In the Linux kernel, the following vulnerability has been resolved:
drm/panthor: Recover from panthor_gpu_flush_caches() failures
We have seen a few cases where the whole memory subsystem is blocked
and flush operations never complete. When that happens, we want to:
- schedule a reset, so we can recover from this situation
- in the reset path, we need to reset the pending_reqs so we can send
new commands after the reset
- if more panthor_gpu_flush_caches() operations are queued after
the timeout, we skip them and return -EIO directly to avoid needless
waits (the memory block won't miraculously work again)
Note that we drop the WARN_ON()s because these hangs can be triggered
with buggy GPU jobs created by the UMD, and there's no way we can
prevent it. We do keep the error messages though.
v2:
- New patch
v3:
- Collect R-b
- Explicitly mention the fact we dropped the WARN_ON()s in the commit
message
v4:
- No changes
An issue was discovered in Django 6.0 before 6.0.6 and 5.2 before 5.2.15.
`django.core.mail.backends.smtp.EmailBackend` in Django fails to prevent reuse of a partially-initialized connection after a failed `STARTTLS` handshake when `fail_silently=True`, which allows on-path network attackers to read email content via cleartext interception.
Earlier, unsupported Django series (such as 5.0.x, 4.1.x, and 3.2.x) were not evaluated and may also be affected.
Django would like to thank Kasper Dupont for reporting this issue.
An issue was discovered in Django 5.2 before 5.2.15 and 6.0 before 6.0.6.
`django.middleware.cache.UpdateCacheMiddleware` in Django does not match `Cache-Control` response directives case-insensitively, which allows remote attackers to read responses that were incorrectly cached because their `Cache-Control` directives used uppercase or mixed-case values.
Earlier, unsupported Django series (such as 5.0.x, 4.1.x, and 3.2.x) were not evaluated and may also be affected.
Django would like to thank Ahmed Badawe for reporting this issue.
A vulnerability in the LightGlue model loading path of huggingface/transformers version 5.2.0 allows an attacker-controlled model repository to execute arbitrary code during model initialization. The issue arises because the `trust_remote_code` parameter, intended to prevent remote code execution, is overridden by untrusted serialized configuration data in a nested code path. Specifically, when loading a LightGlue model using `AutoModel.from_pretrained()` with `trust_remote_code=False`, the `LightGlueConfig` reads the `trust_remote_code` value from the untrusted `config.json` file and propagates it into nested `AutoConfig.from_pretrained()` calls. This results in the execution of attacker-provided Python modules, even when the victim explicitly disables remote code execution. The vulnerability poses a high risk for environments such as API inference servers, research notebooks, CI/CD pipelines, and model evaluation workers, potentially leading to credential theft, lateral movement, or persistence/backdoor deployment.
An issue was discovered in Django 6.0 before 6.0.6 and 5.2 before 5.2.15.
`django.http.HttpRequest.get_signed_cookie` in Django uses a non-injective salt derivation (concatenating the cookie name and salt argument), which allows a remote attacker to use a cookie in a context different from the one where it was signed, via distinct `(name, salt)` pairs that produce the same concatenation.
Earlier, unsupported Django series (such as 5.0.x, 4.1.x, and 3.2.x) were not evaluated and may also be affected.
Django would like to thank Peng Zhou for reporting this issue.
An issue was discovered in Django 5.2 before 5.2.15 and 6.0 before 6.0.6.
`django.utils.cache.has_vary_header()` in Django does not strip leading or trailing whitespace from `Vary` response header values before comparison, which allows remote attackers to read cached responses via requests to URLs whose responses contain whitespace-padded Vary header values.
Earlier, unsupported Django series (such as 5.0.x, 4.1.x, and 3.2.x) were not evaluated and may also be affected.
Django would like to thank Navid Rezazadeh for reporting this issue.
An issue was discovered in Django 5.2 before 5.2.15 and 6.0 before 6.0.6.
`django.middleware.cache.UpdateCacheMiddleware` in Django does not add `Authorization` to the `Vary` response header for requests bearing that header without `Cache-Control: public`, which allows remote attackers to read private cached responses via unauthenticated requests to the same URL.
Earlier, unsupported Django series (such as 5.0.x, 4.1.x, and 3.2.x) were not evaluated and may also be affected.
Django would like to thank Shai Berger for reporting this issue.
A divide-by-zero vulnerability in the ext4_block_set_lb_size function in src/ext4_blockdev.c of the lwext4 1.0.0 library allows attackers to cause a denial of service by providing a malformed ext4 filesystem image that results in a zero logical block size. The vulnerability is triggered during mount or image processing and leads to a Floating-Point Exception (FPE) under sanitizers or a runtime crash in standard builds due to missing validation of lb_size.
An out-of-bounds read in the ext4_ext_binsearch_idx function in src/ext4_extent.c of the lwext4 1.0.0 library allows attackers to cause a denial of service by supplying a specially crafted ext4 filesystem image. The vulnerability occurs due to insufficient validation of extent header fields before performing a binary search over extent index entries, which can result in invalid pointer calculations and an out-of-bounds memory read during extent tree traversal.
An improper limitation of a pathname to a restricted directory ('Path Traversal') vulnerability in Backup.Repository webapi component in Synology Hyper Backup before 4.1.2-4036 allows remote authenticated users with administrator privileges to write specific files containing non-sensitive information via unspecified vectors.