From: Christian König christian.koenig@amd.com

[ Upstream commit 736ec9fadd7a1fde8480df7e5cfac465c07ff6f3 ]

Move setting the job resources into amdgpu_job.c

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Andrey Grodzovsky andrey.grodzovsky@amd.com Reviewed-by: Luben Tuikov luben.tuikov@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Stable-dep-of: 4458da0bb09d ("drm/amdgpu: fix userptr HMM range handling v2") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 21 ++------------------- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 17 +++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 2 ++ 3 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b7bae833c804..aa3ce01cd538 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -495,9 +495,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; struct list_head duplicates; - struct amdgpu_bo *gds; - struct amdgpu_bo *gws; - struct amdgpu_bo *oa; int r;

INIT_LIST_HEAD(&p->validated); @@ -614,22 +611,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved, p->bytes_moved_vis);

- gds = p->bo_list->gds_obj; - gws = p->bo_list->gws_obj; - oa = p->bo_list->oa_obj; - - if (gds) { - p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT; - p->job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT; - } - if (gws) { - p->job->gws_base = amdgpu_bo_gpu_offset(gws) >> PAGE_SHIFT; - p->job->gws_size = amdgpu_bo_size(gws) >> PAGE_SHIFT; - } - if (oa) { - p->job->oa_base = amdgpu_bo_gpu_offset(oa) >> PAGE_SHIFT; - p->job->oa_size = amdgpu_bo_size(oa) >> PAGE_SHIFT; - } + amdgpu_job_set_resources(p->job, p->bo_list->gds_obj, + p->bo_list->gws_obj, p->bo_list->oa_obj);

if (!r && p->uf_entry.tv.bo) { struct amdgpu_bo *uf = ttm_to_amdgpu_bo(p->uf_entry.tv.bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index c2fd6f3076a6..3b025aace283 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -129,6 +129,23 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, return r; }

+void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, + struct amdgpu_bo *gws, struct amdgpu_bo *oa) +{ + if (gds) { + job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT; + job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT; + } + if (gws) { + job->gws_base = amdgpu_bo_gpu_offset(gws) >> PAGE_SHIFT; + job->gws_size = amdgpu_bo_size(gws) >> PAGE_SHIFT; + } + if (oa) { + job->oa_base = amdgpu_bo_gpu_offset(oa) >> PAGE_SHIFT; + job->oa_size = amdgpu_bo_size(oa) >> PAGE_SHIFT; + } +} + void amdgpu_job_free_resources(struct amdgpu_job *job) { struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h index babc0af751c2..2a1961bf1194 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h @@ -76,6 +76,8 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, struct amdgpu_job **job, struct amdgpu_vm *vm); int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, enum amdgpu_ib_pool_type pool, struct amdgpu_job **job); +void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, + struct amdgpu_bo *gws, struct amdgpu_bo *oa); void amdgpu_job_free_resources(struct amdgpu_job *job); void amdgpu_job_free(struct amdgpu_job *job); int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,

From: Christian König christian.koenig@amd.com

[ Upstream commit 4458da0bb09d4435956b4377685e8836935e9b9d ]

The basic problem here is that it's not allowed to page fault while holding the reservation lock.

So it can happen that multiple processes try to validate an userptr at the same time.

Work around that by putting the HMM range object into the mutex protected bo list for now.

v2: make sure range is set to NULL in case of an error

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com CC: stable@vger.kernel.org Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 12 +++-- drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 3 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 8 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 6 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 53 ++++++------------- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 14 +++-- 7 files changed, 46 insertions(+), 51 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 7db4aef9c45c..5e184952ec98 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -985,6 +985,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, struct amdkfd_process_info *process_info = mem->process_info; struct amdgpu_bo *bo = mem->bo; struct ttm_operation_ctx ctx = { true, false }; + struct hmm_range *range; int ret = 0;

mutex_lock(&process_info->lock); @@ -1014,7 +1015,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, return 0; }

- ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range); if (ret) { pr_err("%s: Failed to get user pages: %d\n", __func__, ret); goto unregister_out; @@ -1032,7 +1033,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, amdgpu_bo_unreserve(bo);

release_out: - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); unregister_out: if (ret) amdgpu_mn_unregister(bo); @@ -2367,6 +2368,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, /* Go through userptr_inval_list and update any invalid user_pages */ list_for_each_entry(mem, &process_info->userptr_inval_list, validate_list.head) { + struct hmm_range *range; + invalid = atomic_read(&mem->invalid); if (!invalid) /* BO hasn't been invalidated since the last @@ -2377,7 +2380,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, bo = mem->bo;

/* Get updated user pages */ - ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, + &range); if (ret) { pr_debug("Failed %d to get user pages\n", ret);

@@ -2396,7 +2400,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, * FIXME: Cannot ignore the return code, must hold * notifier_lock */ - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range); }

/* Mark the BO as valid unless it was invalidated diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 2168163aad2d..252a876b0725 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -209,6 +209,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list, list_add_tail(&e->tv.head, &bucket[priority]);

e->user_pages = NULL; + e->range = NULL; }

/* Connect the sorted buckets in the output list. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index 9caea1688fc3..e4d78491bcc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -26,6 +26,8 @@ #include <drm/ttm/ttm_execbuf_util.h> #include <drm/amdgpu_drm.h>

+struct hmm_range; + struct amdgpu_device; struct amdgpu_bo; struct amdgpu_bo_va; @@ -36,6 +38,7 @@ struct amdgpu_bo_list_entry { struct amdgpu_bo_va *bo_va; uint32_t priority; struct page **user_pages; + struct hmm_range *range; bool user_invalidated; };

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index fee99a40804e..7e350ea0368b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -548,7 +548,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, goto out_free_user_pages; }

- r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages); + r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages, &e->range); if (r) { kvfree(e->user_pages); e->user_pages = NULL; @@ -633,9 +633,10 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,

if (!e->user_pages) continue; - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); kvfree(e->user_pages); e->user_pages = NULL; + e->range = NULL; } return r; } @@ -1230,7 +1231,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);

- r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); + e->range = NULL; } if (r) { r = -EAGAIN; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 111484ceb47d..91571b1324f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -378,6 +378,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, struct amdgpu_device *adev = drm_to_adev(dev); struct drm_amdgpu_gem_userptr *args = data; struct drm_gem_object *gobj; + struct hmm_range *range; struct amdgpu_bo *bo; uint32_t handle; int r; @@ -418,7 +419,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data, goto release_object;

if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) { - r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages); + r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, + &range); if (r) goto release_object;

@@ -441,7 +443,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,

user_pages_done: if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) - amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm); + amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);

release_object: drm_gem_object_put(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 9e6c23266a1a..dfb8875e0f28 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -642,9 +642,6 @@ struct amdgpu_ttm_tt { struct task_struct *usertask; uint32_t userflags; bool bound; -#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) - struct hmm_range *range; -#endif };

#define ttm_to_amdgpu_ttm_tt(ptr) container_of(ptr, struct amdgpu_ttm_tt, ttm) @@ -657,7 +654,8 @@ struct amdgpu_ttm_tt { * Calling function must call amdgpu_ttm_tt_userptr_range_done() once and only * once afterwards to stop HMM tracking */ -int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) +int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages, + struct hmm_range **range) { struct ttm_tt *ttm = bo->tbo.ttm; struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm); @@ -667,16 +665,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) bool readonly; int r = 0;

+ /* Make sure get_user_pages_done() can cleanup gracefully */ + *range = NULL; + mm = bo->notifier.mm; if (unlikely(!mm)) { DRM_DEBUG_DRIVER("BO is not registered?\n"); return -EFAULT; }

- /* Another get_user_pages is running at the same time?? */ - if (WARN_ON(gtt->range)) - return -EFAULT; - if (!mmget_not_zero(mm)) /* Happens during process shutdown */ return -ESRCH;

@@ -694,7 +691,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)

readonly = amdgpu_ttm_tt_is_readonly(ttm); r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start, - ttm->num_pages, &gtt->range, readonly, + ttm->num_pages, range, readonly, true, NULL); out_unlock: mmap_read_unlock(mm); @@ -712,30 +709,24 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) * * Returns: true if pages are still valid */ -bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) +bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range) { struct amdgpu_ttm_tt *gtt = ttm_to_amdgpu_ttm_tt(ttm); - bool r = false;

- if (!gtt || !gtt->userptr) + if (!gtt || !gtt->userptr || !range) return false;

DRM_DEBUG_DRIVER("user_pages_done 0x%llx pages 0x%x\n", gtt->userptr, ttm->num_pages);

- WARN_ONCE(!gtt->range || !gtt->range->hmm_pfns, - "No user pages to check\n"); + WARN_ONCE(!range->hmm_pfns, "No user pages to check\n");

- if (gtt->range) { - /* - * FIXME: Must always hold notifier_lock for this, and must - * not ignore the return code. - */ - r = amdgpu_hmm_range_get_pages_done(gtt->range); - gtt->range = NULL; - } - - return !r; + /* + * FIXME: Must always hold notifier_lock for this, and must + * not ignore the return code. + */ + return !amdgpu_hmm_range_get_pages_done(range); } #endif

@@ -812,20 +803,6 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_device *bdev, /* unmap the pages mapped to the device */ dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0); sg_free_table(ttm->sg); - -#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) - if (gtt->range) { - unsigned long i; - - for (i = 0; i < ttm->num_pages; i++) { - if (ttm->pages[i] != - hmm_pfn_to_page(gtt->range->hmm_pfns[i])) - break; - } - - WARN((i == ttm->num_pages), "Missing get_user_page_done\n"); - } -#endif }

static void amdgpu_ttm_gart_bind(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 6a70818039dd..a37207011a69 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -39,6 +39,8 @@

#define AMDGPU_POISON 0xd0bed0be

+struct hmm_range; + struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; @@ -149,15 +151,19 @@ void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo); uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type);

#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR) -int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages); -bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm); +int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages, + struct hmm_range **range); +bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range); #else static inline int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, - struct page **pages) + struct page **pages, + struct hmm_range **range) { return -EPERM; } -static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm) +static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm, + struct hmm_range *range) { return false; }

From: Yang Wang KevinYang.Wang@amd.com

[ Upstream commit 8e039cd176c61a9770e1956038c93738efc800f7 ]

add smu_v13_0_10 driver if version

Signed-off-by: Yang Wang KevinYang.Wang@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Stable-dep-of: f2e1aa267f12 ("drm/amd/pm: update driver if header for smu_13_0_7") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h | 1 + drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 3 +++ 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 3e29fe4cc4ae..dd5867561068 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -32,6 +32,7 @@ #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D

#define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 33710dcf1eb1..e7380aa4f6be 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -304,6 +304,9 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) case IP_VERSION(13, 0, 5): smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_5; break; + case IP_VERSION(13, 0, 10): + smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_10; + break; default: dev_err(adev->dev, "smu unsupported IP version: 0x%x.\n", adev->ip_versions[MP1_HWIP][0]);

From: lyndonli Lyndon.Li@amd.com

[ Upstream commit f2e1aa267f12b82e03927d1e918d2844ddd3eea5 ]

update driver if header for smu_13_0_7

Signed-off-by: lyndonli Lyndon.Li@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Reviewed-by: Kenneth Feng kenneth.feng@amd.com Reviewed-by: Evan Quan evan.quan@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org # 6.0.x Signed-off-by: Sasha Levin sashal@kernel.org --- .../inc/pmfw_if/smu13_driver_if_v13_0_7.h | 117 ++++++++++++------ drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h | 2 +- 2 files changed, 80 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h index 25c08f963f49..d6b13933a98f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h @@ -25,10 +25,10 @@

// *** IMPORTANT *** // PMFW TEAM: Always increment the interface version on any change to this file -#define SMU13_DRIVER_IF_VERSION 0x2C +#define SMU13_DRIVER_IF_VERSION 0x35

//Increment this version if SkuTable_t or BoardTable_t change -#define PPTABLE_VERSION 0x20 +#define PPTABLE_VERSION 0x27

#define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SOCCLK_DPM_LEVELS 8 @@ -96,7 +96,7 @@ #define FEATURE_MEM_TEMP_READ_BIT 47 #define FEATURE_ATHUB_MMHUB_PG_BIT 48 #define FEATURE_SOC_PCC_BIT 49 -#define FEATURE_SPARE_50_BIT 50 +#define FEATURE_EDC_PWRBRK_BIT 50 #define FEATURE_SPARE_51_BIT 51 #define FEATURE_SPARE_52_BIT 52 #define FEATURE_SPARE_53_BIT 53 @@ -282,15 +282,15 @@ typedef enum { } I2cControllerPort_e;

typedef enum { - I2C_CONTROLLER_NAME_VR_GFX = 0, - I2C_CONTROLLER_NAME_VR_SOC, - I2C_CONTROLLER_NAME_VR_VMEMP, - I2C_CONTROLLER_NAME_VR_VDDIO, - I2C_CONTROLLER_NAME_LIQUID0, - I2C_CONTROLLER_NAME_LIQUID1, - I2C_CONTROLLER_NAME_PLX, - I2C_CONTROLLER_NAME_OTHER, - I2C_CONTROLLER_NAME_COUNT, + I2C_CONTROLLER_NAME_VR_GFX = 0, + I2C_CONTROLLER_NAME_VR_SOC, + I2C_CONTROLLER_NAME_VR_VMEMP, + I2C_CONTROLLER_NAME_VR_VDDIO, + I2C_CONTROLLER_NAME_LIQUID0, + I2C_CONTROLLER_NAME_LIQUID1, + I2C_CONTROLLER_NAME_PLX, + I2C_CONTROLLER_NAME_FAN_INTAKE, + I2C_CONTROLLER_NAME_COUNT, } I2cControllerName_e;

typedef enum { @@ -302,6 +302,7 @@ typedef enum { I2C_CONTROLLER_THROTTLER_LIQUID0, I2C_CONTROLLER_THROTTLER_LIQUID1, I2C_CONTROLLER_THROTTLER_PLX, + I2C_CONTROLLER_THROTTLER_FAN_INTAKE, I2C_CONTROLLER_THROTTLER_INA3221, I2C_CONTROLLER_THROTTLER_COUNT, } I2cControllerThrottler_e; @@ -309,8 +310,9 @@ typedef enum { typedef enum { I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5, I2C_CONTROLLER_PROTOCOL_VR_IR35217, - I2C_CONTROLLER_PROTOCOL_TMP_TMP102A, + I2C_CONTROLLER_PROTOCOL_TMP_MAX31875, I2C_CONTROLLER_PROTOCOL_INA3221, + I2C_CONTROLLER_PROTOCOL_TMP_MAX6604, I2C_CONTROLLER_PROTOCOL_COUNT, } I2cControllerProtocol_e;

@@ -690,6 +692,9 @@ typedef struct { #define PP_OD_FEATURE_UCLK_BIT 8 #define PP_OD_FEATURE_ZERO_FAN_BIT 9 #define PP_OD_FEATURE_TEMPERATURE_BIT 10 +#define PP_OD_FEATURE_POWER_FEATURE_CTRL_BIT 11 +#define PP_OD_FEATURE_ASIC_TDC_BIT 12 +#define PP_OD_FEATURE_COUNT 13

typedef enum { PP_OD_POWER_FEATURE_ALWAYS_ENABLED, @@ -697,6 +702,11 @@ typedef enum { PP_OD_POWER_FEATURE_ALWAYS_DISABLED, } PP_OD_POWER_FEATURE_e;

+typedef enum { + FAN_MODE_AUTO = 0, + FAN_MODE_MANUAL_LINEAR, +} FanMode_e; + typedef struct { uint32_t FeatureCtrlMask;

@@ -708,8 +718,8 @@ typedef struct { uint8_t RuntimePwrSavingFeaturesCtrl;

//Frequency changes - int16_t GfxclkFmin; // MHz - int16_t GfxclkFmax; // MHz + int16_t GfxclkFmin; // MHz + int16_t GfxclkFmax; // MHz uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz

@@ -730,7 +740,12 @@ typedef struct { uint8_t MaxOpTemp; uint8_t Padding[4];

- uint32_t Spare[12]; + uint16_t GfxVoltageFullCtrlMode; + uint16_t GfxclkFullCtrlMode; + uint16_t UclkFullCtrlMode; + int16_t AsicTdc; + + uint32_t Spare[10]; uint32_t MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround } OverDriveTable_t;

@@ -748,8 +763,8 @@ typedef struct { uint8_t IdlePwrSavingFeaturesCtrl; uint8_t RuntimePwrSavingFeaturesCtrl;

- uint16_t GfxclkFmin; // MHz - uint16_t GfxclkFmax; // MHz + int16_t GfxclkFmin; // MHz + int16_t GfxclkFmax; // MHz uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz

@@ -769,7 +784,12 @@ typedef struct { uint8_t MaxOpTemp; uint8_t Padding[4];

- uint32_t Spare[12]; + uint16_t GfxVoltageFullCtrlMode; + uint16_t GfxclkFullCtrlMode; + uint16_t UclkFullCtrlMode; + int16_t AsicTdc; + + uint32_t Spare[10];

} OverDriveLimits_t;

@@ -903,7 +923,8 @@ typedef struct { uint16_t FanStartTempMin; uint16_t FanStartTempMax;

- uint32_t Spare[12]; + uint16_t PowerMinPpt0[POWER_SOURCE_COUNT]; + uint32_t Spare[11];

} MsgLimits_t;

@@ -1086,11 +1107,13 @@ typedef struct { uint32_t GfxoffSpare[15];

// GFX GPO - float DfllBtcMasterScalerM; + uint32_t DfllBtcMasterScalerM; int32_t DfllBtcMasterScalerB; - float DfllBtcSlaveScalerM; + uint32_t DfllBtcSlaveScalerM; int32_t DfllBtcSlaveScalerB; - uint32_t GfxGpoSpare[12]; + uint32_t DfllPccAsWaitCtrl; //GDFLL_AS_WAIT_CTRL_PCC register value to be passed to RLC msg + uint32_t DfllPccAsStepCtrl; //GDFLL_AS_STEP_CTRL_PCC register value to be passed to RLC msg + uint32_t GfxGpoSpare[10];

// GFX DCS

@@ -1106,7 +1129,10 @@ typedef struct { uint16_t DcsTimeout; //This is the amount of time SMU FW waits for RLC to put GFX into GFXOFF before reverting to the fallback mechanism of throttling GFXCLK to Fmin.

- uint32_t DcsSpare[16]; + uint32_t DcsSpare[14]; + + // UCLK section + uint16_t ShadowFreqTableUclk[NUM_UCLK_DPM_LEVELS]; // In MHz

// UCLK section uint8_t UseStrobeModeOptimizations; //Set to indicate that FW should use strobe mode optimizations @@ -1163,13 +1189,14 @@ typedef struct { uint16_t IntakeTempHighIntakeAcousticLimit; uint16_t IntakeTempAcouticLimitReleaseRate;

- uint16_t FanStalledTempLimitOffset; + int16_t FanAbnormalTempLimitOffset; uint16_t FanStalledTriggerRpm; - uint16_t FanAbnormalTriggerRpm; - uint16_t FanPadding; - - uint32_t FanSpare[14]; + uint16_t FanAbnormalTriggerRpmCoeff; + uint16_t FanAbnormalDetectionEnable;

+ uint8_t FanIntakeSensorSupport; + uint8_t FanIntakePadding[3]; + uint32_t FanSpare[13]; // SECTION: VDD_GFX AVFS

uint8_t OverrideGfxAvfsFuses; @@ -1193,7 +1220,6 @@ typedef struct { uint32_t dGbV_dT_vmin; uint32_t dGbV_dT_vmax;

- //Unused: PMFW-9370 uint32_t V2F_vmin_range_low; uint32_t V2F_vmin_range_high; uint32_t V2F_vmax_range_low; @@ -1238,8 +1264,21 @@ typedef struct { // SECTION: Advanced Options uint32_t DebugOverrides;

+ // Section: Total Board Power idle vs active coefficients + uint8_t TotalBoardPowerSupport; + uint8_t TotalBoardPowerPadding[3]; + + int16_t TotalIdleBoardPowerM; + int16_t TotalIdleBoardPowerB; + int16_t TotalBoardPowerM; + int16_t TotalBoardPowerB; + + QuadraticInt_t qFeffCoeffGameClock[POWER_SOURCE_COUNT]; + QuadraticInt_t qFeffCoeffBaseClock[POWER_SOURCE_COUNT]; + QuadraticInt_t qFeffCoeffBoostClock[POWER_SOURCE_COUNT]; + // SECTION: Sku Reserved - uint32_t Spare[64]; + uint32_t Spare[43];

// Padding for MMHUB - do not modify this uint32_t MmHubPadding[8]; @@ -1304,7 +1343,8 @@ typedef struct { // SECTION: Clock Spread Spectrum

// UCLK Spread Spectrum - uint16_t UclkSpreadPadding; + uint8_t UclkTrainingModeSpreadPercent; // Q4.4 + uint8_t UclkSpreadPadding; uint16_t UclkSpreadFreq; // kHz

// UCLK Spread Spectrum @@ -1317,11 +1357,7 @@ typedef struct {

// Section: Memory Config uint8_t DramWidth; // Width of interface to the channel for each DRAM module. See DRAM_BIT_WIDTH_TYPE_e - uint8_t PaddingMem1[3]; - - // Section: Total Board Power - uint16_t TotalBoardPower; //Only needed for TCP Estimated case, where TCP = TGP+Total Board Power - uint16_t BoardPowerPadding; + uint8_t PaddingMem1[7];

// SECTION: UMC feature flags uint8_t HsrEnabled; @@ -1423,8 +1459,11 @@ typedef struct { uint16_t Vcn1ActivityPercentage ;

uint32_t EnergyAccumulator; - uint16_t AverageSocketPower ; + uint16_t AverageSocketPower; + uint16_t AverageTotalBoardPower; + uint16_t AvgTemperature[TEMP_COUNT]; + uint16_t AvgTemperatureFanIntake;

uint8_t PcieRate ; uint8_t PcieWidth ; @@ -1592,5 +1631,7 @@ typedef struct { #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D0 0x5 #define IH_INTERRUPT_CONTEXT_ID_AUDIO_D3 0x6 #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7 +#define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8 +#define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9

#endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index b7f4569aff2a..865d6358918d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -31,7 +31,7 @@ #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D

#define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms

From: Johan Hovold johan+linaro@kernel.org

[ Upstream commit eab4c1ebdd657957bf7ae66ffb8849b462db78b3 ]

Since commit 7eb231c337e0 ("PM / Domains: Convert pm_genpd_init() to return an error code") pm_genpd_init() can return an error which the caller must handle.

The current error handling was also incomplete as the runtime PM and regulator use counts were not balanced in all error paths.

Add the missing error handling to the GDSC initialisation to avoid continuing as if nothing happened on errors.

Signed-off-by: Johan Hovold johan+linaro@kernel.org Signed-off-by: Bjorn Andersson andersson@kernel.org Link: https://lore.kernel.org/r/20220929155816.17425-1-johan+linaro@kernel.org Stable-dep-of: 4cc47e8add63 ("clk: qcom: gdsc: Remove direct runtime PM calls") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/qcom/gdsc.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c index d3244006c661..4b66ce0f1940 100644 --- a/drivers/clk/qcom/gdsc.c +++ b/drivers/clk/qcom/gdsc.c @@ -439,11 +439,8 @@ static int gdsc_init(struct gdsc *sc)

/* ...and the power-domain */ ret = gdsc_pm_runtime_get(sc); - if (ret) { - if (sc->rsupply) - regulator_disable(sc->rsupply); - return ret; - } + if (ret) + goto err_disable_supply;

/* * Votable GDSCs can be ON due to Vote from other masters. @@ -452,14 +449,14 @@ static int gdsc_init(struct gdsc *sc) if (sc->flags & VOTABLE) { ret = gdsc_update_collapse_bit(sc, false); if (ret) - return ret; + goto err_put_rpm; }

/* Turn on HW trigger mode if supported */ if (sc->flags & HW_CTRL) { ret = gdsc_hwctrl(sc, true); if (ret < 0) - return ret; + goto err_put_rpm; }

/* @@ -486,9 +483,21 @@ static int gdsc_init(struct gdsc *sc) sc->pd.power_off = gdsc_disable; if (!sc->pd.power_on) sc->pd.power_on = gdsc_enable; - pm_genpd_init(&sc->pd, NULL, !on); + + ret = pm_genpd_init(&sc->pd, NULL, !on); + if (ret) + goto err_put_rpm;

return 0; + +err_put_rpm: + if (on) + gdsc_pm_runtime_put(sc); +err_disable_supply: + if (on && sc->rsupply) + regulator_disable(sc->rsupply); + + return ret; }

int gdsc_register(struct gdsc_desc *desc,

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit 58143c1ed5882c138a3cd2251a336fc8755f23d9 ]

KASAN report out-of-bounds read as follows:

BUG: KASAN: global-out-of-bounds in afe4403_read_raw+0x42e/0x4c0 Read of size 4 at addr ffffffffc02ac638 by task cat/279

Call Trace: afe4403_read_raw iio_read_channel_info dev_attr_show

The buggy address belongs to the variable: afe4403_channel_leds+0x18/0xffffffffffffe9e0

This issue can be reproduced by singe command:

$ cat /sys/bus/spi/devices/spi0.0/iio:device0/in_intensity6_raw

The array size of afe4403_channel_leds is less than channels, so access with chan->address cause OOB read in afe4403_read_raw. Fix it by moving access before use it.

Fixes: b36e8257641a ("iio: health/afe440x: Use regmap fields") Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Acked-by: Andrew Davis afd@ti.com Link: https://lore.kernel.org/r/20221107151946.89260-1-weiyongjun@huaweicloud.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/health/afe4403.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c index 3bb4028c5d74..df3bc5c3d378 100644 --- a/drivers/iio/health/afe4403.c +++ b/drivers/iio/health/afe4403.c @@ -245,14 +245,14 @@ static int afe4403_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct afe4403_data *afe = iio_priv(indio_dev); - unsigned int reg = afe4403_channel_values[chan->address]; - unsigned int field = afe4403_channel_leds[chan->address]; + unsigned int reg, field; int ret;

switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_RAW: + reg = afe4403_channel_values[chan->address]; ret = afe4403_read(afe, reg, val); if (ret) return ret; @@ -262,6 +262,7 @@ static int afe4403_read_raw(struct iio_dev *indio_dev, case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + field = afe4403_channel_leds[chan->address]; ret = regmap_field_read(afe->fields[field], val); if (ret) return ret;

From: Paul Gazzillo paul@pgazz.com

[ Upstream commit 6ac12303572ef9ace5603c2c07f5f1b00a33f580 ]

Fix an implicit declaration of function error for rpr0521 under some configs

When CONFIG_RPR0521 is enabled without CONFIG_IIO_TRIGGERED_BUFFER, the build results in "implicit declaration of function" errors, e.g., drivers/iio/light/rpr0521.c:434:3: error: implicit declaration of function 'iio_trigger_poll_chained' [-Werror=implicit-function-declaration] 434 | iio_trigger_poll_chained(data->drdy_trigger0); | ^~~~~~~~~~~~~~~~~~~~~~~~

This fix adds select dependencies to RPR0521's configuration declaration.

Fixes: e12ffd241c00 ("iio: light: rpr0521 triggered buffer") Signed-off-by: Paul Gazzillo paul@pgazz.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=216678 Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20221110214729.ls5ixav5kxpeftk7@device Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/light/Kconfig | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 8537e88f02e3..c02393009a2c 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -293,6 +293,8 @@ config RPR0521 tristate "ROHM RPR0521 ALS and proximity sensor driver" depends on I2C select REGMAP_I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say Y here if you want to build support for ROHM's RPR0521 ambient light and proximity sensor device.

From: Hou Tao houtao1@huawei.com

[ Upstream commit 47df8a2f78bc34ff170d147d05b121f84e252b85 ]

Since commit bfea9a8574f3 ("bpf: Add name to struct bpf_ksym"), when reporting subprog ksymbol to perf, prog name instead of subprog name is used. The backtrace of bpf program with subprogs will be incorrect as shown below:

ffffffffc02deace bpf_prog_e44a3057dcb151f8_overwrite+0x66 ffffffffc02de9f7 bpf_prog_e44a3057dcb151f8_overwrite+0x9f ffffffffa71d8d4e trace_call_bpf+0xce ffffffffa71c2938 perf_call_bpf_enter.isra.0+0x48

overwrite is the entry program and it invokes the overwrite_htab subprog through bpf_loop, but in above backtrace, overwrite program just jumps inside itself.

Fixing it by using subprog name when reporting subprog ksymbol. After the fix, the output of perf script will be correct as shown below:

ffffffffc031aad2 bpf_prog_37c0bec7d7c764a4_overwrite_htab+0x66 ffffffffc031a9e7 bpf_prog_c7eb827ef4f23e71_overwrite+0x9f ffffffffa3dd8d4e trace_call_bpf+0xce ffffffffa3dc2938 perf_call_bpf_enter.isra.0+0x48

Fixes: bfea9a8574f3 ("bpf: Add name to struct bpf_ksym") Signed-off-by: Hou Tao houtao1@huawei.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Jiri Olsa jolsa@kernel.org Link: https://lore.kernel.org/bpf/20221114095733.158588-1-houtao@huaweicloud.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c index bec18d81b116..8dcbefd90b7f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9006,7 +9006,7 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, PERF_RECORD_KSYMBOL_TYPE_BPF, (u64)(unsigned long)subprog->bpf_func, subprog->jited_len, unregister, - prog->aux->ksym.name); + subprog->aux->ksym.name); } } }

From: Michael Grzeschik m.grzeschik@pengutronix.de

[ Upstream commit 57976762428675f259339385d3324d28ee53ec02 ]

Referring to the datasheet the index 2 is the MCKUDP. When enabled, it "Enables the automatic disable of the Master Clock of the USB Device Port when a suspend condition occurs". We fix the index to the real UDP id which "Enables the 48 MHz clock of the USB Device Port".

Cc: nicolas.ferre@microchip.com Cc: ludovic.desroches@microchip.com Cc: alexandre.belloni@bootlin.com Cc: mturquette@baylibre.com Cc: sboyd@kernel.org Cc: claudiu.beznea@microchip.com Cc: linux-clk@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: kernel@pengutronix.de Fixes: 02ff48e4d7f7 ("clk: at91: add at91rm9200 pmc driver") Fixes: 0e0e528d8260 ("ARM: dts: at91: rm9200: switch to new clock bindings") Reviewed-by: Claudiu Beznea claudiu.beznea@microchip.com Signed-off-by: Michael Grzeschik m.grzeschik@pengutronix.de Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20221114185923.1023249-2-m.grzeschik@pengutronix.d... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/at91rm9200.dtsi | 2 +- drivers/clk/at91/at91rm9200.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi index d1181ead18e5..21344fbc89e5 100644 --- a/arch/arm/boot/dts/at91rm9200.dtsi +++ b/arch/arm/boot/dts/at91rm9200.dtsi @@ -660,7 +660,7 @@ usb1: gadget@fffb0000 { compatible = "atmel,at91rm9200-udc"; reg = <0xfffb0000 0x4000>; interrupts = <11 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&pmc PMC_TYPE_PERIPHERAL 11>, <&pmc PMC_TYPE_SYSTEM 2>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 11>, <&pmc PMC_TYPE_SYSTEM 1>; clock-names = "pclk", "hclk"; status = "disabled"; }; diff --git a/drivers/clk/at91/at91rm9200.c b/drivers/clk/at91/at91rm9200.c index b174f727a8ef..16870943a13e 100644 --- a/drivers/clk/at91/at91rm9200.c +++ b/drivers/clk/at91/at91rm9200.c @@ -40,7 +40,7 @@ static const struct clk_pll_characteristics rm9200_pll_characteristics = { };

static const struct sck at91rm9200_systemck[] = { - { .n = "udpck", .p = "usbck", .id = 2 }, + { .n = "udpck", .p = "usbck", .id = 1 }, { .n = "uhpck", .p = "usbck", .id = 4 }, { .n = "pck0", .p = "prog0", .id = 8 }, { .n = "pck1", .p = "prog1", .id = 9 },

From: Derek Nguyen derek.nguyen@collins.com

[ Upstream commit 07e06193ead86d4812f431b4d87bbd4161222e3f ]

The LTC2947 datasheet (Rev. B) calls out in the section "Register Description: Non-Accumulated Result Registers" (pg. 30) that "To calculate temperature, multiply the TEMP register value by 0.204°C and add 5.5°C". Fix to add 5.5C and not 0.55C.

Fixes: 9f90fd652bed ("hwmon: Add support for ltc2947") Signed-off-by: Derek Nguyen derek.nguyen@collins.com Signed-off-by: Brandon Maier brandon.maier@collins.com Link: https://lore.kernel.org/r/20221110192108.20624-1-brandon.maier@collins.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/ltc2947-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/ltc2947-core.c b/drivers/hwmon/ltc2947-core.c index 5423466de697..e918490f3ff7 100644 --- a/drivers/hwmon/ltc2947-core.c +++ b/drivers/hwmon/ltc2947-core.c @@ -396,7 +396,7 @@ static int ltc2947_read_temp(struct device *dev, const u32 attr, long *val, return ret;

/* in milidegrees celcius, temp is given by: */ - *val = (__val * 204) + 550; + *val = (__val * 204) + 5500;

return 0; }

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 3b7f98f237528c496ea0b689bace0e35eec3e060 ]

pci_disable_device() need be called while module exiting, switch to use pcim_enable(), pci_disable_device() will be called in pcim_release().

Fixes: ada072816be1 ("hwmon: (i5500_temp) New driver for the Intel 5500/5520/X58 chipsets") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Link: https://lore.kernel.org/r/20221112125606.3751430-1-yangyingliang@huawei.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/i5500_temp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/i5500_temp.c b/drivers/hwmon/i5500_temp.c index 05f68e9c9477..23b9f94fe0a9 100644 --- a/drivers/hwmon/i5500_temp.c +++ b/drivers/hwmon/i5500_temp.c @@ -117,7 +117,7 @@ static int i5500_temp_probe(struct pci_dev *pdev, u32 tstimer; s8 tsfsc;

- err = pci_enable_device(pdev); + err = pcim_enable_device(pdev); if (err) { dev_err(&pdev->dev, "Failed to enable device\n"); return err;

From: Joe Korty joe.korty@concurrent-rt.com

[ Upstream commit 839a973988a94c15002cbd81536e4af6ced2bd30 ]

The TVAL register is 32 bit signed. Thus only the lower 31 bits are available to specify when an interrupt is to occur at some time in the near future. Attempting to specify a larger interval with TVAL results in a negative time delta which means the timer fires immediately upon being programmed, rather than firing at that expected future time.

The solution is for Linux to declare that TVAL is a 31 bit register rather than give its true size of 32 bits. This prevents Linux from programming TVAL with a too-large value. Note that, prior to 5.16, this little trick was the standard way to handle TVAL in Linux, so there is nothing new happening here on that front.

The softlockup detector hides the issue, because it keeps generating short timer deadlines that are within the scope of the broken timer.

Disabling it, it starts using NO_HZ with much longer timer deadlines, which turns into an interrupt flood:

11: 1124855130 949168462 758009394 76417474 104782230 30210281 310890 1734323687 GICv2 29 Level arch_timer

And "much longer" isn't that long: it takes less than 43s to underflow TVAL at 50MHz (the frequency of the counter on XGene-1).

Some comments on the v1 version of this patch by Marc Zyngier:

XGene implements CVAL (a 64bit comparator) in terms of TVAL (a countdown register) instead of the other way around. TVAL being a 32bit register, the width of the counter should equally be 32. However, TVAL is a *signed* value, and keeps counting down in the negative range once the timer fires.

It means that any TVAL value with bit 31 set will fire immediately, as it cannot be distinguished from an already expired timer. Reducing the timer range back to a paltry 31 bits papers over the issue.

Another problem cannot be fixed though, which is that the timer interrupt *must* be handled within the negative countdown period, or the interrupt will be lost (TVAL will rollover to a positive value, indicative of a new timer deadline).

Fixes: 012f18850452 ("clocksource/drivers/arm_arch_timer: Work around broken CVAL implementations") Signed-off-by: Joe Korty joe.korty@concurrent-rt.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Marc Zyngier maz@kernel.org Link: https://lore.kernel.org/r/20221024165422.GA51107@zipoli.concurrent-rt.com Link: https://lore.kernel.org/r/20221121145343.896018-1-maz@kernel.org

[maz: revamped the commit message]

Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clocksource/arm_arch_timer.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index a7ff77550e17..933bb960490d 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -806,6 +806,9 @@ static u64 __arch_timer_check_delta(void) /* * XGene-1 implements CVAL in terms of TVAL, meaning * that the maximum timer range is 32bit. Shame on them. + * + * Note that TVAL is signed, thus has only 31 of its + * 32 bits to express magnitude. */ MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, APM_CPU_PART_POTENZA)), @@ -813,8 +816,8 @@ static u64 __arch_timer_check_delta(void) };

if (is_midr_in_range_list(read_cpuid_id(), broken_cval_midrs)) { - pr_warn_once("Broken CNTx_CVAL_EL1, limiting width to 32bits"); - return CLOCKSOURCE_MASK(32); + pr_warn_once("Broken CNTx_CVAL_EL1, using 31 bit TVAL instead.\n"); + return CLOCKSOURCE_MASK(31); } #endif return CLOCKSOURCE_MASK(arch_counter_get_width());

From: Wei Yongjun weiyongjun1@huawei.com

[ Upstream commit 58e92c4a496b27156020a59a98c7f4a92c2b1533 ]

In case of error, the function memremap() returns NULL pointer not ERR_PTR(). The IS_ERR() test in the return value check should be replaced with NULL test.

Fixes: 5a3fa75a4d9c ("nvmem: Add driver to expose reserved memory as nvmem") Cc: Srinivas Kandagatla srinivas.kandagatla@linaro.org Cc: Nicolas Saenz Julienne nsaenzjulienne@suse.de Signed-off-by: Wei Yongjun weiyongjun1@huawei.com Acked-by: Nicolas Saenz Julienne nsaenzjulienne@suse.de Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20221118063840.6357-3-srinivas.kandagatla@linaro.o... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvmem/rmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvmem/rmem.c b/drivers/nvmem/rmem.c index b11c3c974b3d..80cb187f1481 100644 --- a/drivers/nvmem/rmem.c +++ b/drivers/nvmem/rmem.c @@ -37,9 +37,9 @@ static int rmem_read(void *context, unsigned int offset, * but as of Dec 2020 this isn't possible on arm64. */ addr = memremap(priv->mem->base, available, MEMREMAP_WB); - if (IS_ERR(addr)) { + if (!addr) { dev_err(priv->dev, "Failed to remap memory region\n"); - return PTR_ERR(addr); + return -ENOMEM; }

count = memory_read_from_buffer(val, bytes, &off, addr, available);

From: Shazad Hussain quic_shazhuss@quicinc.com

[ Upstream commit f6abcc21d94393801937aed808b8f055ffec8579 ]

The three UFS reference clocks, gcc_ufs_ref_clkref_clk for external UFS devices, gcc_ufs_card_clkref_clk and gcc_ufs_1_card_clkref_clk for two PHYs are all sourced from CXO.

Added parent_data for all three reference clocks described above to reflect that all three clocks are sourced from CXO to have valid frequency for the ref clock needed by UFS controller driver.

Fixes: d65d005f9a6c ("clk: qcom: add sc8280xp GCC driver") Link: https://lore.kernel.org/lkml/Y2Tber39cHuOSR%2FW@hovoldconsulting.com/ Signed-off-by: Shazad Hussain quic_shazhuss@quicinc.com Tested-by: Johan Hovold johan+linaro@kernel.org Reviewed-by: Johan Hovold johan+linaro@kernel.org Tested-by: Andrew Halaney ahalaney@redhat.com Reviewed-by: Andrew Halaney ahalaney@redhat.com Reviewed-by: Brian Masney bmasney@redhat.com Link: https://lore.kernel.org/r/20221115152956.21677-1-quic_shazhuss@quicinc.com Reviewed-by: Bjorn Andersson andersson@kernel.org Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/clk/qcom/gcc-sc8280xp.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index a2f3ffcc5849..fd332383527f 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -5364,6 +5364,8 @@ static struct clk_branch gcc_ufs_1_card_clkref_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "gcc_ufs_1_card_clkref_clk", + .parent_data = &gcc_parent_data_tcxo, + .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -5432,6 +5434,8 @@ static struct clk_branch gcc_ufs_card_clkref_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "gcc_ufs_card_clkref_clk", + .parent_data = &gcc_parent_data_tcxo, + .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -5848,6 +5852,8 @@ static struct clk_branch gcc_ufs_ref_clkref_clk = { .enable_mask = BIT(0), .hw.init = &(const struct clk_init_data) { .name = "gcc_ufs_ref_clkref_clk", + .parent_data = &gcc_parent_data_tcxo, + .num_parents = 1, .ops = &clk_branch2_ops, }, },

From: Shang XiaoJing shangxiaojing@huawei.com

[ Upstream commit 479dd06149425b9e00477f52200872587af76a48 ]

i40e_init_module() won't free the debugfs directory created by i40e_dbg_init() when pci_register_driver() failed. Add fail path to call i40e_dbg_exit() to remove the debugfs entries to prevent the bug.

i40e: Intel(R) Ethernet Connection XL710 Network Driver i40e: Copyright (c) 2013 - 2019 Intel Corporation. debugfs: Directory 'i40e' with parent '/' already present!

Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Shang XiaoJing shangxiaojing@huawei.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Tested-by: Gurucharan G gurucharanx.g@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b3336d31f8a9..023685cca2c1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16652,6 +16652,8 @@ static struct pci_driver i40e_driver = { **/ static int __init i40e_init_module(void) { + int err; + pr_info("%s: %s\n", i40e_driver_name, i40e_driver_string); pr_info("%s: %s\n", i40e_driver_name, i40e_copyright);

@@ -16669,7 +16671,14 @@ static int __init i40e_init_module(void) }

i40e_dbg_init(); - return pci_register_driver(&i40e_driver); + err = pci_register_driver(&i40e_driver); + if (err) { + destroy_workqueue(i40e_wq); + i40e_dbg_exit(); + return err; + } + + return 0; } module_init(i40e_init_module);

From: Yuan Can yuancan@huawei.com

[ Upstream commit 227d8d2f7f2278b8468c5531b0cd0f2a905b4486 ]

The iavf_init_module() won't destroy workqueue when pci_register_driver() failed. Call destroy_workqueue() when pci_register_driver() failed to prevent the resource leak.

Similar to the handling of u132_hcd_init in commit f276e002793c ("usb: u132-hcd: fix resource leak")

Fixes: 2803b16c10ea ("i40e/i40evf: Use private workqueue") Signed-off-by: Yuan Can yuancan@huawei.com Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index cff03723f4f9..4e03712726f2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -5196,6 +5196,8 @@ static struct pci_driver iavf_driver = { **/ static int __init iavf_init_module(void) { + int ret; + pr_info("iavf: %s\n", iavf_driver_string);

pr_info("%s\n", iavf_copyright); @@ -5206,7 +5208,12 @@ static int __init iavf_init_module(void) pr_err("%s: Failed to create workqueue\n", iavf_driver_name); return -ENOMEM; } - return pci_register_driver(&iavf_driver); + + ret = pci_register_driver(&iavf_driver); + if (ret) + destroy_workqueue(iavf_wq); + + return ret; }

module_init(iavf_init_module);

From: YueHaibing yuehaibing@huawei.com

[ Upstream commit 52f7cf70eb8fac6111786c59ae9dfc5cf2bee710 ]

Smatch warns this:

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c:81 mlx5dr_table_set_miss_action() error: uninitialized symbol 'ret'.

Initializing ret with -EOPNOTSUPP and fix missing action case.

Fixes: 7838e1725394 ("net/mlx5: DR, Expose steering table functionality") Signed-off-by: YueHaibing yuehaibing@huawei.com Reviewed-by: Roi Dayan roid@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c index 31d443dd8386..f68461b13391 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c @@ -46,7 +46,7 @@ static int dr_table_set_miss_action_nic(struct mlx5dr_domain *dmn, int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, struct mlx5dr_action *action) { - int ret; + int ret = -EOPNOTSUPP;

if (action && action->action_type != DR_ACTION_TYP_FT) return -EOPNOTSUPP; @@ -67,6 +67,9 @@ int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, goto out; }

+ if (ret) + goto out; + /* Release old action */ if (tbl->miss_action) refcount_dec(&tbl->miss_action->refcount);

From: Chris Mi cmi@nvidia.com

[ Upstream commit e87c6a832f889c093c055a30a7b8c6843e6573bf ]

If creating bond first and then enabling sriov in switchdev mode, will hit the following syndrome:

mlx5_core 0000:08:00.0: mlx5_cmd_out_err:778:(pid 25543): CREATE_LAG(0x840) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x7d49cb), err(-22)

The reason is because the offending patch removes eswitch mode none. In vf lag, the checking of eswitch mode none is replaced by checking if sriov is enabled. But when driver enables sriov, it triggers the bond workqueue task first and then setting sriov number in pci_enable_sriov(). So the check fails.

Fix it by checking if sriov is enabled using eswitch internal counter that is set before triggering the bond workqueue task.

Fixes: f019679ea5f2 ("net/mlx5: E-switch, Remove dependency between sriov and eswitch mode") Signed-off-by: Chris Mi cmi@nvidia.com Reviewed-by: Roi Dayan roid@nvidia.com Reviewed-by: Mark Bloch mbloch@nvidia.com Reviewed-by: Vlad Buslov vladbu@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 8 ++++++++ drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 5 +++-- 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 87ce5a208cb5..5ceed4e6c658 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -731,6 +731,14 @@ void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw); int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);

+static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw) +{ + if (mlx5_esw_allowed(esw)) + return esw->esw_funcs.num_vfs; + + return 0; +} + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 065102278cb8..a879e0b0f702 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -649,8 +649,9 @@ static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)

#ifdef CONFIG_MLX5_ESWITCH dev = ldev->pf[MLX5_LAG_P1].dev; - if ((mlx5_sriov_is_enabled(dev)) && !is_mdev_switchdev_mode(dev)) - return false; + for (i = 0; i < ldev->ports; i++) + if (mlx5_eswitch_num_vfs(dev->priv.eswitch) && !is_mdev_switchdev_mode(dev)) + return false;

mode = mlx5_eswitch_mode(dev); for (i = 0; i < ldev->ports; i++)

From: Roi Dayan roid@nvidia.com

[ Upstream commit 52c795af04441d76f565c4634f893e5b553df2ae ]

When having multiple dests with termination tables and second one or afterwards fails the driver reverts usage of term tables but doesn't reset the assignment in attr->dests[num_vport_dests].termtbl which case a use-after-free when releasing the rule. Fix by resetting the assignment of termtbl to null.

Fixes: 10caabdaad5a ("net/mlx5e: Use termination table for VLAN push actions") Signed-off-by: Roi Dayan roid@nvidia.com Reviewed-by: Maor Dickman maord@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index 108a3503f413..edd910258314 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -312,6 +312,8 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw, for (curr_dest = 0; curr_dest < num_vport_dests; curr_dest++) { struct mlx5_termtbl_handle *tt = attr->dests[curr_dest].termtbl;

+ attr->dests[curr_dest].termtbl = NULL; + /* search for the destination associated with the * current term table */

From: Zhang Changzhong zhangchangzhong@huawei.com

[ Upstream commit 62ec89e74099a3d6995988ed9f2f996b368417ec ]

Add the missing free_cc770dev() before return from cc770_isa_probe() in the register_cc770dev() error handling case.

In addition, remove blanks before goto labels.

Fixes: 7e02e5433e00 ("can: cc770: legacy CC770 ISA bus driver") Signed-off-by: Zhang Changzhong zhangchangzhong@huawei.com Link: https://lore.kernel.org/all/1668168557-6024-1-git-send-email-zhangchangzhong... Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/cc770/cc770_isa.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/cc770/cc770_isa.c b/drivers/net/can/cc770/cc770_isa.c index 194c86e0f340..8f6dccd5a587 100644 --- a/drivers/net/can/cc770/cc770_isa.c +++ b/drivers/net/can/cc770/cc770_isa.c @@ -264,22 +264,24 @@ static int cc770_isa_probe(struct platform_device *pdev) if (err) { dev_err(&pdev->dev, "couldn't register device (err=%d)\n", err); - goto exit_unmap; + goto exit_free; }

dev_info(&pdev->dev, "device registered (reg_base=0x%p, irq=%d)\n", priv->reg_base, dev->irq); return 0;

- exit_unmap: +exit_free: + free_cc770dev(dev); +exit_unmap: if (mem[idx]) iounmap(base); - exit_release: +exit_release: if (mem[idx]) release_mem_region(mem[idx], iosize); else release_region(port[idx], iosize); - exit: +exit: return err; }

From: Zhang Changzhong zhangchangzhong@huawei.com

[ Upstream commit 1eca1d4cc21b6d0fc5f9a390339804c0afce9439 ]

In m_can_pci_remove() and error handling path of m_can_pci_probe(), m_can_class_free_dev() should be called to free resource allocated by m_can_class_allocate_dev(), otherwise there will be memleak.

Fixes: cab7ffc0324f ("can: m_can: add PCI glue driver for Intel Elkhart Lake") Signed-off-by: Zhang Changzhong zhangchangzhong@huawei.com Reviewed-by: Jarkko Nikula jarkko.nikula@linux.intel.com Link: https://lore.kernel.org/all/1668168684-6390-1-git-send-email-zhangchangzhong... Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/can/m_can/m_can_pci.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index 8f184a852a0a..f2219aa2824b 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -120,7 +120,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)

ret = pci_alloc_irq_vectors(pci, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) - return ret; + goto err_free_dev;

mcan_class->dev = &pci->dev; mcan_class->net->irq = pci_irq_vector(pci, 0); @@ -132,7 +132,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)

ret = m_can_class_register(mcan_class); if (ret) - goto err; + goto err_free_irq;

/* Enable interrupt control at CAN wrapper IP */ writel(0x1, base + CTL_CSR_INT_CTL_OFFSET); @@ -144,8 +144,10 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)

return 0;

-err: +err_free_irq: pci_free_irq_vectors(pci); +err_free_dev: + m_can_class_free_dev(mcan_class->net); return ret; }

@@ -161,6 +163,7 @@ static void m_can_pci_remove(struct pci_dev *pci) writel(0x0, priv->base + CTL_CSR_INT_CTL_OFFSET);

m_can_class_unregister(mcan_class); + m_can_class_free_dev(mcan_class->net); pci_free_irq_vectors(pci); }

From: Amir Goldstein amir73il@gmail.com

[ Upstream commit 10bc8e4af65946b727728d7479c028742321b60a ]

Commit 868f9f2f8e00 ("vfs: fix copy_file_range() regression in cross-fs copies") removed fallback to generic_copy_file_range() for cross-fs cases inside vfs_copy_file_range().

To preserve behavior of nfsd and ksmbd server-side-copy, the fallback to generic_copy_file_range() was added in nfsd and ksmbd code, but that call is missing sb_start_write(), fsnotify hooks and more.

Ideally, nfsd and ksmbd would pass a flag to vfs_copy_file_range() that will take care of the fallback, but that code would be subtle and we got vfs_copy_file_range() logic wrong too many times already.

Instead, add a flag to explicitly request vfs_copy_file_range() to perform only generic_copy_file_range() and let nfsd and ksmbd use this flag only in the fallback path.

This choise keeps the logic changes to minimum in the non-nfsd/ksmbd code paths to reduce the risk of further regressions.

Fixes: 868f9f2f8e00 ("vfs: fix copy_file_range() regression in cross-fs copies") Tested-by: Namjae Jeon linkinjeon@kernel.org Tested-by: Luis Henriques lhenriques@suse.de Signed-off-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ksmbd/vfs.c | 6 +++--- fs/nfsd/vfs.c | 4 ++-- fs/read_write.c | 19 +++++++++++++++---- include/linux/fs.h | 8 ++++++++ 4 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 78d01033604c..c5c801e38b63 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -1784,9 +1784,9 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, ret = vfs_copy_file_range(src_fp->filp, src_off, dst_fp->filp, dst_off, len, 0); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src_fp->filp, src_off, - dst_fp->filp, dst_off, - len, 0); + ret = vfs_copy_file_range(src_fp->filp, src_off, + dst_fp->filp, dst_off, len, + COPY_FILE_SPLICE); if (ret < 0) return ret;

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index f3cd614e1f1e..dc24d67d0ca4 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -572,8 +572,8 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0);

if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src, src_pos, dst, dst_pos, - count, 0); + ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, + COPY_FILE_SPLICE); return ret; }

diff --git a/fs/read_write.c b/fs/read_write.c index 328ce8cf9a85..24b9668d6377 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1388,6 +1388,8 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { + lockdep_assert(sb_write_started(file_inode(file_out)->i_sb)); + return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); } @@ -1424,7 +1426,9 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ - if (file_out->f_op->copy_file_range) { + if (flags & COPY_FILE_SPLICE) { + /* cross sb splice is allowed */ + } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; @@ -1474,8 +1478,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, size_t len, unsigned int flags) { ssize_t ret; + bool splice = flags & COPY_FILE_SPLICE;

- if (flags != 0) + if (flags & ~COPY_FILE_SPLICE) return -EINVAL;

ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, @@ -1501,14 +1506,14 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ - if (file_out->f_op->copy_file_range) { + if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); goto done; }

- if (file_in->f_op->remap_file_range && + if (!splice && file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, @@ -1528,6 +1533,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). + * + * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. */ ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); @@ -1582,6 +1589,10 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, pos_out = f_out.file->f_pos; }

+ ret = -EINVAL; + if (flags != 0) + goto out; + ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 7203f5582fd4..be074b6895b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2087,6 +2087,14 @@ struct dir_context { */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN)

+/* + * These flags control the behavior of vfs_copy_file_range(). + * They are not available to the user via syscall. + * + * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops + */ +#define COPY_FILE_SPLICE (1 << 0) + struct iov_iter; struct io_uring_cmd;

From: Izabela Bakollari ibakolla@redhat.com

[ Upstream commit 2a83891130512dafb321418a8e7c9c09268d8c59 ]

IPV6 addresses are purged when setting the number of rx/tx rings using ethtool -G. The function aq_set_ringparam calls dev_close, which removes the addresses. As a solution, call an internal function (aq_ndev_close).

Fixes: c1af5427954b ("net: aquantia: Ethtool based ring size configuration") Signed-off-by: Izabela Bakollari ibakolla@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 5 +++-- drivers/net/ethernet/aquantia/atlantic/aq_main.c | 4 ++-- drivers/net/ethernet/aquantia/atlantic/aq_main.h | 2 ++ 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 1daecd483b8d..9c1378c22a8e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -13,6 +13,7 @@ #include "aq_ptp.h" #include "aq_filters.h" #include "aq_macsec.h" +#include "aq_main.h"

#include <linux/ptp_clock_kernel.h>

@@ -858,7 +859,7 @@ static int aq_set_ringparam(struct net_device *ndev,

if (netif_running(ndev)) { ndev_running = true; - dev_close(ndev); + aq_ndev_close(ndev); }

cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min); @@ -874,7 +875,7 @@ static int aq_set_ringparam(struct net_device *ndev, goto err_exit;

if (ndev_running) - err = dev_open(ndev, NULL); + err = aq_ndev_open(ndev);

err_exit: return err; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 8a0af371e7dc..77609dc0a08d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -58,7 +58,7 @@ struct net_device *aq_ndev_alloc(void) return ndev; }

-static int aq_ndev_open(struct net_device *ndev) +int aq_ndev_open(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); int err = 0; @@ -88,7 +88,7 @@ static int aq_ndev_open(struct net_device *ndev) return err; }

-static int aq_ndev_close(struct net_device *ndev) +int aq_ndev_close(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); int err = 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.h b/drivers/net/ethernet/aquantia/atlantic/aq_main.h index 99870865f66d..a78c1a168d8e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.h @@ -16,5 +16,7 @@ DECLARE_STATIC_KEY_FALSE(aq_xdp_locking_key);

void aq_ndev_schedule_work(struct work_struct *work); struct net_device *aq_ndev_alloc(void); +int aq_ndev_open(struct net_device *ndev); +int aq_ndev_close(struct net_device *ndev);

#endif /* AQ_MAIN_H */

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit acd3c92acc7aaec50a94d0a7faf7ccd74e952493 ]

In S1G beacon frames there shouldn't be multi-BSSID elements since that's not supported, remove that to avoid a potential integer underflow and/or misparsing the frames due to the different length of the fixed part of the frame.

While at it, initialize non_tx_data so we don't send garbage values to the user (even if it doesn't seem to matter now.)

Reported-and-tested-by: Sönke Huster shuster@seemoo.tu-darmstadt.de Fixes: 9eaffe5078ca ("cfg80211: convert S1G beacon to scan results") Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/scan.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 56db0f12ca7c..b4d788572992 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2527,10 +2527,15 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, const struct cfg80211_bss_ies *ies1, *ies2; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); - struct cfg80211_non_tx_bss non_tx_data; + struct cfg80211_non_tx_bss non_tx_data = {};

res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, len, gfp); + + /* don't do any further MBSSID handling for S1G */ + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) + return res; + if (!res || !wiphy->support_mbssid || !cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return res;

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit 369eb2c9f1f72adbe91e0ea8efb130f0a2ba11a6 ]

I got a null-ptr-deref report as following when doing fault injection test:

BUG: kernel NULL pointer dereference, address: 0000000000000058 Oops: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 1 PID: 253 Comm: 507-spi-dm9051 Tainted: G B N 6.1.0-rc3+ Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:klist_put+0x2d/0xd0 Call Trace: <TASK> klist_remove+0xf1/0x1c0 device_release_driver_internal+0x23e/0x2d0 bus_remove_device+0x1bd/0x240 device_del+0x357/0x770 phy_device_remove+0x11/0x30 mdiobus_unregister+0xa5/0x140 release_nodes+0x6a/0xa0 devres_release_all+0xf8/0x150 device_unbind_cleanup+0x19/0xd0

//probe path: phy_device_register() device_add()

phy_connect phy_attach_direct() //set device driver probe() //it's failed, driver is not bound device_bind_driver() // probe failed, it's not called

//remove path: phy_device_remove() device_del() device_release_driver_internal() __device_release_driver() //dev->drv is not NULL klist_remove() <- knode_driver is not added yet, cause null-ptr-deref

In phy_attach_direct(), after setting the 'dev->driver', probe() fails, device_bind_driver() is not called, so the knode_driver->n_klist is not set, then it causes null-ptr-deref in __device_release_driver() while deleting device. Fix this by setting dev->driver to NULL in the error path in phy_attach_direct().

Fixes: e13934563db0 ("[PATCH] PHY Layer fixup") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/phy_device.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 4df8c337221b..70c4d48f32c6 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1518,6 +1518,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,

error_module_put: module_put(d->driver->owner); + d->driver = NULL; error_put_device: put_device(d); if (ndev_owner != bus->owner)

From: Yuan Can yuancan@huawei.com

[ Upstream commit b8f79dccd38edf7db4911c353d9cd792ab13a327 ]

The ntb_netdev_init_module() returns the ntb_transport_register_client() directly without checking its return value, if ntb_transport_register_client() failed, the NTB client device is not unregistered.

Fix by unregister NTB client device when ntb_transport_register_client() failed.

Fixes: 548c237c0a99 ("net: Add support for NTB virtual ethernet device") Signed-off-by: Yuan Can yuancan@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ntb_netdev.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index 80bdc07f2cd3..dd7e273c90cb 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -484,7 +484,14 @@ static int __init ntb_netdev_init_module(void) rc = ntb_transport_register_client_dev(KBUILD_MODNAME); if (rc) return rc; - return ntb_transport_register_client(&ntb_netdev_client); + + rc = ntb_transport_register_client(&ntb_netdev_client); + if (rc) { + ntb_transport_unregister_client_dev(KBUILD_MODNAME); + return rc; + } + + return 0; } module_init(ntb_netdev_init_module);

From: Yuri Karpov YKarpov@ispras.ru

[ Upstream commit 9256db4e45e8b497b0e993cc3ed4ad08eb2389b6 ]

In function nixge_hw_dma_bd_release() dereference of NULL pointer priv->rx_bd_v is possible for the case of its allocation failure in nixge_hw_dma_bd_init().

Move for() loop with priv->rx_bd_v dereference under the check for its validity.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 492caffa8a1a ("net: ethernet: nixge: Add support for National Instruments XGE netdev") Signed-off-by: Yuri Karpov YKarpov@ispras.ru Reviewed-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/ni/nixge.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 4fc279a17562..bef3f0506487 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -249,25 +249,26 @@ static void nixge_hw_dma_bd_release(struct net_device *ndev) struct sk_buff *skb; int i;

- for (i = 0; i < RX_BD_NUM; i++) { - phys_addr = nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], - phys); - - dma_unmap_single(ndev->dev.parent, phys_addr, - NIXGE_MAX_JUMBO_FRAME_SIZE, - DMA_FROM_DEVICE); - - skb = (struct sk_buff *)(uintptr_t) - nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], - sw_id_offset); - dev_kfree_skb(skb); - } + if (priv->rx_bd_v) { + for (i = 0; i < RX_BD_NUM; i++) { + phys_addr = nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], + phys); + + dma_unmap_single(ndev->dev.parent, phys_addr, + NIXGE_MAX_JUMBO_FRAME_SIZE, + DMA_FROM_DEVICE); + + skb = (struct sk_buff *)(uintptr_t) + nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], + sw_id_offset); + dev_kfree_skb(skb); + }

- if (priv->rx_bd_v) dma_free_coherent(ndev->dev.parent, sizeof(*priv->rx_bd_v) * RX_BD_NUM, priv->rx_bd_v, priv->rx_bd_p); + }

if (priv->tx_skb) devm_kfree(ndev->dev.parent, priv->tx_skb);

From: M Chetan Kumar m.chetan.kumar@linux.intel.com

[ Upstream commit 4a99e3c8ed888577b947cbed97d88c9706896105 ]

Fix build error reported on armhf while preparing 6.1-rc5 for Debian.

iosm_ipc_protocol.c:244:36: error: passing argument 3 of 'dma_alloc_coherent' from incompatible pointer type.

Change phy_ap_shm type from phys_addr_t to dma_addr_t.

Fixes: faed4c6f6f48 ("net: iosm: shared memory protocol") Reported-by: Bonaccorso Salvatore carnil@debian.org Signed-off-by: M Chetan Kumar m.chetan.kumar@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wwan/iosm/iosm_ipc_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.h b/drivers/net/wwan/iosm/iosm_ipc_protocol.h index 9b3a6d86ece7..289397c4ea6c 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_protocol.h +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.h @@ -122,7 +122,7 @@ struct iosm_protocol { struct iosm_imem *imem; struct ipc_rsp *rsp_ring[IPC_MEM_MSG_ENTRIES]; struct device *dev; - phys_addr_t phy_ap_shm; + dma_addr_t phy_ap_shm; u32 old_msg_tail; };

From: M Chetan Kumar m.chetan.kumar@linux.intel.com

[ Upstream commit c34ca4f32c24bf748493b49085e43cd714cf8357 ]

skb passed to network layer contains incorrect length.

In mux aggregation protocol, the datagram block received from device contains block signature, packet & datagram header. The right skb len to be calculated by subracting datagram pad len from datagram length.

Whereas in mux lite protocol, the skb contains single datagram so skb len is calculated by subtracting the packet offset from datagram header.

Fixes: 1f52d7b62285 ("net: wwan: iosm: Enable M.2 7360 WWAN card support") Signed-off-by: M Chetan Kumar m.chetan.kumar@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wwan/iosm/iosm_ipc_mux_codec.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index 738420bd14af..d6b166fc5c0e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -365,7 +365,8 @@ static void ipc_mux_dl_cmd_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) /* Pass the DL packet to the netif layer. */ static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, struct iosm_wwan *wwan, u32 offset, - u8 service_class, struct sk_buff *skb) + u8 service_class, struct sk_buff *skb, + u32 pkt_len) { struct sk_buff *dest_skb = skb_clone(skb, GFP_ATOMIC);

@@ -373,7 +374,7 @@ static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, return -ENOMEM;

skb_pull(dest_skb, offset); - skb_set_tail_pointer(dest_skb, dest_skb->len); + skb_trim(dest_skb, pkt_len); /* Pass the packet to the netif layer. */ dest_skb->priority = service_class;

@@ -429,7 +430,7 @@ static void ipc_mux_dl_fcth_decode(struct iosm_mux *ipc_mux, static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) { - u32 pad_len, packet_offset; + u32 pad_len, packet_offset, adgh_len; struct iosm_wwan *wwan; struct mux_adgh *adgh; u8 *block = skb->data; @@ -470,10 +471,12 @@ static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, packet_offset = sizeof(*adgh) + pad_len;

if_id += ipc_mux->wwan_q_offset; + adgh_len = le16_to_cpu(adgh->length);

/* Pass the packet to the netif layer */ rc = ipc_mux_net_receive(ipc_mux, if_id, wwan, packet_offset, - adgh->service_class, skb); + adgh->service_class, skb, + adgh_len - packet_offset); if (rc) { dev_err(ipc_mux->dev, "mux adgh decoding error"); return; @@ -547,7 +550,7 @@ static int mux_dl_process_dg(struct iosm_mux *ipc_mux, struct mux_adbh *adbh, int if_id, int nr_of_dg) { u32 dl_head_pad_len = ipc_mux->session[if_id].dl_head_pad_len; - u32 packet_offset, i, rc; + u32 packet_offset, i, rc, dg_len;

for (i = 0; i < nr_of_dg; i++, dg++) { if (le32_to_cpu(dg->datagram_index) @@ -562,11 +565,12 @@ static int mux_dl_process_dg(struct iosm_mux *ipc_mux, struct mux_adbh *adbh, packet_offset = le32_to_cpu(dg->datagram_index) + dl_head_pad_len; + dg_len = le16_to_cpu(dg->datagram_length); /* Pass the packet to the netif layer. */ rc = ipc_mux_net_receive(ipc_mux, if_id, ipc_mux->wwan, packet_offset, - dg->service_class, - skb); + dg->service_class, skb, + dg_len - dl_head_pad_len); if (rc) goto dg_error; }

From: Menglong Dong imagedong@tencent.com

[ Upstream commit fe94800184f22d4778628f1321dce5acb7513d84 ]

All of the subflows of a msk will be orphaned in mptcp_close(), which means the subflows are in DEAD state. After then, DATA_FIN will be sent, and the other side will response with a DATA_ACK for this DATA_FIN.

However, if the other side still has pending data, the data that received on these subflows will not be passed to the msk, as they are DEAD and subflow_data_ready() will not be called in tcp_data_ready(). Therefore, these data can't be acked, and they will be retransmitted again and again, until timeout.

Fix this by setting ssk->sk_socket and ssk->sk_wq to 'NULL', instead of orphaning the subflows in __mptcp_close(), as Paolo suggested.

Fixes: e16163b6e2b7 ("mptcp: refactor shutdown and close") Reviewed-by: Biao Jiang benbjiang@tencent.com Reviewed-by: Mengen Sun mengensun@tencent.com Signed-off-by: Menglong Dong imagedong@tencent.com Reviewed-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/protocol.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b568f55998f3..42d5e0a7952a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2297,12 +2297,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out; }

- /* if we are invoked by the msk cleanup code, the subflow is - * already orphaned - */ - if (ssk->sk_socket) - sock_orphan(ssk); - + sock_orphan(ssk); subflow->disposable = 1;

/* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops @@ -2833,7 +2828,11 @@ bool __mptcp_close(struct sock *sk, long timeout) if (ssk == msk->first) subflow->fail_tout = 0;

- sock_orphan(ssk); + /* detach from the parent socket, but allow data_ready to + * push incoming data into the mptcp stack, to properly ack it + */ + ssk->sk_socket = NULL; + ssk->sk_wq = NULL; unlock_sock_fast(ssk, slow); } sock_orphan(sk);

From: Xin Long lucien.xin@gmail.com

[ Upstream commit 3067bc61fcfe3081bf4807ce65560f499e895e77 ]

As the call trace shows, the original skb was freed in tipc_msg_validate(), and dereferencing the old skb cb would cause an use-after-free crash.

BUG: KASAN: use-after-free in tipc_crypto_rcv_complete+0x1835/0x2240 [tipc] Call Trace: <IRQ> tipc_crypto_rcv_complete+0x1835/0x2240 [tipc] tipc_crypto_rcv+0xd32/0x1ec0 [tipc] tipc_rcv+0x744/0x1150 [tipc] ... Allocated by task 47078: kmem_cache_alloc_node+0x158/0x4d0 __alloc_skb+0x1c1/0x270 tipc_buf_acquire+0x1e/0xe0 [tipc] tipc_msg_create+0x33/0x1c0 [tipc] tipc_link_build_proto_msg+0x38a/0x2100 [tipc] tipc_link_timeout+0x8b8/0xef0 [tipc] tipc_node_timeout+0x2a1/0x960 [tipc] call_timer_fn+0x2d/0x1c0 ... Freed by task 47078: tipc_msg_validate+0x7b/0x440 [tipc] tipc_crypto_rcv_complete+0x4b5/0x2240 [tipc] tipc_crypto_rcv+0xd32/0x1ec0 [tipc] tipc_rcv+0x744/0x1150 [tipc]

This patch fixes it by re-fetching the skb cb from the new allocated skb after calling tipc_msg_validate().

Fixes: fc1b6d6de220 ("tipc: introduce TIPC encryption & authentication") Reported-by: Shuang Li shuali@redhat.com Signed-off-by: Xin Long lucien.xin@gmail.com Link: https://lore.kernel.org/r/1b1cdba762915325bd8ef9a98d0276eb673df2a5.166939840... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/crypto.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index f09316a9035f..d67440de011e 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1971,6 +1971,9 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, /* Ok, everything's fine, try to synch own keys according to peers' */ tipc_crypto_key_synch(rx, *skb);

+ /* Re-fetch skb cb as skb might be changed in tipc_msg_validate */ + skb_cb = TIPC_SKB_CB(*skb); + /* Mark skb decrypted */ skb_cb->decrypted = 1;

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit cdde1560118f82498fc9e9a7c1ef7f0ef7755891 ]

I got the following report while doing device(mscc-miim) load test with CONFIG_OF_UNITTEST and CONFIG_OF_DYNAMIC enabled:

OF: ERROR: memory leak, expected refcount 1 instead of 2, of_node_get()/of_node_put() unbalanced - destroy cset entry: attach overlay node /spi/soc@0/mdio@7107009c/ethernet-phy@0

If the 'fwnode' is not an acpi node, the refcount is get in fwnode_mdiobus_phy_device_register(), but it has never been put when the device is freed in the normal path. So call fwnode_handle_put() in phy_device_release() to avoid leak.

If it's an acpi node, it has never been get, but it's put in the error path, so call fwnode_handle_get() before phy_device_register() to keep get/put operation balanced.

Fixes: bc1bee3b87ee ("net: mdiobus: Introduce fwnode_mdiobus_register_phy()") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20221124150130.609420-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/mdio/fwnode_mdio.c | 2 +- drivers/net/phy/phy_device.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 1c1584fca632..40e745a1d185 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -120,7 +120,7 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, /* Associate the fwnode with the device structure so it * can be looked up later. */ - phy->mdio.dev.fwnode = child; + phy->mdio.dev.fwnode = fwnode_handle_get(child);

/* All data is now stored in the phy struct, so register it */ rc = phy_device_register(phy); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 70c4d48f32c6..3607077cf86f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -216,6 +216,7 @@ static void phy_mdio_device_free(struct mdio_device *mdiodev)

static void phy_device_release(struct device *dev) { + fwnode_handle_put(dev->fwnode); kfree(to_phy_device(dev)); }

From: Shigeru Yoshida syoshida@redhat.com

[ Upstream commit 5daadc86f27ea4d691e2131c04310d0418c6cd12 ]

syzbot reported use-after-free in tun_detach() [1]. This causes call trace like below:

================================================================== BUG: KASAN: use-after-free in notifier_call_chain+0x1ee/0x200 kernel/notifier.c:75 Read of size 8 at addr ffff88807324e2a8 by task syz-executor.0/3673

CPU: 0 PID: 3673 Comm: syz-executor.0 Not tainted 6.1.0-rc5-syzkaller-00044-gcc675d22e422 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:284 [inline] print_report+0x15e/0x461 mm/kasan/report.c:395 kasan_report+0xbf/0x1f0 mm/kasan/report.c:495 notifier_call_chain+0x1ee/0x200 kernel/notifier.c:75 call_netdevice_notifiers_info+0x86/0x130 net/core/dev.c:1942 call_netdevice_notifiers_extack net/core/dev.c:1983 [inline] call_netdevice_notifiers net/core/dev.c:1997 [inline] netdev_wait_allrefs_any net/core/dev.c:10237 [inline] netdev_run_todo+0xbc6/0x1100 net/core/dev.c:10351 tun_detach drivers/net/tun.c:704 [inline] tun_chr_close+0xe4/0x190 drivers/net/tun.c:3467 __fput+0x27c/0xa90 fs/file_table.c:320 task_work_run+0x16f/0x270 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xb3d/0x2a30 kernel/exit.c:820 do_group_exit+0xd4/0x2a0 kernel/exit.c:950 get_signal+0x21b1/0x2440 kernel/signal.c:2858 arch_do_signal_or_restart+0x86/0x2300 arch/x86/kernel/signal.c:869 exit_to_user_mode_loop kernel/entry/common.c:168 [inline] exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296 do_syscall_64+0x46/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd

The cause of the issue is that sock_put() from __tun_detach() drops last reference count for struct net, and then notifier_call_chain() from netdev_state_change() accesses that struct net.

This patch fixes the issue by calling sock_put() from tun_detach() after all necessary accesses for the struct net has done.

Fixes: 83c1f36f9880 ("tun: send netlink notification when the device is modified") Reported-by: syzbot+106f9b687cd64ee70cd1@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=96eb7f1ce75ef933697f24eeab928c4a716edef... [1] Signed-off-by: Shigeru Yoshida syoshida@redhat.com Link: https://lore.kernel.org/r/20221124175134.1589053-1-syoshida@redhat.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/tun.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3387074a2bdb..167e6a3784ca 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -686,7 +686,6 @@ static void __tun_detach(struct tun_file *tfile, bool clean) if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); - sock_put(&tfile->sk); } }

@@ -702,6 +701,9 @@ static void tun_detach(struct tun_file *tfile, bool clean) if (dev) netdev_state_change(dev); rtnl_unlock(); + + if (clean) + sock_put(&tfile->sk); }

static void tun_detach_all(struct net_device *dev)

From: Willem de Bruijn willemb@google.com

[ Upstream commit b85f628aa158a653c006e9c1405a117baef8c868 ]

CHECKSUM_COMPLETE signals that skb->csum stores the sum over the entire packet. It does not imply that an embedded l4 checksum field has been validated.

Fixes: 682f048bd494 ("af_packet: pass checksum validation status to the user") Signed-off-by: Willem de Bruijn willemb@google.com Link: https://lore.kernel.org/r/20221128161812.640098-1-willemdebruijn.kernel@gmai... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/packet/af_packet.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5cbe07116e04..5727cb7ec174 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2293,8 +2293,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID;

if (snaplen > res) @@ -3520,8 +3519,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID;

aux.tp_len = origlen;

From: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com

[ Upstream commit d66233a312ec9013af3e37e4030b479a20811ec3 ]

After system resumed on some environment board, the promiscuous mode is disabled because the SoC turned off. So, call ravb_set_rx_mode() in the ravb_resume() to fix the issue.

Reported-by: Tho Vu tho.vu.wh@renesas.com Fixes: 0184165b2f42 ("ravb: add sleep PM suspend/resume support") Signed-off-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Reviewed-by: Pavan Chebbi pavan.chebbi@broadcom.com Reviewed-by: Sergey Shtylyov s.shtylyov@omp.ru Link: https://lore.kernel.org/r/20221128065604.1864391-1-yoshihiro.shimoda.uh@rene... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/ravb_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 7e32b04eb0c7..44f9b31f8b99 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -3013,6 +3013,7 @@ static int __maybe_unused ravb_resume(struct device *dev) ret = ravb_open(ndev); if (ret < 0) return ret; + ravb_set_rx_mode(ndev); netif_device_attach(ndev); }

From: Phil Auld pauld@redhat.com

[ Upstream commit a89ff5f5cc64b9fe7a992cf56988fd36f56ca82a ]

If coretemp_add_core() gets an error then pdata->core_data[indx] is already NULL and has been kfreed. Don't pass that to sysfs_remove_group() as that will crash in sysfs_remove_group().

[Shortened for readability] [91854.020159] sysfs: cannot create duplicate filename '/devices/platform/coretemp.0/hwmon/hwmon2/temp20_label' <cpu offline> [91855.126115] BUG: kernel NULL pointer dereference, address: 0000000000000188 [91855.165103] #PF: supervisor read access in kernel mode [91855.194506] #PF: error_code(0x0000) - not-present page [91855.224445] PGD 0 P4D 0 [91855.238508] Oops: 0000 [#1] PREEMPT SMP PTI ... [91855.342716] RIP: 0010:sysfs_remove_group+0xc/0x80 ... [91855.796571] Call Trace: [91855.810524] coretemp_cpu_offline+0x12b/0x1dd [coretemp] [91855.841738] ? coretemp_cpu_online+0x180/0x180 [coretemp] [91855.871107] cpuhp_invoke_callback+0x105/0x4b0 [91855.893432] cpuhp_thread_fun+0x8e/0x150 ...

Fix this by checking for NULL first.

Signed-off-by: Phil Auld pauld@redhat.com Cc: linux-hwmon@vger.kernel.org Cc: Fenghua Yu fenghua.yu@intel.com Cc: Jean Delvare jdelvare@suse.com Cc: Guenter Roeck linux@roeck-us.net Link: https://lore.kernel.org/r/20221117162313.3164803-1-pauld@redhat.com Fixes: 199e0de7f5df3 ("hwmon: (coretemp) Merge pkgtemp with coretemp") Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/coretemp.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 8bf32c6c85d9..30a19d711f89 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -533,6 +533,10 @@ static void coretemp_remove_core(struct platform_data *pdata, int indx) { struct temp_data *tdata = pdata->core_data[indx];

+ /* if we errored on add then this is already gone */ + if (!tdata) + return; + /* Remove the sysfs attributes */ sysfs_remove_group(&pdata->hwmon_dev->kobj, &tdata->attr_group);

From: Yuan Can yuancan@huawei.com

[ Upstream commit 9bdc112be727cf1ba65be79541147f960c3349d8 ]

As the devm_kcalloc may return NULL, the return value needs to be checked to avoid NULL poineter dereference.

Fixes: d0ddfd241e57 ("hwmon: (asus-ec-sensors) add driver for ASUS EC") Signed-off-by: Yuan Can yuancan@huawei.com Link: https://lore.kernel.org/r/20221125014329.121560-1-yuancan@huawei.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/asus-ec-sensors.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 81e688975c6a..a901e4e33d81 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -938,6 +938,8 @@ static int asus_ec_probe(struct platform_device *pdev) ec_data->nr_sensors = hweight_long(ec_data->board_info->sensors); ec_data->sensors = devm_kcalloc(dev, ec_data->nr_sensors, sizeof(struct ec_sensor), GFP_KERNEL); + if (!ec_data->sensors) + return -ENOMEM;

status = setup_lock_data(dev); if (status) {

From: Björn Töpel bjorn@rivosinc.com

commit 6fdd5d2f8c2f54b7fad4ff4df2a19542aeaf6102 upstream.

64-bit RISC-V kernels have the kernel image mapped separately to alias the linear map. The linear map and the kernel image map are documented as "direct mapping" and "kernel" respectively in [1].

At image load time, the linear map corresponding to the kernel image is set to PAGE_READ permission, and the kernel image map is set to PAGE_READ|PAGE_EXEC.

When the initmem is freed, the pages in the linear map should be restored to PAGE_READ|PAGE_WRITE, whereas the corresponding pages in the kernel image map should be restored to PAGE_READ, by removing the PAGE_EXEC permission.

This is not the case. For 64-bit kernels, only the linear map is restored to its proper page permissions at initmem free, and not the kernel image map.

In practise this results in that the kernel can potentially jump to dead __init code, and start executing invalid instructions, without getting an exception.

Restore the freed initmem properly, by setting both the kernel image map to the correct permissions.

[1] Documentation/riscv/vm-layout.rst

Fixes: e5c35fa04019 ("riscv: Map the kernel with correct permissions the first time") Signed-off-by: Björn Töpel bjorn@rivosinc.com Reviewed-by: Alexandre Ghiti alex@ghiti.fr Tested-by: Alexandre Ghiti alex@ghiti.fr Link: https://lore.kernel.org/r/20221115090641.258476-1-bjorn@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/kernel/setup.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -322,10 +322,11 @@ subsys_initcall(topology_init);

void free_initmem(void) { - if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) - set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), - IS_ENABLED(CONFIG_64BIT) ? - set_memory_rw : set_memory_rw_nx); + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) { + set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx); + if (IS_ENABLED(CONFIG_64BIT)) + set_kernel_memory(__init_begin, __init_end, set_memory_nx); + }

free_initmem_default(POISON_FREE_INITMEM); }

From: Ziyang Xuan william.xuanziyang@huawei.com

commit 8fa452cfafed521aaf5a18c71003fe24b1ee6141 upstream.

In can327_feed_frame_to_netdev(), it did not free the skb when netdev is down, and all callers of can327_feed_frame_to_netdev() did not free allocated skb too. That would trigger skb leak.

Fix it by adding kfree_skb() in can327_feed_frame_to_netdev() when netdev is down. Not tested, just compiled.

Fixes: 43da2f07622f ("can: can327: CAN/ldisc driver for ELM327 based OBD-II adapters") Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Link: https://lore.kernel.org/all/20221110061437.411525-1-william.xuanziyang@huawe... Reviewed-by: Max Staudt max@enpas.org Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/can327.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c index 094197780776..ed3d0b8989a0 100644 --- a/drivers/net/can/can327.c +++ b/drivers/net/can/can327.c @@ -263,8 +263,10 @@ static void can327_feed_frame_to_netdev(struct can327 *elm, struct sk_buff *skb) { lockdep_assert_held(&elm->lock);

- if (!netif_running(elm->dev)) + if (!netif_running(elm->dev)) { + kfree_skb(skb); return; + }

/* Queue for NAPI pickup. * rx-offload will update stats and LEDs for us.

From: Tiezhu Yang yangtiezhu@loongson.cn

commit a435874bf626f55d7147026b059008c8de89fbb8 upstream.

The latest version of grep claims the egrep is now obsolete so the build now contains warnings that look like:

egrep: warning: egrep is obsolescent; using grep -E

fix this up by moving the related file to use "grep -E" instead.

sed -i "s/egrep/grep -E/g" `grep egrep -rwl tools/vm`

Here are the steps to install the latest grep:

wget http://ftp.gnu.org/gnu/grep/grep-3.8.tar.gz tar xf grep-3.8.tar.gz cd grep-3.8 && ./configure && make sudo make install export PATH=/usr/local/bin:$PATH

Link: https://lkml.kernel.org/r/1668825419-30584-1-git-send-email-yangtiezhu@loong... Signed-off-by: Tiezhu Yang yangtiezhu@loongson.cn Reviewed-by: Sergey Senozhatsky senozhatsky@chromium.org Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/vm/slabinfo-gnuplot.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/tools/vm/slabinfo-gnuplot.sh +++ b/tools/vm/slabinfo-gnuplot.sh @@ -150,7 +150,7 @@ do_preprocess() let lines=3 out=`basename "$in"`"-slabs-by-loss" `cat "$in" | grep -A "$lines" 'Slabs sorted by loss' |\ - egrep -iv '--|Name|Slabs'\ + grep -E -iv '--|Name|Slabs'\ | awk '{print $1" "$4+$2*$3" "$4}' > "$out"` if [ $? -eq 0 ]; then do_slabs_plotting "$out" @@ -159,7 +159,7 @@ do_preprocess() let lines=3 out=`basename "$in"`"-slabs-by-size" `cat "$in" | grep -A "$lines" 'Slabs sorted by size' |\ - egrep -iv '--|Name|Slabs'\ + grep -E -iv '--|Name|Slabs'\ | awk '{print $1" "$4" "$4-$2*$3}' > "$out"` if [ $? -eq 0 ]; then do_slabs_plotting "$out"

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

commit 66065157420c5b9b3f078f43d313c153e1ff7f83 upstream.

The "force" argument to write_spec_ctrl_current() is currently ambiguous as it does not guarantee the MSR write. This is due to the optimization that writes to the MSR happen only when the new value differs from the cached value.

This is fine in most cases, but breaks for S3 resume when the cached MSR value gets out of sync with the hardware MSR value due to S3 resetting it.

When x86_spec_ctrl_current is same as x86_spec_ctrl_base, the MSR write is skipped. Which results in SPEC_CTRL mitigations not getting restored.

Move the MSR write from write_spec_ctrl_current() to a new function that unconditionally writes to the MSR. Update the callers accordingly and rename functions.

[ bp: Rework a bit. ]

Fixes: caa0ff24d5d0 ("x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value") Suggested-by: Borislav Petkov bp@alien8.de Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Reviewed-by: Thomas Gleixner tglx@linutronix.de Cc: stable@kernel.org Link: https://lore.kernel.org/r/806d39b0bfec2fe8f50dc5446dff20f5bb24a959.166982157... Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/nospec-branch.h | 2 +- arch/x86/kernel/cpu/bugs.c | 21 ++++++++++++++------- arch/x86/kernel/process.c | 2 +- 3 files changed, 16 insertions(+), 9 deletions(-)

--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -321,7 +321,7 @@ static inline void indirect_branch_predi /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); -extern void write_spec_ctrl_current(u64 val, bool force); +extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void);

/* --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -60,11 +60,18 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current)

static DEFINE_MUTEX(spec_ctrl_mutex);

+/* Update SPEC_CTRL MSR and its cached copy unconditionally */ +static void update_spec_ctrl(u64 val) +{ + this_cpu_write(x86_spec_ctrl_current, val); + wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + /* * Keep track of the SPEC_CTRL MSR value for the current task, which may differ * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). */ -void write_spec_ctrl_current(u64 val, bool force) +void update_spec_ctrl_cond(u64 val) { if (this_cpu_read(x86_spec_ctrl_current) == val) return; @@ -75,7 +82,7 @@ void write_spec_ctrl_current(u64 val, bo * When KERNEL_IBRS this MSR is written on return-to-user, unless * forced the update can be delayed until that time. */ - if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) wrmsrl(MSR_IA32_SPEC_CTRL, val); }

@@ -1328,7 +1335,7 @@ static void __init spec_ctrl_disable_ker

if (ia32_cap & ARCH_CAP_RRSBA) { x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } }

@@ -1450,7 +1457,7 @@ static void __init spectre_v2_select_mit

if (spectre_v2_in_ibrs_mode(mode)) { x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); }

switch (mode) { @@ -1564,7 +1571,7 @@ static void __init spectre_v2_select_mit static void update_stibp_msr(void * __unused) { u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); - write_spec_ctrl_current(val, true); + update_spec_ctrl(val); }

/* Update x86_spec_ctrl_base in case SMT state changed. */ @@ -1797,7 +1804,7 @@ static enum ssb_mitigation __init __ssb_ x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } }

@@ -2048,7 +2055,7 @@ int arch_prctl_spec_ctrl_get(struct task void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base);

if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -600,7 +600,7 @@ static __always_inline void __speculatio }

if (updmsr) - write_spec_ctrl_current(msr, false); + update_spec_ctrl_cond(msr); }

static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)

From: Linus Torvalds torvalds@linux-foundation.org

commit 6647e76ab623b2b3fb2efe03a86e9c9046c52c33 upstream.

The V4L2_MEMORY_USERPTR interface is long deprecated and shouldn't be used (and is discouraged for any modern v4l drivers). And Seth Jenkins points out that the fallback to VM_PFNMAP/VM_IO is fundamentally racy and dangerous.

Note that it's not even a case that should trigger, since any normal user pointer logic ends up just using the pin_user_pages_fast() call that does the proper page reference counting. That's not the problem case, only if you try to use special device mappings do you have any issues.

Normally I'd just remove this during the merge window, but since Seth pointed out the problem cases, we really want to know as soon as possible if there are actually any users of this odd special case of a legacy interface. Neither Hans nor Mauro seem to think that such mis-uses of the old legacy interface should exist. As Mauro says:

"See, V4L2 has actually 4 streaming APIs: - Kernel-allocated mmap (usually referred simply as just mmap); - USERPTR mmap; - read(); - dmabuf;

The USERPTR is one of the oldest way to use it, coming from V4L version 1 times, and by far the least used one"

And Hans chimed in on the USERPTR interface:

"To be honest, I wouldn't mind if it goes away completely, but that's a bit of a pipe dream right now"

but while removing this legacy interface entirely may be a pipe dream we can at least try to remove the unlikely (and actively broken) case of using special device mappings for USERPTR accesses.

This replaces it with a WARN_ONCE() that we can remove once we've hopefully confirmed that no actual users exist.

NOTE! Longer term, this means that a 'struct frame_vector' only ever contains proper page pointers, and all the games we have with converting them to pages can go away (grep for 'frame_vector_to_pages()' and the uses of 'vec->is_pfns'). But this is just the first step, to verify that this code really is all dead, and do so as quickly as possible.

Reported-by: Seth Jenkins sethjenkins@google.com Acked-by: Hans Verkuil hverkuil@xs4all.nl Acked-by: Mauro Carvalho Chehab mchehab@kernel.org Cc: David Hildenbrand david@redhat.com Cc: Jan Kara jack@suse.cz Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/media/common/videobuf2/frame_vector.c | 68 ++++---------------------- 1 file changed, 12 insertions(+), 56 deletions(-)

--- a/drivers/media/common/videobuf2/frame_vector.c +++ b/drivers/media/common/videobuf2/frame_vector.c @@ -35,11 +35,7 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, struct frame_vector *vec) { - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - int ret_pin_user_pages_fast = 0; - int ret = 0; - int err; + int ret;

if (nr_frames == 0) return 0; @@ -52,57 +48,17 @@ int get_vaddr_frames(unsigned long start ret = pin_user_pages_fast(start, nr_frames, FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, (struct page **)(vec->ptrs)); - if (ret > 0) { - vec->got_ref = true; - vec->is_pfns = false; - goto out_unlocked; - } - ret_pin_user_pages_fast = ret; - - mmap_read_lock(mm); - vec->got_ref = false; - vec->is_pfns = true; - ret = 0; - do { - unsigned long *nums = frame_vector_pfns(vec); - - vma = vma_lookup(mm, start); - if (!vma) - break; - - while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { - err = follow_pfn(vma, start, &nums[ret]); - if (err) { - if (ret) - goto out; - // If follow_pfn() returns -EINVAL, then this - // is not an IO mapping or a raw PFN mapping. - // In that case, return the original error from - // pin_user_pages_fast(). Otherwise this - // function would return -EINVAL when - // pin_user_pages_fast() returned -ENOMEM, - // which makes debugging hard. - if (err == -EINVAL && ret_pin_user_pages_fast) - ret = ret_pin_user_pages_fast; - else - ret = err; - goto out; - } - start += PAGE_SIZE; - ret++; - } - /* Bail out if VMA doesn't completely cover the tail page. */ - if (start < vma->vm_end) - break; - } while (ret < nr_frames); -out: - mmap_read_unlock(mm); -out_unlocked: - if (!ret) - ret = -EFAULT; - if (ret > 0) - vec->nr_frames = ret; - return ret; + vec->got_ref = true; + vec->is_pfns = false; + vec->nr_frames = ret; + + if (likely(ret > 0)) + return ret; + + /* This used to (racily) return non-refcounted pfns. Let people know */ + WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping"); + vec->nr_frames = 0; + return ret ? ret : -EFAULT; } EXPORT_SYMBOL(get_vaddr_frames);

From: Goh, Wei Sheng wei.sheng.goh@intel.com

commit cc3d2b5fc0d6f8ad8a52da5ea679e5c2ec2adbd4 upstream.

Currently, pause frame register GMAC_RX_FLOW_CTRL_RFE is not updated correctly when 'ethtool -A <IFACE> autoneg off rx off tx off' command is issued. This fix ensures the flow control change is reflected directly in the GMAC_RX_FLOW_CTRL_RFE register.

Fixes: 46f69ded988d ("net: stmmac: Use resolved link config in mac_link_up()") Cc: stable@vger.kernel.org # 5.10.x Signed-off-by: Goh, Wei Sheng wei.sheng.goh@intel.com Signed-off-by: Noor Azura Ahmad Tarmizi noor.azura.ahmad.tarmizi@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 ++ drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-)

--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -749,6 +749,8 @@ static void dwmac4_flow_ctrl(struct mac_ if (fc & FLOW_RX) { pr_debug("\tReceive Flow-Control ON\n"); flow |= GMAC_RX_FLOW_CTRL_RFE; + } else { + pr_debug("\tReceive Flow-Control OFF\n"); } writel(flow, ioaddr + GMAC_RX_FLOW_CTRL);

--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1061,8 +1061,16 @@ static void stmmac_mac_link_up(struct ph ctrl |= priv->hw->link.duplex;

/* Flow Control operation */ - if (tx_pause && rx_pause) - stmmac_mac_flow_ctrl(priv, duplex); + if (rx_pause && tx_pause) + priv->flow_ctrl = FLOW_AUTO; + else if (rx_pause && !tx_pause) + priv->flow_ctrl = FLOW_RX; + else if (!rx_pause && tx_pause) + priv->flow_ctrl = FLOW_TX; + else + priv->flow_ctrl = FLOW_OFF; + + stmmac_mac_flow_ctrl(priv, duplex);

if (ctrl != old_ctrl) writel(ctrl, priv->ioaddr + MAC_CTRL_REG);

From: Gaosheng Cui cuigaosheng1@huawei.com

commit c61bfb1cb63ddab52b31cf5f1924688917e61fad upstream.

The clk_disable_unprepare() should be called in the error handling of devm_clk_bulk_get_optional, fix it by replacing devm_clk_get_optional and clk_prepare_enable by devm_clk_get_optional_enabled.

Fixes: f5eccd94b63f ("mmc: mediatek: Add subsys clock control for MT8192 msdc") Signed-off-by: Gaosheng Cui cuigaosheng1@huawei.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221125090141.3626747-1-cuigaosheng1@huawei.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/mtk-sd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2573,13 +2573,11 @@ static int msdc_of_clock_parse(struct pl return PTR_ERR(host->src_clk_cg); }

- host->sys_clk_cg = devm_clk_get_optional(&pdev->dev, "sys_cg"); + /* If present, always enable for this clock gate */ + host->sys_clk_cg = devm_clk_get_optional_enabled(&pdev->dev, "sys_cg"); if (IS_ERR(host->sys_clk_cg)) host->sys_clk_cg = NULL;

- /* If present, always enable for this clock gate */ - clk_prepare_enable(host->sys_clk_cg); - host->bulk_clks[0].id = "pclk_cg"; host->bulk_clks[1].id = "axi_cg"; host->bulk_clks[2].id = "ahb_cg";

From: Sebastian Falbesoner sebastian.falbesoner@gmail.com

commit a3cab1d2132474969871b5d7f915c5c0167b48b0 upstream.

With the current logic the "failed to exit halt state" error would be shown even if any other bit than CQHCI_HALT was set in the CQHCI_CTL register, since the right hand side is always true. Fix this by using the correct operator (bit-wise instead of logical AND) to only check for the halt bit flag, which was obviously intended here.

Fixes: 85236d2be844 ("mmc: sdhci-esdhc-imx: clear the HALT bit when enable CQE") Signed-off-by: Sebastian Falbesoner sebastian.falbesoner@gmail.com Acked-by: Haibo Chen haibo.chen@nxp.com Acked-by: Adrian Hunter adrian.hunter@intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221121105721.1903878-1-sebastian.falbesoner@gmai... Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/sdhci-esdhc-imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1512,7 +1512,7 @@ static void esdhc_cqe_enable(struct mmc_ * system resume back. */ cqhci_writel(cq_host, 0, CQHCI_CTL); - if (cqhci_readl(cq_host, CQHCI_CTL) && CQHCI_HALT) + if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT) dev_err(mmc_dev(host->mmc), "failed to exit halt state when enable CQE\n");

From: Adrian Hunter adrian.hunter@intel.com

commit c981cdfb9925f64a364f13c2b4f98f877308a408 upstream.

Commit 20b92a30b561 ("mmc: sdhci: update signal voltage switch code") removed voltage switch delays from sdhci because mmc core had been enhanced to support them. However that assumed that sdhci_set_ios() did a single clock change, which it did not, and so the delays in mmc core, which should have come after the first clock change, were not effective.

Fix by avoiding re-configuring UHS and preset settings when the clock is turning on and the settings have not changed. That then also avoids the associated clock changes, so that then sdhci_set_ios() does a single clock change when voltage switching, and the mmc core delays become effective.

To do that has meant keeping track of driver strength (host->drv_type), and cases of reinitialization (host->reinit_uhs).

Note also, the 'turning_on_clk' restriction should not be necessary but is done to minimize the impact of the change on stable kernels.

Fixes: 20b92a30b561 ("mmc: sdhci: update signal voltage switch code") Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter adrian.hunter@intel.com Link: https://lore.kernel.org/r/20221128133259.38305-2-adrian.hunter@intel.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/sdhci.c | 61 +++++++++++++++++++++++++++++++++++++++++------ drivers/mmc/host/sdhci.h | 2 + 2 files changed, 56 insertions(+), 7 deletions(-)

--- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -339,6 +339,7 @@ static void sdhci_init(struct sdhci_host if (soft) { /* force clock reconfiguration */ host->clock = 0; + host->reinit_uhs = true; mmc->ops->set_ios(mmc, &mmc->ios); } } @@ -2258,11 +2259,46 @@ void sdhci_set_uhs_signaling(struct sdhc } EXPORT_SYMBOL_GPL(sdhci_set_uhs_signaling);

+static bool sdhci_timing_has_preset(unsigned char timing) +{ + switch (timing) { + case MMC_TIMING_UHS_SDR12: + case MMC_TIMING_UHS_SDR25: + case MMC_TIMING_UHS_SDR50: + case MMC_TIMING_UHS_SDR104: + case MMC_TIMING_UHS_DDR50: + case MMC_TIMING_MMC_DDR52: + return true; + }; + return false; +} + +static bool sdhci_preset_needed(struct sdhci_host *host, unsigned char timing) +{ + return !(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN) && + sdhci_timing_has_preset(timing); +} + +static bool sdhci_presetable_values_change(struct sdhci_host *host, struct mmc_ios *ios) +{ + /* + * Preset Values are: Driver Strength, Clock Generator and SDCLK/RCLK + * Frequency. Check if preset values need to be enabled, or the Driver + * Strength needs updating. Note, clock changes are handled separately. + */ + return !host->preset_enabled && + (sdhci_preset_needed(host, ios->timing) || host->drv_type != ios->drv_type); +} + void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) { struct sdhci_host *host = mmc_priv(mmc); + bool reinit_uhs = host->reinit_uhs; + bool turning_on_clk = false; u8 ctrl;

+ host->reinit_uhs = false; + if (ios->power_mode == MMC_POWER_UNDEFINED) return;

@@ -2288,6 +2324,8 @@ void sdhci_set_ios(struct mmc_host *mmc, sdhci_enable_preset_value(host, false);

if (!ios->clock || ios->clock != host->clock) { + turning_on_clk = ios->clock && !host->clock; + host->ops->set_clock(host, ios->clock); host->clock = ios->clock;

@@ -2314,6 +2352,17 @@ void sdhci_set_ios(struct mmc_host *mmc,

host->ops->set_bus_width(host, ios->bus_width);

+ /* + * Special case to avoid multiple clock changes during voltage + * switching. + */ + if (!reinit_uhs && + turning_on_clk && + host->timing == ios->timing && + host->version >= SDHCI_SPEC_300 && + !sdhci_presetable_values_change(host, ios)) + return; + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);

if (!(host->quirks & SDHCI_QUIRK_NO_HISPD_BIT)) { @@ -2357,6 +2406,7 @@ void sdhci_set_ios(struct mmc_host *mmc, }

sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2); + host->drv_type = ios->drv_type; } else { /* * According to SDHC Spec v3.00, if the Preset Value @@ -2384,19 +2434,14 @@ void sdhci_set_ios(struct mmc_host *mmc, host->ops->set_uhs_signaling(host, ios->timing); host->timing = ios->timing;

- if (!(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN) && - ((ios->timing == MMC_TIMING_UHS_SDR12) || - (ios->timing == MMC_TIMING_UHS_SDR25) || - (ios->timing == MMC_TIMING_UHS_SDR50) || - (ios->timing == MMC_TIMING_UHS_SDR104) || - (ios->timing == MMC_TIMING_UHS_DDR50) || - (ios->timing == MMC_TIMING_MMC_DDR52))) { + if (sdhci_preset_needed(host, ios->timing)) { u16 preset;

sdhci_enable_preset_value(host, true); preset = sdhci_get_preset_value(host); ios->drv_type = FIELD_GET(SDHCI_PRESET_DRV_MASK, preset); + host->drv_type = ios->drv_type; }

/* Re-enable SD Clock */ @@ -3748,6 +3793,7 @@ int sdhci_resume_host(struct sdhci_host sdhci_init(host, 0); host->pwr = 0; host->clock = 0; + host->reinit_uhs = true; mmc->ops->set_ios(mmc, &mmc->ios); } else { sdhci_init(host, (mmc->pm_flags & MMC_PM_KEEP_POWER)); @@ -3810,6 +3856,7 @@ int sdhci_runtime_resume_host(struct sdh /* Force clock and power re-program */ host->pwr = 0; host->clock = 0; + host->reinit_uhs = true; mmc->ops->start_signal_voltage_switch(mmc, &mmc->ios); mmc->ops->set_ios(mmc, &mmc->ios);

--- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -526,6 +526,8 @@ struct sdhci_host {

unsigned int clock; /* Current clock (MHz) */ u8 pwr; /* Current voltage */ + u8 drv_type; /* Current UHS-I driver type */ + bool reinit_uhs; /* Force UHS-related re-initialization */

bool runtime_suspended; /* Host is runtime suspended */ bool bus_on; /* Bus power prevents runtime suspend */

From: Lee Jones lee@kernel.org

commit 6f6cb1714365a07dbc66851879538df9f6969288 upstream.

Patch series "Fix a bunch of allmodconfig errors", v2.

Since b339ec9c229aa ("kbuild: Only default to -Werror if COMPILE_TEST") WERROR now defaults to COMPILE_TEST meaning that it's enabled for allmodconfig builds. This leads to some interesting build failures when using Clang, each resolved in this set.

With this set applied, I am able to obtain a successful allmodconfig Arm build.

This patch (of 2):

calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64) architectures built with Clang (all released versions), whereby the stack frame gets blown up to well over 5k. This would cause an immediate kernel panic on most architectures. We'll revert this when the following bug report has been resolved: https://github.com/llvm/llvm-project/issues/41896.

Link: https://lkml.kernel.org/r/20221125120750.3537134-1-lee@kernel.org Link: https://lkml.kernel.org/r/20221125120750.3537134-2-lee@kernel.org Signed-off-by: Lee Jones lee@kernel.org Suggested-by: Arnd Bergmann arnd@arndb.de Acked-by: Arnd Bergmann arnd@arndb.de Cc: Alex Deucher alexander.deucher@amd.com Cc: "Christian König" christian.koenig@amd.com Cc: Daniel Vetter daniel@ffwll.ch Cc: David Airlie airlied@gmail.com Cc: Harry Wentland harry.wentland@amd.com Cc: Lee Jones lee@kernel.org Cc: Leo Li sunpeng.li@amd.com Cc: Maarten Lankhorst maarten.lankhorst@linux.intel.com Cc: Maxime Ripard mripard@kernel.org Cc: Nathan Chancellor nathan@kernel.org Cc: Nick Desaulniers ndesaulniers@google.com Cc: "Pan, Xinhui" Xinhui.Pan@amd.com Cc: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Cc: Thomas Zimmermann tzimmermann@suse.de Cc: Tom Rix trix@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/Kconfig | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -5,6 +5,7 @@ menu "Display Engine Configuration" config DRM_AMD_DC bool "AMD DC - Enable new display engine" default y + depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64 select SND_HDA_COMPONENT if SND_HDA_CORE select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128) help @@ -12,6 +13,12 @@ config DRM_AMD_DC support for AMDGPU. This adds required support for Vega and Raven ASICs.

+ calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64) + architectures built with Clang (all released versions), whereby the stack + frame gets blown up to well over 5k. This would cause an immediate kernel + panic on most architectures. We'll revert this when the following bug report + has been resolved: https://github.com/llvm/llvm-project/issues/41896. + config DRM_AMD_DC_DCN def_bool n help

From: Janusz Krzysztofik janusz.krzysztofik@linux.intel.com

commit a8899b8728013c7b2456f0bfa20e5fea85ee0fd1 upstream.

Commit b97060a99b01 ("drm/i915/guc: Update intel_gt_wait_for_idle to work with GuC") extended the API of intel_gt_retire_requests_timeout() with an extra argument 'remaining_timeout', intended for passing back unconsumed portion of requested timeout when 0 (success) is returned. However, when request retirement happens to succeed despite an error returned by a call to dma_fence_wait_timeout(), that error code (a negative value) is passed back instead of remaining time. If we then pass that negative value forward as requested timeout to intel_uc_wait_for_idle(), an explicit BUG will be triggered.

If request retirement succeeds but an error code is passed back via remaininig_timeout, we may have no clue on how much of the initial timeout might have been left for spending it on waiting for GuC to become idle. OTOH, since all pending requests have been successfully retired, that error code has been already ignored by intel_gt_retire_requests_timeout(), then we shouldn't fail.

Assume no more time has been left on error and pass 0 timeout value to intel_uc_wait_for_idle() to give it a chance to return success if GuC is already idle.

v3: Don't fail on any error passed back via remaining_timeout.

v2: Fix the issue on the caller side, not the provider.

Fixes: b97060a99b01 ("drm/i915/guc: Update intel_gt_wait_for_idle to work with GuC") Signed-off-by: Janusz Krzysztofik janusz.krzysztofik@linux.intel.com Cc: stable@vger.kernel.org # v5.15+ Reviewed-by: Andrzej Hajda andrzej.hajda@intel.com Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20221121145655.75141-2-janusz.... (cherry picked from commit f235dbd5b768e238d365fd05d92de5a32abc1c1f) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/gt/intel_gt.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -616,8 +616,13 @@ int intel_gt_wait_for_idle(struct intel_ return -EINTR; }

- return timeout ? timeout : intel_uc_wait_for_idle(&gt->uc, - remaining_timeout); + if (timeout) + return timeout; + + if (remaining_timeout < 0) + remaining_timeout = 0; + + return intel_uc_wait_for_idle(&gt->uc, remaining_timeout); }

int intel_gt_init(struct intel_gt *gt)

From: Daniel Bristot de Oliveira bristot@kernel.org

commit 022632f6c43a86f2135642dccd5686de318e861d upstream.

The duration type is a 64 long value, not an int. This was causing some long noise to report wrong values.

Change the duration to a 64 bits value.

Link: https://lkml.kernel.org/r/a93d8a8378c7973e9c609de05826533c9e977939.166869209...

Cc: stable@vger.kernel.org Cc: Daniel Bristot de Oliveira bristot@kernel.org Cc: Steven Rostedt rostedt@goodmis.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Jonathan Corbet corbet@lwn.net Fixes: bce29ac9ce0b ("trace: Add osnoise tracer") Signed-off-by: Daniel Bristot de Oliveira bristot@kernel.org Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_osnoise.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -917,7 +917,7 @@ void osnoise_trace_irq_entry(int id) void osnoise_trace_irq_exit(int id, const char *desc) { struct osnoise_variables *osn_var = this_cpu_osn_var(); - int duration; + s64 duration;

if (!osn_var->sampling) return; @@ -1048,7 +1048,7 @@ static void trace_softirq_entry_callback static void trace_softirq_exit_callback(void *data, unsigned int vec_nr) { struct osnoise_variables *osn_var = this_cpu_osn_var(); - int duration; + s64 duration;

if (!osn_var->sampling) return; @@ -1144,7 +1144,7 @@ thread_entry(struct osnoise_variables *o static void thread_exit(struct osnoise_variables *osn_var, struct task_struct *t) { - int duration; + s64 duration;

if (!osn_var->sampling) return;

From: Steven Rostedt (Google) rostedt@goodmis.org

commit 4313e5a613049dfc1819a6dfb5f94cf2caff9452 upstream.

After 65536 dynamic events have been added and removed, the "type" field of the event then uses the first type number that is available (not currently used by other events). A type number is the identifier of the binary blobs in the tracing ring buffer (known as events) to map them to logic that can parse the binary blob.

The issue is that if a dynamic event (like a kprobe event) is traced and is in the ring buffer, and then that event is removed (because it is dynamic, which means it can be created and destroyed), if another dynamic event is created that has the same number that new event's logic on parsing the binary blob will be used.

To show how this can be an issue, the following can crash the kernel:

# cd /sys/kernel/tracing # for i in `seq 65536`; do echo 'p:kprobes/foo do_sys_openat2 $arg1:u32' > kprobe_events # done

For every iteration of the above, the writing to the kprobe_events will remove the old event and create a new one (with the same format) and increase the type number to the next available on until the type number reaches over 65535 which is the max number for the 16 bit type. After it reaches that number, the logic to allocate a new number simply looks for the next available number. When an dynamic event is removed, that number is then available to be reused by the next dynamic event created. That is, once the above reaches the max number, the number assigned to the event in that loop will remain the same.

Now that means deleting one dynamic event and created another will reuse the previous events type number. This is where bad things can happen. After the above loop finishes, the kprobes/foo event which reads the do_sys_openat2 function call's first parameter as an integer.

# echo 1 > kprobes/foo/enable # cat /etc/passwd > /dev/null # cat trace cat-2211 [005] .... 2007.849603: foo: (do_sys_openat2+0x0/0x130) arg1=4294967196 cat-2211 [005] .... 2007.849620: foo: (do_sys_openat2+0x0/0x130) arg1=4294967196 cat-2211 [005] .... 2007.849838: foo: (do_sys_openat2+0x0/0x130) arg1=4294967196 cat-2211 [005] .... 2007.849880: foo: (do_sys_openat2+0x0/0x130) arg1=4294967196 # echo 0 > kprobes/foo/enable

Now if we delete the kprobe and create a new one that reads a string:

# echo 'p:kprobes/foo do_sys_openat2 +0($arg2):string' > kprobe_events

And now we can the trace:

# cat trace sendmail-1942 [002] ..... 530.136320: foo: (do_sys_openat2+0x0/0x240) arg1= cat-2046 [004] ..... 530.930817: foo: (do_sys_openat2+0x0/0x240) arg1="������������������������������������������������������������������������������������������������" cat-2046 [004] ..... 530.930961: foo: (do_sys_openat2+0x0/0x240) arg1="������������������������������������������������������������������������������������������������" cat-2046 [004] ..... 530.934278: foo: (do_sys_openat2+0x0/0x240) arg1="������������������������������������������������������������������������������������������������" cat-2046 [004] ..... 530.934563: foo: (do_sys_openat2+0x0/0x240) arg1="������������������������������������������������������������������������������������������������" bash-1515 [007] ..... 534.299093: foo: (do_sys_openat2+0x0/0x240) arg1="kkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkk���������@��4Z����;Y�����U

And dmesg has:

================================================================== BUG: KASAN: use-after-free in string+0xd4/0x1c0 Read of size 1 at addr ffff88805fdbbfa0 by task cat/2049

CPU: 0 PID: 2049 Comm: cat Not tainted 6.1.0-rc6-test+ #641 Hardware name: Hewlett-Packard HP Compaq Pro 6300 SFF/339A, BIOS K01 v03.03 07/14/2016 Call Trace: <TASK> dump_stack_lvl+0x5b/0x77 print_report+0x17f/0x47b kasan_report+0xad/0x130 string+0xd4/0x1c0 vsnprintf+0x500/0x840 seq_buf_vprintf+0x62/0xc0 trace_seq_printf+0x10e/0x1e0 print_type_string+0x90/0xa0 print_kprobe_event+0x16b/0x290 print_trace_line+0x451/0x8e0 s_show+0x72/0x1f0 seq_read_iter+0x58e/0x750 seq_read+0x115/0x160 vfs_read+0x11d/0x460 ksys_read+0xa9/0x130 do_syscall_64+0x3a/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fc2e972ade2 Code: c0 e9 b2 fe ff ff 50 48 8d 3d b2 3f 0a 00 e8 05 f0 01 00 0f 1f 44 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 0f 05 <48> 3d 00 f0 ff ff 77 56 c3 0f 1f 44 00 00 48 83 ec 28 48 89 54 24 RSP: 002b:00007ffc64e687c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007fc2e972ade2 RDX: 0000000000020000 RSI: 00007fc2e980d000 RDI: 0000000000000003 RBP: 00007fc2e980d000 R08: 00007fc2e980c010 R09: 0000000000000000 R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000020f00 R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000 </TASK>

The buggy address belongs to the physical page: page:ffffea00017f6ec0 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5fdbb flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc0000000 0000000000000000 ffffea00017f6ec8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: kasan: bad access detected

Memory state around the buggy address: ffff88805fdbbe80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff88805fdbbf00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

ffff88805fdbbf80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff

^ ffff88805fdbc000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff88805fdbc080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ==================================================================

This was found when Zheng Yejian sent a patch to convert the event type number assignment to use IDA, which gives the next available number, and this bug showed up in the fuzz testing by Yujie Liu and the kernel test robot. But after further analysis, I found that this behavior is the same as when the event type numbers go past the 16bit max (and the above shows that).

As modules have a similar issue, but is dealt with by setting a "WAS_ENABLED" flag when a module event is enabled, and when the module is freed, if any of its events were enabled, the ring buffer that holds that event is also cleared, to prevent reading stale events. The same can be done for dynamic events.

If any dynamic event that is being removed was enabled, then make sure the buffers they were enabled in are now cleared.

Link: https://lkml.kernel.org/r/20221123171434.545706e3@gandalf.local.home Link: https://lore.kernel.org/all/20221110020319.1259291-1-zhengyejian1@huawei.com...

Cc: stable@vger.kernel.org Cc: Andrew Morton akpm@linux-foundation.org Depends-on: e18eb8783ec49 ("tracing: Add tracing_reset_all_online_cpus_unlocked() function") Depends-on: 5448d44c38557 ("tracing: Add unified dynamic event framework") Depends-on: 6212dd29683ee ("tracing/kprobes: Use dyn_event framework for kprobe events") Depends-on: 065e63f951432 ("tracing: Only have rmmod clear buffers that its events were active in") Depends-on: 575380da8b469 ("tracing: Only clear trace buffer on module unload if event was traced") Fixes: 77b44d1b7c283 ("tracing/kprobes: Rename Kprobe-tracer to kprobe-event") Reported-by: Zheng Yejian zhengyejian1@huawei.com Reported-by: Yujie Liu yujie.liu@intel.com Reported-by: kernel test robot yujie.liu@intel.com Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_dynevent.c | 2 ++ kernel/trace/trace_events.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-)

--- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -118,6 +118,7 @@ int dyn_event_release(const char *raw_co if (ret) break; } + tracing_reset_all_online_cpus(); mutex_unlock(&event_mutex); out: argv_free(argv); @@ -214,6 +215,7 @@ int dyn_events_release_all(struct dyn_ev break; } out: + tracing_reset_all_online_cpus(); mutex_unlock(&event_mutex);

return ret; --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2880,7 +2880,10 @@ static int probe_remove_event_call(struc * TRACE_REG_UNREGISTER. */ if (file->flags & EVENT_FILE_FL_ENABLED) - return -EBUSY; + goto busy; + + if (file->flags & EVENT_FILE_FL_WAS_ENABLED) + tr->clear_trace = true; /* * The do_for_each_event_file_safe() is * a double loop. After finding the call for this @@ -2893,6 +2896,12 @@ static int probe_remove_event_call(struc __trace_remove_event_call(call);

return 0; + busy: + /* No need to clear the trace now */ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + tr->clear_trace = false; + } + return -EBUSY; }

/* Remove an event_call */

From: Hui Tang tanghui20@huawei.com

[ Upstream commit 19c5bda74dc45fee598a57600b550c9ea7662f10 ]

sound/soc/codecs/tlv320adc3xxx.c: In function ‘adc3xxx_i2c_probe’: sound/soc/codecs/tlv320adc3xxx.c:1359:21: error: implicit declaration of function ‘devm_gpiod_get’; did you mean ‘devm_gpio_free’? [-Werror=implicit-function-declaration] adc3xxx->rst_pin = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); ^~~~~~~~~~~~~~ devm_gpio_free CC [M] drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgt215.o LD [M] sound/soc/codecs/snd-soc-ak4671.o LD [M] sound/soc/codecs/snd-soc-arizona.o LD [M] sound/soc/codecs/snd-soc-cros-ec-codec.o LD [M] sound/soc/codecs/snd-soc-ak4641.o LD [M] sound/soc/codecs/snd-soc-alc5632.o sound/soc/codecs/tlv320adc3xxx.c:1359:50: error: ‘GPIOD_OUT_LOW’ undeclared (first use in this function); did you mean ‘GPIOF_INIT_LOW’? adc3xxx->rst_pin = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); ^~~~~~~~~~~~~ GPIOF_INIT_LOW sound/soc/codecs/tlv320adc3xxx.c:1359:50: note: each undeclared identifier is reported only once for each function it appears in LD [M] sound/soc/codecs/snd-soc-cs35l32.o sound/soc/codecs/tlv320adc3xxx.c:1408:2: error: implicit declaration of function ‘gpiod_set_value_cansleep’; did you mean ‘gpio_set_value_cansleep’? [-Werror=implicit-function-declaration] gpiod_set_value_cansleep(adc3xxx->rst_pin, 1); ^~~~~~~~~~~~~~~~~~~~~~~~ gpio_set_value_cansleep LD [M] sound/soc/codecs/snd-soc-cs35l41-lib.o LD [M] sound/soc/codecs/snd-soc-cs35l36.o LD [M] sound/soc/codecs/snd-soc-cs35l34.o LD [M] sound/soc/codecs/snd-soc-cs35l41.o CC [M] drivers/gpu/drm/nouveau/nvkm/engine/disp/sormcp89.o cc1: all warnings being treated as errors

Fixes: e9a3b57efd28 ("ASoC: codec: tlv320adc3xxx: New codec driver") Signed-off-by: Hui Tang tanghui20@huawei.com Link: https://lore.kernel.org/r/20220512074640.75550-3-tanghui20@huawei.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/tlv320adc3xxx.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c index 8a0965cd3e66..297c458c4d8b 100644 --- a/sound/soc/codecs/tlv320adc3xxx.c +++ b/sound/soc/codecs/tlv320adc3xxx.c @@ -14,6 +14,7 @@

#include <dt-bindings/sound/tlv320adc3xxx.h> #include <linux/clk.h> +#include <linux/gpio/consumer.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/io.h> @@ -1025,7 +1026,9 @@ static const struct gpio_chip adc3xxx_gpio_chip = {

static void adc3xxx_free_gpio(struct adc3xxx *adc3xxx) { +#ifdef CONFIG_GPIOLIB gpiochip_remove(&adc3xxx->gpio_chip); +#endif }

static void adc3xxx_init_gpio(struct adc3xxx *adc3xxx)

From: Alexandre Ghiti alexghiti@rivosinc.com

[ Upstream commit 3f105a742725a1b78766a55169f1d827732e62b8 ]

The EFI page table is initially created as a copy of the kernel page table. With VMAP_STACK enabled, kernel stacks are allocated in the vmalloc area: if the stack is allocated in a new PGD (one that was not present at the moment of the efi page table creation or not synced in a previous vmalloc fault), the kernel will take a trap when switching to the efi page table when the vmalloc kernel stack is accessed, resulting in a kernel panic.

Fix that by updating the efi kernel mappings before switching to the efi page table.

Signed-off-by: Alexandre Ghiti alexghiti@rivosinc.com Fixes: b91540d52a08 ("RISC-V: Add EFI runtime services") Tested-by: Emil Renner Berthing emil.renner.berthing@canonical.com Reviewed-by: Atish Patra atishp@rivosinc.com Link: https://lore.kernel.org/r/20221121133303.1782246-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/include/asm/efi.h | 6 +++++- arch/riscv/include/asm/pgalloc.h | 11 ++++++++--- 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index f74879a8f1ea..e229d7be4b66 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -10,6 +10,7 @@ #include <asm/mmu_context.h> #include <asm/ptrace.h> #include <asm/tlbflush.h> +#include <asm/pgalloc.h>

#ifdef CONFIG_EFI extern void efi_init(void); @@ -20,7 +21,10 @@ extern void efi_init(void); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);

-#define arch_efi_call_virt_setup() efi_virtmap_load() +#define arch_efi_call_virt_setup() ({ \ + sync_kernel_mappings(efi_mm.pgd); \ + efi_virtmap_load(); \ + }) #define arch_efi_call_virt_teardown() efi_virtmap_unload()

#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index 947f23d7b6af..59dc12b5b7e8 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -127,6 +127,13 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) #define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) #endif /* __PAGETABLE_PMD_FOLDED */

+static inline void sync_kernel_mappings(pgd_t *pgd) +{ + memcpy(pgd + USER_PTRS_PER_PGD, + init_mm.pgd + USER_PTRS_PER_PGD, + (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); +} + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; @@ -135,9 +142,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) if (likely(pgd != NULL)) { memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); /* Copy kernel mappings */ - memcpy(pgd + USER_PTRS_PER_PGD, - init_mm.pgd + USER_PTRS_PER_PGD, - (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); + sync_kernel_mappings(pgd); } return pgd; }

From: Guo Ren guoren@linux.alibaba.com

[ Upstream commit b17d19a5314a37f7197afd1a0200affd21a7227d ]

If a crash happens on cpu3 and all interrupts are binding on cpu0, the bad irq routing will cause a crash kernel which can't receive any irq. Because crash kernel won't clean up all harts' PLIC enable bits in enable registers. This patch is similar to 9141a003a491 ("ARM: 7316/1: kexec: EOI active and mask all interrupts in kexec crash path") and 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()"), and PowerPC also has the same mechanism.

Fixes: fba8a8674f68 ("RISC-V: Add kexec support") Signed-off-by: Guo Ren guoren@linux.alibaba.com Signed-off-by: Guo Ren guoren@kernel.org Reviewed-by: Xianting Tian xianting.tian@linux.alibaba.com Cc: Nick Kossifidis mick@ics.forth.gr Cc: Palmer Dabbelt palmer@rivosinc.com Link: https://lore.kernel.org/r/20221020141603.2856206-2-guoren@kernel.org Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/kernel/machine_kexec.c | 35 +++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+)

diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index ee79e6839b86..db41c676e5a2 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -15,6 +15,8 @@ #include <linux/compiler.h> /* For unreachable() */ #include <linux/cpu.h> /* For cpu_down() */ #include <linux/reboot.h> +#include <linux/interrupt.h> +#include <linux/irq.h>

/* * kexec_image_info - Print received image details @@ -154,6 +156,37 @@ void crash_smp_send_stop(void) cpus_stopped = 1; }

+static void machine_kexec_mask_interrupts(void) +{ + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + int ret; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + /* + * First try to remove the active state. If this + * fails, try to EOI the interrupt. + */ + ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); + + if (ret && irqd_irq_inprogress(&desc->irq_data) && + chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } +} + /* * machine_crash_shutdown - Prepare to kexec after a kernel crash * @@ -169,6 +202,8 @@ machine_crash_shutdown(struct pt_regs *regs) crash_smp_send_stop();

crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + pr_info("Starting crashdump kernel...\n"); }

From: Caleb Sander csander@purestorage.com

[ Upstream commit 899d2a05dc14733cfba6224083c6b0dd5a738590 ]

Walking the nvme_ns_head siblings list is protected by the head's srcu in nvme_ns_head_submit_bio() but not nvme_mpath_revalidate_paths(). Removing namespaces from the list also fails to synchronize the srcu. Concurrent scan work can therefore cause use-after-frees.

Hold the head's srcu lock in nvme_mpath_revalidate_paths() and synchronize with the srcu, not the global RCU, in nvme_ns_remove().

Observed the following panic when making NVMe/RDMA connections with native multipath on the Rocky Linux 8.6 kernel (it seems the upstream kernel has the same race condition). Disassembly shows the faulting instruction is cmp 0x50(%rdx),%rcx; computing capacity != get_capacity(ns->disk). Address 0x50 is dereferenced because ns->disk is NULL. The NULL disk appears to be the result of concurrent scan work freeing the namespace (note the log line in the middle of the panic).

[37314.206036] BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 [37314.206036] nvme0n3: detected capacity change from 0 to 11811160064 [37314.299753] PGD 0 P4D 0 [37314.299756] Oops: 0000 [#1] SMP PTI [37314.299759] CPU: 29 PID: 322046 Comm: kworker/u98:3 Kdump: loaded Tainted: G W X --------- - - 4.18.0-372.32.1.el8test86.x86_64 #1 [37314.299762] Hardware name: Dell Inc. PowerEdge R720/0JP31P, BIOS 2.7.0 05/23/2018 [37314.299763] Workqueue: nvme-wq nvme_scan_work [nvme_core] [37314.299783] RIP: 0010:nvme_mpath_revalidate_paths+0x26/0xb0 [nvme_core] [37314.299790] Code: 1f 44 00 00 66 66 66 66 90 55 53 48 8b 5f 50 48 8b 83 c8 c9 00 00 48 8b 13 48 8b 48 50 48 39 d3 74 20 48 8d 42 d0 48 8b 50 20 <48> 3b 4a 50 74 05 f0 80 60 70 ef 48 8b 50 30 48 8d 42 d0 48 39 d3 [37315.058803] RSP: 0018:ffffabe28f913d10 EFLAGS: 00010202 [37315.121316] RAX: ffff927a077da800 RBX: ffff92991dd70000 RCX: 0000000001600000 [37315.206704] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff92991b719800 [37315.292106] RBP: ffff929a6b70c000 R08: 000000010234cd4a R09: c0000000ffff7fff [37315.377501] R10: 0000000000000001 R11: ffffabe28f913a30 R12: 0000000000000000 [37315.462889] R13: ffff92992716600c R14: ffff929964e6e030 R15: ffff92991dd70000 [37315.548286] FS: 0000000000000000(0000) GS:ffff92b87fb80000(0000) knlGS:0000000000000000 [37315.645111] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [37315.713871] CR2: 0000000000000050 CR3: 0000002208810006 CR4: 00000000000606e0 [37315.799267] Call Trace: [37315.828515] nvme_update_ns_info+0x1ac/0x250 [nvme_core] [37315.892075] nvme_validate_or_alloc_ns+0x2ff/0xa00 [nvme_core] [37315.961871] ? __blk_mq_free_request+0x6b/0x90 [37316.015021] nvme_scan_work+0x151/0x240 [nvme_core] [37316.073371] process_one_work+0x1a7/0x360 [37316.121318] ? create_worker+0x1a0/0x1a0 [37316.168227] worker_thread+0x30/0x390 [37316.212024] ? create_worker+0x1a0/0x1a0 [37316.258939] kthread+0x10a/0x120 [37316.297557] ? set_kthread_struct+0x50/0x50 [37316.347590] ret_from_fork+0x35/0x40 [37316.390360] Modules linked in: nvme_rdma nvme_tcp(X) nvme_fabrics nvme_core netconsole iscsi_tcp libiscsi_tcp dm_queue_length dm_service_time nf_conntrack_netlink br_netfilter bridge stp llc overlay nft_chain_nat ipt_MASQUERADE nf_nat xt_addrtype xt_CT nft_counter xt_state xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_comment xt_multiport nft_compat nf_tables libcrc32c nfnetlink dm_multipath tg3 rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm intel_rapl_msr iTCO_wdt iTCO_vendor_support dcdbas intel_rapl_common sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ipmi_ssif kvm irqbypass crct10dif_pclmul crc32_pclmul mlx5_ib ghash_clmulni_intel ib_uverbs rapl intel_cstate intel_uncore ib_core ipmi_si joydev mei_me pcspkr ipmi_devintf mei lpc_ich wmi ipmi_msghandler acpi_power_meter ext4 mbcache jbd2 sd_mod t10_pi sg mgag200 mlx5_core drm_kms_helper syscopyarea [37316.390419] sysfillrect ahci sysimgblt fb_sys_fops libahci drm crc32c_intel libata mlxfw pci_hyperv_intf tls i2c_algo_bit psample dm_mirror dm_region_hash dm_log dm_mod fuse [last unloaded: nvme_core] [37317.645908] CR2: 0000000000000050

Fixes: e7d65803e2bb ("nvme-multipath: revalidate paths during rescan") Signed-off-by: Caleb Sander csander@purestorage.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 2 +- drivers/nvme/host/multipath.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 01c36284e542..f612a0ba64d0 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4297,7 +4297,7 @@ static void nvme_ns_remove(struct nvme_ns *ns) mutex_unlock(&ns->ctrl->subsys->lock);

/* guarantee not available in head->list */ - synchronize_rcu(); + synchronize_srcu(&ns->head->srcu);

if (!nvme_ns_head_multipath(ns->head)) nvme_cdev_del(&ns->cdev, &ns->cdev_device); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index b9cf17cbbbd5..114e2b9359f8 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -174,11 +174,14 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns) struct nvme_ns_head *head = ns->head; sector_t capacity = get_capacity(head->disk); int node; + int srcu_idx;

+ srcu_idx = srcu_read_lock(&head->srcu); list_for_each_entry_rcu(ns, &head->list, siblings) { if (capacity != get_capacity(ns->disk)) clear_bit(NVME_NS_READY, &ns->flags); } + srcu_read_unlock(&head->srcu, srcu_idx);

for_each_node(node) rcu_assign_pointer(head->current_path[node], NULL);

From: Xiongfeng Wang wangxiongfeng2@huawei.com

[ Upstream commit 4bedbbd782ebbe7287231fea862c158d4f08a9e3 ]

for_each_pci_dev() is implemented by pci_get_device(). The comment of pci_get_device() says that it will increase the reference count for the returned pci_dev and also decrease the reference count for the input pci_dev @from if it is not NULL.

If we break for_each_pci_dev() loop with pdev not NULL, we need to call pci_dev_put() to decrease the reference count. Add the missing pci_dev_put() for the error path to avoid reference count leak.

Fixes: 2e4552893038 ("iommu/vt-d: Unify the way to process DMAR device scope array") Signed-off-by: Xiongfeng Wang wangxiongfeng2@huawei.com Link: https://lore.kernel.org/r/20221121113649.190393-3-wangxiongfeng2@huawei.com Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/intel/dmar.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 5a8f780e7ffd..bc94059a5b87 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -820,6 +820,7 @@ int __init dmar_dev_scope_init(void) info = dmar_alloc_pci_notify_info(dev, BUS_NOTIFY_ADD_DEVICE); if (!info) { + pci_dev_put(dev); return dmar_dev_scope_status; } else { dmar_pci_bus_add_dev(info);

From: Ido Schimmel idosch@nvidia.com

[ Upstream commit d5082d386eee7e8ec46fa8581932c81a4961dcef ]

When the kernel receives a route deletion request from user space it tries to delete a route that matches the route attributes specified in the request.

If only prefix information is specified in the request, the kernel should delete the first matching FIB alias regardless of its associated FIB info. However, an error is currently returned when the FIB info is backed by a nexthop object:

# ip nexthop add id 1 via 192.0.2.2 dev dummy10 # ip route add 198.51.100.0/24 nhid 1 # ip route del 198.51.100.0/24 RTNETLINK answers: No such process

Fix by matching on such a FIB info when legacy nexthop attributes are not specified in the request. An earlier check already covers the case where a nexthop ID is specified in the request.

Add tests that cover these flows. Before the fix:

# ./fib_nexthops.sh -t ipv4_fcnal ... TEST: Delete route when not specifying nexthop attributes [FAIL]

Tests passed: 11 Tests failed: 1

After the fix:

# ./fib_nexthops.sh -t ipv4_fcnal ... TEST: Delete route when not specifying nexthop attributes [ OK ]

Tests passed: 12 Tests failed: 0

No regressions in other tests:

# ./fib_nexthops.sh ... Tests passed: 228 Tests failed: 0

# ./fib_tests.sh ... Tests passed: 186 Tests failed: 0

Cc: stable@vger.kernel.org Reported-by: Jonas Gorski jonas.gorski@gmail.com Tested-by: Jonas Gorski jonas.gorski@gmail.com Fixes: 493ced1ac47c ("ipv4: Allow routes to use nexthop objects") Fixes: 6bf92d70e690 ("net: ipv4: fix route with nexthop object delete warning") Fixes: 61b91eb33a69 ("ipv4: Handle attempt to delete multipath route when fib_info contains an nh reference") Signed-off-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Nikolay Aleksandrov razor@blackwall.org Reviewed-by: David Ahern dsahern@kernel.org Link: https://lore.kernel.org/r/20221124210932.2470010-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/fib_semantics.c | 8 +++++--- tools/testing/selftests/net/fib_nexthops.sh | 11 +++++++++++ 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e9a7f70a54df..cb24260692e1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -888,9 +888,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, return 1; }

- /* cannot match on nexthop object attributes */ - if (fi->nh) - return 1; + if (fi->nh) { + if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp) + return 1; + return 0; + }

if (cfg->fc_oif || cfg->fc_gw_family) { struct fib_nh *nh; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index ee5e98204d3d..a47b26ab48f2 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1228,6 +1228,17 @@ ipv4_fcnal() run_cmd "$IP ro add 172.16.101.0/24 nhid 21" run_cmd "$IP ro del 172.16.101.0/24 nexthop via 172.16.1.7 dev veth1 nexthop via 172.16.1.8 dev veth1" log_test $? 2 "Delete multipath route with only nh id based entry" + + run_cmd "$IP nexthop add id 22 via 172.16.1.6 dev veth1" + run_cmd "$IP ro add 172.16.102.0/24 nhid 22" + run_cmd "$IP ro del 172.16.102.0/24 dev veth1" + log_test $? 2 "Delete route when specifying only nexthop device" + + run_cmd "$IP ro del 172.16.102.0/24 via 172.16.1.6" + log_test $? 2 "Delete route when specifying only gateway" + + run_cmd "$IP ro del 172.16.102.0/24" + log_test $? 0 "Delete route when not specifying nexthop attributes" }

ipv4_grp_fcnal()

From: SeongJae Park sj@kernel.org

[ Upstream commit 95bc35f9bee5220dad4e8567654ab3288a181639 ]

Commit da87878010e5 ("mm/damon/sysfs: support online inputs update") made 'damon_sysfs_set_schemes()' to be called for running DAMON context, which could have schemes. In the case, DAMON sysfs interface is supposed to update, remove, or add schemes to reflect the sysfs files. However, the code is assuming the DAMON context wouldn't have schemes at all, and therefore creates and adds new schemes. As a result, the code doesn't work as intended for online schemes tuning and could have more than expected memory footprint. The schemes are all in the DAMON context, so it doesn't leak the memory, though.

Remove the wrong asssumption (the DAMON context wouldn't have schemes) in 'damon_sysfs_set_schemes()' to fix the bug.

Link: https://lkml.kernel.org/r/20221122194831.3472-1-sj@kernel.org Fixes: da87878010e5 ("mm/damon/sysfs: support online inputs update") Signed-off-by: SeongJae Park sj@kernel.org Cc: stable@vger.kernel.org [5.19+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/damon/sysfs.c | 46 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 44 insertions(+), 2 deletions(-)

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index ec88644c51df..1b782ca41396 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -2293,12 +2293,54 @@ static struct damos *damon_sysfs_mk_scheme( &wmarks); }

+static void damon_sysfs_update_scheme(struct damos *scheme, + struct damon_sysfs_scheme *sysfs_scheme) +{ + struct damon_sysfs_access_pattern *access_pattern = + sysfs_scheme->access_pattern; + struct damon_sysfs_quotas *sysfs_quotas = sysfs_scheme->quotas; + struct damon_sysfs_weights *sysfs_weights = sysfs_quotas->weights; + struct damon_sysfs_watermarks *sysfs_wmarks = sysfs_scheme->watermarks; + + scheme->pattern.min_sz_region = access_pattern->sz->min; + scheme->pattern.max_sz_region = access_pattern->sz->max; + scheme->pattern.min_nr_accesses = access_pattern->nr_accesses->min; + scheme->pattern.max_nr_accesses = access_pattern->nr_accesses->max; + scheme->pattern.min_age_region = access_pattern->age->min; + scheme->pattern.max_age_region = access_pattern->age->max; + + scheme->action = sysfs_scheme->action; + + scheme->quota.ms = sysfs_quotas->ms; + scheme->quota.sz = sysfs_quotas->sz; + scheme->quota.reset_interval = sysfs_quotas->reset_interval_ms; + scheme->quota.weight_sz = sysfs_weights->sz; + scheme->quota.weight_nr_accesses = sysfs_weights->nr_accesses; + scheme->quota.weight_age = sysfs_weights->age; + + scheme->wmarks.metric = sysfs_wmarks->metric; + scheme->wmarks.interval = sysfs_wmarks->interval_us; + scheme->wmarks.high = sysfs_wmarks->high; + scheme->wmarks.mid = sysfs_wmarks->mid; + scheme->wmarks.low = sysfs_wmarks->low; +} + static int damon_sysfs_set_schemes(struct damon_ctx *ctx, struct damon_sysfs_schemes *sysfs_schemes) { - int i; + struct damos *scheme, *next; + int i = 0; + + damon_for_each_scheme_safe(scheme, next, ctx) { + if (i < sysfs_schemes->nr) + damon_sysfs_update_scheme(scheme, + sysfs_schemes->schemes_arr[i]); + else + damon_destroy_scheme(scheme); + i++; + }

- for (i = 0; i < sysfs_schemes->nr; i++) { + for (; i < sysfs_schemes->nr; i++) { struct damos *scheme, *next;

scheme = damon_sysfs_mk_scheme(sysfs_schemes->schemes_arr[i]);

From: Yuan Can yuancan@huawei.com

[ Upstream commit 145900cf91c4b32ac05dbc8675a0c7f4a278749d ]

A problem about i2c-npcm7xx create debugfs failed is triggered with the following log given:

[ 173.827310] debugfs: Directory 'npcm_i2c' with parent '/' already present!

The reason is that npcm_i2c_init() returns platform_driver_register() directly without checking its return value, if platform_driver_register() failed, it returns without destroy the newly created debugfs, resulting the debugfs of npcm_i2c can never be created later.

npcm_i2c_init() debugfs_create_dir() # create debugfs directory platform_driver_register() driver_register() bus_add_driver() priv = kzalloc(...) # OOM happened # return without destroy debugfs directory

Fix by removing debugfs when platform_driver_register() returns error.

Fixes: 56a1485b102e ("i2c: npcm7xx: Add Nuvoton NPCM I2C controller driver") Signed-off-by: Yuan Can yuancan@huawei.com Reviewed-by: Tali Perry tali.perry@nuvoton.com Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-npcm7xx.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 0c365b57d957..83457359ec45 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -2393,8 +2393,17 @@ static struct platform_driver npcm_i2c_bus_driver = {

static int __init npcm_i2c_init(void) { + int ret; + npcm_i2c_debugfs_dir = debugfs_create_dir("npcm_i2c", NULL); - return platform_driver_register(&npcm_i2c_bus_driver); + + ret = platform_driver_register(&npcm_i2c_bus_driver); + if (ret) { + debugfs_remove_recursive(npcm_i2c_debugfs_dir); + return ret; + } + + return 0; } module_init(npcm_i2c_init);

From: Andrew Lunn andrew@lunn.ch

[ Upstream commit d36678f7905cbd1dc55a8a96e066dafd749d4600 ]

Recent changes to the DMA code has resulting in the IMX driver failing I2C transfers when the buffer has been vmalloc. Only perform DMA transfers if the message has the I2C_M_DMA_SAFE flag set, indicating the client is providing a buffer which is DMA safe.

This is a minimal fix for stable. The I2C core provides helpers to allocate a bounce buffer. For a fuller fix the master should make use of these helpers.

Fixes: 4544b9f25e70 ("dma-mapping: Add vmap checks to dma_map_single()") Signed-off-by: Andrew Lunn andrew@lunn.ch Acked-by: Oleksij Rempel o.rempel@pengutronix.de Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-imx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 3082183bd66a..fc70920c4dda 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1132,7 +1132,8 @@ static int i2c_imx_read(struct imx_i2c_struct *i2c_imx, struct i2c_msg *msgs, int i, result; unsigned int temp; int block_data = msgs->flags & I2C_M_RECV_LEN; - int use_dma = i2c_imx->dma && msgs->len >= DMA_THRESHOLD && !block_data; + int use_dma = i2c_imx->dma && msgs->flags & I2C_M_DMA_SAFE && + msgs->len >= DMA_THRESHOLD && !block_data;

dev_dbg(&i2c_imx->adapter.dev, "<%s> write slave address: addr=0x%x\n", @@ -1298,7 +1299,8 @@ static int i2c_imx_xfer_common(struct i2c_adapter *adapter, result = i2c_imx_read(i2c_imx, &msgs[i], is_lastmsg, atomic); } else { if (!atomic && - i2c_imx->dma && msgs[i].len >= DMA_THRESHOLD) + i2c_imx->dma && msgs[i].len >= DMA_THRESHOLD && + msgs[i].flags & I2C_M_DMA_SAFE) result = i2c_imx_dma_write(i2c_imx, &msgs[i]); else result = i2c_imx_write(i2c_imx, &msgs[i], atomic);

From: Vishal Verma vishal.l.verma@intel.com

[ Upstream commit 48d4180939e12c4bd2846f984436d895bb9699ed ]

In a system with a single initiator node, and one or more memory-only 'target' nodes, the memory-only node(s) would fail to register their initiator node correctly. i.e. in sysfs:

# ls /sys/devices/system/node/node0/access0/targets/ node0

Where as the correct behavior should be:

# ls /sys/devices/system/node/node0/access0/targets/ node0 node1

This happened because hmat_register_target_initiators() uses list_sort() to sort the initiator list, but the sort comparision function (initiator_cmp()) is overloaded to also set the node mask's bits.

In a system with a single initiator, the list is singular, and list_sort elides the comparision helper call. Thus the node mask never gets set, and the subsequent search for the best initiator comes up empty.

Add a new helper to consume the sorted initiator list, and generate the nodemask, decoupling it from the overloaded initiator_cmp() comparision callback. This prevents the singular list corner case naturally, and makes the code easier to follow as well.

Cc: stable@vger.kernel.org Cc: Rafael J. Wysocki rafael@kernel.org Cc: Liu Shixin liushixin2@huawei.com Cc: Dan Williams dan.j.williams@intel.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Reported-by: Chris Piper chris.d.piper@intel.com Signed-off-by: Vishal Verma vishal.l.verma@intel.com Acked-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Link: https://lore.kernel.org/r/20221116-acpi_hmat_fix-v2-2-3712569be691@intel.com Signed-off-by: Dan Williams dan.j.williams@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/numa/hmat.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index fca69a726360..b42653707fdc 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -563,17 +563,26 @@ static int initiator_cmp(void *priv, const struct list_head *a, { struct memory_initiator *ia; struct memory_initiator *ib; - unsigned long *p_nodes = priv;

ia = list_entry(a, struct memory_initiator, node); ib = list_entry(b, struct memory_initiator, node);

- set_bit(ia->processor_pxm, p_nodes); - set_bit(ib->processor_pxm, p_nodes); - return ia->processor_pxm - ib->processor_pxm; }

+static int initiators_to_nodemask(unsigned long *p_nodes) +{ + struct memory_initiator *initiator; + + if (list_empty(&initiators)) + return -ENXIO; + + list_for_each_entry(initiator, &initiators, node) + set_bit(initiator->processor_pxm, p_nodes); + + return 0; +} + static void hmat_register_target_initiators(struct memory_target *target) { static DECLARE_BITMAP(p_nodes, MAX_NUMNODES); @@ -610,7 +619,10 @@ static void hmat_register_target_initiators(struct memory_target *target) * initiators. */ bitmap_zero(p_nodes, MAX_NUMNODES); - list_sort(p_nodes, &initiators, initiator_cmp); + list_sort(NULL, &initiators, initiator_cmp); + if (initiators_to_nodemask(p_nodes) < 0) + return; + if (!access0done) { for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) { loc = localities_types[i]; @@ -644,7 +656,9 @@ static void hmat_register_target_initiators(struct memory_target *target)

/* Access 1 ignores Generic Initiators */ bitmap_zero(p_nodes, MAX_NUMNODES); - list_sort(p_nodes, &initiators, initiator_cmp); + if (initiators_to_nodemask(p_nodes) < 0) + return; + for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) { loc = localities_types[i]; if (!loc)

From: Jan Dabros jsd@semihalf.com

commit 23393c6461422df5bf8084a086ada9a7e17dc2ba upstream.

Currently tpm transactions are executed unconditionally in tpm_pm_suspend() function, which may lead to races with other tpm accessors in the system.

Specifically, the hw_random tpm driver makes use of tpm_get_random(), and this function is called in a loop from a kthread, which means it's not frozen alongside userspace, and so can race with the work done during system suspend:

tpm tpm0: tpm_transmit: tpm_recv: error -52 tpm tpm0: invalid TPM_STS.x 0xff, dumping stack for forensics CPU: 0 PID: 1 Comm: init Not tainted 6.1.0-rc5+ #135 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.0-20220807_005459-localhost 04/01/2014 Call Trace: tpm_tis_status.cold+0x19/0x20 tpm_transmit+0x13b/0x390 tpm_transmit_cmd+0x20/0x80 tpm1_pm_suspend+0xa6/0x110 tpm_pm_suspend+0x53/0x80 __pnp_bus_suspend+0x35/0xe0 __device_suspend+0x10f/0x350

Fix this by calling tpm_try_get_ops(), which itself is a wrapper around tpm_chip_start(), but takes the appropriate mutex.

Signed-off-by: Jan Dabros jsd@semihalf.com Reported-by: Vlastimil Babka vbabka@suse.cz Tested-by: Jason A. Donenfeld Jason@zx2c4.com Tested-by: Vlastimil Babka vbabka@suse.cz Link: https://lore.kernel.org/all/c5ba47ef-393f-1fba-30bd-1230d1b4b592@suse.cz/ Cc: stable@vger.kernel.org Fixes: e891db1a18bf ("tpm: turn on TPM on suspend for TPM 1.x") [Jason: reworked commit message, added metadata] Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Reviewed-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/tpm/tpm-interface.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -401,13 +401,14 @@ int tpm_pm_suspend(struct device *dev) !pm_suspend_via_firmware()) goto suspended;

- if (!tpm_chip_start(chip)) { + rc = tpm_try_get_ops(chip); + if (!rc) { if (chip->flags & TPM_CHIP_FLAG_TPM2) tpm2_shutdown(chip, TPM2_SU_STATE); else rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);

- tpm_chip_stop(chip); + tpm_put_ops(chip); }

suspended:

From: Christophe Leroy christophe.leroy@csgroup.eu

commit 89d21e259a94f7d5582ec675aa445f5a79f347e4 upstream.

test_bpf tail call tests end up as:

test_bpf: #0 Tail call leaf jited:1 85 PASS test_bpf: #1 Tail call 2 jited:1 111 PASS test_bpf: #2 Tail call 3 jited:1 145 PASS test_bpf: #3 Tail call 4 jited:1 170 PASS test_bpf: #4 Tail call load/store leaf jited:1 190 PASS test_bpf: #5 Tail call load/store jited:1 BUG: Unable to handle kernel data access on write at 0xf1b4e000 Faulting instruction address: 0xbe86b710 Oops: Kernel access of bad area, sig: 11 [#1] BE PAGE_SIZE=4K MMU=Hash PowerMac Modules linked in: test_bpf(+) CPU: 0 PID: 97 Comm: insmod Not tainted 6.1.0-rc4+ #195 Hardware name: PowerMac3,1 750CL 0x87210 PowerMac NIP: be86b710 LR: be857e88 CTR: be86b704 REGS: f1b4df20 TRAP: 0300 Not tainted (6.1.0-rc4+) MSR: 00009032 <EE,ME,IR,DR,RI> CR: 28008242 XER: 00000000 DAR: f1b4e000 DSISR: 42000000 GPR00: 00000001 f1b4dfe0 c11d2280 00000000 00000000 00000000 00000002 00000000 GPR08: f1b4e000 be86b704 f1b4e000 00000000 00000000 100d816a f2440000 fe73baa8 GPR16: f2458000 00000000 c1941ae4 f1fe2248 00000045 c0de0000 f2458030 00000000 GPR24: 000003e8 0000000f f2458000 f1b4dc90 3e584b46 00000000 f24466a0 c1941a00 NIP [be86b710] 0xbe86b710 LR [be857e88] __run_one+0xec/0x264 [test_bpf] Call Trace: [f1b4dfe0] [00000002] 0x2 (unreliable) Instruction dump: XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX ---[ end trace 0000000000000000 ]---

This is a tentative to write above the stack. The problem is encoutered with tests added by commit 38608ee7b690 ("bpf, tests: Add load store test case for tail call")

This happens because tail call is done to a BPF prog with a different stack_depth. At the time being, the stack is kept as is when the caller tail calls its callee. But at exit, the callee restores the stack based on its own properties. Therefore here, at each run, r1 is erroneously increased by 32 - 16 = 16 bytes.

This was done that way in order to pass the tail call count from caller to callee through the stack. As powerpc32 doesn't have a red zone in the stack, it was necessary the maintain the stack as is for the tail call. But it was not anticipated that the BPF frame size could be different.

Let's take a new approach. Use register r4 to carry the tail call count during the tail call, and save it into the stack at function entry if required. This means the input parameter must be in r3, which is more correct as it is a 32 bits parameter, then tail call better match with normal BPF function entry, the down side being that we move that input parameter back and forth between r3 and r4. That can be optimised later.

Doing that also has the advantage of maximising the common parts between tail calls and a normal function exit.

With the fix, tail call tests are now successfull:

test_bpf: #0 Tail call leaf jited:1 53 PASS test_bpf: #1 Tail call 2 jited:1 115 PASS test_bpf: #2 Tail call 3 jited:1 154 PASS test_bpf: #3 Tail call 4 jited:1 165 PASS test_bpf: #4 Tail call load/store leaf jited:1 101 PASS test_bpf: #5 Tail call load/store jited:1 141 PASS test_bpf: #6 Tail call error path, max count reached jited:1 994 PASS test_bpf: #7 Tail call count preserved across function calls jited:1 140975 PASS test_bpf: #8 Tail call error path, NULL target jited:1 110 PASS test_bpf: #9 Tail call error path, index out of range jited:1 69 PASS test_bpf: test_tail_calls: Summary: 10 PASSED, 0 FAILED, [10/10 JIT'ed]

Suggested-by: Naveen N. Rao naveen.n.rao@linux.vnet.ibm.com Fixes: 51c66ad849a7 ("powerpc/bpf: Implement extended BPF on PPC32") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy christophe.leroy@csgroup.eu Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/757acccb7fbfc78efa42dcf3c974b46678198905.166927888... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/net/bpf_jit_comp32.c | 52 +++++++++++++++----------------------- 1 file changed, 21 insertions(+), 31 deletions(-)

--- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -113,23 +113,19 @@ void bpf_jit_build_prologue(u32 *image, { int i;

- /* First arg comes in as a 32 bits pointer. */ - EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3)); - EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0)); + /* Initialize tail_call_cnt, to be skipped if we do tail calls. */ + EMIT(PPC_RAW_LI(_R4, 0)); + +#define BPF_TAILCALL_PROLOGUE_SIZE 4 + EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx)));

- /* - * Initialize tail_call_cnt in stack frame if we do tail calls. - * Otherwise, put in NOPs so that it can be skipped when we are - * invoked through a tail call. - */ if (ctx->seen & SEEN_TAILCALL) - EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1, - bpf_jit_stack_offsetof(ctx, BPF_PPC_TC))); - else - EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_STW(_R4, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));

-#define BPF_TAILCALL_PROLOGUE_SIZE 16 + /* First arg comes in as a 32 bits pointer. */ + EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3)); + EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0));

/* * We need a stack frame, but we don't necessarily need to @@ -170,24 +166,24 @@ static void bpf_jit_emit_common_epilogue for (i = BPF_PPC_NVR_MIN; i <= 31; i++) if (bpf_is_seen_register(ctx, i)) EMIT(PPC_RAW_LWZ(i, _R1, bpf_jit_stack_offsetof(ctx, i))); -} - -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) -{ - EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); - - bpf_jit_emit_common_epilogue(image, ctx); - - /* Tear down our stack frame */

if (ctx->seen & SEEN_FUNC) EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF));

+ /* Tear down our stack frame */ EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME(ctx)));

if (ctx->seen & SEEN_FUNC) EMIT(PPC_RAW_MTLR(_R0));

+} + +void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +{ + EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); + + bpf_jit_emit_common_epilogue(image, ctx); + EMIT(PPC_RAW_BLR()); }

@@ -244,7 +240,6 @@ static int bpf_jit_emit_tail_call(u32 *i EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29)); EMIT(PPC_RAW_ADD(_R3, _R3, b2p_bpf_array)); EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_array, ptrs))); - EMIT(PPC_RAW_STW(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC)));

/* * if (prog == NULL) @@ -255,19 +250,14 @@ static int bpf_jit_emit_tail_call(u32 *i

/* goto *(prog->bpf_func + prologue_size); */ EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func))); - - if (ctx->seen & SEEN_FUNC) - EMIT(PPC_RAW_LWZ(_R0, _R1, BPF_PPC_STACKFRAME(ctx) + PPC_LR_STKOFF)); - EMIT(PPC_RAW_ADDIC(_R3, _R3, BPF_TAILCALL_PROLOGUE_SIZE)); - - if (ctx->seen & SEEN_FUNC) - EMIT(PPC_RAW_MTLR(_R0)); - EMIT(PPC_RAW_MTCTR(_R3));

EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_1)));

+ /* Put tail_call_cnt in r4 */ + EMIT(PPC_RAW_MR(_R4, _R0)); + /* tear restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx);