- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6 v2 0/2] Fix KASAN: slab-use-after-free Read in r1buf_pool_alloc
by Zhou Minqiang 16 Oct '26

16 Oct '26

Fix KASAN: slab-use-after-free Read in r1buf_pool_alloc Zhou Minqiang (2): md/raid1: change r1conf->r1bio_pool to a pointer type md/raid1: remove struct pool_info and related code drivers/md/raid1.c | 86 +++++++++++++++++----------------------------- drivers/md/raid1.h | 22 +----------- 2 files changed, 32 insertions(+), 76 deletions(-) -- 2.52.0

2 3

[PATCH OLK-6.6] perf/x86/intel: Prevent drain_pebs() reentry
by Luo Gengkun 16 Oct '26

16 Oct '26

From: Dapeng Mi <dapeng1.mi(a)linux.intel.com> mainline inclusion from mainline-v7.3-rc3 commit a56c03a397e2cd0c4cf8da96dcd6214f7d0e7d8c category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ---------------------------------------------------------------------- The PEBS buffer is shared by all events on a CPU, so drain_pebs() must not be reentered. If so, one instance may observe stale buffer state and potentially access out-of-bound memory. Most invocations happen in NMI context, which naturally prevents reentry. However, drain_pebs() is also reachable from process context via intel_pmu_drain_pebs_buffer(). In those paths, the PMU is often already disabled, but not guaranteed. For example, __intel_pmu_pebs_disable() only disables the target counter, so other active counters can still raise a PMI and interrupt an in-flight drain_pebs(). Here is an example, __perf_addr_filters_adjust() perf_event_stop() __perf_event_stop() x86_pmu_stop() (event->pmu->stop) intel_pmu_disable_event() intel_pmu_pebs_disable() __intel_pmu_pebs_disable() intel_pmu_drain_large_pebs() intel_pmu_drain_pebs_buffer() Introduce __intel_pmu_quiesce() and __intel_pmu_resume() helpers and use them in intel_pmu_drain_large_pebs() to disable the full PMU around the intel_pmu_drain_pebs_buffer() call, preventing reentry. Also add a warning in intel_pmu_drain_pebs_buffer() when the full PMU is not disabled. Fixes: b752ea0c28e3 ("perf/x86/intel/ds: Flush PEBS DS when changing PEBS_DATA_CFG") Signed-off-by: Dapeng Mi <dapeng1.mi(a)linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://patch.msgid.link/20260813064346.335458-1-dapeng1.mi@linux.intel.com Conflicts: arch/x86/events/perf_event.h [Fix ctx diff.] Signed-off-by: Luo Gengkun <luogengkun2(a)huawei.com> --- arch/x86/events/intel/core.c | 33 ++++++++++++++++++++++++--------- arch/x86/events/intel/ds.c | 8 +++++++- arch/x86/events/perf_event.h | 3 +++ 3 files changed, 34 insertions(+), 10 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 78c514520bb3..7c47ea0403cc 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3053,6 +3053,27 @@ static void intel_pmu_del_event(struct perf_event *event) this_cpu_ptr(&cpu_hw_events)->n_late_setup--; } +int __intel_pmu_quiesce(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int pmu_enabled = cpuc->enabled; + + cpuc->enabled = 0; + if (pmu_enabled) + intel_pmu_disable_all(); + + return pmu_enabled; +} + +void __intel_pmu_resume(int pmu_enabled) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + cpuc->enabled = pmu_enabled; + if (pmu_enabled) + intel_pmu_enable_all(0); +} + static int icl_set_topdown_event_period(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -3244,16 +3265,13 @@ static void intel_pmu_read_event(struct perf_event *event) if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) || is_pebs_counter_event_group(event)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - bool pmu_enabled = cpuc->enabled; + int pmu_enabled; /* Only need to call update_topdown_event() once for group read. */ if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ)) return; - cpuc->enabled = 0; - if (pmu_enabled) - intel_pmu_disable_all(); - + pmu_enabled = __intel_pmu_quiesce(); /* * If the PEBS counters snapshotting is enabled, * the topdown event is available in PEBS records. @@ -3262,10 +3280,7 @@ static void intel_pmu_read_event(struct perf_event *event) static_call(intel_pmu_update_topdown_event)(event, NULL); else intel_pmu_drain_pebs_buffer(); - - cpuc->enabled = pmu_enabled; - if (pmu_enabled) - intel_pmu_enable_all(0); + __intel_pmu_resume(pmu_enabled); return; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 4966728eb4f4..9d425dd015da 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1139,8 +1139,11 @@ int intel_pmu_drain_bts_buffer(void) void intel_pmu_drain_pebs_buffer(void) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_sample_data data; + WARN_ON_ONCE(cpuc->enabled); + static_call(x86_pmu_drain_pebs)(NULL, &data); } @@ -1761,8 +1764,11 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc) { if (cpuc->n_pebs == cpuc->n_large_pebs && - cpuc->n_pebs != cpuc->n_pebs_via_pt) + cpuc->n_pebs != cpuc->n_pebs_via_pt) { + int enabled = __intel_pmu_quiesce(); intel_pmu_drain_pebs_buffer(); + __intel_pmu_resume(enabled); + } } static void __intel_pmu_pebs_enable(struct perf_event *event) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index d3273b181ecd..1e53155503bb 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1632,6 +1632,9 @@ static __always_inline void __intel_pmu_lbr_disable(void) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } +extern int __intel_pmu_quiesce(void); +extern void __intel_pmu_resume(int pmu_enabled); + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * -- 2.34.1

2 2

[PATCH OLK-6.6] mm/huge_memory: fix unconditional pgtable deposit/withdraw for special huge PMD
by Jinjiang Tu 16 Oct '26

16 Oct '26

hulk inclusion category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/10116 -------------------------------- The special huge PMD path in copy_huge_pmd() unconditionally allocates a pgtable and deposits it to the destination PMD, while the corresponding withdraw in zap_huge_pmd() is guarded by arch_needs_pgtable_deposit(). On x86 and powerpc64 radix this macro returns false, so the deposit is never matched by a withdraw, leaking a 4KB pgtable page and permanently incrementing mm->nr_ptes on every fork+zap cycle of a special huge PMD. The same asymmetry exists in __split_huge_pmd_locked(), where the special huge PMD path unconditionally calls pgtable_trans_huge_withdraw() regardless of whether a pgtable was ever deposited. Guard both the deposit in copy_huge_pmd() and the withdraw in __split_huge_pmd_locked() with arch_needs_pgtable_deposit(), matching what vmf_insert_pfn_pmd() does at insertion and what zap_huge_pmd() does at teardown. Fixes: 923e224a1246 ("mm: introduce remap_pfn_range_try_pmd() for PMD-level hugepage mapping") Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> --- mm/huge_memory.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 805a903d8423..26f04e64ad28 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1834,9 +1834,11 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd = pmdp_get_lockless(src_pmd); if (unlikely(pmd_present(pmd) && pmd_special(pmd))) { - pgtable = pte_alloc_one(dst_mm); - if (unlikely(!pgtable)) - goto out; + if (arch_needs_pgtable_deposit(dst_vma)) { + pgtable = pte_alloc_one(dst_mm); + if (unlikely(!pgtable)) + goto out; + } dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -1854,8 +1856,10 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* dax won't reach here, it will be intercepted at vma_needs_copy() */ VM_WARN_ON_ONCE(vma_is_dax(src_vma)); - mm_inc_nr_ptes(dst_mm); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + if (pgtable) { + mm_inc_nr_ptes(dst_mm); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + } goto set_pmd; } @@ -2933,6 +2937,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (vma_is_dax(vma)) return; + if (!arch_needs_pgtable_deposit(vma)) + return; pgtable = pgtable_trans_huge_withdraw(mm, pmd); if (unlikely(!pgtable)) return; -- 2.43.0

2 1

[PATCH OLK-6.6 0/2] mm/hugetlb: fix gigantic hugetkb reservation for remote NUMA
by Jinjiang Tu 16 Oct '26

16 Oct '26

This series fixes the inability to reserve gigantic hugetlb on remote NUMA nodes. Gregory Price (1): mm, hugetlb: implement movable_gigantic_pages sysctl Jinjiang Tu (1): mm, hugetlb: restrict __GFP_MEMALLOC to non-gigantic pages .../admin-guide/mm/memory-hotplug.rst | 14 ++++++++-- Documentation/admin-guide/sysctl/vm.rst | 28 +++++++++++++++++++ include/linux/hugetlb.h | 3 +- mm/hugetlb.c | 12 +++++++- 4 files changed, 53 insertions(+), 4 deletions(-) -- 2.43.0

2 3

[PATCH OLK-6.6 v2] net/mlx5e: Move representor vnic reporter to eswitch devlink port
by Cai Xinchen 16 Oct '26

16 Oct '26

From: Carolina Jubran <cjubran(a)nvidia.com> mainline inclusion from mainline-v7.3-rc3 commit 7f26a5e8040b4957ef4dbdfcde6cc7ba2db53937 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/20184 CVE: CVE-2026-97962 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- The representor vnic devlink health reporter is created and destroyed along the representor netdev (un)load path, which is not serialized by the devlink instance lock. Destroying the reporter from there triggers a devl_assert_locked() splat on driver unbind: WARNING: net/devlink/core.c:259 at devl_assert_locked+0x54/0x70, CPU#2: bash/3758 Modules linked in: mlx5_vdpa vringh vdpa mlx5_ib mlx5_fwctl mlx5_core ... CPU: 2 UID: 0 PID: 3758 Comm: bash Tainted: G W 6.19.0+ #1 PREEMPT Tainted: [W]=WARN Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), ... RIP: 0010:devl_assert_locked+0x54/0x70 Call Trace: <TASK> devl_health_reporter_destroy+0x3a/0x1b0 mlx5e_vport_rep_unload+0x12d/0x2b0 [mlx5_core] mlx5_eswitch_unregister_vport_reps+0x1b8/0x220 [mlx5_core] ? __esw_offloads_unload_rep+0x190/0x190 [mlx5_core] ? kernfs_remove_by_name_ns+0xc3/0xf0 device_release_driver_internal+0x3b2/0x560 unbind_store+0xce/0xf0 Move the reporter's lifecycle to the eswitch devlink port (un)register paths, which are already serialized by the devlink instance lock, and store the handle on mlx5_devlink_port. Use the port's mlx5_vport as the reporter priv since the diagnose callback only needs a device handle and a vport number, and mlx5_vport carries both and is initialized before any representor driver probes. Fixes: cf14af140a5a ("net/mlx5e: Add vnic devlink health reporter to representors") Signed-off-by: Carolina Jubran <cjubran(a)nvidia.com> Reviewed-by: Cosmin Ratiu <cratiu(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20260906090700.3761260-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_rep.c drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c [Commit 7f26a5e8040b4 built on newer mainline context not present in this tree: devl_port_health_reporter_create() still takes a graceful_period argument in 6.6, so pass 0 like the old en_rep.c code did, and the mlx5_esw_devlink_port_res_register/unregister() calls in the upstream context do not exist here, so drop them; the local "devlink.h" include is not needed either.] Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 51 +------------------ .../net/ethernet/mellanox/mlx5/core/en_rep.h | 1 - .../mellanox/mlx5/core/esw/devlink_port.c | 34 +++++++++++++ .../net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + 4 files changed, 36 insertions(+), 51 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ce2151d98af9..71b7aff78ccd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -54,7 +54,6 @@ #include "lib/vxlan.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" -#include "diag/reporter_vnic.h" #include "en_accel/ipsec.h" #include "en/tc/int_port.h" #include "en/ptp.h" @@ -1364,50 +1363,6 @@ static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv) return ARRAY_SIZE(mlx5e_ul_rep_stats_grps); } -static int -mlx5e_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) -{ - struct mlx5e_rep_priv *rpriv = devlink_health_reporter_priv(reporter); - struct mlx5_eswitch_rep *rep = rpriv->rep; - - return mlx5_reporter_vnic_diagnose_counters(rep->esw->dev, fmsg, - rep->vport, true); -} - -static const struct devlink_health_reporter_ops mlx5_rep_vnic_reporter_ops = { - .name = "vnic", - .diagnose = mlx5e_rep_vnic_reporter_diagnose, -}; - -static void mlx5e_rep_vnic_reporter_create(struct mlx5e_priv *priv, - struct devlink_port *dl_port) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct devlink_health_reporter *reporter; - - reporter = devl_port_health_reporter_create(dl_port, - &mlx5_rep_vnic_reporter_ops, - 0, rpriv); - if (IS_ERR(reporter)) { - mlx5_core_err(priv->mdev, - "Failed to create representor vnic reporter, err = %ld\n", - PTR_ERR(reporter)); - return; - } - - rpriv->rep_vnic_reporter = reporter; -} - -static void mlx5e_rep_vnic_reporter_destroy(struct mlx5e_priv *priv) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - if (!IS_ERR_OR_NULL(rpriv->rep_vnic_reporter)) - devl_health_reporter_destroy(rpriv->rep_vnic_reporter); -} - static const struct mlx5e_profile mlx5e_rep_profile = { .init = mlx5e_init_rep, .cleanup = mlx5e_cleanup_rep, @@ -1516,10 +1471,8 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (!IS_ERR(dl_port)) { + if (!IS_ERR(dl_port)) SET_NETDEV_DEVLINK_PORT(netdev, dl_port); - mlx5e_rep_vnic_reporter_create(priv, dl_port); - } err = register_netdev(netdev); if (err) { @@ -1532,7 +1485,6 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return 0; err_detach_netdev: - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(netdev_priv(netdev)); err_cleanup_profile: priv->profile->cleanup(priv); @@ -1590,7 +1542,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) } unregister_netdev(netdev); - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); mlx5e_destroy_netdev(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 70640fa1ad7b..bcd7b4e814d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -118,7 +118,6 @@ struct mlx5e_rep_priv { struct rtnl_link_stats64 prev_vf_vport_stats; struct mlx5_flow_handle *send_to_vport_meta_rule; struct rhashtable tc_ht; - struct devlink_health_reporter *rep_vnic_reporter; }; static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 91319b5acd3d..1bca99f4f293 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -3,6 +3,24 @@ #include <linux/mlx5/driver.h> #include "eswitch.h" +#include "diag/reporter_vnic.h" + +static int +mlx5_esw_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport = devlink_health_reporter_priv(reporter); + + return mlx5_reporter_vnic_diagnose_counters(vport->dev, fmsg, vport->vport, + true); +} + +static const +struct devlink_health_reporter_ops mlx5_esw_rep_vnic_reporter_ops = { + .name = "vnic", + .diagnose = mlx5_esw_rep_vnic_reporter_diagnose, +}; static void mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) @@ -149,6 +167,7 @@ static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = { int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *dev = esw->dev; const struct devlink_port_ops *ops; struct mlx5_devlink_port *dl_port; @@ -178,6 +197,16 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx if (err) goto rate_err; + reporter = devl_port_health_reporter_create( + &dl_port->dl_port, &mlx5_esw_rep_vnic_reporter_ops, + 0, vport); + if (IS_ERR(reporter)) + mlx5_core_err(dev, + "Failed to create vnic health reporter for vport %d: %pe\n", + vport_num, reporter); + else + dl_port->vnic_reporter = reporter; + return 0; rate_err: @@ -193,6 +222,11 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, struct return; dl_port = vport->dl_port; + if (dl_port->vnic_reporter) { + devl_health_reporter_destroy(dl_port->vnic_reporter); + dl_port->vnic_reporter = NULL; + } + mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL); devl_rate_leaf_destroy(&dl_port->dl_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d5ebd4f01103..a47692141f8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -179,6 +179,7 @@ struct mlx5_vport; struct mlx5_devlink_port { struct devlink_port dl_port; struct mlx5_vport *vport; + struct devlink_health_reporter *vnic_reporter; }; static inline void mlx5_devlink_port_init(struct mlx5_devlink_port *dl_port, -- 2.18.0.huawei.25

2 1

[PATCH OLK-5.10 0/2] CVE-2026-89860
by Yifan Qiao 16 Oct '26

16 Oct '26

Nilesh Javali (2): scsi: qla2xxx: Initialize NVMe abort_work once at submission scsi: qla2xxx: Fix NVMe abort reference leak on repeated abort drivers/scsi/qla2xxx/qla_nvme.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) -- 2.52.0

2 3

[PATCH OLK-5.10] nfsd: split nfsd4_copy into transient and durable async copy objects
by Lu Jialin 16 Oct '26

16 Oct '26

From: Jeff Layton <jlayton(a)kernel.org> mainline inclusion from mainline-v7.3-rc1 commit f307b4f7ed174a3252d2f292904fd276c78c77de category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/18939 CVE: CVE-2026-89676 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- struct nfsd4_copy served two roles: as &u->copy it is a transient per-COMPOUND argument in the request buffer; as the heap async_copy it is a durable object (worker kthread, reaper linkage, CB_OFFLOAD callback, IDR stateid) that outlives the COMPOUND, with dup_copy_fields() shuttling state between them. That dual identity was the root of the recent lifetime bugs. Introduce struct nfsd4_async_copy for the durable object. It embeds a struct nfsd4_copy (cp_copy) for the operation parameters/result and adds the durable-only fields: async_copies linkage, task_struct, refcount, reaper TTL, copy stateid, and CB_OFFLOAD callback. The durable object therefore never points into the request buffer. cp_clp stays in nfsd4_copy -- it is a request property read by the sync-copy tracepoints on the transient object. Mechanical split, no intended behavioral change; a step toward folding the copy stateids into the common nfs4_stid infrastructure. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Jeff Layton <jlayton(a)kernel.org> Link: https://patch.msgid.link/20260710-nfsd-testing-v3-8-a0ff7db6aa3e@kernel.org Signed-off-by: Chuck Lever <cel(a)kernel.org> Conflicts: fs/nfsd/nfs4proc.c [OLK-5.10 carries the original 5.10 nfsd async-copy design, not the modern one the patch targets, so the split is re-derived on top of OLK-5.10's helpers: nfsd4_get_copy() (not nfsd4_unhash_copy()), check_and_set_stop_copy()/stopped, find_async_copy(), and the separate cb_copy allocated in nfsd4_do_async_copy() for CB_OFFLOAD; cb_copy is retyped to struct nfsd4_async_copy so nfs4_put_copy() keeps working; nfs4_put_copy()/nfsd4_stop_copy()/cleanup_async_copy() adjust only the type and cp_copy field paths; dup_copy_fields() drops the cp_stateid copy] fs/nfsd/nfs4state.c [nfs4_init_copy_state()/nfs4_free_copy_state() updated to struct nfsd4_async_copy; nfs4_free_copy_state() reads cp_copy.cp_clp while the callback stateid stays in the outer struct] fs/nfsd/state.h [forward declaration plus the nfs4_*_copy_state(), nfs4_put_copy() and find_async_copy() prototypes updated to struct nfsd4_async_copy] fs/nfsd/xdr4.h [OLK-5.10's struct nfsd4_copy differs from mainline (cp_intra/ cp_synchronous/stopped/ss_mnt, embedded cp_cb/nfserr, embedded cp_src); only copies/copy_task/refcount/cp_stateid move into the new struct nfsd4_async_copy, and mainline's cp_ttl/cp_cb_offload are omitted since they do not exist in OLK-5.10] Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> --- fs/nfsd/nfs4proc.c | 79 +++++++++++++++++++++++---------------------- fs/nfsd/nfs4state.c | 6 ++-- fs/nfsd/state.h | 9 +++--- fs/nfsd/xdr4.h | 23 ++++++++++--- 4 files changed, 66 insertions(+), 51 deletions(-) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ecbde42093d5..76d218280c3a 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1110,11 +1110,11 @@ nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; } -void nfs4_put_copy(struct nfsd4_copy *copy) +void nfs4_put_copy(struct nfsd4_async_copy *copy) { if (!refcount_dec_and_test(&copy->refcount)) return; - atomic_dec(&copy->cp_nn->pending_async_copies); + atomic_dec(&copy->cp_copy.cp_nn->pending_async_copies); kfree(copy); } @@ -1131,22 +1131,22 @@ check_and_set_stop_copy(struct nfsd4_copy *copy) return value; } -static void nfsd4_stop_copy(struct nfsd4_copy *copy) +static void nfsd4_stop_copy(struct nfsd4_async_copy *copy) { /* only 1 thread should stop the copy */ - if (!check_and_set_stop_copy(copy)) + if (!check_and_set_stop_copy(&copy->cp_copy)) kthread_stop(copy->copy_task); nfs4_put_copy(copy); } -static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp) +static struct nfsd4_async_copy *nfsd4_get_copy(struct nfs4_client *clp) { - struct nfsd4_copy *copy = NULL; + struct nfsd4_async_copy *copy = NULL; spin_lock(&clp->async_lock); if (!list_empty(&clp->async_copies)) { - copy = list_first_entry(&clp->async_copies, struct nfsd4_copy, - copies); + copy = list_first_entry(&clp->async_copies, + struct nfsd4_async_copy, copies); refcount_inc(&copy->refcount); } spin_unlock(&clp->async_lock); @@ -1155,7 +1155,7 @@ static struct nfsd4_copy *nfsd4_get_copy(struct nfs4_client *clp) void nfsd4_shutdown_copy(struct nfs4_client *clp) { - struct nfsd4_copy *copy; + struct nfsd4_async_copy *copy; while ((copy = nfsd4_get_copy(clp)) != NULL) nfsd4_stop_copy(copy); @@ -1351,7 +1351,8 @@ nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { - struct nfsd4_copy *copy = container_of(cb, struct nfsd4_copy, cp_cb); + struct nfsd4_async_copy *copy = + container_of(cb, struct nfsd4_async_copy, cp_copy.cp_cb); nfs4_put_copy(copy); } @@ -1437,29 +1438,29 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) if (src->cp_intra) /* for inter, file_src doesn't exist yet */ dst->nf_src = nfsd_file_get(src->nf_src); - memcpy(&dst->cp_stateid, &src->cp_stateid, sizeof(src->cp_stateid)); memcpy(&dst->cp_src, &src->cp_src, sizeof(struct nl4_server)); memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); dst->ss_mnt = src->ss_mnt; } -static void cleanup_async_copy(struct nfsd4_copy *copy) +static void cleanup_async_copy(struct nfsd4_async_copy *copy) { nfs4_free_copy_state(copy); - nfsd_file_put(copy->nf_dst); - if (copy->cp_intra) - nfsd_file_put(copy->nf_src); - spin_lock(&copy->cp_clp->async_lock); + nfsd_file_put(copy->cp_copy.nf_dst); + if (copy->cp_copy.cp_intra) + nfsd_file_put(copy->cp_copy.nf_src); + spin_lock(&copy->cp_copy.cp_clp->async_lock); list_del(&copy->copies); - spin_unlock(&copy->cp_clp->async_lock); + spin_unlock(&copy->cp_copy.cp_clp->async_lock); nfs4_put_copy(copy); } static int nfsd4_do_async_copy(void *data) { - struct nfsd4_copy *copy = (struct nfsd4_copy *)data; - struct nfsd4_copy *cb_copy; + struct nfsd4_async_copy *async = data; + struct nfsd4_copy *copy = &async->cp_copy; + struct nfsd4_async_copy *cb_copy; if (!copy->cp_intra) { /* Inter server SSC */ copy->nf_src = kzalloc(sizeof(struct nfsd_file), GFP_KERNEL); @@ -1479,21 +1480,21 @@ static int nfsd4_do_async_copy(void *data) copy->nfserr = nfsd4_do_copy(copy, 0); do_callback: - cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); + cb_copy = kzalloc(sizeof(struct nfsd4_async_copy), GFP_KERNEL); if (!cb_copy) goto out; refcount_set(&cb_copy->refcount, 1); - memcpy(&cb_copy->cp_res, &copy->cp_res, sizeof(copy->cp_res)); - cb_copy->cp_clp = copy->cp_clp; - cb_copy->nfserr = copy->nfserr; - memcpy(&cb_copy->fh, &copy->fh, sizeof(copy->fh)); - nfsd4_init_cb(&cb_copy->cp_cb, cb_copy->cp_clp, + memcpy(&cb_copy->cp_copy.cp_res, &copy->cp_res, sizeof(copy->cp_res)); + cb_copy->cp_copy.cp_clp = copy->cp_clp; + cb_copy->cp_copy.nfserr = copy->nfserr; + memcpy(&cb_copy->cp_copy.fh, &copy->fh, sizeof(copy->fh)); + nfsd4_init_cb(&cb_copy->cp_copy.cp_cb, cb_copy->cp_copy.cp_clp, &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); - nfsd4_run_cb(&cb_copy->cp_cb); + nfsd4_run_cb(&cb_copy->cp_copy.cp_cb); out: if (!copy->cp_intra) kfree(copy->nf_src); - cleanup_async_copy(copy); + cleanup_async_copy(async); return 0; } @@ -1503,7 +1504,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { struct nfsd4_copy *copy = &u->copy; __be32 status; - struct nfsd4_copy *async_copy = NULL; + struct nfsd4_async_copy *async_copy = NULL; if (!copy->cp_intra) { /* Inter server SSC */ if (!inter_copy_offload_enable || copy->cp_synchronous) { @@ -1526,16 +1527,16 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!copy->cp_synchronous) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); + async_copy = kzalloc(sizeof(struct nfsd4_async_copy), GFP_KERNEL); if (!async_copy) goto out_err; - async_copy->cp_nn = nn; + async_copy->cp_copy.cp_nn = nn; refcount_set(&async_copy->refcount, 1); /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > (int)rqstp->rq_pool->sp_nrthreads) goto out_err; - dup_copy_fields(copy, async_copy); + dup_copy_fields(copy, &async_copy->cp_copy); if (!nfs4_init_copy_state(nn, async_copy)) goto out_err; @@ -1545,10 +1546,10 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, async_copy, "%s", "copy thread"); if (IS_ERR(async_copy->copy_task)) goto out_err; - spin_lock(&async_copy->cp_clp->async_lock); + spin_lock(&async_copy->cp_copy.cp_clp->async_lock); list_add(&async_copy->copies, - &async_copy->cp_clp->async_copies); - spin_unlock(&async_copy->cp_clp->async_lock); + &async_copy->cp_copy.cp_clp->async_copies); + spin_unlock(&async_copy->cp_copy.cp_clp->async_lock); wake_up_process(async_copy->copy_task); status = nfs_ok; } else { @@ -1567,10 +1568,10 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } -struct nfsd4_copy * +struct nfsd4_async_copy * find_async_copy(struct nfs4_client *clp, stateid_t *stateid) { - struct nfsd4_copy *copy; + struct nfsd4_async_copy *copy; spin_lock(&clp->async_lock); list_for_each_entry(copy, &clp->async_copies, copies) { @@ -1590,7 +1591,7 @@ nfsd4_offload_cancel(struct svc_rqst *rqstp, union nfsd4_op_u *u) { struct nfsd4_offload_status *os = &u->offload_status; - struct nfsd4_copy *copy; + struct nfsd4_async_copy *copy; struct nfs4_client *clp = cstate->clp; copy = find_async_copy(clp, &os->stateid); @@ -1677,12 +1678,12 @@ nfsd4_offload_status(struct svc_rqst *rqstp, { struct nfsd4_offload_status *os = &u->offload_status; __be32 status = 0; - struct nfsd4_copy *copy; + struct nfsd4_async_copy *copy; struct nfs4_client *clp = cstate->clp; copy = find_async_copy(clp, &os->stateid); if (copy) { - os->count = copy->cp_res.wr_bytes_written; + os->count = copy->cp_copy.cp_res.wr_bytes_written; nfs4_put_copy(copy); } else status = nfserr_bad_stateid; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 7bfe0a6bc5fd..d1541848e1d0 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -820,7 +820,7 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, return 1; } -int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) +int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_async_copy *copy) { return nfs4_init_cp_state(nn, &copy->cp_stateid, NFS4_COPY_STID); } @@ -846,12 +846,12 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, return NULL; } -void nfs4_free_copy_state(struct nfsd4_copy *copy) +void nfs4_free_copy_state(struct nfsd4_async_copy *copy) { struct nfsd_net *nn; WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID); - nn = net_generic(copy->cp_clp->net, nfsd_net_id); + nn = net_generic(copy->cp_copy.cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.stid.si_opaque.so_id); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index a16e3d6fcbc0..6c080c63e880 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -636,6 +636,7 @@ struct nfsd4_blocked_lock { struct nfsd4_compound_state; struct nfsd_net; struct nfsd4_copy; +struct nfsd4_async_copy; extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct svc_fh *fhp, @@ -646,8 +647,8 @@ __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, struct nfs4_stid **s, struct nfsd_net *nn); struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, void (*sc_free)(struct nfs4_stid *)); -int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy); -void nfs4_free_copy_state(struct nfsd4_copy *copy); +int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_async_copy *copy); +void nfs4_free_copy_state(struct nfsd4_async_copy *copy); struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, struct nfs4_stid *p_stid); void nfs4_unhash_stid(struct nfs4_stid *s); @@ -676,8 +677,8 @@ extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn struct nfs4_file *find_file(struct knfsd_fh *fh); void put_nfs4_file(struct nfs4_file *fi); -extern void nfs4_put_copy(struct nfsd4_copy *copy); -extern struct nfsd4_copy * +extern void nfs4_put_copy(struct nfsd4_async_copy *copy); +extern struct nfsd4_async_copy * find_async_copy(struct nfs4_client *clp, stateid_t *staetid); extern void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 1ced060704a3..e18979147010 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -569,11 +569,6 @@ struct nfsd4_copy { struct nfsd_file *nf_src; struct nfsd_file *nf_dst; - copy_stateid_t cp_stateid; - - struct list_head copies; - struct task_struct *copy_task; - refcount_t refcount; bool stopped; struct vfsmount *ss_mnt; @@ -581,6 +576,24 @@ struct nfsd4_copy { nfs4_stateid stateid; struct nfsd_net *cp_nn; }; + +/* + * Durable state for an async (background) server-side COPY. + * + * struct nfsd4_copy is transient: it lives in the COMPOUND argument buffer + * and is reused once the op returns. An async COPY outlives the COMPOUND + * (worker kthread, reaper linkage), so its params and result are snapshotted + * into the embedded cp_copy and it never points into the request buffer. + */ +struct nfsd4_async_copy { + struct nfsd4_copy cp_copy; /* operation params + result */ + + struct list_head copies; /* nfs4_client.async_copies */ + struct task_struct *copy_task; + refcount_t refcount; + copy_stateid_t cp_stateid; /* s2s_cp_stateids IDR entry */ +}; + extern bool inter_copy_offload_enable; struct nfsd4_seek { -- 2.34.1

2 1

[PATCH OLK-6.6 00/10] net: dynthread: dynamic threaded NAPI scheduler
by Cai Xinchen 15 Oct '26

15 Oct '26

This series adds net/dynthread, a loadable module that adapts the NAPI processing and the RX queue IRQ placement of a set of net devices to the scheduling behaviour of a target application at runtime. Motivation ---------- Interrupt and softirq processing of network RX competes with latency sensitive applications (e.g. mysqld) for CPU time. When such an application runs for a long time on a CPU without blocking, the softirq work of the NIC completion queues can preempt it on the same CPU and inflate its tail latency. The usual remedies are to steer the RX queue IRQs to other CPUs and/or to move NAPI processing into kernel threads bound to spare CPUs, but a static configuration cannot follow the application: once the target goes idle, is scheduled in short bursts, or is displaced, the reserved CPUs are simply wasted. Approach -------- The module periodically samples the scheduling statistics of all threads matching the appname module parameter and classifies them into one of five statuses (DATA_LOSS, NO_TASK, NOT_RUNNING, FRAGMENTATION, LONG_RUNNING_WITH_INTERRUPTS). Acting on that status it: - restores the RX queue IRQs to their original affinity when the target is gone or barely running; - spreads the IRQs over the NUMA node of their queues when processing in softirq context is acceptable again; - switches the NAPI processing of the configured net devices to kernel threads and binds the NAPI threads (and, optionally, the queue IRQs) to the CPUs of their NUMA node that the target tasks are not allowed to use; - scales the number of CPUs used by those threads with their measured load while the target stays in the long-running status. An unusable sample (counters moved backwards: DATA_LOSS) keeps the previous status, so a single bad sample cannot toggle the mode. Everything is controlled through module parameters, and the original IRQ affinity and NAPI mode are restored when the target disappears or the module is unloaded. The module is buildable only as a loadable module; the Kconfig entry currently allows ARM64. Patch breakdown --------------- 1/6 net: dynthread: Add dynamic threaded NAPI scheduler framework Kconfig/Makefile and the module skeleton: record the RX queue IRQs of the configured net devices and their original affinity, and count the NUMA nodes those queues span. 2/6 net: dynthread: Monitor the load of the target tasks The sampling loop and the status judgement. 3/6 net: dynthread: Steer the RX queue IRQs away from the target tasks Manage the affinity of the recorded IRQs based on the status and the placement of the target tasks. 4/6 net: dynthread: Switch NAPI to threads on spare CPUs Enable threaded NAPI and bind the NAPI threads (and optionally the queue IRQs) to the CPUs not used by the target tasks; switch back to softirq mode in the non-long-running statuses. 5/6 net: dynthread: Scale the number of NAPI thread CPUs Adapt the number of CPUs used by the NAPI threads to their load. 6/6 net: dynthread: Add debug switch and instrumentation Add the dyn_threaded_debug module parameter and the ftrace based instrumentation of the sampling, the status transitions and the IRQ/NAPI placement decisions. Amritha Nambiar (2): net: Add queue and napi association net: Add NAPI IRQ support Cai Xinchen (6): net: dynthread: Add dynamic threaded NAPI scheduler framework net: dynthread: Monitor the load of the target tasks net: dynthread: Steer the RX queue IRQs away from the target tasks net: dynthread: Switch NAPI to threads on spare CPUs net: dynthread: Scale the number of NAPI thread CPUs net: dynthread: Add debug switch and instrumentation Carolina Jubran (1): net/mlx5e: Acquire RTNL lock before RQs/SQs activation/deactivation Joe Damato (1): net/mlx5e: link NAPI instances to queues and IRQs .../net/ethernet/mellanox/mlx5/core/en/ptp.c | 5 +- .../mellanox/mlx5/core/en/reporter_tx.c | 7 + .../net/ethernet/mellanox/mlx5/core/en_main.c | 7 + include/linux/netdevice.h | 20 +- include/net/netdev_rx_queue.h | 2 +- net/core/dev.c | 38 + net/dynthread/Kconfig | 13 + net/dynthread/Makefile | 2 + net/dynthread/net_dynthread.c | 1258 +++++++++++++++++ 9 files changed, 1349 insertions(+), 3 deletions(-) create mode 100644 net/dynthread/Kconfig create mode 100644 net/dynthread/Makefile create mode 100644 net/dynthread/net_dynthread.c -- 2.18.0.huawei.25

2 11

[PATCH OLK-6.6 v2 0/8] Add support for vTLBID
by Jinqian Yang 15 Oct '26

15 Oct '26

This series adds KVM/arm64 support for the ARM TLB invalidation domain (TLBID) extension. With TLBID a guest can scope its TLB invalidation broadcasts to a virtual domain (vDomain). User space discovers the feature through the new KVM_CAP_ARM_TLBIDOMAIN capability. The number of supported vDomains is queried with the new VM ioctl KVM_ARM_GET_VDOMAIN_NUM, and the per-vCPU ioctl KVM_ARM_VCPU_SET_VDOMAIN tells KVM which vDomains each vCPU belongs to, via a vDomain bitmap. KVM maintains a per-VM mapping from vDomains to the physical CPUs that run their member vCPUs, and reprogrammes the VTLBID(n)_EL2 registers on every vCPU load, so that a guest TLBI tagged with a vDomain ID only reaches the physical CPUs currently running that vDomain's vCPUs. Because DVMBM and TLBID are mutually exclusive, DVMBM is force-disabled once TLBID is enabled for a VM. On the guest side, TLBIDIDR_EL1 is emulated with virtual domain counts clamped to the hardware limits, the ID_AA64MMFR4_EL1.TLBID field is exposed only when the feature is active for the VM, and guest accesses to TLBIDIDR_EL1 are trapped and handled by KVM. The feature is gated behind CONFIG_KVM_ARM_VTLBID and additionally requires hardware TLBID support at run time. Tracepoints are added for the vCPU load path so that the vDomain-to-pCPU mapping can be observed. ChangeLog: v1 -> v2: - Document how the max_vdomains value of KVM_CAP_ARM_TLBIDOMAIN is derived and that it is capped at 32. - Enable HCRX_EL2.VTLBIDEn from the guest entry path instead of the vCPU load path, so that the host never runs with it set. - Move kvm_arm_init_tlbidomain() after the realm initialization, so a failed realm creation does not leak vTLBID allocations. - Inject an UNDEFINED exception on guest TLBIDIDR_EL1 accesses when vTLBID is not enabled for the VM or is compiled out. - Clarify several commit messages (DVMBM disablement, the HFGRTR2_EL2 sysreg definition, and the tracepoint descriptions). Jinqian Yang (8): KVM: arm64: Introduce TLBID virtualization infrastructure KVM: arm64: Add VTLBID sysregs and update VTLBID(n) on vCPU load KVM: arm64: Wire up TLBID vDomain configuration ioctls KVM: arm64: Ensure DVMBM is disabled when TLBID is enabled KVM: arm64: Emulate TLBIDIDR_EL1 with virtual domain counts KVM: arm64: Conditionally expose ID_AA64MMFR4_EL1.TLBID to guest KVM: arm64: Enable TLBIDIDR_EL1 access trap in guest KVM: arm64: Add tracepoints for TLBID vDomain load events Documentation/virt/kvm/api.rst | 58 +++ arch/arm64/include/asm/kvm_host.h | 53 +++ arch/arm64/include/uapi/asm/kvm.h | 2 + arch/arm64/kvm/Kconfig | 12 + arch/arm64/kvm/arm.c | 526 +++++++++++++++++++++++- arch/arm64/kvm/hisilicon/hisi_virt.c | 9 + arch/arm64/kvm/hyp/include/hyp/switch.h | 4 + arch/arm64/kvm/sys_regs.c | 79 +++- arch/arm64/kvm/sys_regs.h | 6 + arch/arm64/kvm/trace_arm.h | 47 +++ arch/arm64/tools/sysreg | 23 +- include/uapi/linux/kvm.h | 14 + 12 files changed, 829 insertions(+), 4 deletions(-) -- 2.33.0

2 9

[PATCH OLK-6.6] net/mlx5e: Move representor vnic reporter to eswitch devlink port
by Cai Xinchen 15 Oct '26

15 Oct '26

From: Carolina Jubran <cjubran(a)nvidia.com> mainline inclusion from mainline-v7.3-rc3 commit 7f26a5e8040b4957ef4dbdfcde6cc7ba2db53937 category: bugfix bugzilla: https://atomgit.com/src-openeuler/kernel/issues/20184 CVE: CVE-2026-97962 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- The representor vnic devlink health reporter is created and destroyed along the representor netdev (un)load path, which is not serialized by the devlink instance lock. Destroying the reporter from there triggers a devl_assert_locked() splat on driver unbind: WARNING: net/devlink/core.c:259 at devl_assert_locked+0x54/0x70, CPU#2: bash/3758 Modules linked in: mlx5_vdpa vringh vdpa mlx5_ib mlx5_fwctl mlx5_core ... CPU: 2 UID: 0 PID: 3758 Comm: bash Tainted: G W 6.19.0+ #1 PREEMPT Tainted: [W]=WARN Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), ... RIP: 0010:devl_assert_locked+0x54/0x70 Call Trace: <TASK> devl_health_reporter_destroy+0x3a/0x1b0 mlx5e_vport_rep_unload+0x12d/0x2b0 [mlx5_core] mlx5_eswitch_unregister_vport_reps+0x1b8/0x220 [mlx5_core] ? __esw_offloads_unload_rep+0x190/0x190 [mlx5_core] ? kernfs_remove_by_name_ns+0xc3/0xf0 device_release_driver_internal+0x3b2/0x560 unbind_store+0xce/0xf0 Move the reporter's lifecycle to the eswitch devlink port (un)register paths, which are already serialized by the devlink instance lock, and store the handle on mlx5_devlink_port. Use the port's mlx5_vport as the reporter priv since the diagnose callback only needs a device handle and a vport number, and mlx5_vport carries both and is initialized before any representor driver probes. Fixes: cf14af140a5a ("net/mlx5e: Add vnic devlink health reporter to representors") Signed-off-by: Carolina Jubran <cjubran(a)nvidia.com> Reviewed-by: Cosmin Ratiu <cratiu(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/20260906090700.3761260-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/en_rep.c drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c [Commit 7f26a5e8040b4 built on newer mainline context not present in this tree: devl_port_health_reporter_create() still takes a graceful_period argument in 6.6, so pass 0 like the old en_rep.c code did, and the mlx5_esw_devlink_port_res_register/unregister() calls in the upstream context do not exist here, so drop them; the local "devlink.h" include is not needed either.] Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> --- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 51 +------------------ .../net/ethernet/mellanox/mlx5/core/en_rep.h | 1 - .../mellanox/mlx5/core/esw/devlink_port.c | 36 +++++++++++++ .../net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + 4 files changed, 38 insertions(+), 51 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index ce2151d98af9..71b7aff78ccd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -54,7 +54,6 @@ #include "lib/vxlan.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" -#include "diag/reporter_vnic.h" #include "en_accel/ipsec.h" #include "en/tc/int_port.h" #include "en/ptp.h" @@ -1364,50 +1363,6 @@ static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv) return ARRAY_SIZE(mlx5e_ul_rep_stats_grps); } -static int -mlx5e_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) -{ - struct mlx5e_rep_priv *rpriv = devlink_health_reporter_priv(reporter); - struct mlx5_eswitch_rep *rep = rpriv->rep; - - return mlx5_reporter_vnic_diagnose_counters(rep->esw->dev, fmsg, - rep->vport, true); -} - -static const struct devlink_health_reporter_ops mlx5_rep_vnic_reporter_ops = { - .name = "vnic", - .diagnose = mlx5e_rep_vnic_reporter_diagnose, -}; - -static void mlx5e_rep_vnic_reporter_create(struct mlx5e_priv *priv, - struct devlink_port *dl_port) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct devlink_health_reporter *reporter; - - reporter = devl_port_health_reporter_create(dl_port, - &mlx5_rep_vnic_reporter_ops, - 0, rpriv); - if (IS_ERR(reporter)) { - mlx5_core_err(priv->mdev, - "Failed to create representor vnic reporter, err = %ld\n", - PTR_ERR(reporter)); - return; - } - - rpriv->rep_vnic_reporter = reporter; -} - -static void mlx5e_rep_vnic_reporter_destroy(struct mlx5e_priv *priv) -{ - struct mlx5e_rep_priv *rpriv = priv->ppriv; - - if (!IS_ERR_OR_NULL(rpriv->rep_vnic_reporter)) - devl_health_reporter_destroy(rpriv->rep_vnic_reporter); -} - static const struct mlx5e_profile mlx5e_rep_profile = { .init = mlx5e_init_rep, .cleanup = mlx5e_cleanup_rep, @@ -1516,10 +1471,8 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (!IS_ERR(dl_port)) { + if (!IS_ERR(dl_port)) SET_NETDEV_DEVLINK_PORT(netdev, dl_port); - mlx5e_rep_vnic_reporter_create(priv, dl_port); - } err = register_netdev(netdev); if (err) { @@ -1532,7 +1485,6 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return 0; err_detach_netdev: - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(netdev_priv(netdev)); err_cleanup_profile: priv->profile->cleanup(priv); @@ -1590,7 +1542,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) } unregister_netdev(netdev); - mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); mlx5e_destroy_netdev(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 70640fa1ad7b..bcd7b4e814d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -118,7 +118,6 @@ struct mlx5e_rep_priv { struct rtnl_link_stats64 prev_vf_vport_stats; struct mlx5_flow_handle *send_to_vport_meta_rule; struct rhashtable tc_ht; - struct devlink_health_reporter *rep_vnic_reporter; }; static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 91319b5acd3d..4c4cdd62f5dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -3,6 +3,26 @@ #include <linux/mlx5/driver.h> #include "eswitch.h" +#include "diag/reporter_vnic.h" + +static int +mlx5_esw_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct mlx5_vport *vport = devlink_health_reporter_priv(reporter); + + mlx5_reporter_vnic_diagnose_counters(vport->dev, fmsg, vport->vport, + true); + + return 0; +} + +static const +struct devlink_health_reporter_ops mlx5_esw_rep_vnic_reporter_ops = { + .name = "vnic", + .diagnose = mlx5_esw_rep_vnic_reporter_diagnose, +}; static void mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) @@ -149,6 +169,7 @@ static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = { int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *dev = esw->dev; const struct devlink_port_ops *ops; struct mlx5_devlink_port *dl_port; @@ -178,6 +199,16 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, struct mlx if (err) goto rate_err; + reporter = devl_port_health_reporter_create( + &dl_port->dl_port, &mlx5_esw_rep_vnic_reporter_ops, + 0, vport); + if (IS_ERR(reporter)) + mlx5_core_err(dev, + "Failed to create vnic health reporter for vport %d: %pe\n", + vport_num, reporter); + else + dl_port->vnic_reporter = reporter; + return 0; rate_err: @@ -193,6 +224,11 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, struct return; dl_port = vport->dl_port; + if (dl_port->vnic_reporter) { + devl_health_reporter_destroy(dl_port->vnic_reporter); + dl_port->vnic_reporter = NULL; + } + mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL); devl_rate_leaf_destroy(&dl_port->dl_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d5ebd4f01103..a47692141f8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -179,6 +179,7 @@ struct mlx5_vport; struct mlx5_devlink_port { struct devlink_port dl_port; struct mlx5_vport *vport; + struct devlink_health_reporter *vnic_reporter; }; static inline void mlx5_devlink_port_init(struct mlx5_devlink_port *dl_port, -- 2.18.0.huawei.25

2 1