- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] drm/i915/gem: Fix Virtual Memory mapping boundaries calculation
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Andi Shyti <andi.shyti(a)linux.intel.com> stable inclusion from stable-v4.19.320 commit 3e06073d24807f04b4694108a8474decb7b99e60 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAK3GU CVE: CVE-2024-42259 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 8bdd9ef7e9b1b2a73e394712b72b22055e0e26c3 upstream. Calculating the size of the mapped area as the lesser value between the requested size and the actual size does not consider the partial mapping offset. This can cause page fault access. Fix the calculation of the starting and ending addresses, the total size is now deduced from the difference between the end and start addresses. Additionally, the calculations have been rewritten in a clearer and more understandable form. Fixes: c58305af1835 ("drm/i915: Use remap_io_mapping() to prefault all PTE in a single pass") Reported-by: Jann Horn <jannh(a)google.com> Co-developed-by: Chris Wilson <chris.p.wilson(a)linux.intel.com> Signed-off-by: Chris Wilson <chris.p.wilson(a)linux.intel.com> Signed-off-by: Andi Shyti <andi.shyti(a)linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: Matthew Auld <matthew.auld(a)intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: <stable(a)vger.kernel.org> # v4.9+ Reviewed-by: Jann Horn <jannh(a)google.com> Reviewed-by: Jonathan Cavitt <Jonathan.cavitt(a)intel.com> [Joonas: Add Requires: tag] Requires: 60a2066c5005 ("drm/i915/gem: Adjust vma offset for framebuffer mmap offset") Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240802083850.103694-3-andi.… (cherry picked from commit 97b6784753da06d9d40232328efc5c5367e53417) Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> --- drivers/gpu/drm/i915/i915_gem.c | 47 +++++++++++++++++++++++++++++---- 1 file changed, 42 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b1b207747f39..0835643e9495 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2006,6 +2006,39 @@ compute_partial_view(struct drm_i915_gem_object *obj, return view; } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start += vma->ggtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + /** * i915_gem_fault - fault a page into the GTT * @vmf: fault info @@ -2033,8 +2066,10 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) struct drm_i915_private *dev_priv = to_i915(dev); struct i915_ggtt *ggtt = &dev_priv->ggtt; bool write = !!(vmf->flags & FAULT_FLAG_WRITE); + unsigned long start, end; /* memory boundaries */ struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int ret; /* Sanity check that we allow writing into this object */ @@ -2116,12 +2151,14 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf) if (ret) goto err_unpin; + set_address_limits(area, vma, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn -= vma->ggtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->ggtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] drm/i915/gem: Fix Virtual Memory mapping boundaries calculation
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Andi Shyti <andi.shyti(a)linux.intel.com> stable inclusion from stable-v5.10.224 commit 50111a8098fb9ade621eeff82228a997d42732ab category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMM9L CVE: CVE-2024-42259 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 8bdd9ef7e9b1b2a73e394712b72b22055e0e26c3 upstream. Calculating the size of the mapped area as the lesser value between the requested size and the actual size does not consider the partial mapping offset. This can cause page fault access. Fix the calculation of the starting and ending addresses, the total size is now deduced from the difference between the end and start addresses. Additionally, the calculations have been rewritten in a clearer and more understandable form. Fixes: c58305af1835 ("drm/i915: Use remap_io_mapping() to prefault all PTE in a single pass") Reported-by: Jann Horn <jannh(a)google.com> Co-developed-by: Chris Wilson <chris.p.wilson(a)linux.intel.com> Signed-off-by: Chris Wilson <chris.p.wilson(a)linux.intel.com> Signed-off-by: Andi Shyti <andi.shyti(a)linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: Matthew Auld <matthew.auld(a)intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: <stable(a)vger.kernel.org> # v4.9+ Reviewed-by: Jann Horn <jannh(a)google.com> Reviewed-by: Jonathan Cavitt <Jonathan.cavitt(a)intel.com> [Joonas: Add Requires: tag] Requires: 60a2066c5005 ("drm/i915/gem: Adjust vma offset for framebuffer mmap offset") Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240802083850.103694-3-andi.… (cherry picked from commit 97b6784753da06d9d40232328efc5c5367e53417) Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 53 +++++++++++++++++++++--- 1 file changed, 47 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 92dd65befbcb..edbd363afb00 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -272,6 +272,41 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) return i915_error_to_vmf_fault(err); } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long obj_offset, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start -= obj_offset; + start += vma->ggtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) { #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) @@ -284,14 +319,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct i915_ggtt *ggtt = &i915->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; + unsigned long obj_offset; + unsigned long start, end; /* memory boundaries */ intel_wakeref_t wakeref; struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int srcu; int ret; - /* We don't use vmf->pgoff since that has the fake offset */ + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; + page_offset += obj_offset; trace_i915_gem_object_fault(obj, page_offset, true, write); @@ -362,12 +401,14 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) if (ret) goto err_unpin; + set_address_limits(area, vma, obj_offset, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn += obj_offset - vma->ggtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->ggtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; -- 2.34.1

2 1

[PATCH OLK-5.10] drm/i915/gem: Fix Virtual Memory mapping boundaries calculation
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Andi Shyti <andi.shyti(a)linux.intel.com> stable inclusion from stable-v5.10.224 commit 50111a8098fb9ade621eeff82228a997d42732ab category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMM9L CVE: CVE-2024-42259 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 8bdd9ef7e9b1b2a73e394712b72b22055e0e26c3 upstream. Calculating the size of the mapped area as the lesser value between the requested size and the actual size does not consider the partial mapping offset. This can cause page fault access. Fix the calculation of the starting and ending addresses, the total size is now deduced from the difference between the end and start addresses. Additionally, the calculations have been rewritten in a clearer and more understandable form. Fixes: c58305af1835 ("drm/i915: Use remap_io_mapping() to prefault all PTE in a single pass") Reported-by: Jann Horn <jannh(a)google.com> Co-developed-by: Chris Wilson <chris.p.wilson(a)linux.intel.com> Signed-off-by: Chris Wilson <chris.p.wilson(a)linux.intel.com> Signed-off-by: Andi Shyti <andi.shyti(a)linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: Matthew Auld <matthew.auld(a)intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: <stable(a)vger.kernel.org> # v4.9+ Reviewed-by: Jann Horn <jannh(a)google.com> Reviewed-by: Jonathan Cavitt <Jonathan.cavitt(a)intel.com> [Joonas: Add Requires: tag] Requires: 60a2066c5005 ("drm/i915/gem: Adjust vma offset for framebuffer mmap offset") Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240802083850.103694-3-andi.… (cherry picked from commit 97b6784753da06d9d40232328efc5c5367e53417) Signed-off-by: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 53 +++++++++++++++++++++--- 1 file changed, 47 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 01a88b03bc6d..0021b039b72b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -273,6 +273,41 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf) return i915_error_to_vmf_fault(err); } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long obj_offset, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start -= obj_offset; + start += vma->ggtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) { #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) @@ -285,14 +320,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct i915_ggtt *ggtt = &i915->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; + unsigned long obj_offset; + unsigned long start, end; /* memory boundaries */ intel_wakeref_t wakeref; struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int srcu; int ret; - /* We don't use vmf->pgoff since that has the fake offset */ + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; + page_offset += obj_offset; trace_i915_gem_object_fault(obj, page_offset, true, write); @@ -363,12 +402,14 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) if (ret) goto err_unpin; + set_address_limits(area, vma, obj_offset, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn += obj_offset - vma->ggtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->ggtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; -- 2.34.1

2 1

[PATCH OLK-5.10] mlxsw: spectrum_acl_erp: Fix object nesting warning
by Dong Chenchen 03 Sep '24

03 Sep '24

From: Ido Schimmel <idosch(a)nvidia.com> stable inclusion from stable-v5.10.223 commit 36a9996e020dd5aa325e0ecc55eb2328288ea6bb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IALEAO CVE: CVE-2024-43880 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 97d833ceb27dc19f8777d63f90be4a27b5daeedf ] ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM (A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can contain more ACLs (i.e., tc filters), but the number of masks in each region (i.e., tc chain) is limited. In order to mitigate the effects of the above limitation, the device allows filters to share a single mask if their masks only differ in up to 8 consecutive bits. For example, dst_ip/25 can be represented using dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the number of masks being used (and therefore does not support mask aggregation), but can contain a limited number of filters. The driver uses the "objagg" library to perform the mask aggregation by passing it objects that consist of the filter's mask and whether the filter is to be inserted into the A-TCAM or the C-TCAM since filters in different TCAMs cannot share a mask. The set of created objects is dependent on the insertion order of the filters and is not necessarily optimal. Therefore, the driver will periodically ask the library to compute a more optimal set ("hints") by looking at all the existing objects. When the library asks the driver whether two objects can be aggregated the driver only compares the provided masks and ignores the A-TCAM / C-TCAM indication. This is the right thing to do since the goal is to move as many filters as possible to the A-TCAM. The driver also forbids two identical masks from being aggregated since this can only happen if one was intentionally put in the C-TCAM to avoid a conflict in the A-TCAM. The above can result in the following set of hints: H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta After getting the hints from the library the driver will start migrating filters from one region to another while consulting the computed hints and instructing the device to perform a lookup in both regions during the transition. Assuming a filter with mask X is being migrated into the A-TCAM in the new region, the hints lookup will return H1. Since H2 is the parent of H1, the library will try to find the object associated with it and create it if necessary in which case another hints lookup (recursive) will be performed. This hints lookup for {mask Y, A-TCAM} will either return H2 or H3 since the driver passes the library an object comparison function that ignores the A-TCAM / C-TCAM indication. This can eventually lead to nested objects which are not supported by the library [1]. Fix by removing the object comparison function from both the driver and the library as the driver was the only user. That way the lookup will only return exact matches. I do not have a reliable reproducer that can reproduce the issue in a timely manner, but before the fix the issue would reproduce in several minutes and with the fix it does not reproduce in over an hour. Note that the current usefulness of the hints is limited because they include the C-TCAM indication and represent aggregation that cannot actually happen. This will be addressed in net-next. [1] WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0 Modules linked in: CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42 Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0 [...] Call Trace: <TASK> __objagg_obj_get+0x2bb/0x580 objagg_obj_get+0xe/0x80 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Tested-by: Alexander Zubkov <green(a)qrator.net> Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- .../ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ------------- include/linux/objagg.h | 1 - lib/objagg.c | 15 --------------- 3 files changed, 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index d231f4d2888b..9eee229303cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, return err ? false : true; } -static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) -{ - const struct mlxsw_sp_acl_erp_key *key1 = obj1; - const struct mlxsw_sp_acl_erp_key *key2 = obj2; - - /* For hints purposes, two objects are considered equal - * in case the masks are the same. Does not matter what - * the "ctcam" value is. - */ - return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); -} - static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), .delta_check = mlxsw_sp_acl_erp_delta_check, - .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/lib/objagg.c b/lib/objagg.c index 5e1676ccdadd..6917d5974345 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -906,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -958,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] mlxsw: spectrum_acl_erp: Fix object nesting warning
by Dong Chenchen 03 Sep '24

03 Sep '24

From: Ido Schimmel <idosch(a)nvidia.com> stable inclusion from stable-v5.10.223 commit 36a9996e020dd5aa325e0ecc55eb2328288ea6bb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IALEAO CVE: CVE-2024-43880 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 97d833ceb27dc19f8777d63f90be4a27b5daeedf ] ACLs in Spectrum-2 and newer ASICs can reside in the algorithmic TCAM (A-TCAM) or in the ordinary circuit TCAM (C-TCAM). The former can contain more ACLs (i.e., tc filters), but the number of masks in each region (i.e., tc chain) is limited. In order to mitigate the effects of the above limitation, the device allows filters to share a single mask if their masks only differ in up to 8 consecutive bits. For example, dst_ip/25 can be represented using dst_ip/24 with a delta of 1 bit. The C-TCAM does not have a limit on the number of masks being used (and therefore does not support mask aggregation), but can contain a limited number of filters. The driver uses the "objagg" library to perform the mask aggregation by passing it objects that consist of the filter's mask and whether the filter is to be inserted into the A-TCAM or the C-TCAM since filters in different TCAMs cannot share a mask. The set of created objects is dependent on the insertion order of the filters and is not necessarily optimal. Therefore, the driver will periodically ask the library to compute a more optimal set ("hints") by looking at all the existing objects. When the library asks the driver whether two objects can be aggregated the driver only compares the provided masks and ignores the A-TCAM / C-TCAM indication. This is the right thing to do since the goal is to move as many filters as possible to the A-TCAM. The driver also forbids two identical masks from being aggregated since this can only happen if one was intentionally put in the C-TCAM to avoid a conflict in the A-TCAM. The above can result in the following set of hints: H1: {mask X, A-TCAM} -> H2: {mask Y, A-TCAM} // X is Y + delta H3: {mask Y, C-TCAM} -> H4: {mask Z, A-TCAM} // Y is Z + delta After getting the hints from the library the driver will start migrating filters from one region to another while consulting the computed hints and instructing the device to perform a lookup in both regions during the transition. Assuming a filter with mask X is being migrated into the A-TCAM in the new region, the hints lookup will return H1. Since H2 is the parent of H1, the library will try to find the object associated with it and create it if necessary in which case another hints lookup (recursive) will be performed. This hints lookup for {mask Y, A-TCAM} will either return H2 or H3 since the driver passes the library an object comparison function that ignores the A-TCAM / C-TCAM indication. This can eventually lead to nested objects which are not supported by the library [1]. Fix by removing the object comparison function from both the driver and the library as the driver was the only user. That way the lookup will only return exact matches. I do not have a reliable reproducer that can reproduce the issue in a timely manner, but before the fix the issue would reproduce in several minutes and with the fix it does not reproduce in over an hour. Note that the current usefulness of the hints is limited because they include the C-TCAM indication and represent aggregation that cannot actually happen. This will be addressed in net-next. [1] WARNING: CPU: 0 PID: 153 at lib/objagg.c:170 objagg_obj_parent_assign+0xb5/0xd0 Modules linked in: CPU: 0 PID: 153 Comm: kworker/0:18 Not tainted 6.9.0-rc6-custom-g70fbc2c1c38b #42 Hardware name: Mellanox Technologies Ltd. MSN3700C/VMOD0008, BIOS 5.11 10/10/2018 Workqueue: mlxsw_core mlxsw_sp_acl_tcam_vregion_rehash_work RIP: 0010:objagg_obj_parent_assign+0xb5/0xd0 [...] Call Trace: <TASK> __objagg_obj_get+0x2bb/0x580 objagg_obj_get+0xe/0x80 mlxsw_sp_acl_erp_mask_get+0xb5/0xf0 mlxsw_sp_acl_atcam_entry_add+0xe8/0x3c0 mlxsw_sp_acl_tcam_entry_create+0x5e/0xa0 mlxsw_sp_acl_tcam_vchunk_migrate_one+0x16b/0x270 mlxsw_sp_acl_tcam_vregion_rehash_work+0xbe/0x510 process_one_work+0x151/0x370 Fixes: 9069a3817d82 ("lib: objagg: implement optimization hints assembly and use hints for object creation") Signed-off-by: Ido Schimmel <idosch(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Tested-by: Alexander Zubkov <green(a)qrator.net> Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- .../ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ------------- include/linux/objagg.h | 1 - lib/objagg.c | 15 --------------- 3 files changed, 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index d231f4d2888b..9eee229303cc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, return err ? false : true; } -static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) -{ - const struct mlxsw_sp_acl_erp_key *key1 = obj1; - const struct mlxsw_sp_acl_erp_key *key2 = obj2; - - /* For hints purposes, two objects are considered equal - * in case the masks are the same. Does not matter what - * the "ctcam" value is. - */ - return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); -} - static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), .delta_check = mlxsw_sp_acl_erp_delta_check, - .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/lib/objagg.c b/lib/objagg.c index 5e1676ccdadd..6917d5974345 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -906,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = { [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, }; -static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, - const void *obj) -{ - struct rhashtable *ht = arg->ht; - struct objagg_hints *objagg_hints = - container_of(ht, struct objagg_hints, node_ht); - const struct objagg_ops *ops = objagg_hints->ops; - const char *ptr = obj; - - ptr += ht->p.key_offset; - return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : - memcmp(ptr, arg->key, ht->p.key_len); -} - /** * objagg_hints_get - obtains hints instance * @objagg: objagg instance @@ -958,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg, offsetof(struct objagg_hints_node, obj); objagg_hints->ht_params.head_offset = offsetof(struct objagg_hints_node, ht_node); - objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); if (err) -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] xdp: fix invalid wait context of page_pool_destroy()
by Dong Chenchen 03 Sep '24

03 Sep '24

From: Taehee Yoo <ap420073(a)gmail.com> stable inclusion from stable-v5.10.224 commit be9d08ff102df3ac4f66e826ea935cf3af63a4bd category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAKQ5B CVE: CVE-2024-43834 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 59a931c5b732ca5fc2ca727f5a72aeabaafa85ec ] If the driver uses a page pool, it creates a page pool with page_pool_create(). The reference count of page pool is 1 as default. A page pool will be destroyed only when a reference count reaches 0. page_pool_destroy() is used to destroy page pool, it decreases a reference count. When a page pool is destroyed, ->disconnect() is called, which is mem_allocator_disconnect(). This function internally acquires mutex_lock(). If the driver uses XDP, it registers a memory model with xdp_rxq_info_reg_mem_model(). The xdp_rxq_info_reg_mem_model() internally increases a page pool reference count if a memory model is a page pool. Now the reference count is 2. To destroy a page pool, the driver should call both page_pool_destroy() and xdp_unreg_mem_model(). The xdp_unreg_mem_model() internally calls page_pool_destroy(). Only page_pool_destroy() decreases a reference count. If a driver calls page_pool_destroy() then xdp_unreg_mem_model(), we will face an invalid wait context warning. Because xdp_unreg_mem_model() calls page_pool_destroy() with rcu_read_lock(). The page_pool_destroy() internally acquires mutex_lock(). Splat looks like: ============================= [ BUG: Invalid wait context ] 6.10.0-rc6+ #4 Tainted: G W ----------------------------- ethtool/1806 is trying to lock: ffffffff90387b90 (mem_id_lock){+.+.}-{4:4}, at: mem_allocator_disconnect+0x73/0x150 other info that might help us debug this: context-{5:5} 3 locks held by ethtool/1806: stack backtrace: CPU: 0 PID: 1806 Comm: ethtool Tainted: G W 6.10.0-rc6+ #4 f916f41f172891c800f2fed Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021 Call Trace: <TASK> dump_stack_lvl+0x7e/0xc0 __lock_acquire+0x1681/0x4de0 ? _printk+0x64/0xe0 ? __pfx_mark_lock.part.0+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 lock_acquire+0x1b3/0x580 ? mem_allocator_disconnect+0x73/0x150 ? __wake_up_klogd.part.0+0x16/0xc0 ? __pfx_lock_acquire+0x10/0x10 ? dump_stack_lvl+0x91/0xc0 __mutex_lock+0x15c/0x1690 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_prb_read_valid+0x10/0x10 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_llist_add_batch+0x10/0x10 ? console_unlock+0x193/0x1b0 ? lockdep_hardirqs_on+0xbe/0x140 ? __pfx___mutex_lock+0x10/0x10 ? tick_nohz_tick_stopped+0x16/0x90 ? __irq_work_queue_local+0x1e5/0x330 ? irq_work_queue+0x39/0x50 ? __wake_up_klogd.part.0+0x79/0xc0 ? mem_allocator_disconnect+0x73/0x150 mem_allocator_disconnect+0x73/0x150 ? __pfx_mem_allocator_disconnect+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? rcu_is_watching+0x11/0xb0 page_pool_release+0x36e/0x6d0 page_pool_destroy+0xd7/0x440 xdp_unreg_mem_model+0x1a7/0x2a0 ? __pfx_xdp_unreg_mem_model+0x10/0x10 ? kfree+0x125/0x370 ? bnxt_free_ring.isra.0+0x2eb/0x500 ? bnxt_free_mem+0x5ac/0x2500 xdp_rxq_info_unreg+0x4a/0xd0 bnxt_free_mem+0x1356/0x2500 bnxt_close_nic+0xf0/0x3b0 ? __pfx_bnxt_close_nic+0x10/0x10 ? ethnl_parse_bit+0x2c6/0x6d0 ? __pfx___nla_validate_parse+0x10/0x10 ? __pfx_ethnl_parse_bit+0x10/0x10 bnxt_set_features+0x2a8/0x3e0 __netdev_update_features+0x4dc/0x1370 ? ethnl_parse_bitset+0x4ff/0x750 ? __pfx_ethnl_parse_bitset+0x10/0x10 ? __pfx___netdev_update_features+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? _raw_spin_unlock_irqrestore+0x42/0x70 ? __pm_runtime_resume+0x7d/0x110 ethnl_set_features+0x32d/0xa20 To fix this problem, it uses rhashtable_lookup_fast() instead of rhashtable_lookup() with rcu_read_lock(). Using xa without rcu_read_lock() here is safe. xa is freed by __xdp_mem_allocator_rcu_free() and this is called by call_rcu() of mem_xa_remove(). The mem_xa_remove() is called by page_pool_destroy() if a reference count reaches 0. The xa is already protected by the reference count mechanism well in the control plane. So removing rcu_read_lock() for page_pool_destroy() is safe. Fixes: c3f812cea0d7 ("page_pool: do not release pool until inflight == 0.") Signed-off-by: Taehee Yoo <ap420073(a)gmail.com> Reviewed-by: Jakub Kicinski <kuba(a)kernel.org> Link: https://patch.msgid.link/20240712095116.3801586-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/xdp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/core/xdp.c b/net/core/xdp.c index fd98d6059007..b2ad644df21f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -124,10 +124,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem) return; if (type == MEM_TYPE_PAGE_POOL) { - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); - rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); -- 2.25.1

2 1

[PATCH OLK-5.10] xdp: fix invalid wait context of page_pool_destroy()
by Dong Chenchen 03 Sep '24

03 Sep '24

From: Taehee Yoo <ap420073(a)gmail.com> stable inclusion from stable-v5.10.224 commit be9d08ff102df3ac4f66e826ea935cf3af63a4bd category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAKQ5B CVE: CVE-2024-43834 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 59a931c5b732ca5fc2ca727f5a72aeabaafa85ec ] If the driver uses a page pool, it creates a page pool with page_pool_create(). The reference count of page pool is 1 as default. A page pool will be destroyed only when a reference count reaches 0. page_pool_destroy() is used to destroy page pool, it decreases a reference count. When a page pool is destroyed, ->disconnect() is called, which is mem_allocator_disconnect(). This function internally acquires mutex_lock(). If the driver uses XDP, it registers a memory model with xdp_rxq_info_reg_mem_model(). The xdp_rxq_info_reg_mem_model() internally increases a page pool reference count if a memory model is a page pool. Now the reference count is 2. To destroy a page pool, the driver should call both page_pool_destroy() and xdp_unreg_mem_model(). The xdp_unreg_mem_model() internally calls page_pool_destroy(). Only page_pool_destroy() decreases a reference count. If a driver calls page_pool_destroy() then xdp_unreg_mem_model(), we will face an invalid wait context warning. Because xdp_unreg_mem_model() calls page_pool_destroy() with rcu_read_lock(). The page_pool_destroy() internally acquires mutex_lock(). Splat looks like: ============================= [ BUG: Invalid wait context ] 6.10.0-rc6+ #4 Tainted: G W ----------------------------- ethtool/1806 is trying to lock: ffffffff90387b90 (mem_id_lock){+.+.}-{4:4}, at: mem_allocator_disconnect+0x73/0x150 other info that might help us debug this: context-{5:5} 3 locks held by ethtool/1806: stack backtrace: CPU: 0 PID: 1806 Comm: ethtool Tainted: G W 6.10.0-rc6+ #4 f916f41f172891c800f2fed Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021 Call Trace: <TASK> dump_stack_lvl+0x7e/0xc0 __lock_acquire+0x1681/0x4de0 ? _printk+0x64/0xe0 ? __pfx_mark_lock.part.0+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 lock_acquire+0x1b3/0x580 ? mem_allocator_disconnect+0x73/0x150 ? __wake_up_klogd.part.0+0x16/0xc0 ? __pfx_lock_acquire+0x10/0x10 ? dump_stack_lvl+0x91/0xc0 __mutex_lock+0x15c/0x1690 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_prb_read_valid+0x10/0x10 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_llist_add_batch+0x10/0x10 ? console_unlock+0x193/0x1b0 ? lockdep_hardirqs_on+0xbe/0x140 ? __pfx___mutex_lock+0x10/0x10 ? tick_nohz_tick_stopped+0x16/0x90 ? __irq_work_queue_local+0x1e5/0x330 ? irq_work_queue+0x39/0x50 ? __wake_up_klogd.part.0+0x79/0xc0 ? mem_allocator_disconnect+0x73/0x150 mem_allocator_disconnect+0x73/0x150 ? __pfx_mem_allocator_disconnect+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? rcu_is_watching+0x11/0xb0 page_pool_release+0x36e/0x6d0 page_pool_destroy+0xd7/0x440 xdp_unreg_mem_model+0x1a7/0x2a0 ? __pfx_xdp_unreg_mem_model+0x10/0x10 ? kfree+0x125/0x370 ? bnxt_free_ring.isra.0+0x2eb/0x500 ? bnxt_free_mem+0x5ac/0x2500 xdp_rxq_info_unreg+0x4a/0xd0 bnxt_free_mem+0x1356/0x2500 bnxt_close_nic+0xf0/0x3b0 ? __pfx_bnxt_close_nic+0x10/0x10 ? ethnl_parse_bit+0x2c6/0x6d0 ? __pfx___nla_validate_parse+0x10/0x10 ? __pfx_ethnl_parse_bit+0x10/0x10 bnxt_set_features+0x2a8/0x3e0 __netdev_update_features+0x4dc/0x1370 ? ethnl_parse_bitset+0x4ff/0x750 ? __pfx_ethnl_parse_bitset+0x10/0x10 ? __pfx___netdev_update_features+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? _raw_spin_unlock_irqrestore+0x42/0x70 ? __pm_runtime_resume+0x7d/0x110 ethnl_set_features+0x32d/0xa20 To fix this problem, it uses rhashtable_lookup_fast() instead of rhashtable_lookup() with rcu_read_lock(). Using xa without rcu_read_lock() here is safe. xa is freed by __xdp_mem_allocator_rcu_free() and this is called by call_rcu() of mem_xa_remove(). The mem_xa_remove() is called by page_pool_destroy() if a reference count reaches 0. The xa is already protected by the reference count mechanism well in the control plane. So removing rcu_read_lock() for page_pool_destroy() is safe. Fixes: c3f812cea0d7 ("page_pool: do not release pool until inflight == 0.") Signed-off-by: Taehee Yoo <ap420073(a)gmail.com> Reviewed-by: Jakub Kicinski <kuba(a)kernel.org> Link: https://patch.msgid.link/20240712095116.3801586-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/core/xdp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/core/xdp.c b/net/core/xdp.c index fd98d6059007..b2ad644df21f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -124,10 +124,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem) return; if (type == MEM_TYPE_PAGE_POOL) { - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); - rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS v4 00/30] support block hierarchy stats
by Yu Kuai 03 Sep '24

03 Sep '24

Changes in v4: - remove changes to cfq in patch 2, also fix kabi change for blk-wbt in patch 2; - check q->mq_ops from the only caller from blk-flush.c in patch 12; Changes in v3: - fix patch 7 format; Changes in v2: - find_get_pid(current->pid); -> get_pid(task_pid(current)); - check q->mq_ops in blk_mq_get_alloc_task(); - remove blk_mq_debugfs_unregister_hierarchy_stats(); - include cgroup_path() inside CONFIG_BLK_CGROUP; Bart Van Assche (1): blk-mq: remove blk_mq_put_ctx() Jens Axboe (4): block: add blk_time_get_ns() and blk_time_get() helpers block: cache current nsec time in struct blk_plug block: update cached timestamp post schedule/preemption block: limit block time caching to in_task() context Yu Kuai (25): blk-mq: export blk-mq-debugfs apis block: fix that blk_time_get_ns() doesn't update time after schedule block: fix kabi broken in struct blk_plug block: support to recored bio allocation time block: support to recored bio allocation task block: support to recored bio allocation time in request block: fix kabi broken for struct request block: support to recored bio allocation task in request block: block: fix kabi broken for struct blk_mq_alloc_data blk-mq-debugfs: factor out a new helper to show allocated request block: support to record when request is completed block-io-hierarchy: core hierarchy stats implementation block-io-hierarchy: core hierarchy iodump implementation blk-io-hierarchy: support to recored the number of slow IO blk-io-hierarchy: support new bio based stage blk-throtl blk-io-hierarchy: support new bio based stage blk-wbt blk-io-hierarchy: support new bio based stage gettag blk-io-hierarchy: support new rq based stage plug blk-io-hierarchy: support new rq based stage mq-deadline blk-io-hierarchy: support new rq based stage bfq blk-io-hierarchy: support new rq based stage kyber blk-io-hierarchy: support new rq based stage hctx blk-io-hierarchy: support new rq based stage requeue blk-io-hierarchy: support new rq based stage rq_driver blk-io-hierarchy: support new stage for bio lifetime arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/Kconfig | 8 + block/Makefile | 1 + block/bfq-cgroup.c | 15 +- block/bfq-iosched.c | 34 +- block/bio.c | 17 + block/blk-cgroup.c | 2 +- block/blk-core.c | 37 +- block/blk-flush.c | 21 +- block/blk-io-hierarchy/Kconfig | 145 +++++ block/blk-io-hierarchy/Makefile | 8 + block/blk-io-hierarchy/debugfs.c | 230 ++++++++ block/blk-io-hierarchy/iodump.c | 756 +++++++++++++++++++++++++ block/blk-io-hierarchy/iodump.h | 103 ++++ block/blk-io-hierarchy/stats.c | 429 ++++++++++++++ block/blk-io-hierarchy/stats.h | 371 ++++++++++++ block/blk-iolatency.c | 6 +- block/blk-merge.c | 1 + block/blk-mq-debugfs.c | 21 +- block/blk-mq-debugfs.h | 10 + block/blk-mq-sched.c | 7 +- block/blk-mq-tag.c | 13 +- block/blk-mq.c | 76 ++- block/blk-mq.h | 56 +- block/blk-sysfs.c | 16 + block/blk-throttle.c | 29 +- block/blk-wbt.c | 15 +- block/blk.h | 89 ++- block/kyber-iosched.c | 10 +- block/mq-deadline.c | 15 +- include/linux/blk_types.h | 55 +- include/linux/blkdev.h | 16 + include/linux/sched.h | 2 + kernel/sched/core.c | 6 +- 35 files changed, 2533 insertions(+), 89 deletions(-) create mode 100644 block/blk-io-hierarchy/Kconfig create mode 100644 block/blk-io-hierarchy/Makefile create mode 100644 block/blk-io-hierarchy/debugfs.c create mode 100644 block/blk-io-hierarchy/iodump.c create mode 100644 block/blk-io-hierarchy/iodump.h create mode 100644 block/blk-io-hierarchy/stats.c create mode 100644 block/blk-io-hierarchy/stats.h -- 2.39.2

2 31

[PATCH openEuler-1.0-LTS] nilfs2: handle inconsistent state in nilfs_btnode_create_block()
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> stable inclusion from stable-v4.19.320 commit 19cce46238ffe3546e44b9c74057103ff8b24c62 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0L CVE: CVE-2024-42295 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4811f7af6090e8f5a398fbdd766f903ef6c0d787 upstream. Syzbot reported that a buffer state inconsistency was detected in nilfs_btnode_create_block(), triggering a kernel bug. It is not appropriate to treat this inconsistency as a bug; it can occur if the argument block address (the buffer index of the newly created block) is a virtual block number and has been reallocated due to corruption of the bitmap used to manage its allocation state. So, modify nilfs_btnode_create_block() and its callers to treat it as a possible filesystem error, rather than triggering a kernel bug. Link: https://lkml.kernel.org/r/20240725052007.4562-1-konishi.ryusuke@gmail.com Fixes: a60be987d45d ("nilfs2: B-tree node cache") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+89cc4f2324ed37988b60(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=89cc4f2324ed37988b60 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/nilfs2/btnode.c | 25 ++++++++++++++++++++----- fs/nilfs2/btree.c | 4 ++-- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index ebb24a314f43..050cdb256da8 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -34,12 +34,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); if (unlikely(!bh)) - return NULL; + return ERR_PTR(-ENOMEM); if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) || buffer_dirty(bh))) { - brelse(bh); - BUG(); + /* + * The block buffer at the specified new address was already + * in use. This can happen if it is a virtual block number + * and has been reallocated due to corruption of the bitmap + * used to manage its allocation state (if not, the buffer + * clearing of an abandoned b-tree node is missing somewhere). + */ + nilfs_error(inode->i_sb, + "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)", + (unsigned long long)blocknr, inode->i_ino); + goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; @@ -50,6 +59,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) unlock_page(bh->b_page); put_page(bh->b_page); return bh; + +failed: + unlock_page(bh->b_page); + put_page(bh->b_page); + brelse(bh); + return ERR_PTR(-EIO); } int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, @@ -207,8 +222,8 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, } nbh = nilfs_btnode_create_block(btnc, newkey); - if (!nbh) - return -ENOMEM; + if (IS_ERR(nbh)) + return PTR_ERR(nbh); BUG_ON(nbh == obh); ctxt->newbh = nbh; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 7959d3c34d20..0e396e22b7b2 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -62,8 +62,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); - if (!bh) - return -ENOMEM; + if (IS_ERR(bh)) + return PTR_ERR(bh); set_buffer_nilfs_volatile(bh); *bhp = bh; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] nilfs2: handle inconsistent state in nilfs_btnode_create_block()
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> stable inclusion from stable-v5.10.224 commit 5f0a6800b8aec1b453c7fe4c44fcaac5ffe9d52e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0L CVE: CVE-2024-42295 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4811f7af6090e8f5a398fbdd766f903ef6c0d787 upstream. Syzbot reported that a buffer state inconsistency was detected in nilfs_btnode_create_block(), triggering a kernel bug. It is not appropriate to treat this inconsistency as a bug; it can occur if the argument block address (the buffer index of the newly created block) is a virtual block number and has been reallocated due to corruption of the bitmap used to manage its allocation state. So, modify nilfs_btnode_create_block() and its callers to treat it as a possible filesystem error, rather than triggering a kernel bug. Link: https://lkml.kernel.org/r/20240725052007.4562-1-konishi.ryusuke@gmail.com Fixes: a60be987d45d ("nilfs2: B-tree node cache") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+89cc4f2324ed37988b60(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=89cc4f2324ed37988b60 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/nilfs2/btnode.c | 25 ++++++++++++++++++++----- fs/nilfs2/btree.c | 4 ++-- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index e00e184b1261..793bd853d564 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -51,12 +51,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); if (unlikely(!bh)) - return NULL; + return ERR_PTR(-ENOMEM); if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) || buffer_dirty(bh))) { - brelse(bh); - BUG(); + /* + * The block buffer at the specified new address was already + * in use. This can happen if it is a virtual block number + * and has been reallocated due to corruption of the bitmap + * used to manage its allocation state (if not, the buffer + * clearing of an abandoned b-tree node is missing somewhere). + */ + nilfs_error(inode->i_sb, + "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)", + (unsigned long long)blocknr, inode->i_ino); + goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; @@ -67,6 +76,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) unlock_page(bh->b_page); put_page(bh->b_page); return bh; + +failed: + unlock_page(bh->b_page); + put_page(bh->b_page); + brelse(bh); + return ERR_PTR(-EIO); } int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, @@ -217,8 +232,8 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, } nbh = nilfs_btnode_create_block(btnc, newkey); - if (!nbh) - return -ENOMEM; + if (IS_ERR(nbh)) + return PTR_ERR(nbh); BUG_ON(nbh == obh); ctxt->newbh = nbh; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 77efd69213a3..270c5422df86 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -63,8 +63,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); - if (!bh) - return -ENOMEM; + if (IS_ERR(bh)) + return PTR_ERR(bh); set_buffer_nilfs_volatile(bh); *bhp = bh; -- 2.34.1

2 1

[PATCH OLK-5.10] nilfs2: handle inconsistent state in nilfs_btnode_create_block()
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> stable inclusion from stable-v5.10.224 commit 5f0a6800b8aec1b453c7fe4c44fcaac5ffe9d52e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0L CVE: CVE-2024-42295 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4811f7af6090e8f5a398fbdd766f903ef6c0d787 upstream. Syzbot reported that a buffer state inconsistency was detected in nilfs_btnode_create_block(), triggering a kernel bug. It is not appropriate to treat this inconsistency as a bug; it can occur if the argument block address (the buffer index of the newly created block) is a virtual block number and has been reallocated due to corruption of the bitmap used to manage its allocation state. So, modify nilfs_btnode_create_block() and its callers to treat it as a possible filesystem error, rather than triggering a kernel bug. Link: https://lkml.kernel.org/r/20240725052007.4562-1-konishi.ryusuke@gmail.com Fixes: a60be987d45d ("nilfs2: B-tree node cache") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+89cc4f2324ed37988b60(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=89cc4f2324ed37988b60 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/nilfs2/btnode.c | 25 ++++++++++++++++++++----- fs/nilfs2/btree.c | 4 ++-- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 1776121677e2..28a726553318 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -51,12 +51,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node)); if (unlikely(!bh)) - return NULL; + return ERR_PTR(-ENOMEM); if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) || buffer_dirty(bh))) { - brelse(bh); - BUG(); + /* + * The block buffer at the specified new address was already + * in use. This can happen if it is a virtual block number + * and has been reallocated due to corruption of the bitmap + * used to manage its allocation state (if not, the buffer + * clearing of an abandoned b-tree node is missing somewhere). + */ + nilfs_error(inode->i_sb, + "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)", + (unsigned long long)blocknr, inode->i_ino); + goto failed; } memset(bh->b_data, 0, i_blocksize(inode)); bh->b_bdev = inode->i_sb->s_bdev; @@ -67,6 +76,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr) unlock_page(bh->b_page); put_page(bh->b_page); return bh; + +failed: + unlock_page(bh->b_page); + put_page(bh->b_page); + brelse(bh); + return ERR_PTR(-EIO); } int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr, @@ -217,8 +232,8 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc, } nbh = nilfs_btnode_create_block(btnc, newkey); - if (!nbh) - return -ENOMEM; + if (IS_ERR(nbh)) + return PTR_ERR(nbh); BUG_ON(nbh == obh); ctxt->newbh = nbh; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 4905b7cd7bf3..a426e4e2acda 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -63,8 +63,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree, struct buffer_head *bh; bh = nilfs_btnode_create_block(btnc, ptr); - if (!bh) - return -ENOMEM; + if (IS_ERR(bh)) + return PTR_ERR(bh); set_buffer_nilfs_volatile(bh); *bhp = bh; -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] ibmvnic: free reset-work-item when flushing
by Dong Chenchen 03 Sep '24

03 Sep '24

From: Sukadev Bhattiprolu <sukadev(a)linux.ibm.com> stable inclusion from stable-v4.19.233 commit 786576c03b313a9ff6585458aa0dfd039d897f51 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IALPUM CVE: CVE-2022-48905 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 8d0657f39f487d904fca713e0bc39c2707382553 upstream. Fix a tiny memory leak when flushing the reset work queue. Fixes: 2770a7984db5 ("ibmvnic: Introduce hard reset recovery") Signed-off-by: Sukadev Bhattiprolu <sukadev(a)linux.ibm.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- drivers/net/ethernet/ibm/ibmvnic.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 8a1916443235..1e9193b8ad94 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2081,8 +2081,10 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, * flush reset queue and process this reset */ if (adapter->force_reset_recovery && !list_empty(&adapter->rwi_list)) { - list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) + list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) { list_del(entry); + kfree(list_entry(entry, struct ibmvnic_rwi, list)); + } } rwi->reset_reason = reason; list_add_tail(&rwi->list, &adapter->rwi_list); -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.6.47 commit ae00e6536a2dd54b64b39e9a39548870cf835745 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMMF CVE: CVE-2024-44942 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit fc01008c92f40015aeeced94750855a7111b6929 ] syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing. Reported-by: syzbot+848062ba19c8782ca5c8(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000d103ce06174d7ec3@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/f2fs/gc.c [Code logic conflict, f2fs_info_ratelimited was introduced since commit b1c9d3f833ba ("f2fs: support printk_ratelimited() in f2fs_printk()"), so replace it with f2fs_msg, and f2fs_gc_pinned_control was introduced since commit 71419129625a ("f2fs: give priority to select unpinned section for foreground GC"), ingore it.] Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/f2fs/gc.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index f4f7b8feebef..6db285a8af33 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -957,6 +957,16 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, special_file(inode->i_mode)) continue; + if (f2fs_has_inline_data(inode)) { + iput(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_ERR, + "inode %lx has both inline_data flag and " + "data block, nid=%u, ofs_in_node=%u", + inode->i_ino, dni.nid, ofs_in_node); + continue; + } + if (!down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.6.47 commit ae00e6536a2dd54b64b39e9a39548870cf835745 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMMF CVE: CVE-2024-44942 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit fc01008c92f40015aeeced94750855a7111b6929 ] syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing. Reported-by: syzbot+848062ba19c8782ca5c8(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000d103ce06174d7ec3@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/f2fs/gc.c [Code logic conflict, f2fs_info_ratelimited was introduced since commit b1c9d3f833ba ("f2fs: support printk_ratelimited() in f2fs_printk()"), so replace it with f2fs_err, and f2fs_gc_pinned_control was introduced since commit 71419129625a ("f2fs: give priority to select unpinned section for foreground GC"), ingore it.] Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/f2fs/gc.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 6e75437a6a2e..9bd64b8c2e92 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1450,6 +1450,16 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, continue; } + if (f2fs_has_inline_data(inode)) { + iput(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err(sbi, + "inode %lx has both inline_data flag and " + "data block, nid=%u, ofs_in_node=%u", + inode->i_ino, dni.nid, ofs_in_node); + continue; + } + if (!down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] hfs: fix to initialize fields of hfs_inode_info after hfs_alloc_inode()
by Liu Mingrui 03 Sep '24

03 Sep '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v4.19.320 commit f7316b2b2f11cf0c6de917beee8d3de728be24db category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKPRV CVE: CVE-2024-42311 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 26a2ed107929a855155429b11e1293b83e6b2a8b upstream. Syzbot reports uninitialized value access issue as below: loop0: detected capacity change from 0 to 64 ===================================================== BUG: KMSAN: uninit-value in hfs_revalidate_dentry+0x307/0x3f0 fs/hfs/sysdep.c:30 hfs_revalidate_dentry+0x307/0x3f0 fs/hfs/sysdep.c:30 d_revalidate fs/namei.c:862 [inline] lookup_fast+0x89e/0x8e0 fs/namei.c:1649 walk_component fs/namei.c:2001 [inline] link_path_walk+0x817/0x1480 fs/namei.c:2332 path_lookupat+0xd9/0x6f0 fs/namei.c:2485 filename_lookup+0x22e/0x740 fs/namei.c:2515 user_path_at_empty+0x8b/0x390 fs/namei.c:2924 user_path_at include/linux/namei.h:57 [inline] do_mount fs/namespace.c:3689 [inline] __do_sys_mount fs/namespace.c:3898 [inline] __se_sys_mount+0x66b/0x810 fs/namespace.c:3875 __x64_sys_mount+0xe4/0x140 fs/namespace.c:3875 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b BUG: KMSAN: uninit-value in hfs_ext_read_extent fs/hfs/extent.c:196 [inline] BUG: KMSAN: uninit-value in hfs_get_block+0x92d/0x1620 fs/hfs/extent.c:366 hfs_ext_read_extent fs/hfs/extent.c:196 [inline] hfs_get_block+0x92d/0x1620 fs/hfs/extent.c:366 block_read_full_folio+0x4ff/0x11b0 fs/buffer.c:2271 hfs_read_folio+0x55/0x60 fs/hfs/inode.c:39 filemap_read_folio+0x148/0x4f0 mm/filemap.c:2426 do_read_cache_folio+0x7c8/0xd90 mm/filemap.c:3553 do_read_cache_page mm/filemap.c:3595 [inline] read_cache_page+0xfb/0x2f0 mm/filemap.c:3604 read_mapping_page include/linux/pagemap.h:755 [inline] hfs_btree_open+0x928/0x1ae0 fs/hfs/btree.c:78 hfs_mdb_get+0x260c/0x3000 fs/hfs/mdb.c:204 hfs_fill_super+0x1fb1/0x2790 fs/hfs/super.c:406 mount_bdev+0x628/0x920 fs/super.c:1359 hfs_mount+0xcd/0xe0 fs/hfs/super.c:456 legacy_get_tree+0x167/0x2e0 fs/fs_context.c:610 vfs_get_tree+0xdc/0x5d0 fs/super.c:1489 do_new_mount+0x7a9/0x16f0 fs/namespace.c:3145 path_mount+0xf98/0x26a0 fs/namespace.c:3475 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x919/0x9e0 fs/namespace.c:3674 __ia32_sys_mount+0x15b/0x1b0 fs/namespace.c:3674 do_syscall_32_irqs_on arch/x86/entry/common.c:112 [inline] __do_fast_syscall_32+0xa2/0x100 arch/x86/entry/common.c:178 do_fast_syscall_32+0x37/0x80 arch/x86/entry/common.c:203 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:246 entry_SYSENTER_compat_after_hwframe+0x70/0x82 Uninit was created at: __alloc_pages+0x9a6/0xe00 mm/page_alloc.c:4590 __alloc_pages_node include/linux/gfp.h:238 [inline] alloc_pages_node include/linux/gfp.h:261 [inline] alloc_slab_page mm/slub.c:2190 [inline] allocate_slab mm/slub.c:2354 [inline] new_slab+0x2d7/0x1400 mm/slub.c:2407 ___slab_alloc+0x16b5/0x3970 mm/slub.c:3540 __slab_alloc mm/slub.c:3625 [inline] __slab_alloc_node mm/slub.c:3678 [inline] slab_alloc_node mm/slub.c:3850 [inline] kmem_cache_alloc_lru+0x64d/0xb30 mm/slub.c:3879 alloc_inode_sb include/linux/fs.h:3018 [inline] hfs_alloc_inode+0x5a/0xc0 fs/hfs/super.c:165 alloc_inode+0x83/0x440 fs/inode.c:260 new_inode_pseudo fs/inode.c:1005 [inline] new_inode+0x38/0x4f0 fs/inode.c:1031 hfs_new_inode+0x61/0x1010 fs/hfs/inode.c:186 hfs_mkdir+0x54/0x250 fs/hfs/dir.c:228 vfs_mkdir+0x49a/0x700 fs/namei.c:4126 do_mkdirat+0x529/0x810 fs/namei.c:4149 __do_sys_mkdirat fs/namei.c:4164 [inline] __se_sys_mkdirat fs/namei.c:4162 [inline] __x64_sys_mkdirat+0xc8/0x120 fs/namei.c:4162 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xcf/0x1e0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x63/0x6b It missed to initialize .tz_secondswest, .cached_start and .cached_blocks fields in struct hfs_inode_info after hfs_alloc_inode(), fix it. Cc: stable(a)vger.kernel.org Reported-by: syzbot+3ae6be33a50b5aae4dab(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-fsdevel/0000000000005ad04005ee48897f@google.c… Signed-off-by: Chao Yu <chao(a)kernel.org> Link: https://lore.kernel.org/r/20240616013841.2217-1-chao@kernel.org Signed-off-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Mingrui <liumingrui(a)huawei.com> --- fs/hfs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index da243c84e93b..aa5e2ef3b8a3 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -199,6 +199,7 @@ struct inode *hfs_new_inode(struct inode *dir, const struct qstr *name, umode_t HFS_I(inode)->flags = 0; HFS_I(inode)->rsrc_inode = NULL; HFS_I(inode)->fs_blocks = 0; + HFS_I(inode)->tz_secondswest = sys_tz.tz_minuteswest * 60; if (S_ISDIR(mode)) { inode->i_size = 2; HFS_SB(sb)->folder_count++; @@ -274,6 +275,8 @@ void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, for (count = 0, i = 0; i < 3; i++) count += be16_to_cpu(ext[i].count); HFS_I(inode)->first_blocks = count; + HFS_I(inode)->cached_start = 0; + HFS_I(inode)->cached_blocks = 0; inode->i_size = HFS_I(inode)->phys_size = log_size; HFS_I(inode)->fs_blocks = (log_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; -- 2.25.1

2 1

[PATCH OLK-6.6] kcm: Serialise kcm_sendmsg() for the same socket.
by Zhang Changzhong 03 Sep '24

03 Sep '24

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v6.11-rc5 commit 807067bf014d4a3ae2cc55bd3de16f22a01eb580 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IANVRN CVE: CVE-2024-44946 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- syzkaller reported UAF in kcm_release(). [0] The scenario is 1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb. 2. Thread A resumes building skb from kcm->seq_skb but is blocked by sk_stream_wait_memory() 3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb and puts the skb to the write queue 4. Thread A faces an error and finally frees skb that is already in the write queue 5. kcm_release() does double-free the skb in the write queue When a thread is building a MSG_MORE skb, another thread must not touch it. Let's add a per-sk mutex and serialise kcm_sendmsg(). [0]: BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline] BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline] BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167 CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G B 6.8.0-rc5-syzkaller-g9abbc24128bc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:377 [inline] print_report+0x178/0x518 mm/kasan/report.c:488 kasan_report+0xd8/0x138 mm/kasan/report.c:601 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381 __skb_unlink include/linux/skbuff.h:2366 [inline] __skb_dequeue include/linux/skbuff.h:2385 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] __skb_queue_purge include/linux/skbuff.h:3181 [inline] kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Allocated by task 6166: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626 unpoison_slab_object mm/kasan/common.c:314 [inline] __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3813 [inline] slab_alloc_node mm/slub.c:3860 [inline] kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1296 [inline] kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x220/0x2c0 net/socket.c:768 splice_to_socket+0x7cc/0xd58 fs/splice.c:889 do_splice_from fs/splice.c:941 [inline] direct_splice_actor+0xec/0x1d8 fs/splice.c:1164 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108 do_splice_direct_actor fs/splice.c:1207 [inline] do_splice_direct+0x1e4/0x304 fs/splice.c:1233 do_sendfile+0x460/0xb3c fs/read_write.c:1295 __do_sys_sendfile64 fs/read_write.c:1362 [inline] __se_sys_sendfile64 fs/read_write.c:1348 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Freed by task 6167: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640 poison_slab_object+0x124/0x18c mm/kasan/common.c:241 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2121 [inline] slab_free mm/slub.c:4299 [inline] kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363 kfree_skbmem+0x10c/0x19c __kfree_skb net/core/skbuff.c:1109 [inline] kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144 kfree_skb include/linux/skbuff.h:1244 [inline] kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The buggy address belongs to the object at ffff0000ced0fc80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 0 bytes inside of freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70) The buggy address belongs to the physical page: page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+b72d86aa5df17ce74c60(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60 Tested-by: syzbot+b72d86aa5df17ce74c60(a)syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- include/net/kcm.h | 1 + net/kcm/kcmsock.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5..441e993 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 41d892b..829eb67 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -754,6 +754,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -925,6 +926,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -950,6 +952,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1203,6 +1206,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); -- 2.9.5

2 1

[PATCH openEuler-22.03-LTS-SP1] kcm: Serialise kcm_sendmsg() for the same socket.
by Zhang Changzhong 03 Sep '24

03 Sep '24

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v6.11-rc5 commit 807067bf014d4a3ae2cc55bd3de16f22a01eb580 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IANVRN CVE: CVE-2024-44946 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- syzkaller reported UAF in kcm_release(). [0] The scenario is 1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb. 2. Thread A resumes building skb from kcm->seq_skb but is blocked by sk_stream_wait_memory() 3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb and puts the skb to the write queue 4. Thread A faces an error and finally frees skb that is already in the write queue 5. kcm_release() does double-free the skb in the write queue When a thread is building a MSG_MORE skb, another thread must not touch it. Let's add a per-sk mutex and serialise kcm_sendmsg(). [0]: BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline] BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline] BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167 CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G B 6.8.0-rc5-syzkaller-g9abbc24128bc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:377 [inline] print_report+0x178/0x518 mm/kasan/report.c:488 kasan_report+0xd8/0x138 mm/kasan/report.c:601 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381 __skb_unlink include/linux/skbuff.h:2366 [inline] __skb_dequeue include/linux/skbuff.h:2385 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] __skb_queue_purge include/linux/skbuff.h:3181 [inline] kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Allocated by task 6166: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626 unpoison_slab_object mm/kasan/common.c:314 [inline] __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3813 [inline] slab_alloc_node mm/slub.c:3860 [inline] kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1296 [inline] kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x220/0x2c0 net/socket.c:768 splice_to_socket+0x7cc/0xd58 fs/splice.c:889 do_splice_from fs/splice.c:941 [inline] direct_splice_actor+0xec/0x1d8 fs/splice.c:1164 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108 do_splice_direct_actor fs/splice.c:1207 [inline] do_splice_direct+0x1e4/0x304 fs/splice.c:1233 do_sendfile+0x460/0xb3c fs/read_write.c:1295 __do_sys_sendfile64 fs/read_write.c:1362 [inline] __se_sys_sendfile64 fs/read_write.c:1348 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Freed by task 6167: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640 poison_slab_object+0x124/0x18c mm/kasan/common.c:241 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2121 [inline] slab_free mm/slub.c:4299 [inline] kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363 kfree_skbmem+0x10c/0x19c __kfree_skb net/core/skbuff.c:1109 [inline] kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144 kfree_skb include/linux/skbuff.h:1244 [inline] kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The buggy address belongs to the object at ffff0000ced0fc80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 0 bytes inside of freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70) The buggy address belongs to the physical page: page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+b72d86aa5df17ce74c60(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60 Tested-by: syzbot+b72d86aa5df17ce74c60(a)syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- include/net/kcm.h | 1 + net/kcm/kcmsock.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/include/net/kcm.h b/include/net/kcm.h index 2d704f8..8e8252e 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 178f6a7..aea36eb 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -906,6 +906,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -1054,6 +1055,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -1076,6 +1078,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1360,6 +1363,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); -- 2.9.5

2 1

[PATCH openEuler-1.0-LTS] cifs: Fix pages leak when cifs_writedata allocate fails in cifs_writedata_direct_alloc()
by Zizhi Wo 03 Sep '24

03 Sep '24

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAOH1I -------------------------------- The function cifs_writedata_alloc() first allocates pages and then executes cifs_writedata_direct_alloc(). If the subsequent allocation of wdata fails, the previously allocated pages are not released, leading to a memory leak: hex dump (first 8 bytes): 00 00 00 00 00 00 00 00 ........ backtrace: [<00000000c2b9cca5>] cifs_write_from_iter.isra.0+0x103/0x730 [<0000000069a4b2e6>] cifs_user_writev+0x138/0x280 [<00000000bfdbeacd>] __vfs_write+0x12b/0x190 [<00000000460567cf>] vfs_write+0xac/0x1a0 [<00000000f92e5dfc>] ksys_write+0x43/0xb0 [<0000000094ddd57e>] do_syscall_64+0x63/0x220 [<0000000055ce26ff>] entry_SYSCALL_64_after_hwframe+0x5c/0xc1 [<00000000359223fa>] 0xffffffffffffffff This issue can be avoided by promptly using kvfree. Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/cifs/cifssmb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index cb70f0c6aa1b..7950c906e7b3 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -2129,6 +2129,8 @@ cifs_writedata_direct_alloc(struct page **pages, work_func_t complete) INIT_LIST_HEAD(&wdata->list); init_completion(&wdata->done); INIT_WORK(&wdata->work, complete); + } else { + kvfree(pages); } return wdata; } -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.6.47 commit ae00e6536a2dd54b64b39e9a39548870cf835745 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMMF CVE: CVE-2024-44942 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit fc01008c92f40015aeeced94750855a7111b6929 ] syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing. Reported-by: syzbot+848062ba19c8782ca5c8(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000d103ce06174d7ec3@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/f2fs/gc.c [Code logic conflict, f2fs_info_ratelimited was introduced since commit b1c9d3f833ba ("f2fs: support printk_ratelimited() in f2fs_printk()"), so replace it with f2fs_err, and f2fs_gc_pinned_control was introduced since commit 71419129625a ("f2fs: give priority to select unpinned section for foreground GC"), ingore it.] Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/f2fs/gc.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index f4f7b8feebef..6db285a8af33 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -957,6 +957,16 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, special_file(inode->i_mode)) continue; + if (f2fs_has_inline_data(inode)) { + iput(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_ERR, + "inode %lx has both inline_data flag and " + "data block, nid=%u, ofs_in_node=%u", + inode->i_ino, dni.nid, ofs_in_node); + continue; + } + if (!down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] dev/parport: fix the array out-of-bounds risk
by dinglongwei 03 Sep '24

03 Sep '24

From: tuhaowen <tuhaowen(a)uniontech.com> stable inclusion from stable-v6.1.103 commit 7f4da759092a1a6ce35fb085182d02de8cc4cc84 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQAA CVE: CVE-2024-42301 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit ab11dac93d2d568d151b1918d7b84c2d02bacbd5 upstream. Fixed array out-of-bounds issues caused by sprintf by replacing it with snprintf for safer data copying, ensuring the destination buffer is not overflowed. Below is the stack trace I encountered during the actual issue: [ 66.575408s] [pid:5118,cpu4,QThread,4]Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: do_hardware_base_addr+0xcc/0xd0 [parport] [ 66.575408s] [pid:5118,cpu4,QThread,5]CPU: 4 PID: 5118 Comm: QThread Tainted: G S W O 5.10.97-arm64-desktop #7100.57021.2 [ 66.575439s] [pid:5118,cpu4,QThread,6]TGID: 5087 Comm: EFileApp [ 66.575439s] [pid:5118,cpu4,QThread,7]Hardware name: HUAWEI HUAWEI QingYun PGUX-W515x-B081/SP1PANGUXM, BIOS 1.00.07 04/29/2024 [ 66.575439s] [pid:5118,cpu4,QThread,8]Call trace: [ 66.575469s] [pid:5118,cpu4,QThread,9] dump_backtrace+0x0/0x1c0 [ 66.575469s] [pid:5118,cpu4,QThread,0] show_stack+0x14/0x20 [ 66.575469s] [pid:5118,cpu4,QThread,1] dump_stack+0xd4/0x10c [ 66.575500s] [pid:5118,cpu4,QThread,2] panic+0x1d8/0x3bc [ 66.575500s] [pid:5118,cpu4,QThread,3] __stack_chk_fail+0x2c/0x38 [ 66.575500s] [pid:5118,cpu4,QThread,4] do_hardware_base_addr+0xcc/0xd0 [parport] Signed-off-by: tuhaowen <tuhaowen(a)uniontech.com> Cc: stable <stable(a)kernel.org> Link: https://lore.kernel.org/r/20240708080430.8221-1-tuhaowen@uniontech.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/parport/procfs.c [Fix context] Signed-off-by: dinglongwei <dinglongwei1(a)huawei.com> --- drivers/parport/procfs.c | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-) diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c index 48804049d697..4a40f6a5b6ce 100644 --- a/drivers/parport/procfs.c +++ b/drivers/parport/procfs.c @@ -51,12 +51,12 @@ static int do_active_device(struct ctl_table *table, int write, for (dev = port->devices; dev ; dev = dev->next) { if(dev == port->cad) { - len += sprintf(buffer, "%s\n", dev->name); + len += snprintf(buffer, sizeof(buffer), "%s\n", dev->name); } } if(!len) { - len += sprintf(buffer, "%s\n", "none"); + len += snprintf(buffer, sizeof(buffer), "%s\n", "none"); } if (len > *lenp) @@ -87,19 +87,19 @@ static int do_autoprobe(struct ctl_table *table, int write, } if ((str = info->class_name) != NULL) - len += sprintf (buffer + len, "CLASS:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "CLASS:%s;\n", str); if ((str = info->model) != NULL) - len += sprintf (buffer + len, "MODEL:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "MODEL:%s;\n", str); if ((str = info->mfr) != NULL) - len += sprintf (buffer + len, "MANUFACTURER:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "MANUFACTURER:%s;\n", str); if ((str = info->description) != NULL) - len += sprintf (buffer + len, "DESCRIPTION:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "DESCRIPTION:%s;\n", str); if ((str = info->cmdset) != NULL) - len += sprintf (buffer + len, "COMMAND SET:%s;\n", str); + len += snprintf (buffer + len, sizeof(buffer) - len, "COMMAND SET:%s;\n", str); if (len > *lenp) len = *lenp; @@ -117,7 +117,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos) { struct parport *port = (struct parport *)table->extra1; - char buffer[20]; + char buffer[64]; int len = 0; if (*ppos) { @@ -128,7 +128,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write, if (write) /* permissions prevent this anyway */ return -EACCES; - len += sprintf (buffer, "%lu\t%lu\n", port->base, port->base_hi); + len += snprintf (buffer, sizeof(buffer), "%lu\t%lu\n", port->base, port->base_hi); if (len > *lenp) len = *lenp; @@ -156,7 +156,7 @@ static int do_hardware_irq(struct ctl_table *table, int write, if (write) /* permissions prevent this anyway */ return -EACCES; - len += sprintf (buffer, "%d\n", port->irq); + len += snprintf (buffer, sizeof(buffer), "%d\n", port->irq); if (len > *lenp) len = *lenp; @@ -184,7 +184,7 @@ static int do_hardware_dma(struct ctl_table *table, int write, if (write) /* permissions prevent this anyway */ return -EACCES; - len += sprintf (buffer, "%d\n", port->dma); + len += snprintf (buffer, sizeof(buffer), "%d\n", port->dma); if (len > *lenp) len = *lenp; @@ -213,7 +213,15 @@ static int do_hardware_modes(struct ctl_table *table, int write, return -EACCES; { -#define printmode(x) {if(port->modes&PARPORT_MODE_##x){len+=sprintf(buffer+len,"%s%s",f?",":"",#x);f++;}} +#define printmode(x) \ +{ \ + if (port->modes & PARPORT_MODE_##x) { \ + len += snprintf(buffer + len, sizeof(buffer) - len, \ + "%s%s", f ? "," : "", #x); \ + f++; \ + } \ +} + int f = 0; printmode(PCSPP); printmode(TRISTATE); -- 2.17.1

2 1

[PATCH OLK-5.10] kcm: Serialise kcm_sendmsg() for the same socket.
by Zhang Changzhong 03 Sep '24

03 Sep '24

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v6.11-rc5 commit 807067bf014d4a3ae2cc55bd3de16f22a01eb580 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IANVRN CVE: CVE-2024-44946 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- syzkaller reported UAF in kcm_release(). [0] The scenario is 1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb. 2. Thread A resumes building skb from kcm->seq_skb but is blocked by sk_stream_wait_memory() 3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb and puts the skb to the write queue 4. Thread A faces an error and finally frees skb that is already in the write queue 5. kcm_release() does double-free the skb in the write queue When a thread is building a MSG_MORE skb, another thread must not touch it. Let's add a per-sk mutex and serialise kcm_sendmsg(). [0]: BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline] BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline] BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167 CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G B 6.8.0-rc5-syzkaller-g9abbc24128bc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:377 [inline] print_report+0x178/0x518 mm/kasan/report.c:488 kasan_report+0xd8/0x138 mm/kasan/report.c:601 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381 __skb_unlink include/linux/skbuff.h:2366 [inline] __skb_dequeue include/linux/skbuff.h:2385 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] __skb_queue_purge include/linux/skbuff.h:3181 [inline] kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Allocated by task 6166: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626 unpoison_slab_object mm/kasan/common.c:314 [inline] __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3813 [inline] slab_alloc_node mm/slub.c:3860 [inline] kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1296 [inline] kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x220/0x2c0 net/socket.c:768 splice_to_socket+0x7cc/0xd58 fs/splice.c:889 do_splice_from fs/splice.c:941 [inline] direct_splice_actor+0xec/0x1d8 fs/splice.c:1164 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108 do_splice_direct_actor fs/splice.c:1207 [inline] do_splice_direct+0x1e4/0x304 fs/splice.c:1233 do_sendfile+0x460/0xb3c fs/read_write.c:1295 __do_sys_sendfile64 fs/read_write.c:1362 [inline] __se_sys_sendfile64 fs/read_write.c:1348 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Freed by task 6167: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640 poison_slab_object+0x124/0x18c mm/kasan/common.c:241 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2121 [inline] slab_free mm/slub.c:4299 [inline] kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363 kfree_skbmem+0x10c/0x19c __kfree_skb net/core/skbuff.c:1109 [inline] kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144 kfree_skb include/linux/skbuff.h:1244 [inline] kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The buggy address belongs to the object at ffff0000ced0fc80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 0 bytes inside of freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70) The buggy address belongs to the physical page: page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+b72d86aa5df17ce74c60(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60 Tested-by: syzbot+b72d86aa5df17ce74c60(a)syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- include/net/kcm.h | 1 + net/kcm/kcmsock.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/include/net/kcm.h b/include/net/kcm.h index 2d704f8..8e8252e 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 39b3c7f..194a2d5 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -911,6 +911,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -1059,6 +1060,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -1084,6 +1086,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1325,6 +1328,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); -- 2.9.5

2 1

[PATCH openEuler-1.0-LTS] f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.6.47 commit ae00e6536a2dd54b64b39e9a39548870cf835745 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMMF CVE: CVE-2024-44942 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit fc01008c92f40015aeeced94750855a7111b6929 ] syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing. Reported-by: syzbot+848062ba19c8782ca5c8(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000d103ce06174d7ec3@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/f2fs/gc.c [Code logic conflict, f2fs_info_ratelimited was introduced since commit b1c9d3f833ba ("f2fs: support printk_ratelimited() in f2fs_printk()"), so replace it with f2fs_err, and f2fs_gc_pinned_control was introduced since commit 71419129625a ("f2fs: give priority to select unpinned section for foreground GC"), ingore it.] Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/f2fs/gc.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index f4f7b8feebef..b880af5cea63 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -957,6 +957,16 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, special_file(inode->i_mode)) continue; + if (f2fs_has_inline_data(inode)) { + iput(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err(sbi, + "inode %lx has both inline_data flag and " + "data block, nid=%u, ofs_in_node=%u", + inode->i_ino, dni.nid, ofs_in_node); + continue; + } + if (!down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); -- 2.34.1

2 1

[openeuler:OLK-5.10 27064/30000] drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:4324:6: warning: variable 'err' is used uninitialized whenever 'if' condition is false
by kernel test robot 03 Sep '24

03 Sep '24

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: b7bed6628b750ffd687d1da0a170dece4b0c08bd commit: a398c3637a33330c134f067e06df959550d44f7b [27064/30000] drivers: initial support for rnpgbe drivers from Mucse Technology config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20240903/202409031257.Y7C0PYH5-lkp@…) compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240903/202409031257.Y7C0PYH5-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202409031257.Y7C0PYH5-lkp@intel.com/ All warnings (new ones prefixed by >>): drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:2353:6: warning: variable 'cleaned_total' set but not used [-Wunused-but-set-variable] 2353 | int cleaned_total = 0; | ^ drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:2899:6: warning: variable 'rxctrl' set but not used [-Wunused-but-set-variable] 2899 | u32 rxctrl = 0, dma_axi_ctl; | ^ >> drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:4324:6: warning: variable 'err' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] 4324 | if (netif_running(netdev)) | ^~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:4329:6: note: uninitialized use occurs here 4329 | if (err) | ^~~ drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:4324:2: note: remove the 'if' if its condition is always true 4324 | if (netif_running(netdev)) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ 4325 | err = rnpgbe_open(netdev); drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:4318:9: note: initialize the variable 'err' to silence this warning 4318 | u32 err; | ^ | = 0 drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c:6160:29: warning: unused function 'rnpgbe_tso_features' [-Wunused-function] 6160 | static inline unsigned long rnpgbe_tso_features(struct rnpgbe_hw *hw) | ^~~~~~~~~~~~~~~~~~~ 4 warnings generated. vim +4324 drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c 4309 4310 /** 4311 * rnpgbe_thaw - un-quiesce the device 4312 * @dev: The port's netdev 4313 */ 4314 static int rnpgbe_thaw(struct device *dev) 4315 { 4316 struct rnpgbe_adapter *adapter = pci_get_drvdata(to_pci_dev(dev)); 4317 struct net_device *netdev = adapter->netdev; 4318 u32 err; 4319 4320 rnpgbe_set_interrupt_capability(adapter); 4321 register_mbx_irq(adapter); 4322 4323 rtnl_lock(); > 4324 if (netif_running(netdev)) 4325 err = rnpgbe_open(netdev); 4326 4327 rtnl_unlock(); 4328 4329 if (err) 4330 return err; 4331 netif_device_attach(netdev); 4332 4333 return 0; 4334 } 4335 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:OLK-5.10 29999/30000] drivers/acpi/numa/hmat.c:726:6: warning: no previous prototype for function 'hmat_restore_target'
by kernel test robot 03 Sep '24

03 Sep '24

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: b7bed6628b750ffd687d1da0a170dece4b0c08bd commit: 2e1b00fcf1e3152a1e73846f5f9ec37cef088a65 [29999/30000] ACPI/HMAT: Add missing locality information for hot-added device config: x86_64-rhel-8.3-rust (https://download.01.org/0day-ci/archive/20240903/202409031250.rcUC04W4-lkp@…) compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240903/202409031250.rcUC04W4-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202409031250.rcUC04W4-lkp@intel.com/ All warnings (new ones prefixed by >>): >> drivers/acpi/numa/hmat.c:726:6: warning: no previous prototype for function 'hmat_restore_target' [-Wmissing-prototypes] 726 | void hmat_restore_target(int nid) | ^ drivers/acpi/numa/hmat.c:726:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 726 | void hmat_restore_target(int nid) | ^ | static 1 warning generated. vim +/hmat_restore_target +726 drivers/acpi/numa/hmat.c 725 > 726 void hmat_restore_target(int nid) 727 { 728 struct memory_target *target; 729 int pxm; 730 731 pxm = node_to_pxm(nid); 732 target = find_mem_target(pxm); 733 if (!target) 734 return; 735 736 mutex_lock(&target_lock); 737 hmat_register_target_cache(target); 738 hmat_register_target_perf(target, 0); 739 hmat_register_target_perf(target, 1); 740 mutex_unlock(&target_lock); 741 } 742 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10] f2fs: fix to do sanity check on F2FS_INLINE_DATA flag in inode during GC
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.6.47 commit ae00e6536a2dd54b64b39e9a39548870cf835745 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMMMF CVE: CVE-2024-44942 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit fc01008c92f40015aeeced94750855a7111b6929 ] syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/inline.c:258! CPU: 1 PID: 34 Comm: kworker/u8:2 Not tainted 6.9.0-rc6-syzkaller-00012-g9e4bc4bcae01 #0 RIP: 0010:f2fs_write_inline_data+0x781/0x790 fs/f2fs/inline.c:258 Call Trace: f2fs_write_single_data_page+0xb65/0x1d60 fs/f2fs/data.c:2834 f2fs_write_cache_pages fs/f2fs/data.c:3133 [inline] __f2fs_write_data_pages fs/f2fs/data.c:3288 [inline] f2fs_write_data_pages+0x1efe/0x3a90 fs/f2fs/data.c:3315 do_writepages+0x35b/0x870 mm/page-writeback.c:2612 __writeback_single_inode+0x165/0x10b0 fs/fs-writeback.c:1650 writeback_sb_inodes+0x905/0x1260 fs/fs-writeback.c:1941 wb_writeback+0x457/0xce0 fs/fs-writeback.c:2117 wb_do_writeback fs/fs-writeback.c:2264 [inline] wb_workfn+0x410/0x1090 fs/fs-writeback.c:2304 process_one_work kernel/workqueue.c:3254 [inline] process_scheduled_works+0xa12/0x17c0 kernel/workqueue.c:3335 worker_thread+0x86d/0xd70 kernel/workqueue.c:3416 kthread+0x2f2/0x390 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 The root cause is: inline_data inode can be fuzzed, so that there may be valid blkaddr in its direct node, once f2fs triggers background GC to migrate the block, it will hit f2fs_bug_on() during dirty page writeback. Let's add sanity check on F2FS_INLINE_DATA flag in inode during GC, so that, it can forbid migrating inline_data inode's data block for fixing. Reported-by: syzbot+848062ba19c8782ca5c8(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000d103ce06174d7ec3@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/f2fs/gc.c [Code logic conflict, f2fs_info_ratelimited was introduced since commit b1c9d3f833ba ("f2fs: support printk_ratelimited() in f2fs_printk()"), so replace it with f2fs_err, and f2fs_gc_pinned_control was introduced since commit 71419129625a ("f2fs: give priority to select unpinned section for foreground GC"), ingore it.] Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- fs/f2fs/gc.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 1a6122628ec3..84b19733a3c2 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1456,6 +1456,16 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, continue; } + if (f2fs_has_inline_data(inode)) { + iput(inode); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_err(sbi, + "inode %lx has both inline_data flag and " + "data block, nid=%u, ofs_in_node=%u", + inode->i_ino, dni.nid, ofs_in_node); + continue; + } + if (!down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); -- 2.34.1

2 1

[PATCH OLK-6.6] ext4: Fix wrong da count caused by concurrent racing on extent tree
by Zhihao Cheng 03 Sep '24

03 Sep '24

Offering: HULK hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAODWM -------------------------------- The writeback process and error branch in writeback process may concurrently access extent tree, which leads to wrong da reservation count is calculated, specifically: write(4M) // folio 0, 1 are dirty wb_workfn fsync ext4_iomap_writepages iomap_do_writepage // writeback folio 0 iomap_writepage_map_blocks ext4_iomap_map_blocks ext4_iomap_map_one_extent ext4_map_create_blocks // down write(EXT4_I(inode)->i_data_sem) ext4_ext_map_blocks ext4_da_update_reserve_space // da reservation becomes 0 . . >> EIO occurs, journal is aborted << . ext4_sync_file . file_write_and_wait_range . do_writepages // writeback folio 1 . ext4_iomap_writepages . iomap_writepage_map_blocks . map_blocks // failed . discard_folio // error branch . ext4_es_remove_extent . // scan extents, delayed es is 512 . ext4_da_release_space . // da reservation count, 0 < 512 . WARN_ON(1) ext4_es_insert_extent // convert delayed es to unwritten status Since all changes on extent tree are protected by holding EXT4_I(inode)->i_data_sem, fix the problem by adding the lock while doing ext4_es_remove_extent(). Fixes: 7f6416dcd4a3 ("ext4: implement writeback iomap path") Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> --- fs/ext4/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a22c4184d9ef..ef5dfb994f0e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3676,8 +3676,10 @@ static inline int ext4_iomap_buffered_da_write_begin(struct inode *inode, static int ext4_iomap_punch_delalloc(struct inode *inode, loff_t offset, loff_t length) { + down_write(&EXT4_I(inode)->i_data_sem); ext4_es_remove_extent(inode, offset >> inode->i_blkbits, DIV_ROUND_UP_ULL(length, EXT4_BLOCK_SIZE(inode->i_sb))); + up_write(&EXT4_I(inode)->i_data_sem); return 0; } -- 2.31.1

2 1

[PATCH openEuler-1.0-LTS v3 00/30] support block hierarchy stats
by Yu Kuai 03 Sep '24

03 Sep '24

Changes in v3: - fix patch 7 format; Changes in v2: - find_get_pid(current->pid); -> get_pid(task_pid(current)); - check q->mq_ops in blk_mq_get_alloc_task(); - remove blk_mq_debugfs_unregister_hierarchy_stats(); - include cgroup_path() inside CONFIG_BLK_CGROUP; Bart Van Assche (1): blk-mq: remove blk_mq_put_ctx() Jens Axboe (4): block: add blk_time_get_ns() and blk_time_get() helpers block: cache current nsec time in struct blk_plug block: update cached timestamp post schedule/preemption block: limit block time caching to in_task() context Yu Kuai (25): blk-mq: export blk-mq-debugfs apis block: fix that blk_time_get_ns() doesn't update time after schedule block: fix kabi broken in struct blk_plug block: support to recored bio allocation time block: support to recored bio allocation task block: support to recored bio allocation time in request block: fix kabi broken for struct request block: support to recored bio allocation task in request block: block: fix kabi broken for struct blk_mq_alloc_data blk-mq-debugfs: factor out a new helper to show allocated request block: support to record when request is completed block-io-hierarchy: core hierarchy stats implementation block-io-hierarchy: core hierarchy iodump implementation blk-io-hierarchy: support to recored the number of slow IO blk-io-hierarchy: support new bio based stage blk-throtl blk-io-hierarchy: support new bio based stage blk-wbt blk-io-hierarchy: support new bio based stage gettag blk-io-hierarchy: support new rq based stage plug blk-io-hierarchy: support new rq based stage mq-deadline blk-io-hierarchy: support new rq based stage bfq blk-io-hierarchy: support new rq based stage kyber blk-io-hierarchy: support new rq based stage hctx blk-io-hierarchy: support new rq based stage requeue blk-io-hierarchy: support new rq based stage rq_driver blk-io-hierarchy: support new stage for bio lifetime arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/Kconfig | 8 + block/Makefile | 1 + block/bfq-cgroup.c | 15 +- block/bfq-iosched.c | 34 +- block/bio.c | 17 + block/blk-cgroup.c | 2 +- block/blk-core.c | 37 +- block/blk-flush.c | 19 +- block/blk-io-hierarchy/Kconfig | 145 +++++ block/blk-io-hierarchy/Makefile | 8 + block/blk-io-hierarchy/debugfs.c | 230 ++++++++ block/blk-io-hierarchy/iodump.c | 756 +++++++++++++++++++++++++ block/blk-io-hierarchy/iodump.h | 103 ++++ block/blk-io-hierarchy/stats.c | 429 ++++++++++++++ block/blk-io-hierarchy/stats.h | 371 ++++++++++++ block/blk-iolatency.c | 6 +- block/blk-merge.c | 1 + block/blk-mq-debugfs.c | 21 +- block/blk-mq-debugfs.h | 10 + block/blk-mq-sched.c | 7 +- block/blk-mq-tag.c | 13 +- block/blk-mq.c | 76 ++- block/blk-mq.h | 59 +- block/blk-sysfs.c | 16 + block/blk-throttle.c | 29 +- block/blk-wbt.c | 12 +- block/blk.h | 89 ++- block/cfq-iosched.c | 60 +- block/kyber-iosched.c | 10 +- block/mq-deadline.c | 15 +- include/linux/blk_types.h | 55 +- include/linux/blkdev.h | 16 + include/linux/sched.h | 2 + kernel/sched/core.c | 6 +- 36 files changed, 2562 insertions(+), 118 deletions(-) create mode 100644 block/blk-io-hierarchy/Kconfig create mode 100644 block/blk-io-hierarchy/Makefile create mode 100644 block/blk-io-hierarchy/debugfs.c create mode 100644 block/blk-io-hierarchy/iodump.c create mode 100644 block/blk-io-hierarchy/iodump.h create mode 100644 block/blk-io-hierarchy/stats.c create mode 100644 block/blk-io-hierarchy/stats.h -- 2.39.2

2 31

[PATCH openEuler-22.03-LTS-SP1] regulator: da9211: Use irq handler when ready
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Ricardo Ribalda <ribalda(a)chromium.org> stable inclusion from stable-v5.10.164 commit d4aa749e046435f054e94ebf50cad143d6229fae category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALM7R CVE: CVE-2022-48891 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 02228f6aa6a64d588bc31e3267d05ff184d772eb ] If the system does not come from reset (like when it is kexec()), the regulator might have an IRQ waiting for us. If we enable the IRQ handler before its structures are ready, we crash. This patch fixes: [ 1.141839] Unable to handle kernel read from unreadable memory at virtual address 0000000000000078 [ 1.316096] Call trace: [ 1.316101] blocking_notifier_call_chain+0x20/0xa8 [ 1.322757] cpu cpu0: dummy supplies not allowed for exclusive requests [ 1.327823] regulator_notifier_call_chain+0x1c/0x2c [ 1.327825] da9211_irq_handler+0x68/0xf8 [ 1.327829] irq_thread+0x11c/0x234 [ 1.327833] kthread+0x13c/0x154 Signed-off-by: Ricardo Ribalda <ribalda(a)chromium.org> Reviewed-by: Adam Ward <DLG-Adam.Ward.opensource(a)dm.renesas.com> Link: https://lore.kernel.org/r/20221124-da9211-v2-0-1779e3c5d491@chromium.org Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- drivers/regulator/da9211-regulator.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index e01b32d1fa17..00828f5baa97 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -498,6 +498,12 @@ static int da9211_i2c_probe(struct i2c_client *i2c) chip->chip_irq = i2c->irq; + ret = da9211_regulator_init(chip); + if (ret < 0) { + dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); + return ret; + } + if (chip->chip_irq != 0) { ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL, da9211_irq_handler, @@ -512,11 +518,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c) dev_warn(chip->dev, "No IRQ configured\n"); } - ret = da9211_regulator_init(chip); - - if (ret < 0) - dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); - return ret; } -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS v2 00/30] support block hierarchy stats
by Yu Kuai 03 Sep '24

03 Sep '24

Changes in v2: - find_get_pid(current->pid); -> get_pid(task_pid(current)); - check q->mq_ops in blk_mq_get_alloc_task(); - remove blk_mq_debugfs_unregister_hierarchy_stats(); - include cgroup_path() inside CONFIG_BLK_CGROUP; Bart Van Assche (1): blk-mq: remove blk_mq_put_ctx() Jens Axboe (4): block: add blk_time_get_ns() and blk_time_get() helpers block: cache current nsec time in struct blk_plug block: update cached timestamp post schedule/preemption block: limit block time caching to in_task() context Yu Kuai (25): blk-mq: export blk-mq-debugfs apis block: fix that blk_time_get_ns() doesn't update time after schedule block: fix kabi broken in struct blk_plug block: support to recored bio allocation time block: support to recored bio allocation task block: support to recored bio allocation time in request block: fix kabi broken for struct request block: support to recored bio allocation task in request block: block: fix kabi broken for struct blk_mq_alloc_data blk-mq-debugfs: factor out a new helper to show allocated request block: support to record when request is completed block-io-hierarchy: core hierarchy stats implementation block-io-hierarchy: core hierarchy iodump implementation blk-io-hierarchy: support to recored the number of slow IO blk-io-hierarchy: support new bio based stage blk-throtl blk-io-hierarchy: support new bio based stage blk-wbt blk-io-hierarchy: support new bio based stage gettag blk-io-hierarchy: support new rq based stage plug blk-io-hierarchy: support new rq based stage mq-deadline blk-io-hierarchy: support new rq based stage bfq blk-io-hierarchy: support new rq based stage kyber blk-io-hierarchy: support new rq based stage hctx blk-io-hierarchy: support new rq based stage requeue blk-io-hierarchy: support new rq based stage rq_driver blk-io-hierarchy: support new stage for bio lifetime arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/Kconfig | 8 + block/Makefile | 1 + block/bfq-cgroup.c | 15 +- block/bfq-iosched.c | 34 +- block/bio.c | 17 + block/blk-cgroup.c | 2 +- block/blk-core.c | 37 +- block/blk-flush.c | 19 +- block/blk-io-hierarchy/Kconfig | 145 +++++ block/blk-io-hierarchy/Makefile | 8 + block/blk-io-hierarchy/debugfs.c | 230 ++++++++ block/blk-io-hierarchy/iodump.c | 756 +++++++++++++++++++++++++ block/blk-io-hierarchy/iodump.h | 103 ++++ block/blk-io-hierarchy/stats.c | 429 ++++++++++++++ block/blk-io-hierarchy/stats.h | 371 ++++++++++++ block/blk-iolatency.c | 6 +- block/blk-merge.c | 1 + block/blk-mq-debugfs.c | 21 +- block/blk-mq-debugfs.h | 10 + block/blk-mq-sched.c | 7 +- block/blk-mq-tag.c | 13 +- block/blk-mq.c | 76 ++- block/blk-mq.h | 59 +- block/blk-sysfs.c | 16 + block/blk-throttle.c | 29 +- block/blk-wbt.c | 12 +- block/blk.h | 89 ++- block/cfq-iosched.c | 60 +- block/kyber-iosched.c | 10 +- block/mq-deadline.c | 15 +- include/linux/blk_types.h | 55 +- include/linux/blkdev.h | 16 + include/linux/sched.h | 2 + kernel/sched/core.c | 6 +- 36 files changed, 2562 insertions(+), 118 deletions(-) create mode 100644 block/blk-io-hierarchy/Kconfig create mode 100644 block/blk-io-hierarchy/Makefile create mode 100644 block/blk-io-hierarchy/debugfs.c create mode 100644 block/blk-io-hierarchy/iodump.c create mode 100644 block/blk-io-hierarchy/iodump.h create mode 100644 block/blk-io-hierarchy/stats.c create mode 100644 block/blk-io-hierarchy/stats.h -- 2.39.2

2 31

[PATCH openEuler-1.0-LTS] regulator: da9211: Use irq handler when ready
by Cui GaoSheng 03 Sep '24

03 Sep '24

From: Ricardo Ribalda <ribalda(a)chromium.org> stable inclusion from stable-v4.19.270 commit f75cde714e0a67f73ef169aa50d4ed77d04f7236 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALM7R CVE: CVE-2022-48891 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 02228f6aa6a64d588bc31e3267d05ff184d772eb ] If the system does not come from reset (like when it is kexec()), the regulator might have an IRQ waiting for us. If we enable the IRQ handler before its structures are ready, we crash. This patch fixes: [ 1.141839] Unable to handle kernel read from unreadable memory at virtual address 0000000000000078 [ 1.316096] Call trace: [ 1.316101] blocking_notifier_call_chain+0x20/0xa8 [ 1.322757] cpu cpu0: dummy supplies not allowed for exclusive requests [ 1.327823] regulator_notifier_call_chain+0x1c/0x2c [ 1.327825] da9211_irq_handler+0x68/0xf8 [ 1.327829] irq_thread+0x11c/0x234 [ 1.327833] kthread+0x13c/0x154 Signed-off-by: Ricardo Ribalda <ribalda(a)chromium.org> Reviewed-by: Adam Ward <DLG-Adam.Ward.opensource(a)dm.renesas.com> Link: https://lore.kernel.org/r/20221124-da9211-v2-0-1779e3c5d491@chromium.org Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cui GaoSheng <cuigaosheng1(a)huawei.com> --- drivers/regulator/da9211-regulator.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index 6c122b3df5d0..8847d15c2b90 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -469,6 +469,12 @@ static int da9211_i2c_probe(struct i2c_client *i2c, chip->chip_irq = i2c->irq; + ret = da9211_regulator_init(chip); + if (ret < 0) { + dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); + return ret; + } + if (chip->chip_irq != 0) { ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL, da9211_irq_handler, @@ -483,11 +489,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c, dev_warn(chip->dev, "No IRQ configured\n"); } - ret = da9211_regulator_init(chip); - - if (ret < 0) - dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); - return ret; } -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] devres: Fix memory leakage caused by driver API devm_free_percpu()
by Zhang Zekun 03 Sep '24

03 Sep '24

From: Zijun Hu <quic_zijuhu(a)quicinc.com> stable inclusion from stable-v4.19.320 commit 700e8abd65b10792b2f179ce4e858f2ca2880f85 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALERD CVE: CVE-2024-43871 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ----------------------------------------------- [ Upstream commit bd50a974097bb82d52a458bd3ee39fb723129a0c ] It will cause memory leakage when use driver API devm_free_percpu() to free memory allocated by devm_alloc_percpu(), fixed by using devres_release() instead of devres_destroy() within devm_free_percpu(). Fixes: ff86aae3b411 ("devres: add devm_alloc_percpu()") Cc: stable(a)vger.kernel.org Signed-off-by: Zijun Hu <quic_zijuhu(a)quicinc.com> Link: https://lore.kernel.org/r/1719931914-19035-3-git-send-email-quic_zijuhu@qui… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/base/devres.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index d68b52cf9225..0813c16e31a3 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -1057,7 +1057,11 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu); */ void devm_free_percpu(struct device *dev, void __percpu *pdata) { - WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match, + /* + * Use devres_release() to prevent memory leakage as + * devm_free_pages() does. + */ + WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match, (void *)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); -- 2.17.1

2 1

[PATCH openEuler-1.0-LTS] jfs: Fix array-index-out-of-bounds in diFree
by Zhang Zekun 03 Sep '24

03 Sep '24

From: Jeongjun Park <aha310510(a)gmail.com> stable inclusion from stable-v4.19.320 commit 55b732c8b09b41148eaab2fa8e31b0af47671e00 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ4Y CVE: CVE-2024-43858 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------------------------------- [ Upstream commit f73f969b2eb39ad8056f6c7f3a295fa2f85e313a ] Reported-by: syzbot+241c815bda521982cb49(a)syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jeongjun Park <aha310510(a)gmail.com> Signed-off-by: Dave Kleikamp <dave.kleikamp(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- fs/jfs/jfs_imap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 529630106320..5088182e2ef7 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -304,7 +304,7 @@ int diSync(struct inode *ipimap) int diRead(struct inode *ip) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); - int iagno, ino, extno, rc; + int iagno, ino, extno, rc, agno; struct inode *ipimap; struct dinode *dp; struct iag *iagp; @@ -353,8 +353,11 @@ int diRead(struct inode *ip) /* get the ag for the iag */ agstart = le64_to_cpu(iagp->agstart); + agno = BLKTOAG(agstart, JFS_SBI(ip->i_sb)); release_metapage(mp); + if (agno >= MAXAG || agno < 0) + return -EIO; rel_inode = (ino & (INOSPERPAGE - 1)); pageno = blkno >> sbi->l2nbperpage; -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1 V2] ext4: sanity check for NULL pointer after ext4_force_shutdown
by Zizhi Wo 03 Sep '24

03 Sep '24

From: Wojciech Gładysz <wojciech.gladysz(a)infogain.com> stable inclusion from stable-6.6.47 commit 3f6bbe6e07e5239294ecc3d2efa70d1f98aed52e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMM9L CVE: CVE-2024-43898 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- [ Upstream commit 83f4414b8f84249d538905825b088ff3ae555652 ] Test case: 2 threads write short inline data to a file. In ext4_page_mkwrite the resulting inline data is converted. Handling ext4_grp_locked_error with description "block bitmap and bg descriptor inconsistent: X vs Y free clusters" calls ext4_force_shutdown. The conversion clears EXT4_STATE_MAY_INLINE_DATA but fails for ext4_destroy_inline_data_nolock and ext4_mark_iloc_dirty due to ext4_forced_shutdown. The restoration of inline data fails for the same reason not setting EXT4_STATE_MAY_INLINE_DATA. Without the flag set a regular process path in ext4_da_write_end follows trying to dereference page folio private pointer that has not been set. The fix calls early return with -EIO error shall the pointer to private be NULL. Sample crash report: Unable to handle kernel paging request at virtual address dfff800000000004 KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] Mem abort info: ESR = 0x0000000096000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [dfff800000000004] address between user and kernel address ranges Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 20274 Comm: syz-executor185 Not tainted 6.9.0-rc7-syzkaller-gfda5695d692c #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __block_commit_write+0x64/0x2b0 fs/buffer.c:2167 lr : __block_commit_write+0x3c/0x2b0 fs/buffer.c:2160 sp : ffff8000a1957600 x29: ffff8000a1957610 x28: dfff800000000000 x27: ffff0000e30e34b0 x26: 0000000000000000 x25: dfff800000000000 x24: dfff800000000000 x23: fffffdffc397c9e0 x22: 0000000000000020 x21: 0000000000000020 x20: 0000000000000040 x19: fffffdffc397c9c0 x18: 1fffe000367bd196 x17: ffff80008eead000 x16: ffff80008ae89e3c x15: 00000000200000c0 x14: 1fffe0001cbe4e04 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000001 x10: 0000000000ff0100 x9 : 0000000000000000 x8 : 0000000000000004 x7 : 0000000000000000 x6 : 0000000000000000 x5 : fffffdffc397c9c0 x4 : 0000000000000020 x3 : 0000000000000020 x2 : 0000000000000040 x1 : 0000000000000020 x0 : fffffdffc397c9c0 Call trace: __block_commit_write+0x64/0x2b0 fs/buffer.c:2167 block_write_end+0xb4/0x104 fs/buffer.c:2253 ext4_da_do_write_end fs/ext4/inode.c:2955 [inline] ext4_da_write_end+0x2c4/0xa40 fs/ext4/inode.c:3028 generic_perform_write+0x394/0x588 mm/filemap.c:3985 ext4_buffered_write_iter+0x2c0/0x4ec fs/ext4/file.c:299 ext4_file_write_iter+0x188/0x1780 call_write_iter include/linux/fs.h:2110 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x968/0xc3c fs/read_write.c:590 ksys_write+0x15c/0x26c fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __arm64_sys_write+0x7c/0x90 fs/read_write.c:652 __invoke_syscall arch/arm64/kernel/syscall.c:34 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:48 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:133 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:152 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Code: 97f85911 f94002da 91008356 d343fec8 (38796908) ---[ end trace 0000000000000000 ]--- ---------------- Code disassembly (best guess): 0: 97f85911 bl 0xffffffffffe16444 4: f94002da ldr x26, [x22] 8: 91008356 add x22, x26, #0x20 c: d343fec8 lsr x8, x22, #3 * 10: 38796908 ldrb w8, [x8, x25] <-- trapping instruction Reported-by: syzbot+18df508cf00a0598d9a6(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=18df508cf00a0598d9a6 Link: https://lore.kernel.org/all/000000000000f19a1406109eb5c5@google.com/T/ Signed-off-by: Wojciech Gładysz <wojciech.gladysz(a)infogain.com> Link: https://patch.msgid.link/20240703070112.10235-1-wojciech.gladysz@infogain.c… Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/buffer.c fs/ext4/inode.c [Since folio is not defined in the earlier version, page_private is judged ahead of time.] Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/buffer.c | 3 +++ fs/ext4/inode.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/fs/buffer.c b/fs/buffer.c index 93324b06ecb4..9b169f2987b8 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2070,6 +2070,9 @@ static int __block_commit_write(struct inode *inode, struct page *page, unsigned blocksize; struct buffer_head *bh, *head; + if (!page_has_buffers(page)) + return 0; + bh = head = page_buffers(page); blocksize = bh->b_size; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 690f7866dc0c..d5b462d03978 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3089,6 +3089,11 @@ static int ext4_da_do_write_end(struct address_space *mapping, bool disksize_changed = false; loff_t new_i_size; + if (unlikely(!page_has_buffers(page))) { + unlock_page(page); + put_page(page); + return -EIO; + } /* * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES * flag, which all that's needed to trigger page writeback. -- 2.39.2

2 1

[PATCH OLK-5.10 V2] ext4: sanity check for NULL pointer after ext4_force_shutdown
by Zizhi Wo 03 Sep '24

03 Sep '24

From: Wojciech Gładysz <wojciech.gladysz(a)infogain.com> stable inclusion from stable-6.6.47 commit 3f6bbe6e07e5239294ecc3d2efa70d1f98aed52e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMM9L CVE: CVE-2024-43898 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- [ Upstream commit 83f4414b8f84249d538905825b088ff3ae555652 ] Test case: 2 threads write short inline data to a file. In ext4_page_mkwrite the resulting inline data is converted. Handling ext4_grp_locked_error with description "block bitmap and bg descriptor inconsistent: X vs Y free clusters" calls ext4_force_shutdown. The conversion clears EXT4_STATE_MAY_INLINE_DATA but fails for ext4_destroy_inline_data_nolock and ext4_mark_iloc_dirty due to ext4_forced_shutdown. The restoration of inline data fails for the same reason not setting EXT4_STATE_MAY_INLINE_DATA. Without the flag set a regular process path in ext4_da_write_end follows trying to dereference page folio private pointer that has not been set. The fix calls early return with -EIO error shall the pointer to private be NULL. Sample crash report: Unable to handle kernel paging request at virtual address dfff800000000004 KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] Mem abort info: ESR = 0x0000000096000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [dfff800000000004] address between user and kernel address ranges Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 20274 Comm: syz-executor185 Not tainted 6.9.0-rc7-syzkaller-gfda5695d692c #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __block_commit_write+0x64/0x2b0 fs/buffer.c:2167 lr : __block_commit_write+0x3c/0x2b0 fs/buffer.c:2160 sp : ffff8000a1957600 x29: ffff8000a1957610 x28: dfff800000000000 x27: ffff0000e30e34b0 x26: 0000000000000000 x25: dfff800000000000 x24: dfff800000000000 x23: fffffdffc397c9e0 x22: 0000000000000020 x21: 0000000000000020 x20: 0000000000000040 x19: fffffdffc397c9c0 x18: 1fffe000367bd196 x17: ffff80008eead000 x16: ffff80008ae89e3c x15: 00000000200000c0 x14: 1fffe0001cbe4e04 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000001 x10: 0000000000ff0100 x9 : 0000000000000000 x8 : 0000000000000004 x7 : 0000000000000000 x6 : 0000000000000000 x5 : fffffdffc397c9c0 x4 : 0000000000000020 x3 : 0000000000000020 x2 : 0000000000000040 x1 : 0000000000000020 x0 : fffffdffc397c9c0 Call trace: __block_commit_write+0x64/0x2b0 fs/buffer.c:2167 block_write_end+0xb4/0x104 fs/buffer.c:2253 ext4_da_do_write_end fs/ext4/inode.c:2955 [inline] ext4_da_write_end+0x2c4/0xa40 fs/ext4/inode.c:3028 generic_perform_write+0x394/0x588 mm/filemap.c:3985 ext4_buffered_write_iter+0x2c0/0x4ec fs/ext4/file.c:299 ext4_file_write_iter+0x188/0x1780 call_write_iter include/linux/fs.h:2110 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x968/0xc3c fs/read_write.c:590 ksys_write+0x15c/0x26c fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __arm64_sys_write+0x7c/0x90 fs/read_write.c:652 __invoke_syscall arch/arm64/kernel/syscall.c:34 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:48 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:133 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:152 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Code: 97f85911 f94002da 91008356 d343fec8 (38796908) ---[ end trace 0000000000000000 ]--- ---------------- Code disassembly (best guess): 0: 97f85911 bl 0xffffffffffe16444 4: f94002da ldr x26, [x22] 8: 91008356 add x22, x26, #0x20 c: d343fec8 lsr x8, x22, #3 * 10: 38796908 ldrb w8, [x8, x25] <-- trapping instruction Reported-by: syzbot+18df508cf00a0598d9a6(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=18df508cf00a0598d9a6 Link: https://lore.kernel.org/all/000000000000f19a1406109eb5c5@google.com/T/ Signed-off-by: Wojciech Gładysz <wojciech.gladysz(a)infogain.com> Link: https://patch.msgid.link/20240703070112.10235-1-wojciech.gladysz@infogain.c… Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/buffer.c fs/ext4/inode.c [Since folio is not defined in the earlier version, page_private is judged ahead of time.] Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/buffer.c | 3 +++ fs/ext4/inode.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/fs/buffer.c b/fs/buffer.c index a74312b1bb42..fb8cb9993fc1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2070,6 +2070,9 @@ static int __block_commit_write(struct inode *inode, struct page *page, unsigned blocksize; struct buffer_head *bh, *head; + if (!page_has_buffers(page)) + return 0; + bh = head = page_buffers(page); blocksize = bh->b_size; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8e4407120cbc..ad7918c8df7b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3078,6 +3078,11 @@ static int ext4_da_do_write_end(struct address_space *mapping, bool disksize_changed = false; loff_t new_i_size; + if (unlikely(!page_has_buffers(page))) { + unlock_page(page); + put_page(page); + return -EIO; + } /* * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES * flag, which all that's needed to trigger page writeback. -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS V2] ext4: sanity check for NULL pointer after ext4_force_shutdown
by Zizhi Wo 03 Sep '24

03 Sep '24

From: Wojciech Gładysz <wojciech.gladysz(a)infogain.com> stable inclusion from stable-6.6.47 commit 3f6bbe6e07e5239294ecc3d2efa70d1f98aed52e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAMM9L CVE: CVE-2024-43898 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- [ Upstream commit 83f4414b8f84249d538905825b088ff3ae555652 ] Test case: 2 threads write short inline data to a file. In ext4_page_mkwrite the resulting inline data is converted. Handling ext4_grp_locked_error with description "block bitmap and bg descriptor inconsistent: X vs Y free clusters" calls ext4_force_shutdown. The conversion clears EXT4_STATE_MAY_INLINE_DATA but fails for ext4_destroy_inline_data_nolock and ext4_mark_iloc_dirty due to ext4_forced_shutdown. The restoration of inline data fails for the same reason not setting EXT4_STATE_MAY_INLINE_DATA. Without the flag set a regular process path in ext4_da_write_end follows trying to dereference page folio private pointer that has not been set. The fix calls early return with -EIO error shall the pointer to private be NULL. Sample crash report: Unable to handle kernel paging request at virtual address dfff800000000004 KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] Mem abort info: ESR = 0x0000000096000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [dfff800000000004] address between user and kernel address ranges Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 20274 Comm: syz-executor185 Not tainted 6.9.0-rc7-syzkaller-gfda5695d692c #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : __block_commit_write+0x64/0x2b0 fs/buffer.c:2167 lr : __block_commit_write+0x3c/0x2b0 fs/buffer.c:2160 sp : ffff8000a1957600 x29: ffff8000a1957610 x28: dfff800000000000 x27: ffff0000e30e34b0 x26: 0000000000000000 x25: dfff800000000000 x24: dfff800000000000 x23: fffffdffc397c9e0 x22: 0000000000000020 x21: 0000000000000020 x20: 0000000000000040 x19: fffffdffc397c9c0 x18: 1fffe000367bd196 x17: ffff80008eead000 x16: ffff80008ae89e3c x15: 00000000200000c0 x14: 1fffe0001cbe4e04 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000001 x10: 0000000000ff0100 x9 : 0000000000000000 x8 : 0000000000000004 x7 : 0000000000000000 x6 : 0000000000000000 x5 : fffffdffc397c9c0 x4 : 0000000000000020 x3 : 0000000000000020 x2 : 0000000000000040 x1 : 0000000000000020 x0 : fffffdffc397c9c0 Call trace: __block_commit_write+0x64/0x2b0 fs/buffer.c:2167 block_write_end+0xb4/0x104 fs/buffer.c:2253 ext4_da_do_write_end fs/ext4/inode.c:2955 [inline] ext4_da_write_end+0x2c4/0xa40 fs/ext4/inode.c:3028 generic_perform_write+0x394/0x588 mm/filemap.c:3985 ext4_buffered_write_iter+0x2c0/0x4ec fs/ext4/file.c:299 ext4_file_write_iter+0x188/0x1780 call_write_iter include/linux/fs.h:2110 [inline] new_sync_write fs/read_write.c:497 [inline] vfs_write+0x968/0xc3c fs/read_write.c:590 ksys_write+0x15c/0x26c fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __arm64_sys_write+0x7c/0x90 fs/read_write.c:652 __invoke_syscall arch/arm64/kernel/syscall.c:34 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:48 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:133 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:152 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Code: 97f85911 f94002da 91008356 d343fec8 (38796908) ---[ end trace 0000000000000000 ]--- ---------------- Code disassembly (best guess): 0: 97f85911 bl 0xffffffffffe16444 4: f94002da ldr x26, [x22] 8: 91008356 add x22, x26, #0x20 c: d343fec8 lsr x8, x22, #3 * 10: 38796908 ldrb w8, [x8, x25] <-- trapping instruction Reported-by: syzbot+18df508cf00a0598d9a6(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=18df508cf00a0598d9a6 Link: https://lore.kernel.org/all/000000000000f19a1406109eb5c5@google.com/T/ Signed-off-by: Wojciech Gładysz <wojciech.gladysz(a)infogain.com> Link: https://patch.msgid.link/20240703070112.10235-1-wojciech.gladysz@infogain.c… Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: fs/buffer.c fs/ext4/inode.c [Since folio is not defined in the earlier version, page_private is judged ahead of time.] Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/buffer.c | 3 +++ fs/ext4/inode.c | 6 ++++++ 2 files changed, 9 insertions(+) diff --git a/fs/buffer.c b/fs/buffer.c index af88734d1d38..ab98aefd8de3 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2037,6 +2037,9 @@ static int __block_commit_write(struct inode *inode, struct page *page, unsigned blocksize; struct buffer_head *bh, *head; + if (!page_has_buffers(page)) + return 0; + bh = head = page_buffers(page); blocksize = bh->b_size; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 35033bb43149..939def774e17 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3155,6 +3155,12 @@ static int ext4_da_write_end(struct file *file, if (unlikely(copied < len) && !PageUptodate(page)) copied = 0; + if (unlikely(!page_has_buffers(page))) { + unlock_page(page); + put_page(page); + return -EIO; + } + start = pos & (PAGE_SIZE - 1); end = start + copied - 1; -- 2.39.2

2 1

[openeuler:OLK-5.10 25143/30000] drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:104: warning: Excess function parameter 'direction' description in 'rnpgbevf_set_ring_vector'
by kernel test robot 03 Sep '24

03 Sep '24

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: b7bed6628b750ffd687d1da0a170dece4b0c08bd commit: 656d579e9c4f700f9f7debda0c2541f34fc39a35 [25143/30000] drivers: initial support for rnpgbevf drivers from Mucse Technology config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20240903/202409030213.Wm0NsmFj-lkp@…) compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240903/202409030213.Wm0NsmFj-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202409030213.Wm0NsmFj-lkp@intel.com/ All warnings (new ones prefixed by >>): drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:104: warning: Function parameter or member 'rnpgbevf_queue' not described in 'rnpgbevf_set_ring_vector' drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:104: warning: Function parameter or member 'rnpgbevf_msix_vector' not described in 'rnpgbevf_set_ring_vector' >> drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:104: warning: Excess function parameter 'direction' description in 'rnpgbevf_set_ring_vector' >> drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:104: warning: Excess function parameter 'queue' description in 'rnpgbevf_set_ring_vector' >> drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:104: warning: Excess function parameter 'msix_vector' description in 'rnpgbevf_set_ring_vector' drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:892: warning: Excess function parameter 'skb' description in 'rnpgbevf_is_non_eop' drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:1738: warning: Excess function parameter 'rx_ring' description in 'rnpgbevf_pull_tail' drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:2049: warning: Function parameter or member 'type' not described in 'rnpgbevf_update_itr' drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:3728: warning: Function parameter or member 't' not described in 'rnpgbevf_watchdog' drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c:3728: warning: Excess function parameter 'data' description in 'rnpgbevf_watchdog' vim +104 drivers/net/ethernet/mucse/rnpgbevf/rnpgbevf_main.c 94 95 /** 96 * rnpgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors 97 * @adapter: pointer to adapter struct 98 * @direction: 0 for Rx, 1 for Tx, -1 for other causes 99 * @queue: queue to map the corresponding interrupt to 100 * @msix_vector: the vector to map to the corresponding queue 101 */ 102 static void rnpgbevf_set_ring_vector(struct rnpgbevf_adapter *adapter, 103 u8 rnpgbevf_queue, u8 rnpgbevf_msix_vector) > 104 { 105 struct rnpgbevf_hw *hw = &adapter->hw; 106 u32 data = 0; 107 108 data = hw->vfnum << 24; 109 data |= (rnpgbevf_msix_vector << 8); 110 data |= (rnpgbevf_msix_vector << 0); 111 DPRINTK(IFUP, INFO, 112 "Set Ring-Vector queue:%d (reg:0x%x) <-- Rx-MSIX:%d, Tx-MSIX:%d\n", 113 rnpgbevf_queue, RING_VECTOR(rnpgbevf_queue), 114 rnpgbevf_msix_vector, rnpgbevf_msix_vector); 115 116 rnpgbevf_wr_reg(hw->ring_msix_base + RING_VECTOR(rnpgbevf_queue), data); 117 } 118 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] netfilter: ctnetlink: use helper function to calculate expect ID
by Zhang Changzhong 02 Sep '24

02 Sep '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> stable inclusion from stable-v4.19.320 commit 66e7650dbbb8e236e781c670b167edc81e771450 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IANOZB CVE: CVE-2024-44944 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit 782161895eb4ac45cf7cfa8db375bd4766cb8299 ] Delete expectation path is missing a call to the nf_expect_get_id() helper function to calculate the expectation ID, otherwise LSB of the expectation object address is leaked to userspace. Fixes: 3c79107631db ("netfilter: ctnetlink: don't use conntrack/expect object addresses as id") Reported-by: zdi-disclosures(a)trendmicro.com Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/netfilter/nf_conntrack_netlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 58bba2e2691f..331839218a1c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3142,7 +3142,8 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] netfilter: ctnetlink: use helper function to calculate expect ID
by Zhang Changzhong 02 Sep '24

02 Sep '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> stable inclusion from stable-v5.10.224 commit eb4ca1a97e08ff5b920664ba292e576257e2d184 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IANOZB CVE: CVE-2024-44944 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit 782161895eb4ac45cf7cfa8db375bd4766cb8299 ] Delete expectation path is missing a call to the nf_expect_get_id() helper function to calculate the expectation ID, otherwise LSB of the expectation object address is leaked to userspace. Fixes: 3c79107631db ("netfilter: ctnetlink: don't use conntrack/expect object addresses as id") Reported-by: zdi-disclosures(a)trendmicro.com Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/netfilter/nf_conntrack_netlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d44af1f3e7c5..e69a19357ade 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3385,7 +3385,8 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } -- 2.34.1

2 1

[PATCH OLK-5.10] netfilter: ctnetlink: use helper function to calculate expect ID
by Zhang Changzhong 02 Sep '24

02 Sep '24

From: Pablo Neira Ayuso <pablo(a)netfilter.org> stable inclusion from stable-v5.10.224 commit eb4ca1a97e08ff5b920664ba292e576257e2d184 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IANOZB CVE: CVE-2024-44944 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- [ Upstream commit 782161895eb4ac45cf7cfa8db375bd4766cb8299 ] Delete expectation path is missing a call to the nf_expect_get_id() helper function to calculate the expectation ID, otherwise LSB of the expectation object address is leaked to userspace. Fixes: 3c79107631db ("netfilter: ctnetlink: don't use conntrack/expect object addresses as id") Reported-by: zdi-disclosures(a)trendmicro.com Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/netfilter/nf_conntrack_netlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index c4c2659d0600..78329f4e171b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3387,7 +3387,8 @@ static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } -- 2.34.1

2 1

[PATCH OLK-6.6 00/22] large folios swap-in: handle refault cases first
by Liu Shixin 02 Sep '24

02 Sep '24

Barry Song (7): mm: remove the implementation of swap_free() and always use swap_free_nr() mm: introduce pte_move_swp_offset() helper which can move offset bidirectionally mm: introduce arch_do_swap_page_nr() which allows restore metadata for nr pages mm: swap: reuse exclusive folio directly instead of wp page faults mm: extend rmap flags arguments for folio_add_new_anon_rmap mm: use folio_add_new_anon_rmap() if folio_test_anon(folio)==false mm: remove folio_test_anon(folio)==false path in __folio_add_anon_rmap() Chuanhua Han (3): mm: swap: introduce swap_free_nr() for batched swap_free() mm: swap: make should_try_to_free_swap() support large-folio mm: swap: entirely map large folios found in swapcache Kefeng Wang (2): mm: ksm: use more folio api in ksm_might_need_to_copy() mm: memory: use a folio in validate_page_before_insert() Liu Shixin (1): mm: userswap: page_add_new_anon_rmap() -> folio_add_new_anon_rmap() Matthew Wilcox (Oracle) (8): mm: convert ksm_might_need_to_copy() to work on folios mm: convert unuse_pte() to use a folio throughout mm: remove some calls to page_add_new_anon_rmap() mm: remove stale example from comment mm: remove references to page_add_new_anon_rmap in comments mm: convert migrate_vma_insert_page() to use a folio mm: convert collapse_huge_page() to use a folio mm: remove page_add_new_anon_rmap and lru_cache_add_inactive_or_unevictable Yosry Ahmed (1): mm: rmap: abstract updating per-node and per-memcg stats include/linux/ksm.h | 10 ++-- include/linux/pgtable.h | 26 ++++++--- include/linux/rmap.h | 4 +- include/linux/swap.h | 12 +++-- kernel/events/uprobes.c | 2 +- kernel/power/swap.c | 5 +- mm/folio-compat.c | 16 ------ mm/huge_memory.c | 2 +- mm/internal.h | 25 +++++++-- mm/khugepaged.c | 15 +++--- mm/ksm.c | 58 ++++++++++---------- mm/memory.c | 115 ++++++++++++++++++++++++++++++---------- mm/memremap.c | 18 ++----- mm/migrate_device.c | 23 ++++---- mm/rmap.c | 102 ++++++++++++++++++----------------- mm/swapfile.c | 111 ++++++++++++++++++++++++++++---------- mm/userfaultfd.c | 2 +- mm/userswap.c | 6 +-- 18 files changed, 337 insertions(+), 215 deletions(-) -- 2.25.1

2 23

[PATCH OLK-5.10] nfsd: map the EBADMSG to nfserr_io to avoid warning
by Li Lingfeng 02 Sep '24

02 Sep '24

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAO6R4 Reference: https://lore.kernel.org/all/20240817062713.1819908-1-lilingfeng@huaweicloud… ---------------------------------------- Ext4 will throw -EBADMSG through ext4_readdir when a checksum error occurs, resulting in the following WARNING. Fix it by mapping EBADMSG to nfserr_io. nfsd_buffered_readdir iterate_dir // -EBADMSG -74 ext4_readdir // .iterate_shared ext4_dx_readdir ext4_htree_fill_tree htree_dirblock_to_tree ext4_read_dirblock __ext4_read_dirblock ext4_dirblock_csum_verify warn_no_space_for_csum __warn_no_space_for_csum return ERR_PTR(-EFSBADCRC) // -EBADMSG -74 nfserrno // WARNING [ 161.115610] ------------[ cut here ]------------ [ 161.116465] nfsd: non-standard errno: -74 [ 161.117315] WARNING: CPU: 1 PID: 780 at fs/nfsd/nfsproc.c:878 nfserrno+0x9d/0xd0 [ 161.118596] Modules linked in: [ 161.119243] CPU: 1 PID: 780 Comm: nfsd Not tainted 5.10.0-00014-g79679361fd5d #138 [ 161.120684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qe mu.org 04/01/2014 [ 161.123601] RIP: 0010:nfserrno+0x9d/0xd0 [ 161.124676] Code: 0f 87 da 30 dd 00 83 e3 01 b8 00 00 00 05 75 d7 44 89 ee 48 c7 c7 c0 57 24 98 89 44 24 04 c6 05 ce 2b 61 03 01 e8 99 20 d8 00 <0f> 0b 8b 44 24 04 eb b5 4c 89 e6 48 c7 c7 a0 6d a4 99 e8 cc 15 33 [ 161.127797] RSP: 0018:ffffc90000e2f9c0 EFLAGS: 00010286 [ 161.128794] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 161.130089] RDX: 1ffff1103ee16f6d RSI: 0000000000000008 RDI: fffff520001c5f2a [ 161.131379] RBP: 0000000000000022 R08: 0000000000000001 R09: ffff8881f70c1827 [ 161.132664] R10: ffffed103ee18304 R11: 0000000000000001 R12: 0000000000000021 [ 161.133949] R13: 00000000ffffffb6 R14: ffff8881317c0000 R15: ffffc90000e2fbd8 [ 161.135244] FS: 0000000000000000(0000) GS:ffff8881f7080000(0000) knlGS:0000000000000000 [ 161.136695] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 161.137761] CR2: 00007fcaad70b348 CR3: 0000000144256006 CR4: 0000000000770ee0 [ 161.139041] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 161.140291] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 161.141519] PKRU: 55555554 [ 161.142076] Call Trace: [ 161.142575] ? __warn+0x9b/0x140 [ 161.143229] ? nfserrno+0x9d/0xd0 [ 161.143872] ? report_bug+0x125/0x150 [ 161.144595] ? handle_bug+0x41/0x90 [ 161.145284] ? exc_invalid_op+0x14/0x70 [ 161.146009] ? asm_exc_invalid_op+0x12/0x20 [ 161.146816] ? nfserrno+0x9d/0xd0 [ 161.147487] nfsd_buffered_readdir+0x28b/0x2b0 [ 161.148333] ? nfsd4_encode_dirent_fattr+0x380/0x380 [ 161.149258] ? nfsd_buffered_filldir+0xf0/0xf0 [ 161.150093] ? wait_for_concurrent_writes+0x170/0x170 [ 161.151004] ? generic_file_llseek_size+0x48/0x160 [ 161.151895] nfsd_readdir+0x132/0x190 [ 161.152606] ? nfsd4_encode_dirent_fattr+0x380/0x380 [ 161.153516] ? nfsd_unlink+0x380/0x380 [ 161.154256] ? override_creds+0x45/0x60 [ 161.155006] nfsd4_encode_readdir+0x21a/0x3d0 [ 161.155850] ? nfsd4_encode_readlink+0x210/0x210 [ 161.156731] ? write_bytes_to_xdr_buf+0x97/0xe0 [ 161.157598] ? __write_bytes_to_xdr_buf+0xd0/0xd0 [ 161.158494] ? lock_downgrade+0x90/0x90 [ 161.159232] ? nfs4svc_decode_voidarg+0x10/0x10 [ 161.160092] nfsd4_encode_operation+0x15a/0x440 [ 161.160959] nfsd4_proc_compound+0x718/0xe90 [ 161.161818] nfsd_dispatch+0x18e/0x2c0 [ 161.162586] svc_process_common+0x786/0xc50 [ 161.163403] ? nfsd_svc+0x380/0x380 [ 161.164137] ? svc_printk+0x160/0x160 [ 161.164846] ? svc_xprt_do_enqueue.part.0+0x365/0x380 [ 161.165808] ? nfsd_svc+0x380/0x380 [ 161.166523] ? rcu_is_watching+0x23/0x40 [ 161.167309] svc_process+0x1a5/0x200 [ 161.168019] nfsd+0x1f5/0x380 [ 161.168663] ? nfsd_shutdown_threads+0x260/0x260 [ 161.169554] kthread+0x1c4/0x210 [ 161.170224] ? kthread_insert_work_sanity_check+0x80/0x80 [ 161.171246] ret_from_fork+0x1f/0x30 Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> Conflicts: fs/nfsd/vfs.c [Commit 68f7bd7f29a0 ("nfsd: move nfserrno() to vfs.c") move nfserrno() to vfs.c] Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/nfsd/nfsproc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index bbd01e8397f6..6e9369b19f89 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -843,6 +843,7 @@ nfserrno (int errno) { nfserr_serverfault, -ENFILE }, { nfserr_io, -EUCLEAN }, { nfserr_perm, -ENOKEY }, + { nfserr_io, -EBADMSG }, }; int i; -- 2.31.1

2 1

[PATCH OLK-5.10 0/3] soc: hisilicon: Support memory repair driver
by Junhao He 02 Sep '24

02 Sep '24

Support memory repair driver on Kunpeng SoC. Junhao He (1): config: enable CONFIG_HISI_MEM_RAS by default Xiaofei Tan (2): soc: hisilicon: Support memory repair driver on Kunpeng SoC docs: ABI: add ABI document for driver hisi_mem_ras .../sysfs-devices-platform-hisi_mem_ras | 41 ++ MAINTAINERS | 7 + arch/arm64/configs/openeuler_defconfig | 1 + drivers/soc/hisilicon/Kconfig | 14 + drivers/soc/hisilicon/Makefile | 1 + drivers/soc/hisilicon/hisi_mem_ras.c | 582 ++++++++++++++++++ drivers/soc/hisilicon/hisi_mem_ras.h | 112 ++++ 7 files changed, 758 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-devices-platform-hisi_mem_ras create mode 100644 drivers/soc/hisilicon/hisi_mem_ras.c create mode 100644 drivers/soc/hisilicon/hisi_mem_ras.h -- 2.33.0

2 4

[PATCH OLK-5.10 0/2] Fix xfs fsmap error
by Zizhi Wo 02 Sep '24

02 Sep '24

xfs fsmap bugfix. Darrick J. Wong (2): xfs: fix interval filtering in multi-step fsmap queries xfs: fix an agbno overflow in __xfs_getfsmap_datadev fs/xfs/xfs_fsmap.c | 80 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 60 insertions(+), 20 deletions(-) -- 2.39.2

2 3

[PATCH OLK-5.10] xfs: fix log recovery when unknown rocompat bits are set
by Zizhi Wo 02 Sep '24

02 Sep '24

From: "Darrick J. Wong" <djwong(a)kernel.org> mainline inclusion from mainline-v6.6-rc3 commit 74ad4693b6473950e971b3dc525b5ee7570e05d0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAO91J Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Log recovery has always run on read only mounts, even where the primary superblock advertises unknown rocompat bits. Due to a misunderstanding between Eric and Darrick back in 2018, we accidentally changed the superblock write verifier to shutdown the fs over that exact scenario. As a result, the log cleaning that occurs at the end of the mounting process fails if there are unknown rocompat bits set. As we now allow writing of the superblock if there are unknown rocompat bits set on a RO mount, we no longer want to turn off RO state to allow log recovery to succeed on a RO mount. Hence we also remove all the (now unnecessary) RO state toggling from the log recovery path. Fixes: 9e037cb7972f ("xfs: check for unknown v5 feature bits in superblock write verifier" Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: Dave Chinner <dchinner(a)redhat.com> Conflicts: fs/xfs/xfs_log.c [Simple context inconsistencies do not affect the code logic.] Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/xfs/libxfs/xfs_sb.c | 3 ++- fs/xfs/xfs_log.c | 17 ----------------- 2 files changed, 2 insertions(+), 18 deletions(-) diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a4354504986c..d7ab26cb3312 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -280,7 +280,8 @@ xfs_validate_sb_write( return -EFSCORRUPTED; } - if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { + if (!xfs_is_readonly(mp) && + xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 9a363f787ba4..f8cf48d3aaf7 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -687,15 +687,7 @@ xfs_log_mount( * just worked. */ if (!xfs_has_norecovery(mp)) { - /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - bool readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, - &mp->m_opstate); error = xlog_recover(log); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); if (error) { xfs_warn(mp, "log mount/recovery failed: error %d", error); @@ -744,7 +736,6 @@ xfs_log_mount_finish( struct xfs_mount *mp) { struct xlog *log = mp->m_log; - bool readonly; int error = 0; if (xfs_has_norecovery(mp)) { @@ -752,12 +743,6 @@ xfs_log_mount_finish( return 0; } - /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); - /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. @@ -809,8 +794,6 @@ xfs_log_mount_finish( xfs_wait_buftarg(mp->m_ddev_targp); clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); /* Make sure the log is dead if we're returning failure. */ ASSERT(!error || xlog_is_shutdown(log)); -- 2.39.2

2 1

[PATCH v3 OLK-5.10 0/4] Some features and fixs for hbmdev and hbm cache
by Zhang Zekun 02 Sep '24

02 Sep '24

hbmdev and hbmcache new features and new fixs. v2: - Fix format warning v3: - Improve the patch subject Zhang Zekun (4): soc:hisilicon: Use _ON and _OFF in hbmcache hisilicon/hisi_hbmcache: Add a lock to protect pcc operation region hisilicon/hisi_hbmdev: Add lock to protect pcc operation region ACPI/HMAT: Add missing locality information for hot-added device drivers/acpi/acpi_memhotplug.c | 13 +++++++++++++ drivers/acpi/internal.h | 1 + drivers/acpi/numa/hmat.c | 17 +++++++++++++++++ drivers/soc/hisilicon/hisi_hbmcache.c | 20 +++++++++++++------- drivers/soc/hisilicon/hisi_hbmdev.c | 2 ++ 5 files changed, 46 insertions(+), 7 deletions(-) -- 2.17.1

2 5

[PATCH OLK-6.6] nfsd: map the EBADMSG to nfserr_io to avoid warning
by Li Lingfeng 02 Sep '24

02 Sep '24

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAO6R4 Reference: https://lore.kernel.org/all/20240817062713.1819908-1-lilingfeng@huaweicloud… ---------------------------------------- Ext4 will throw -EBADMSG through ext4_readdir when a checksum error occurs, resulting in the following WARNING. Fix it by mapping EBADMSG to nfserr_io. nfsd_buffered_readdir iterate_dir // -EBADMSG -74 ext4_readdir // .iterate_shared ext4_dx_readdir ext4_htree_fill_tree htree_dirblock_to_tree ext4_read_dirblock __ext4_read_dirblock ext4_dirblock_csum_verify warn_no_space_for_csum __warn_no_space_for_csum return ERR_PTR(-EFSBADCRC) // -EBADMSG -74 nfserrno // WARNING [ 161.115610] ------------[ cut here ]------------ [ 161.116465] nfsd: non-standard errno: -74 [ 161.117315] WARNING: CPU: 1 PID: 780 at fs/nfsd/nfsproc.c:878 nfserrno+0x9d/0xd0 [ 161.118596] Modules linked in: [ 161.119243] CPU: 1 PID: 780 Comm: nfsd Not tainted 5.10.0-00014-g79679361fd5d #138 [ 161.120684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qe mu.org 04/01/2014 [ 161.123601] RIP: 0010:nfserrno+0x9d/0xd0 [ 161.124676] Code: 0f 87 da 30 dd 00 83 e3 01 b8 00 00 00 05 75 d7 44 89 ee 48 c7 c7 c0 57 24 98 89 44 24 04 c6 05 ce 2b 61 03 01 e8 99 20 d8 00 <0f> 0b 8b 44 24 04 eb b5 4c 89 e6 48 c7 c7 a0 6d a4 99 e8 cc 15 33 [ 161.127797] RSP: 0018:ffffc90000e2f9c0 EFLAGS: 00010286 [ 161.128794] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 161.130089] RDX: 1ffff1103ee16f6d RSI: 0000000000000008 RDI: fffff520001c5f2a [ 161.131379] RBP: 0000000000000022 R08: 0000000000000001 R09: ffff8881f70c1827 [ 161.132664] R10: ffffed103ee18304 R11: 0000000000000001 R12: 0000000000000021 [ 161.133949] R13: 00000000ffffffb6 R14: ffff8881317c0000 R15: ffffc90000e2fbd8 [ 161.135244] FS: 0000000000000000(0000) GS:ffff8881f7080000(0000) knlGS:0000000000000000 [ 161.136695] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 161.137761] CR2: 00007fcaad70b348 CR3: 0000000144256006 CR4: 0000000000770ee0 [ 161.139041] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 161.140291] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 161.141519] PKRU: 55555554 [ 161.142076] Call Trace: [ 161.142575] ? __warn+0x9b/0x140 [ 161.143229] ? nfserrno+0x9d/0xd0 [ 161.143872] ? report_bug+0x125/0x150 [ 161.144595] ? handle_bug+0x41/0x90 [ 161.145284] ? exc_invalid_op+0x14/0x70 [ 161.146009] ? asm_exc_invalid_op+0x12/0x20 [ 161.146816] ? nfserrno+0x9d/0xd0 [ 161.147487] nfsd_buffered_readdir+0x28b/0x2b0 [ 161.148333] ? nfsd4_encode_dirent_fattr+0x380/0x380 [ 161.149258] ? nfsd_buffered_filldir+0xf0/0xf0 [ 161.150093] ? wait_for_concurrent_writes+0x170/0x170 [ 161.151004] ? generic_file_llseek_size+0x48/0x160 [ 161.151895] nfsd_readdir+0x132/0x190 [ 161.152606] ? nfsd4_encode_dirent_fattr+0x380/0x380 [ 161.153516] ? nfsd_unlink+0x380/0x380 [ 161.154256] ? override_creds+0x45/0x60 [ 161.155006] nfsd4_encode_readdir+0x21a/0x3d0 [ 161.155850] ? nfsd4_encode_readlink+0x210/0x210 [ 161.156731] ? write_bytes_to_xdr_buf+0x97/0xe0 [ 161.157598] ? __write_bytes_to_xdr_buf+0xd0/0xd0 [ 161.158494] ? lock_downgrade+0x90/0x90 [ 161.159232] ? nfs4svc_decode_voidarg+0x10/0x10 [ 161.160092] nfsd4_encode_operation+0x15a/0x440 [ 161.160959] nfsd4_proc_compound+0x718/0xe90 [ 161.161818] nfsd_dispatch+0x18e/0x2c0 [ 161.162586] svc_process_common+0x786/0xc50 [ 161.163403] ? nfsd_svc+0x380/0x380 [ 161.164137] ? svc_printk+0x160/0x160 [ 161.164846] ? svc_xprt_do_enqueue.part.0+0x365/0x380 [ 161.165808] ? nfsd_svc+0x380/0x380 [ 161.166523] ? rcu_is_watching+0x23/0x40 [ 161.167309] svc_process+0x1a5/0x200 [ 161.168019] nfsd+0x1f5/0x380 [ 161.168663] ? nfsd_shutdown_threads+0x260/0x260 [ 161.169554] kthread+0x1c4/0x210 [ 161.170224] ? kthread_insert_work_sanity_check+0x80/0x80 [ 161.171246] ret_from_fork+0x1f/0x30 Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- fs/nfsd/vfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 1f2a5b22b649..b3e51d88faff 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -101,6 +101,7 @@ nfserrno (int errno) { nfserr_io, -EUCLEAN }, { nfserr_perm, -ENOKEY }, { nfserr_no_grace, -ENOGRACE}, + { nfserr_io, -EBADMSG }, }; int i; -- 2.31.1

2 1

[PATCH v2 OLK-5.10 0/4] Some features and fixs for hbmdev and hbm cache
by Zhang Zekun 02 Sep '24

02 Sep '24

hbmdev and hbmcache new features and new fixs. v2: - Fix format warning Zhang Zekun (4): soc:hisilicon: Use _ON and _OFF in hbmcache hisilicon/hisi_hbmcache: Add a lock to prevent conrrency hisilicon/hisi_hbmdev: Add lock to prevent correnctly ACPI/HMAT: Add missing locality information for hot-added device drivers/acpi/acpi_memhotplug.c | 13 +++++++++++++ drivers/acpi/internal.h | 1 + drivers/acpi/numa/hmat.c | 17 +++++++++++++++++ drivers/soc/hisilicon/hisi_hbmcache.c | 20 +++++++++++++------- drivers/soc/hisilicon/hisi_hbmdev.c | 2 ++ 5 files changed, 46 insertions(+), 7 deletions(-) -- 2.17.1

2 5

[openeuler:OLK-5.10 26911/30000] drivers/ub/urma/ubcore/ubcore_umem.c:284:10: warning: no previous prototype for function 'ubcore_umem_find_best_page_size'
by kernel test robot 02 Sep '24

02 Sep '24

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: 02994a9b68a17040658e1a32a4438a31ae6f273b commit: 5d130e2cfa3d2aaee4d10e18c075f6c3750600c5 [26911/30000] urma: upload kernel patch for 20240511_mig config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20240902/202409021518.znzh3BK4-lkp@…) compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240902/202409021518.znzh3BK4-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202409021518.znzh3BK4-lkp@intel.com/ All warnings (new ones prefixed by >>): drivers/ub/urma/ubcore/ubcore_umem.c:242:21: warning: no previous prototype for function 'ubcore_umem_get' [-Wmissing-prototypes] 242 | struct ubcore_umem *ubcore_umem_get(struct ubcore_device *dev, uint64_t va, | ^ drivers/ub/urma/ubcore/ubcore_umem.c:242:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 242 | struct ubcore_umem *ubcore_umem_get(struct ubcore_device *dev, uint64_t va, | ^ | static drivers/ub/urma/ubcore/ubcore_umem.c:260:6: warning: no previous prototype for function 'ubcore_umem_release' [-Wmissing-prototypes] 260 | void ubcore_umem_release(struct ubcore_umem *umem) | ^ drivers/ub/urma/ubcore/ubcore_umem.c:260:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 260 | void ubcore_umem_release(struct ubcore_umem *umem) | ^ | static >> drivers/ub/urma/ubcore/ubcore_umem.c:284:10: warning: no previous prototype for function 'ubcore_umem_find_best_page_size' [-Wmissing-prototypes] 284 | uint64_t ubcore_umem_find_best_page_size(struct ubcore_umem *umem, uint64_t page_size_bitmap, | ^ drivers/ub/urma/ubcore/ubcore_umem.c:284:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 284 | uint64_t ubcore_umem_find_best_page_size(struct ubcore_umem *umem, uint64_t page_size_bitmap, | ^ | static 3 warnings generated. -- drivers/ub/urma/ubcore/ubcore_netdev.c:41:25: warning: no previous prototype for function 'ubcore_lookup_sip_info_without_lock' [-Wmissing-prototypes] 41 | struct ubcore_sip_info *ubcore_lookup_sip_info_without_lock( | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:41:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 41 | struct ubcore_sip_info *ubcore_lookup_sip_info_without_lock( | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:75:5: warning: no previous prototype for function 'ubcore_notify_uvs_del_sip' [-Wmissing-prototypes] 75 | int ubcore_notify_uvs_del_sip(struct ubcore_device *dev, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:75:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 75 | int ubcore_notify_uvs_del_sip(struct ubcore_device *dev, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:113:22: warning: no previous prototype for function 'ubcore_new_sip_req_msg' [-Wmissing-prototypes] 113 | struct ubcore_nlmsg *ubcore_new_sip_req_msg(struct ubcore_device *dev, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:113:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 113 | struct ubcore_nlmsg *ubcore_new_sip_req_msg(struct ubcore_device *dev, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:145:5: warning: no previous prototype for function 'ubcore_notify_uvs_add_sip' [-Wmissing-prototypes] 145 | int ubcore_notify_uvs_add_sip(struct ubcore_device *dev, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:145:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 145 | int ubcore_notify_uvs_add_sip(struct ubcore_device *dev, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:177:5: warning: no previous prototype for function 'ubcore_check_port_state' [-Wmissing-prototypes] 177 | int ubcore_check_port_state(struct ubcore_device *dev) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:177:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 177 | int ubcore_check_port_state(struct ubcore_device *dev) | ^ | static >> drivers/ub/urma/ubcore/ubcore_netdev.c:204:6: warning: no previous prototype for function 'ubcore_fill_port_netdev' [-Wmissing-prototypes] 204 | void ubcore_fill_port_netdev(struct ubcore_device *dev, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:204:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 204 | void ubcore_fill_port_netdev(struct ubcore_device *dev, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:268:5: warning: no previous prototype for function 'ubcore_set_port_netdev' [-Wmissing-prototypes] 268 | int ubcore_set_port_netdev(struct ubcore_device *dev, struct net_device *ndev, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:268:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 268 | int ubcore_set_port_netdev(struct ubcore_device *dev, struct net_device *ndev, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:353:5: warning: no previous prototype for function 'ubcore_unset_port_netdev' [-Wmissing-prototypes] 353 | int ubcore_unset_port_netdev(struct ubcore_device *dev, struct net_device *ndev, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:353:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 353 | int ubcore_unset_port_netdev(struct ubcore_device *dev, struct net_device *ndev, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:385:6: warning: no previous prototype for function 'ubcore_put_port_netdev' [-Wmissing-prototypes] 385 | void ubcore_put_port_netdev(struct ubcore_device *dev) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:385:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 385 | void ubcore_put_port_netdev(struct ubcore_device *dev) | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:412:5: warning: no previous prototype for function 'ubcore_sip_table_init' [-Wmissing-prototypes] 412 | int ubcore_sip_table_init(struct ubcore_sip_table *sip_table, uint32_t size) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:412:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 412 | int ubcore_sip_table_init(struct ubcore_sip_table *sip_table, uint32_t size) | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:431:6: warning: no previous prototype for function 'ubcore_sip_table_uninit' [-Wmissing-prototypes] 431 | void ubcore_sip_table_uninit(struct ubcore_sip_table *sip_table) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:431:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 431 | void ubcore_sip_table_uninit(struct ubcore_sip_table *sip_table) | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:442:5: warning: no previous prototype for function 'ubcore_sip_idx_alloc' [-Wmissing-prototypes] 442 | int ubcore_sip_idx_alloc(struct ubcore_sip_table *sip_table) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:442:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 442 | int ubcore_sip_idx_alloc(struct ubcore_sip_table *sip_table) | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:458:5: warning: no previous prototype for function 'ubcore_sip_idx_free' [-Wmissing-prototypes] 458 | int ubcore_sip_idx_free(struct ubcore_sip_table *sip_table, uint32_t idx) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:458:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 458 | int ubcore_sip_idx_free(struct ubcore_sip_table *sip_table, uint32_t idx) | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:471:5: warning: no previous prototype for function 'ubcore_add_sip_entry' [-Wmissing-prototypes] 471 | int ubcore_add_sip_entry(struct ubcore_sip_table *sip_table, const struct ubcore_sip_info *sip, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:471:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 471 | int ubcore_add_sip_entry(struct ubcore_sip_table *sip_table, const struct ubcore_sip_info *sip, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:489:5: warning: no previous prototype for function 'ubcore_del_sip_entry' [-Wmissing-prototypes] 489 | int ubcore_del_sip_entry(struct ubcore_sip_table *sip_table, uint32_t idx) | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:489:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 489 | int ubcore_del_sip_entry(struct ubcore_sip_table *sip_table, uint32_t idx) | ^ | static >> drivers/ub/urma/ubcore/ubcore_netdev.c:519:5: warning: no previous prototype for function 'ubcore_update_sip_entry' [-Wmissing-prototypes] 519 | int ubcore_update_sip_entry(struct ubcore_sip_table *sip_table, struct ubcore_sip_info *new_sip, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:519:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 519 | int ubcore_update_sip_entry(struct ubcore_sip_table *sip_table, struct ubcore_sip_info *new_sip, | ^ | static drivers/ub/urma/ubcore/ubcore_netdev.c:548:5: warning: no previous prototype for function 'ubcore_lookup_sip_idx' [-Wmissing-prototypes] 548 | int ubcore_lookup_sip_idx(struct ubcore_sip_table *sip_table, struct ubcore_sip_info *sip, | ^ drivers/ub/urma/ubcore/ubcore_netdev.c:548:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 548 | int ubcore_lookup_sip_idx(struct ubcore_sip_table *sip_table, struct ubcore_sip_info *sip, | ^ | static 17 warnings generated. -- >> drivers/ub/urma/ubcore/ubcore_tpg.c:85:6: warning: no previous prototype for function 'ubcore_tpg_kref_get' [-Wmissing-prototypes] 85 | void ubcore_tpg_kref_get(struct ubcore_tpg *tpg) | ^ drivers/ub/urma/ubcore/ubcore_tpg.c:85:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 85 | void ubcore_tpg_kref_get(struct ubcore_tpg *tpg) | ^ | static drivers/ub/urma/ubcore/ubcore_tpg.c:100:30: warning: comparison of address of 'dev->ht[UBCORE_HT_TPG].head' equal to a null pointer is always false [-Wtautological-pointer-compare] 100 | if (&dev->ht[UBCORE_HT_TPG].head == NULL) { | ~~~~~~~~~~~~~~~~~~~~~~~^~~~ ~~~~ >> drivers/ub/urma/ubcore/ubcore_tpg.c:131:29: warning: comparison of address of 'dev->ht[UBCORE_HT_TP].head' equal to a null pointer is always false [-Wtautological-pointer-compare] 131 | if (&dev->ht[UBCORE_HT_TP].head == NULL) { | ~~~~~~~~~~~~~~~~~~~~~~^~~~ ~~~~ 3 warnings generated. -- >> drivers/ub/urma/uburma/uburma_mmap.c:29:6: warning: no previous prototype for function 'uburma_umap_priv_init' [-Wmissing-prototypes] 29 | void uburma_umap_priv_init(struct uburma_umap_priv *priv, | ^ drivers/ub/urma/uburma/uburma_mmap.c:29:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 29 | void uburma_umap_priv_init(struct uburma_umap_priv *priv, | ^ | static >> drivers/ub/urma/uburma/uburma_mmap.c:42:6: warning: no previous prototype for function 'uburma_unmap_vma_pages' [-Wmissing-prototypes] 42 | void uburma_unmap_vma_pages(struct uburma_file *ufile) | ^ drivers/ub/urma/uburma/uburma_mmap.c:42:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 42 | void uburma_unmap_vma_pages(struct uburma_file *ufile) | ^ | static >> drivers/ub/urma/uburma/uburma_mmap.c:157:36: warning: no previous prototype for function 'uburma_get_umap_ops' [-Wmissing-prototypes] 157 | const struct vm_operations_struct *uburma_get_umap_ops(void) | ^ drivers/ub/urma/uburma/uburma_mmap.c:157:7: note: declare 'static' if the function is not intended to be used outside of this translation unit 157 | const struct vm_operations_struct *uburma_get_umap_ops(void) | ^ | static 3 warnings generated. vim +/ubcore_umem_find_best_page_size +284 drivers/ub/urma/ubcore/ubcore_umem.c 259 > 260 void ubcore_umem_release(struct ubcore_umem *umem) 261 { 262 uint64_t npages; 263 264 if (IS_ERR_OR_NULL(umem) || umem->ub_dev == NULL || umem->owning_mm == NULL) { 265 ubcore_log_err("Invalid parameter.\n"); 266 return; 267 } 268 269 if (((umem->va + umem->length) < umem->va) || 270 PAGE_ALIGN(umem->va + umem->length) < (umem->va + umem->length)) { 271 ubcore_log_err("Invalid parameter, va or len is invalid.\n"); 272 return; 273 } 274 275 npages = umem_cal_npages(umem->va, umem->length); 276 dma_unmap_sg(umem->ub_dev->dma_dev, umem->sg_head.sgl, (int)umem->nmap, DMA_BIDIRECTIONAL); 277 umem_free_sgt(umem); 278 umem_atomic_sub(npages, umem->owning_mm); 279 mmdrop(umem->owning_mm); 280 kfree(umem); 281 } 282 EXPORT_SYMBOL(ubcore_umem_release); 283 > 284 uint64_t ubcore_umem_find_best_page_size(struct ubcore_umem *umem, uint64_t page_size_bitmap, -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] jbd2: avoid mount failed when commit block is partial submitted
by Baokun Li 02 Sep '24

02 Sep '24

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v6.11-rc1 commit 0bab8db4152c4a2185a1367db09cc402bdc62d5e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAJ5DD CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- We encountered a problem that the file system could not be mounted in the power-off scenario. The analysis of the file system mirror shows that only part of the data is written to the last commit block. The valid data of the commit block is concentrated in the first sector. However, the data of the entire block is involved in the checksum calculation. For different hardware, the minimum atomic unit may be different. If the checksum of a committed block is incorrect, clear the data except the 'commit_header' and then calculate the checksum. If the checkusm is correct, it is considered that the block is partially committed, Then continue to replay journal. Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://patch.msgid.link/20240620072405.3533701-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/jbd2/recovery.c [There is a context conflict because commit a20d1cebb98b ("jbd2: fix portability problems caused by unaligned accesses") is not merged.] Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/jbd2/recovery.c | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 55f89fcee666..3aa91c8bf8d2 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -401,6 +401,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) return provided == cpu_to_be32(calculated); } +static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf) +{ + struct commit_header *h; + __be32 provided; + __u32 calculated; + void *tmpbuf; + + tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL); + if (!tmpbuf) + return false; + + memcpy(tmpbuf, buf, sizeof(struct commit_header)); + h = tmpbuf; + provided = h->h_chksum[0]; + h->h_chksum[0] = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize); + kfree(tmpbuf); + + return provided == cpu_to_be32(calculated); +} + static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, void *buf, __u32 sequence) { @@ -768,6 +789,13 @@ static int do_one_pass(journal_t *journal, if (pass == PASS_SCAN && !jbd2_commit_block_csum_verify(journal, bh->b_data)) { + if (jbd2_commit_block_csum_verify_partial( + journal, + bh->b_data)) { + pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n", + next_commit_ID, next_log_block); + goto chksum_ok; + } chksum_error: if (commit_time < last_trans_commit_time) goto ignore_crc_mismatch; @@ -780,8 +808,10 @@ static int do_one_pass(journal_t *journal, break; } } - if (pass == PASS_SCAN) + if (pass == PASS_SCAN) { + chksum_ok: last_trans_commit_time = commit_time; + } brelse(bh); next_commit_ID++; continue; @@ -798,6 +828,7 @@ static int do_one_pass(journal_t *journal, next_log_block); need_check_commit_time = true; } + /* If we aren't in the REVOKE pass, then we can * just skip over this block. */ if (pass != PASS_REVOKE) { -- 2.31.1

2 1

[PATCH openEuler-22.03-LTS-SP1] jbd2: avoid mount failed when commit block is partial submitted
by Baokun Li 02 Sep '24

02 Sep '24

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v6.11-rc1 commit 0bab8db4152c4a2185a1367db09cc402bdc62d5e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAJ5DD Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- We encountered a problem that the file system could not be mounted in the power-off scenario. The analysis of the file system mirror shows that only part of the data is written to the last commit block. The valid data of the commit block is concentrated in the first sector. However, the data of the entire block is involved in the checksum calculation. For different hardware, the minimum atomic unit may be different. If the checksum of a committed block is incorrect, clear the data except the 'commit_header' and then calculate the checksum. If the checkusm is correct, it is considered that the block is partially committed, Then continue to replay journal. Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://patch.msgid.link/20240620072405.3533701-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/jbd2/recovery.c [There is a context conflict because commit a20d1cebb98b ("jbd2: fix portability problems caused by unaligned accesses") is not merged.] Signed-off-by: Baokun Li <libaokun1(a)huawei.com> --- fs/jbd2/recovery.c | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index cdf4c553f058..6301badc8cbd 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -446,6 +446,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) return provided == cpu_to_be32(calculated); } +static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf) +{ + struct commit_header *h; + __be32 provided; + __u32 calculated; + void *tmpbuf; + + tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL); + if (!tmpbuf) + return false; + + memcpy(tmpbuf, buf, sizeof(struct commit_header)); + h = tmpbuf; + provided = h->h_chksum[0]; + h->h_chksum[0] = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize); + kfree(tmpbuf); + + return provided == cpu_to_be32(calculated); +} + static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, void *buf, __u32 sequence) { @@ -814,6 +835,13 @@ static int do_one_pass(journal_t *journal, if (pass == PASS_SCAN && !jbd2_commit_block_csum_verify(journal, bh->b_data)) { + if (jbd2_commit_block_csum_verify_partial( + journal, + bh->b_data)) { + pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n", + next_commit_ID, next_log_block); + goto chksum_ok; + } chksum_error: if (commit_time < last_trans_commit_time) goto ignore_crc_mismatch; @@ -826,8 +854,10 @@ static int do_one_pass(journal_t *journal, break; } } - if (pass == PASS_SCAN) + if (pass == PASS_SCAN) { + chksum_ok: last_trans_commit_time = commit_time; + } brelse(bh); next_commit_ID++; continue; @@ -844,6 +874,7 @@ static int do_one_pass(journal_t *journal, next_log_block); need_check_commit_time = true; } + /* If we aren't in the REVOKE pass, then we can * just skip over this block. */ if (pass != PASS_REVOKE) { -- 2.31.1

2 1