June 2025 - Linux-stable-mirror

[PATCH 6.1] Revert "cpufreq: tegra186: Share policy per cluster"

by Jon Hunter

This reverts commit 89172666228de1cefcacf5bc6f61c6281751d2ed which is upstream commit be4ae8c19492cd6d5de61ccb34ffb3f5ede5eec8. This commit is causing a suspend regression on Tegra186 Jetson TX2 with Linux v6.12.y kernels. This is not seen with Linux v6.15 that includes this change but indicates that there are there changes missing. Therefore, revert this change. Link: https://lore.kernel.org/linux-tegra/bf1dabf7-0337-40e9-8b8e-4e93a0ffd4cc@nv… Fixes: 89172666228d ("cpufreq: tegra186: Share policy per cluster") Signed-off-by: Jon Hunter <jonathanh(a)nvidia.com> --- drivers/cpufreq/tegra186-cpufreq.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 1d6b54303723..6c88827f4e62 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -73,18 +73,11 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; - u32 cpu; policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; - /* set same policy for all cpus in a cluster */ - for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { - if (data->cpus[cpu].bpmp_cluster_id == cluster) - cpumask_set_cpu(cpu, policy->cpus); - } - return 0; } -- 2.43.0

1 day, 8 hours

1
0
0 0

[PATCH 5.15] Revert "cpufreq: tegra186: Share policy per cluster"

by Jon Hunter

This reverts commit 2592aeda794c9ea73193effdab69f1cf90d0851a which is upstream commit be4ae8c19492cd6d5de61ccb34ffb3f5ede5eec8. This commit is causing a suspend regression on Tegra186 Jetson TX2 with Linux v6.12.y kernels. This is not seen with Linux v6.15 that includes this change but indicates that there are there changes missing. Therefore, revert this change. Fixes: 2592aeda794c ("cpufreq: tegra186: Share policy per cluster") Link: https://lore.kernel.org/linux-tegra/bf1dabf7-0337-40e9-8b8e-4e93a0ffd4cc@nv… Signed-off-by: Jon Hunter <jonathanh(a)nvidia.com> --- drivers/cpufreq/tegra186-cpufreq.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 19597246f9cc..5d1943e787b0 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -73,18 +73,11 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; - u32 cpu; policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; - /* set same policy for all cpus in a cluster */ - for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { - if (data->cpus[cpu].bpmp_cluster_id == cluster) - cpumask_set_cpu(cpu, policy->cpus); - } - return 0; } -- 2.43.0

1 day, 8 hours

1
0
0 0

[PATCH v2] accel/ivpu: Fix warning in ivpu_gem_bo_free()

by Jacek Lawrynowicz

Don't WARN if imported buffers are in use in ivpu_gem_bo_free() as they can be indeed used in the original context/driver. Fixes: 647371a6609d ("accel/ivpu: Add GEM buffer object management") Cc: stable(a)vger.kernel.org # v6.3 Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com> --- v2: Use drm_gem_is_imported() to check if the buffer is imported. --- drivers/accel/ivpu/ivpu_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index c193a80241f5f..5ff0bac739fc9 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -278,7 +278,8 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj) list_del(&bo->bo_list_node); mutex_unlock(&vdev->bo_list_lock); - drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); + drm_WARN_ON(&vdev->drm, !drm_gem_is_imported(&bo->base.base) && + !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); drm_WARN_ON(&vdev->drm, ivpu_bo_size(bo) == 0); drm_WARN_ON(&vdev->drm, bo->base.vaddr); -- 2.45.1

1 day, 8 hours

3
3
0 0

[PATCH] accel/ivpu: Trigger device recovery on engine reset/resume failure

by Jacek Lawrynowicz

From: Karol Wachowski <karol.wachowski(a)intel.com> Trigger full device recovery when the driver fails to restore device state via engine reset and resume operations. This is necessary because, even if submissions from a faulty context are blocked, the NPU may still process previously submitted faulty jobs if the engine reset fails to abort them. Such jobs can continue to generate faults and occupy device resources. When engine reset is ineffective, the only way to recover is to perform a full device recovery. Fixes: dad945c27a42 ("accel/ivpu: Add handling of VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW") Cc: <stable(a)vger.kernel.org> # v6.15+ Signed-off-by: Karol Wachowski <karol.wachowski(a)intel.com> Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com> --- drivers/accel/ivpu/ivpu_job.c | 6 ++++-- drivers/accel/ivpu/ivpu_jsm_msg.c | 9 +++++++-- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 1c8e283ad9854..fae8351aa3309 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -986,7 +986,8 @@ void ivpu_context_abort_work_fn(struct work_struct *work) return; if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) - ivpu_jsm_reset_engine(vdev, 0); + if (ivpu_jsm_reset_engine(vdev, 0)) + return; mutex_lock(&vdev->context_list_lock); xa_for_each(&vdev->context_xa, ctx_id, file_priv) { @@ -1009,7 +1010,8 @@ void ivpu_context_abort_work_fn(struct work_struct *work) if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW) goto runtime_put; - ivpu_jsm_hws_resume_engine(vdev, 0); + if (ivpu_jsm_hws_resume_engine(vdev, 0)) + return; /* * In hardware scheduling mode NPU already has stopped processing jobs * and won't send us any further notifications, thus we have to free job related resources diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c index 219ab8afefabd..0256b2dfefc10 100644 --- a/drivers/accel/ivpu/ivpu_jsm_msg.c +++ b/drivers/accel/ivpu/ivpu_jsm_msg.c @@ -7,6 +7,7 @@ #include "ivpu_hw.h" #include "ivpu_ipc.h" #include "ivpu_jsm_msg.h" +#include "ivpu_pm.h" #include "vpu_jsm_api.h" const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type) @@ -163,8 +164,10 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 engine) ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_ENGINE_RESET_DONE, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); - if (ret) + if (ret) { ivpu_err_ratelimited(vdev, "Failed to reset engine %d: %d\n", engine, ret); + ivpu_pm_trigger_recovery(vdev, "Engine reset failed"); + } return ret; } @@ -354,8 +357,10 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine) ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); - if (ret) + if (ret) { ivpu_err_ratelimited(vdev, "Failed to resume engine %d: %d\n", engine, ret); + ivpu_pm_trigger_recovery(vdev, "Engine resume failed"); + } return ret; } -- 2.45.1

1 day, 8 hours

2
4
0 0

[PATCH] accel/ivpu: Use dma_resv_lock() instead of a custom mutex

by Jacek Lawrynowicz

This fixes a potential race conditions in: - ivpu_bo_unbind_locked() where we modified the shmem->sgt without holding the dma_resv_lock(). - ivpu_bo_print_info() where we read the shmem->pages without holding the dma_resv_lock(). Using dma_resv_lock() also protects against future syncronisation issues that may arise when accessing drm_gem_shmem_object or drm_gem_object members. Fixes: 42328003ecb6 ("accel/ivpu: Refactor BO creation functions") Cc: <stable(a)vger.kernel.org> # v6.9+ Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com> --- drivers/accel/ivpu/ivpu_gem.c | 63 +++++++++++++++++++---------------- drivers/accel/ivpu/ivpu_gem.h | 1 - 2 files changed, 34 insertions(+), 30 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index c193a80241f5f..5908268ca45e9 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -33,6 +33,16 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con (bool)bo->base.base.import_attach); } +static inline int ivpu_bo_lock(struct ivpu_bo *bo) +{ + return dma_resv_lock(bo->base.base.resv, NULL); +} + +static inline void ivpu_bo_unlock(struct ivpu_bo *bo) +{ + dma_resv_unlock(bo->base.base.resv); +} + /* * ivpu_bo_pin() - pin the backing physical pages and map them to VPU. * @@ -43,22 +53,22 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con int __must_check ivpu_bo_pin(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); + struct sg_table *sgt; int ret = 0; - mutex_lock(&bo->lock); - ivpu_dbg_bo(vdev, bo, "pin"); - drm_WARN_ON(&vdev->drm, !bo->ctx); - if (!bo->mmu_mapped) { - struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); + return ret; + } - if (IS_ERR(sgt)) { - ret = PTR_ERR(sgt); - ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); - goto unlock; - } + ivpu_bo_lock(bo); + if (!bo->mmu_mapped) { + drm_WARN_ON(&vdev->drm, !bo->ctx); ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, sgt, ivpu_bo_is_snooped(bo)); if (ret) { @@ -69,7 +79,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo) } unlock: - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); return ret; } @@ -84,7 +94,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, if (!drm_dev_enter(&vdev->drm, &idx)) return -ENODEV; - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node); if (!ret) { @@ -94,7 +104,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret); } - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); drm_dev_exit(idx); @@ -105,7 +115,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); - lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount)); + lockdep_assert(dma_resv_held(bo->base.base.resv) || !kref_read(&bo->base.base.refcount)); if (bo->mmu_mapped) { drm_WARN_ON(&vdev->drm, !bo->ctx); @@ -123,14 +133,12 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) if (bo->base.base.import_attach) return; - dma_resv_lock(bo->base.base.resv, NULL); if (bo->base.sgt) { dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(bo->base.sgt); kfree(bo->base.sgt); bo->base.sgt = NULL; } - dma_resv_unlock(bo->base.base.resv); } void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx) @@ -142,12 +150,12 @@ void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m mutex_lock(&vdev->bo_list_lock); list_for_each_entry(bo, &vdev->bo_list, bo_list_node) { - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); if (bo->ctx == ctx) { ivpu_dbg_bo(vdev, bo, "unbind"); ivpu_bo_unbind_locked(bo); } - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); } mutex_unlock(&vdev->bo_list_lock); } @@ -167,7 +175,6 @@ struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t siz bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */ INIT_LIST_HEAD(&bo->bo_list_node); - mutex_init(&bo->lock); return &bo->base.base; } @@ -286,8 +293,6 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj) drm_WARN_ON(&vdev->drm, bo->mmu_mapped); drm_WARN_ON(&vdev->drm, bo->ctx); - mutex_destroy(&bo->lock); - drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1); drm_gem_shmem_free(&bo->base); } @@ -370,9 +375,9 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, goto err_put; if (flags & DRM_IVPU_BO_MAPPABLE) { - dma_resv_lock(bo->base.base.resv, NULL); + ivpu_bo_lock(bo); ret = drm_gem_shmem_vmap(&bo->base, &map); - dma_resv_unlock(bo->base.base.resv); + ivpu_bo_unlock(bo); if (ret) goto err_put; @@ -395,9 +400,9 @@ void ivpu_bo_free(struct ivpu_bo *bo) struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr); if (bo->flags & DRM_IVPU_BO_MAPPABLE) { - dma_resv_lock(bo->base.base.resv, NULL); + ivpu_bo_lock(bo); drm_gem_shmem_vunmap(&bo->base, &map); - dma_resv_unlock(bo->base.base.resv); + ivpu_bo_unlock(bo); } drm_gem_object_put(&bo->base.base); @@ -416,12 +421,12 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file bo = to_ivpu_bo(obj); - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); args->flags = bo->flags; args->mmap_offset = drm_vma_node_offset_addr(&obj->vma_node); args->vpu_addr = bo->vpu_addr; args->size = obj->size; - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); drm_gem_object_put(obj); return ret; @@ -458,7 +463,7 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) { - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u", bo, bo->ctx_id, bo->vpu_addr, bo->base.base.size, @@ -475,7 +480,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) drm_printf(p, "\n"); - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); } void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p) diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index 0c93118c85bd3..aa8ff14f7aae1 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -17,7 +17,6 @@ struct ivpu_bo { struct list_head bo_list_node; struct drm_mm_node mm_node; - struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */ u64 vpu_addr; u32 flags; u32 job_status; /* Valid only for command buffer */ -- 2.45.1

1 day, 8 hours

2
4
0 0

[PATCH wireless v1] Revert "wifi: mwifiex: Fix HT40 bandwidth issue."

by Francesco Dolcini

From: Francesco Dolcini <francesco.dolcini(a)toradex.com> This reverts commit 34253084291cb210b251d64657958b8041ce4ab1. That commit introduces a regression, when HT40 mode is enabled, received packets are lost, this was experience with W8997 with both SDIO-UART and SDIO-SDIO variants. From an initial investigation the issue solves on its own after some time, but it's not clear what is the reason. Given that this was just a performance optimization, let's revert it till we have a better understanding of the issue and a proper fix. Cc: Jeff Chen <jeff.chen_1(a)nxp.com> Cc: stable(a)vger.kernel.org Fixes: 34253084291c ("wifi: mwifiex: Fix HT40 bandwidth issue.") Closes: https://lore.kernel.org/all/20250603203337.GA109929@francesco-nb/ Signed-off-by: Francesco Dolcini <francesco.dolcini(a)toradex.com> --- drivers/net/wireless/marvell/mwifiex/11n.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c index 738bafc3749b..66f0f5377ac1 100644 --- a/drivers/net/wireless/marvell/mwifiex/11n.c +++ b/drivers/net/wireless/marvell/mwifiex/11n.c @@ -403,14 +403,12 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv, if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && bss_desc->bcn_ht_oper->ht_param & - IEEE80211_HT_PARAM_CHAN_WIDTH_ANY) { - chan_list->chan_scan_param[0].radio_type |= - CHAN_BW_40MHZ << 2; + IEEE80211_HT_PARAM_CHAN_WIDTH_ANY) SET_SECONDARYCHAN(chan_list->chan_scan_param[0]. radio_type, (bss_desc->bcn_ht_oper->ht_param & IEEE80211_HT_PARAM_CHA_SEC_OFFSET)); - } + *buffer += struct_size(chan_list, chan_scan_param, 1); ret_len += struct_size(chan_list, chan_scan_param, 1); } -- 2.39.5

1 day, 9 hours

2
2
0 0

[PATCH 6.1] Mm/uffd: fix vma operation where start addr cuts part of vma

by Jakub Acs

commit 270aa010620697fb27b8f892cc4e194bc2b7d134 upstream. Patch series "mm/uffd: Fix vma merge/split", v2. This series contains two patches that fix vma merge/split for userfaultfd on two separate issues. Patch 1 fixes a regression since 6.1+ due to something we overlooked when converting to maple tree apis. The plan is we use patch 1 to replace the commit "2f628010799e (mm: userfaultfd: avoid passing an invalid range to vma_merge())" in mm-hostfixes-unstable tree if possible, so as to bring uffd vma operations back aligned with the rest code again. Patch 2 fixes a long standing issue that vma can be left unmerged even if we can for either uffd register or unregister. Many thanks to Lorenzo on either noticing this issue from the assert movement patch, looking at this problem, and also provided a reproducer on the unmerged vma issue [1]. [1] https://gist.github.com/lorenzo-stoakes/a11a10f5f479e7a977fc456331266e0e This patch (of 2): It seems vma merging with uffd paths is broken with either register/unregister, where right now we can feed wrong parameters to vma_merge() and it's found by recent patch which moved asserts upwards in vma_merge() by Lorenzo Stoakes: https://lore.kernel.org/all/ZFunF7DmMdK05MoF@FVFF77S0Q05N.cambridge.arm.com/ It's possible that "start" is contained within vma but not clamped to its start. We need to convert this into either "cannot merge" case or "can merge" case 4 which permits subdivision of prev by assigning vma to prev. As we loop, each subsequent VMA will be clamped to the start. This patch will eliminate the report and make sure vma_merge() calls will become legal again. One thing to mention is that the "Fixes: 29417d292bd0" below is there only to help explain where the warning can start to trigger, the real commit to fix should be 69dbe6daf104. Commit 29417d292bd0 helps us to identify the issue, but unfortunately we may want to keep it in Fixes too just to ease kernel backporters for easier tracking. Link: https://lkml.kernel.org/r/20230517190916.3429499-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20230517190916.3429499-2-peterx@redhat.com Fixes: 69dbe6daf104 ("userfaultfd: use maple tree iterator to iterate VMAs") Signed-off-by: Peter Xu <peterx(a)redhat.com> Reported-by: Mark Rutland <mark.rutland(a)arm.com> Reviewed-by: Lorenzo Stoakes <lstoakes(a)gmail.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Closes: https://lore.kernel.org/all/ZFunF7DmMdK05MoF@FVFF77S0Q05N.cambridge.arm.com/ Cc: Lorenzo Stoakes <lstoakes(a)gmail.com> Cc: Mike Rapoport (IBM) <rppt(a)kernel.org> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Jakub Acs <acsjakub(a)amazon.com> [acsjakub: contextual change - keep call to mas_next()] Cc: linux-mm(a)kvack.org --- This backport fixes a security issue - dangling pointer to a VMA in maple tree. Omitting details in this message to be brief, but happy to provide if requested. Since the envelope mentions series fixes 2 separate issues I hope the patch is acceptable on its own? fs/userfaultfd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 82101a2cf933..fcf96f52b2e9 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1426,6 +1426,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, if (prev != vma) mas_next(&mas, ULONG_MAX); + if (vma->vm_start < start) + prev = vma; + ret = 0; do { cond_resched(); @@ -1603,6 +1606,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (prev != vma) mas_next(&mas, ULONG_MAX); + if (vma->vm_start < start) + prev = vma; + ret = 0; do { cond_resched(); -- 2.47.1 Amazon Web Services Development Center Germany GmbH Tamara-Danz-Str. 13 10243 Berlin Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss Eingetragen am Amtsgericht Charlottenburg unter HRB 257764 B Sitz: Berlin Ust-ID: DE 365 538 597

1 day, 9 hours

2
1
0 0

Re: [PATCH v3] PCI/ASPM: Disable L1 before disabling L1ss

by Macpaul Lin (林智斌)

On Tue, 2024-10-22 at 17:30 -0500, Bjorn Helgaas wrote: > On Mon, Oct 07, 2024 at 08:59:17AM +0530, Ajay Agarwal wrote: > > The current sequence in the driver for L1ss update is as follows. > > > > Disable L1ss > > Disable L1 > > Enable L1ss as required > > Enable L1 if required > > > > With this sequence, a bus hang is observed during the L1ss > > disable sequence when the RC CPU attempts to clear the RC L1ss > > register after clearing the EP L1ss register. It looks like the > > RC attempts to enter L1ss again and at the same time, access to > > RC L1ss register fails because aux clk is still not active. > > > > PCIe spec r6.2, section 5.5.4, recommends that setting either > > or both of the enable bits for ASPM L1 PM Substates must be done > > while ASPM L1 is disabled. My interpretation here is that > > clearing L1ss should also be done when L1 is disabled. Thereby, > > change the sequence as follows. > > > > Disable L1 > > Disable L1ss > > Enable L1ss as required > > Enable L1 if required > > > > Signed-off-by: Ajay Agarwal <ajayagarwal(a)google.com> > > Applied to pci/aspm for v6.13, thank you, Ajay! Thanks! MediaTek also found this issue will happen on some old kernel, for example 6.11 or 6.12. would you please pick this patch also to some stable tree? LINK:https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commi… Thanks a lot. Macpaul Lin

1 day, 10 hours

2
1
0 0

[PATCH net] netrom: fix possible deadlock in nr_rt_device_down

by Denis Arefev

Syzkaller detected a possible deadlock in nr_rt_device_down [1] Locking in concurrent threads can cause deadlock. CPU0 ---- nr_rt_device_down() |-> spin_lock_bh(&nr_neigh_list_lock); capture . . . |-> spin_lock_bh(&nr_node_list_lock); waiting and deadlock CPU1 ---- nr_del_node() |-> spin_lock_bh(&nr_node_list_lock); capture . . . |-> nr_remove_neigh(nr_neigh); |-> spin_lock_bh(&nr_neigh_list_lock); waiting for capture Make sure we always get nr_neigh_list_lock before nr_node_list_lock. [1] WARNING: possible circular locking dependency detected 6.15.0-rc2-syzkaller-00278-gfc96b232f8e7 #0 Not tainted ------------------------------------------------------ syz-executor107/6105 is trying to acquire lock: ffffffff902543b8 (nr_node_list_lock){+...}-{3:3}, at: spin_lock_bh include/linux/spinlock.h:356 [inline] ffffffff902543b8 (nr_node_list_lock){+...}-{3:3}, at: nr_rt_device_down+0xb5/0x7b0 net/netrom/nr_route.c:517 but task is already holding lock: ffffffff90254358 (nr_neigh_list_lock){+...}-{3:3}, at: spin_lock_bh include/linux/spinlock.h:356 [inline] ffffffff90254358 (nr_neigh_list_lock){+...}-{3:3}, at: nr_rt_device_down+0x28/0x7b0 net/netrom/nr_route.c:514 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (nr_neigh_list_lock){+...}-{3:3}: lock_acquire+0x116/0x2f0 kernel/locking/lockdep.c:5866 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline] _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178 spin_lock_bh include/linux/spinlock.h:356 [inline] nr_remove_neigh net/netrom/nr_route.c:307 [inline] nr_dec_obs net/netrom/nr_route.c:472 [inline] nr_rt_ioctl+0x39a/0xff0 net/netrom/nr_route.c:692 sock_do_ioctl+0x152/0x400 net/socket.c:1190 sock_ioctl+0x644/0x900 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf3/0x210 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f -> #1 (&nr_node->node_lock){+...}-{3:3}: lock_acquire+0x116/0x2f0 kernel/locking/lockdep.c:5866 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline] _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178 spin_lock_bh include/linux/spinlock.h:356 [inline] nr_node_lock include/net/netrom.h:152 [inline] nr_dec_obs net/netrom/nr_route.c:459 [inline] nr_rt_ioctl+0x194/0xff0 net/netrom/nr_route.c:692 sock_do_ioctl+0x152/0x400 net/socket.c:1190 sock_ioctl+0x644/0x900 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf3/0x210 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f -> #0 (nr_node_list_lock){+...}-{3:3}: check_prev_add kernel/locking/lockdep.c:3166 [inline] check_prevs_add kernel/locking/lockdep.c:3285 [inline] validate_chain+0xa69/0x24e0 kernel/locking/lockdep.c:3909 __lock_acquire+0xad5/0xd80 kernel/locking/lockdep.c:5235 lock_acquire+0x116/0x2f0 kernel/locking/lockdep.c:5866 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline] _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178 spin_lock_bh include/linux/spinlock.h:356 [inline] nr_rt_device_down+0xb5/0x7b0 net/netrom/nr_route.c:517 nr_device_event+0x134/0x150 net/netrom/af_netrom.c:126 notifier_call_chain+0x1a5/0x3f0 kernel/notifier.c:85 __dev_notify_flags+0x209/0x410 net/core/dev.c:-1 netif_change_flags+0xf0/0x1a0 net/core/dev.c:9434 dev_change_flags+0x146/0x270 net/core/dev_api.c:68 dev_ioctl+0x80f/0x1260 net/core/dev_ioctl.c:821 sock_do_ioctl+0x22f/0x400 net/socket.c:1204 sock_ioctl+0x644/0x900 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf3/0x210 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f other info that might help us debug this: Chain exists of: nr_node_list_lock --> &nr_node->node_lock --> nr_neigh_list_lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(nr_neigh_list_lock); lock(&nr_node->node_lock); lock(nr_neigh_list_lock); lock(nr_node_list_lock); *** DEADLOCK *** 2 locks held by syz-executor107/6105: #0: ffffffff900fd788 (rtnl_mutex){+.+.}-{4:4}, at: rtnl_net_lock include/linux/rtnetlink.h:130 [inline] #0: ffffffff900fd788 (rtnl_mutex){+.+.}-{4:4}, at: dev_ioctl+0x7fd/0x1260 net/core/dev_ioctl.c:820 #1: ffffffff90254358 (nr_neigh_list_lock){+...}-{3:3}, at: spin_lock_bh include/linux/spinlock.h:356 [inline] #1: ffffffff90254358 (nr_neigh_list_lock){+...}-{3:3}, at: nr_rt_device_down+0x28/0x7b0 net/netrom/nr_route.c:514 stack backtrace: CPU: 0 UID: 0 PID: 6105 Comm: syz-executor107 Not tainted 6.15.0-rc2-syzkaller-00278-gfc96b232f8e7 #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_circular_bug+0x2e1/0x300 kernel/locking/lockdep.c:2079 check_noncircular+0x142/0x160 kernel/locking/lockdep.c:2211 check_prev_add kernel/locking/lockdep.c:3166 [inline] check_prevs_add kernel/locking/lockdep.c:3285 [inline] validate_chain+0xa69/0x24e0 kernel/locking/lockdep.c:3909 __lock_acquire+0xad5/0xd80 kernel/locking/lockdep.c:5235 lock_acquire+0x116/0x2f0 kernel/locking/lockdep.c:5866 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:126 [inline] _raw_spin_lock_bh+0x35/0x50 kernel/locking/spinlock.c:178 spin_lock_bh include/linux/spinlock.h:356 [inline] nr_rt_device_down+0xb5/0x7b0 net/netrom/nr_route.c:517 nr_device_event+0x134/0x150 net/netrom/af_netrom.c:126 notifier_call_chain+0x1a5/0x3f0 kernel/notifier.c:85 __dev_notify_flags+0x209/0x410 net/core/dev.c:-1 netif_change_flags+0xf0/0x1a0 net/core/dev.c:9434 dev_change_flags+0x146/0x270 net/core/dev_api.c:68 dev_ioctl+0x80f/0x1260 net/core/dev_ioctl.c:821 sock_do_ioctl+0x22f/0x400 net/socket.c:1204 sock_ioctl+0x644/0x900 net/socket.c:1311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:906 [inline] __se_sys_ioctl+0xf1/0x160 fs/ioctl.c:892 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf3/0x210 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable(a)vger.kernel.org Reported-by: syzbot+ccdfb85a561b973219c7(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=ccdfb85a561b973219c7 Signed-off-by: Denis Arefev <arefev(a)swemel.ru> --- net/netrom/nr_route.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index b94cb2ffbaf8..aae0923dbcf0 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -331,6 +331,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n return -EINVAL; } + spin_lock_bh(&nr_neigh_list_lock); spin_lock_bh(&nr_node_list_lock); nr_node_lock(nr_node); for (i = 0; i < nr_node->count; i++) { @@ -339,7 +340,7 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n nr_neigh_put(nr_neigh); if (nr_neigh->count == 0 && !nr_neigh->locked) - nr_remove_neigh(nr_neigh); + nr_remove_neigh_locked(nr_neigh); nr_neigh_put(nr_neigh); nr_node->count--; @@ -361,13 +362,14 @@ static int nr_del_node(ax25_address *callsign, ax25_address *neighbour, struct n } nr_node_unlock(nr_node); spin_unlock_bh(&nr_node_list_lock); - + spin_unlock_bh(&nr_neigh_list_lock); return 0; } } nr_neigh_put(nr_neigh); nr_node_unlock(nr_node); spin_unlock_bh(&nr_node_list_lock); + spin_unlock_bh(&nr_neigh_list_lock); nr_node_put(nr_node); return -EINVAL; -- 2.43.0

1 day, 10 hours

1
0
0 0

[PATCH v2 1/4] wifi: ath12k: fix dest ring-buffer corruption

by Johan Hovold

Add the missing memory barrier to make sure that destination ring descriptors are read after the head pointers to avoid using stale data on weakly ordered architectures like aarch64. The barrier is added to the ath12k_hal_srng_access_begin() helper for symmetry with follow-on fixes for source ring buffer corruption which will add barriers to ath12k_hal_srng_access_end(). Note that this may fix the empty descriptor issue recently worked around by commit 51ad34a47e9f ("wifi: ath12k: Add drop descriptor handling for monitor ring"). Tested-on: WCN7850 hw2.0 WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3 Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices") Cc: stable(a)vger.kernel.org # 6.3 Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> --- drivers/net/wireless/ath/ath12k/ce.c | 3 --- drivers/net/wireless/ath/ath12k/hal.c | 17 ++++++++++++++--- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ath/ath12k/ce.c b/drivers/net/wireless/ath/ath12k/ce.c index 740586fe49d1..b66d23d6b2bd 100644 --- a/drivers/net/wireless/ath/ath12k/ce.c +++ b/drivers/net/wireless/ath/ath12k/ce.c @@ -343,9 +343,6 @@ static int ath12k_ce_completed_recv_next(struct ath12k_ce_pipe *pipe, goto err; } - /* Make sure descriptor is read after the head pointer. */ - dma_rmb(); - *nbytes = ath12k_hal_ce_dst_status_get_length(desc); *skb = pipe->dest_ring->skb[sw_index]; diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c index 91d5126ca149..9eea13ed5565 100644 --- a/drivers/net/wireless/ath/ath12k/hal.c +++ b/drivers/net/wireless/ath/ath12k/hal.c @@ -2126,13 +2126,24 @@ void *ath12k_hal_srng_src_get_next_reaped(struct ath12k_base *ab, void ath12k_hal_srng_access_begin(struct ath12k_base *ab, struct hal_srng *srng) { + u32 hp; + lockdep_assert_held(&srng->lock); - if (srng->ring_dir == HAL_SRNG_DIR_SRC) + if (srng->ring_dir == HAL_SRNG_DIR_SRC) { srng->u.src_ring.cached_tp = *(volatile u32 *)srng->u.src_ring.tp_addr; - else - srng->u.dst_ring.cached_hp = READ_ONCE(*srng->u.dst_ring.hp_addr); + } else { + hp = READ_ONCE(*srng->u.dst_ring.hp_addr); + + if (hp != srng->u.dst_ring.cached_hp) { + srng->u.dst_ring.cached_hp = hp; + /* Make sure descriptor is read after the head + * pointer. + */ + dma_rmb(); + } + } } /* Update cached ring head/tail pointers to HW. ath12k_hal_srng_access_begin() -- 2.49.0

1 day, 10 hours

3
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025