); + scpi_info = scpi_drvinfo; + + ret = scpi_init_versions(scpi_drvinfo); if (ret) { dev_err(dev, "incorrect or no SCP firmware found\n"); + scpi_info = NULL; return ret; } - if (scpi_info->is_legacy && !scpi_info->protocol_version && - !scpi_info->firmware_version) + if (scpi_drvinfo->is_legacy && !scpi_drvinfo->protocol_version && + !scpi_drvinfo->firmware_version) dev_info(dev, "SCP Protocol legacy pre-1.0 firmware\n"); else dev_info(dev, "SCP Protocol %lu.%lu Firmware %lu.%lu.%lu version\n", FIELD_GET(PROTO_REV_MAJOR_MASK, - scpi_info->protocol_version), + scpi_drvinfo->protocol_version), FIELD_GET(PROTO_REV_MINOR_MASK, - scpi_info->protocol_version), + scpi_drvinfo->protocol_version), FIELD_GET(FW_REV_MAJOR_MASK, - scpi_info->firmware_version), + scpi_drvinfo->firmware_version), FIELD_GET(FW_REV_MINOR_MASK, - scpi_info->firmware_version), + scpi_drvinfo->firmware_version), FIELD_GET(FW_REV_PATCH_MASK, - scpi_info->firmware_version)); - scpi_info->scpi_ops = &scpi_ops; + scpi_drvinfo->firmware_version)); + + scpi_drvinfo->scpi_ops = &scpi_ops; - return devm_of_platform_populate(dev); + ret = devm_of_platform_populate(dev); + if (ret) + scpi_info = NULL; + + return ret; } static const struct of_device_id scpi_of_match[] = { diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 4f01e2a6b6bbf..d5022cddc0311 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1210,10 +1210,11 @@ i40e_status i40e_pf_reset(struct i40e_hw *hw) void i40e_clear_hw(struct i40e_hw *hw) { u32 num_queues, base_queue; - u32 num_pf_int; - u32 num_vf_int; + s32 num_pf_int; + s32 num_vf_int; u32 num_vfs; - u32 i, j; + s32 i; + u32 j; u32 val; u32 eol = 0x7ff; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index eca945feeec3e..469824c329e75 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4300,6 +4300,12 @@ static irqreturn_t dwc3_check_event_buf(struct dwc3_event_buffer *evt) if (!count) return IRQ_NONE; + if (count > evt->length) { + dev_err_ratelimited(dwc->dev, "invalid count(%u) > evt->length(%u)\n", + count, evt->length); + return IRQ_NONE; + } + evt->count = count; evt->flags |= DWC3_EVENT_PENDING; diff --git a/fs/namespace.c b/fs/namespace.c index 58659bf9d0d73..733d5e8791136 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2287,6 +2287,19 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) return attach_recursive_mnt(mnt, p, mp, false); } +static int may_change_propagation(const struct mount *m) +{ + struct mnt_namespace *ns = m->mnt_ns; + + // it must be mounted in some namespace + if (IS_ERR_OR_NULL(ns)) // is_mounted() + return -EINVAL; + // and the caller must be admin in userns of that namespace + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + return 0; +} + /* * Sanity check the flags to change_mnt_propagation. */ @@ -2323,6 +2336,10 @@ static int do_change_type(struct path *path, int ms_flags) return -EINVAL; namespace_lock(); + err = may_change_propagation(mnt); + if (err) + goto out_unlock; + if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) @@ -2695,6 +2712,71 @@ static bool check_for_nsfs_mounts(struct mount *subtree) return ret; } +static int do_set_group(struct path *from_path, struct path *to_path) +{ + struct mount *from, *to; + int err; + + from = real_mount(from_path->mnt); + to = real_mount(to_path->mnt); + + namespace_lock(); + + err = may_change_propagation(from); + if (err) + goto out; + err = may_change_propagation(to); + if (err) + goto out; + + err = -EINVAL; + /* To and From paths should be mount roots */ + if (from_path->dentry != from_path->mnt->mnt_root) + goto out; + if (to_path->dentry != to_path->mnt->mnt_root) + goto out; + + /* Setting sharing groups is only allowed across same superblock */ + if (from->mnt.mnt_sb != to->mnt.mnt_sb) + goto out; + + /* From mount root should be wider than To mount root */ + if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) + goto out; + + /* From mount should not have locked children in place of To's root */ + if (has_locked_children(from, to->mnt.mnt_root)) + goto out; + + /* Setting sharing groups is only allowed on private mounts */ + if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) + goto out; + + /* From should not be private */ + if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) + goto out; + + if (IS_MNT_SLAVE(from)) { + struct mount *m = from->mnt_master; + + list_add(&to->mnt_slave, &from->mnt_slave); + to->mnt_master = m; + } + + if (IS_MNT_SHARED(from)) { + to->mnt_group_id = from->mnt_group_id; + list_add(&to->mnt_share, &from->mnt_share); + lock_mount_hash(); + set_mnt_shared(to); + unlock_mount_hash(); + } + + err = 0; +out: + namespace_unlock(); + return err; +} + static int do_move_mount(struct path *old_path, struct path *new_path) { struct mnt_namespace *ns; @@ -3679,7 +3761,10 @@ SYSCALL_DEFINE5(move_mount, if (ret < 0) goto out_to; - ret = do_move_mount(&from_path, &to_path); + if (flags & MOVE_MOUNT_SET_GROUP) + ret = do_set_group(&from_path, &to_path); + else + ret = do_move_mount(&from_path, &to_path); out_to: path_put(&to_path); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 1419391199f79..016cc7f41c54d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -300,8 +300,19 @@ static inline bool nf_ct_is_expired(const struct nf_conn *ct) /* use after obtaining a reference count */ static inline bool nf_ct_should_gc(const struct nf_conn *ct) { - return nf_ct_is_expired(ct) && nf_ct_is_confirmed(ct) && - !nf_ct_is_dying(ct); + if (!nf_ct_is_confirmed(ct)) + return false; + + /* load ct->timeout after is_confirmed() test. + * Pairs with __nf_conntrack_confirm() which: + * 1. Increases ct->timeout value + * 2. Inserts ct into rcu hlist + * 3. Sets the confirmed bit + * 4. Unlocks the hlist lock + */ + smp_acquire__after_ctrl_dep(); + + return nf_ct_is_expired(ct) && !nf_ct_is_dying(ct); } #define NF_CT_DAY (86400 * HZ) diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index dd7a166fdf9c2..4d93967f8aea0 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -73,7 +73,8 @@ #define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */ #define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ #define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ -#define MOVE_MOUNT__MASK 0x00000077 +#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ +#define MOVE_MOUNT__MASK 0x00000177 /* * fsopen() flags. diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2d779a8469474..b981fc1c994e2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5391,18 +5391,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* In general, avoid mixing slab allocated and page_pool allocated - * pages within the same SKB. However when @to is not pp_recycle and - * @from is cloned, we can transition frag pages from page_pool to - * reference counted. - * - * On the other hand, don't allow coalescing two pp_recycle SKBs if - * @from is cloned, in case the SKB is using page_pool fragment + /* In general, avoid mixing page_pool and non-page_pool allocated + * pages within the same SKB. Additionally avoid dealing with clones + * with page_pool pages, in case the SKB is using page_pool fragment * references (PP_FLAG_PAGE_FRAG). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. + * In theory we could take full references if @from is cloned and + * !@to->pp_recycle but its tricky (due to potential race with + * the clone disappearing) and rare, so not worth dealing with. */ - if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle || + (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3a194a89a3a8d..e8843c397b0b7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1083,6 +1083,12 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &nf_conntrack_hash[repl_idx]); + /* confirmed bit must be set after hlist add, not before: + * loser_ct can still be visible to other cpu due to + * SLAB_TYPESAFE_BY_RCU. + */ + smp_mb__before_atomic(); + set_bit(IPS_CONFIRMED_BIT, &loser_ct->status); NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; @@ -1220,8 +1226,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) * user context, else we insert an already 'dead' hash, blocking * further use of that particular connection -JM. */ - ct->status |= IPS_CONFIRMED; - if (unlikely(nf_ct_is_dying(ct))) { NF_CT_STAT_INC(net, insert_failed); goto dying; @@ -1253,7 +1257,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) } } - /* Timer relative to confirmation time, not original + /* Timeout is relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; @@ -1261,11 +1265,21 @@ __nf_conntrack_confirm(struct sk_buff *skb) __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after - * starting the timer and setting the CONFIRMED bit. The RCU barriers - * guarantee that no other CPU can find the conntrack before the above - * stores are visible. + * setting ct->timeout. The RCU barriers guarantee that no other CPU + * can find the conntrack before the above stores are visible. */ __nf_conntrack_hash_insert(ct, hash, reply_hash); + + /* IPS_CONFIRMED unset means 'ct not (yet) in hash', conntrack lookups + * skip entries that lack this bit. This happens when a CPU is looking + * at a stale entry that is being recycled due to SLAB_TYPESAFE_BY_RCU + * or when another CPU encounters this entry right after the insertion + * but before the set-confirm-bit below. This bit must not be set until + * after __nf_conntrack_hash_insert(). + */ + smp_mb__before_atomic(); + set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_double_unlock(hash, reply_hash); local_bh_enable(); diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 2a36b11c31b76..836a4b47b3879 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -74,6 +74,11 @@ static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = { [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, }; +static bool cl_is_active(struct ets_class *cl) +{ + return !list_empty(&cl->alist); +} + static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, unsigned int *quantum, struct netlink_ext_ack *extack) @@ -421,7 +426,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct ets_sched *q = qdisc_priv(sch); struct ets_class *cl; int err = 0; - bool first; cl = ets_classify(skb, sch, &err); if (!cl) { @@ -431,7 +435,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { @@ -441,7 +444,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - if (first && !ets_class_is_strict(q, cl)) { + if (!cl_is_active(cl) && !ets_class_is_strict(q, cl)) { list_add_tail(&cl->alist, &q->active); cl->deficit = cl->quantum; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index cb9760deba836..6c22879c1620a 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -399,6 +399,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept); static bool vsock_use_local_transport(unsigned int remote_cid) { + lockdep_assert_held(&vsock_register_mutex); + if (!transport_local) return false; @@ -456,6 +458,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) remote_flags = vsk->remote_addr.svm_flags; + mutex_lock(&vsock_register_mutex); + switch (sk->sk_type) { case SOCK_DGRAM: new_transport = transport_dgram; @@ -471,12 +475,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_h2g; break; default: - return -ESOCKTNOSUPPORT; + ret = -ESOCKTNOSUPPORT; + goto err; } if (vsk->transport) { - if (vsk->transport == new_transport) - return 0; + if (vsk->transport == new_transport) { + ret = 0; + goto err; + } /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we @@ -491,8 +498,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) /* We increase the module refcnt to prevent the transport unloading * while there are open sockets assigned to it. */ - if (!new_transport || !try_module_get(new_transport->module)) - return -ENODEV; + if (!new_transport || !try_module_get(new_transport->module)) { + ret = -ENODEV; + goto err; + } + + /* It's safe to release the mutex after a successful try_module_get(). + * Whichever transport `new_transport` points at, it won't go away until + * the last module_put() below or in vsock_deassign_transport(). + */ + mutex_unlock(&vsock_register_mutex); if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || @@ -511,6 +526,9 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) vsk->transport = new_transport; return 0; +err: + mutex_unlock(&vsock_register_mutex); + return ret; } EXPORT_SYMBOL_GPL(vsock_assign_transport);