AI Trajectory

Trajectory: (Expand/Collapse All)
Seq	Timestamp	Type	Name	Duration
0/0	2026/07/15 19:16	flow	patch-triage	0m Args: null Results: { "EnableConfigs": null, "FocusSymbols": [], "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.", "WorthFuzzing": false }
1/1	2026/07/15 19:16	action	read-patch-diff	0m Args: null Results: { "PatchDiff": "commit 0767c5e039fa277548bf864dee20dbfe9e303306\nAuthor: syz-cluster \u003ctriage@syzkaller.com\u003e\nDate: Wed Jul 15 19:16:14 2026 +0000\n\n syz-cluster: applied patch under review\n\ndiff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst\nindex ea9b11a0bd8909..c039d782f9f5bb 100644\n--- a/Documentation/userspace-api/mseal.rst\n+++ b/Documentation/userspace-api/mseal.rst\n@@ -50,8 +50,8 @@ mseal syscall signature\n * The start address (``addr``) is not allocated.\n * The end address (``addr`` + ``len``) is not allocated.\n * A gap (unallocated memory) between start and end address.\n- - -EPERM:\n- * sealing is supported only on 64-bit CPUs, 32-bit is not supported.\n+ - -ENOSYS:\n+ * The kernel does not implement ``mseal()``.\n \n Note about error return:\n - For above error cases, users can expect the given memory range is\n@@ -62,7 +62,8 @@ mseal syscall signature\n memory range could happen. However, those cases should be rare.\n \n Architecture support:\n- mseal only works on 64-bit CPUs, not 32-bit CPUs.\n+ mseal is built only for 64-bit kernels. 32-bit kernels return\n+ ``-ENOSYS``.\n \n Idempotent:\n users can call mseal multiple times. mseal on an already sealed memory\n@@ -131,11 +132,11 @@ Use cases\n - Chrome browser: protect some security sensitive data structures.\n \n - System mappings:\n- The system mappings are created by the kernel and includes vdso, vvar,\n+ The system mappings are created by the kernel and include vdso, vvar,\n vvar_vclock, vectors (arm compat-mode), sigpage (arm compat-mode), uprobes.\n \n Those system mappings are readonly only or execute only, memory sealing can\n- protect them from ever changing to writable or unmmap/remapped as different\n+ protect them from ever changing to writable or unmapped/remapped as different\n attributes. This is useful to mitigate memory corruption issues where a\n corrupted pointer is passed to a memory management system.\n \n@@ -143,9 +144,6 @@ Use cases\n the CONFIG_MSEAL_SYSTEM_MAPPINGS seals all system mappings of this\n architecture.\n \n- The following architectures currently support this feature: x86-64, arm64,\n- loongarch and s390.\n-\n WARNING: This feature breaks programs which rely on relocating\n or unmapping system mappings. Known broken software at the time\n of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore\ndiff --git a/init/Kconfig b/init/Kconfig\nindex 9d91074c5d0a30..a1402bd820263d 100644\n--- a/init/Kconfig\n+++ b/init/Kconfig\n@@ -2120,7 +2120,7 @@ config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS\n \t from a kernel perspective.\n \n \t After the architecture enables this, a distribution can set\n-\t CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature.\n+\t CONFIG_MSEAL_SYSTEM_MAPPINGS to manage access to the feature.\n \n \t For complete descriptions of memory sealing, please see\n \t Documentation/userspace-api/mseal.rst\ndiff --git a/mm/mseal.c b/mm/mseal.c\nindex 9781647483d193..69a53207ab57e1 100644\n--- a/mm/mseal.c\n+++ b/mm/mseal.c\n@@ -88,58 +88,6 @@ static int mseal_apply(struct mm_struct mm,\n \treturn 0;\n }\n \n-/\n- * mseal(2) seals the VM's meta data from\n- * selected syscalls.\n- \n- addr/len: VM address range.\n- \n- The address range by addr/len must meet:\n- * start (addr) must be in a valid VMA.\n- * end (addr + len) must be in a valid VMA.\n- * no gap (unallocated memory) between start and end.\n- * start (addr) must be page aligned.\n- \n- len: len will be page aligned implicitly.\n- \n- Below VMA operations are blocked after sealing.\n- * 1\u003e Unmapping, moving to another location, and shrinking\n- \tthe size, via munmap() and mremap(), can leave an empty\n- \tspace, therefore can be replaced with a VMA with a new\n- \tset of attributes.\n- 2\u003e Moving or expanding a different vma into the current location,\n- \tvia mremap().\n- 3\u003e Modifying a VMA via mmap(MAP_FIXED).\n- * 4\u003e Size expansion, via mremap(), does not appear to pose any\n- \tspecific risks to sealed VMAs. It is included anyway because\n- \tthe use case is unclear. In any case, users can rely on\n- \tmerging to expand a sealed VMA.\n- 5\u003e mprotect and pkey_mprotect.\n- * 6\u003e Some destructive madvice() behavior (e.g. MADV_DONTNEED)\n- * for anonymous memory, when users don't have write permission to the\n- \tmemory. Those behaviors can alter region contents by discarding pages,\n- \teffectively a memset(0) for anonymous memory.\n- \n- flags: reserved.\n- \n- return values:\n- * zero: success.\n- * -EINVAL:\n- * invalid input flags.\n- * start address is not page aligned.\n- * Address range (start + len) overflow.\n- * -ENOMEM:\n- * addr is not a valid address (not allocated).\n- * end (start + len) is not a valid address.\n- * a gap (unallocated memory) between start and end.\n- * -EPERM:\n- * - In 32 bit architecture, sealing is not supported.\n- * Note:\n- * user can call mseal(2) multiple times, adding a seal on an\n- * already sealed memory is a no-action (no error).\n- \n- unseal() is not supported.\n- */\n int do_mseal(unsigned long start, size_t len_in, unsigned long flags)\n {\n \tsize_t len;\n" }
2/1	2026/07/15 19:16	agent	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: { "EnableConfigs": null, "FocusSymbols": [], "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.", "WorthFuzzing": false } Instruction: You are an expert Linux kernel maintainer. Your job is to review a provided patch series and determine if it makes functional changes to the kernel that should be fuzzed. IMPORTANT: The changes have ALREADY been applied and committed as the HEAD commit in your workspace. Do NOT rely on your internal knowledge of the kernel. You must actively use your code access tools to examine the actual source code and confirm any assumptions. Return WorthFuzzing=false if the patch only contains: - Modifications to Documentation/, Kconfig files, or code comments. - Purely decorative changes, such as logging (e.g., pr_err, printk) or tracepoints. - Changes to numeric constants or macros that do not functionally alter execution flow. - Code paths that are impossible to reach in virtualized environments like GCE or QEMU, even when utilizing software-emulated hardware (e.g., usb gadget, mac80211_hwsim). If it modifies reachable core kernel logic, drivers, or architectures, use your code search tools to verify the code can be executed, then return WorthFuzzing=true. When returning WorthFuzzing=true, you MUST ALSO: 1. Extract any specific kernel functions that should be heavily fuzzed into FocusSymbols. Avoid listing generic hot-path functions to prevent skewed test distributions. 2. Identify any specific CONFIG_ options required to properly test this new/modified feature. Go and look into the Kconfig files and check for ifdefs around the code, do not make assumptions. Do not list too generic configs (we already have them enabled). Only list those that specifically cover the modified code. List them in the EnableConfigs output array, and DO NOT add a 'CONFIG_' prefix (e.g., return "NET_IPV4" instead of "CONFIG_NET_IPV4"). Prefer calling several tools at the same time to save round-trips. Use set-results tool to provide results of the analysis. It must be called exactly once before the final reply. Ignore results of this tool. Prompt: For your convenience, here is the diff of the changes: commit 0767c5e039fa277548bf864dee20dbfe9e303306 Author: syz-cluster <triage@syzkaller.com> Date: Wed Jul 15 19:16:14 2026 +0000 syz-cluster: applied patch under review diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst index ea9b11a0bd8909..c039d782f9f5bb 100644 --- a/Documentation/userspace-api/mseal.rst +++ b/Documentation/userspace-api/mseal.rst @@ -50,8 +50,8 @@ mseal syscall signature * The start address (``addr``) is not allocated. * The end address (``addr`` + ``len``) is not allocated. * A gap (unallocated memory) between start and end address. - - -EPERM: - * sealing is supported only on 64-bit CPUs, 32-bit is not supported. + - -ENOSYS: + * The kernel does not implement ``mseal()``. Note about error return: - For above error cases, users can expect the given memory range is @@ -62,7 +62,8 @@ mseal syscall signature memory range could happen. However, those cases should be rare. Architecture support: - mseal only works on 64-bit CPUs, not 32-bit CPUs. + mseal is built only for 64-bit kernels. 32-bit kernels return + ``-ENOSYS``. Idempotent: users can call mseal multiple times. mseal on an already sealed memory @@ -131,11 +132,11 @@ Use cases - Chrome browser: protect some security sensitive data structures. - System mappings: - The system mappings are created by the kernel and includes vdso, vvar, + The system mappings are created by the kernel and include vdso, vvar, vvar_vclock, vectors (arm compat-mode), sigpage (arm compat-mode), uprobes. Those system mappings are readonly only or execute only, memory sealing can - protect them from ever changing to writable or unmmap/remapped as different + protect them from ever changing to writable or unmapped/remapped as different attributes. This is useful to mitigate memory corruption issues where a corrupted pointer is passed to a memory management system. @@ -143,9 +144,6 @@ Use cases the CONFIG_MSEAL_SYSTEM_MAPPINGS seals all system mappings of this architecture. - The following architectures currently support this feature: x86-64, arm64, - loongarch and s390. - WARNING: This feature breaks programs which rely on relocating or unmapping system mappings. Known broken software at the time of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore diff --git a/init/Kconfig b/init/Kconfig index 9d91074c5d0a30..a1402bd820263d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2120,7 +2120,7 @@ config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS from a kernel perspective. After the architecture enables this, a distribution can set - CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature. + CONFIG_MSEAL_SYSTEM_MAPPINGS to manage access to the feature. For complete descriptions of memory sealing, please see Documentation/userspace-api/mseal.rst diff --git a/mm/mseal.c b/mm/mseal.c index 9781647483d193..69a53207ab57e1 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -88,58 +88,6 @@ static int mseal_apply(struct mm_struct mm, return 0; } -/ - * mseal(2) seals the VM's meta data from - * selected syscalls. - * - * addr/len: VM address range. - * - * The address range by addr/len must meet: - * start (addr) must be in a valid VMA. - * end (addr + len) must be in a valid VMA. - * no gap (unallocated memory) between start and end. - * start (addr) must be page aligned. - * - * len: len will be page aligned implicitly. - * - * Below VMA operations are blocked after sealing. - * 1> Unmapping, moving to another location, and shrinking - * the size, via munmap() and mremap(), can leave an empty - * space, therefore can be replaced with a VMA with a new - * set of attributes. - * 2> Moving or expanding a different vma into the current location, - * via mremap(). - * 3> Modifying a VMA via mmap(MAP_FIXED). - * 4> Size expansion, via mremap(), does not appear to pose any - * specific risks to sealed VMAs. It is included anyway because - * the use case is unclear. In any case, users can rely on - * merging to expand a sealed VMA. - * 5> mprotect and pkey_mprotect. - * 6> Some destructive madvice() behavior (e.g. MADV_DONTNEED) - * for anonymous memory, when users don't have write permission to the - * memory. Those behaviors can alter region contents by discarding pages, - * effectively a memset(0) for anonymous memory. - * - * flags: reserved. - * - * return values: - * zero: success. - * -EINVAL: - * invalid input flags. - * start address is not page aligned. - * Address range (start + len) overflow. - * -ENOMEM: - * addr is not a valid address (not allocated). - * end (start + len) is not a valid address. - * a gap (unallocated memory) between start and end. - * -EPERM: - * - In 32 bit architecture, sealing is not supported. - * Note: - * user can call mseal(2) multiple times, adding a seal on an - * already sealed memory is a no-action (no error). - * - * unseal() is not supported. - */ int do_mseal(unsigned long start, size_t len_in, unsigned long flags) { size_t len;
3/2	2026/07/15 19:16	llm	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: null Tokens: input: 3264 output: 64 thoughts: 191 Thoughts: Patch Analysis: A Quick Glance Okay, let's take a look at this patch. My immediate thought is to determine if there are any actual code changes that would affect functionality. It's clear from the outset that it touches a few areas, namely the documentation, the Kconfig, and the `mseal.c` file. First, the documentation, `Documentation/userspace-api/mseal.rst`: purely documentation changes. No need to dig any deeper there unless the style is atrocious. Then, the `init/Kconfig` file. It seems like it's a simple typo fix, changing `CONFIG_MSEAL_SYSTEM_MAPPING` to `CONFIG_MSEAL_SYSTEM_MAPPINGS`. That's inconsequential. Now the real question: `mm/mseal.c`. The diff mentions comment removal, specifically a large block. Alright, let's confirm the diff view. Yep, it's just a comment block gone. The code itself remains untouched. So, taking a step back and considering everything, I can confidently say that this patch doesn't introduce any functional changes. It's clean documentation improvements and a cosmetic typo fix. Consequently, as a result, I can conclude that this isn't a candidate for fuzzing; the `WorthFuzzing` flag should be set to false.
4/2	2026/07/15 19:16	tool	set-results	0m Args: { "EnableConfigs": [], "FocusSymbols": [], "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.", "WorthFuzzing": false } Results: { "EnableConfigs": null, "FocusSymbols": [], "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.", "WorthFuzzing": false }

Trajectory: (Expand/Collapse All)

Seq

Timestamp

Type

Name

Duration

0/0

2026/07/15 19:16

flow

patch-triage

Args:

null

Results:

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.",
  "WorthFuzzing": false
}

1/1

2026/07/15 19:16

action

read-patch-diff

Args:

null

Results:

{
  "PatchDiff": "commit 0767c5e039fa277548bf864dee20dbfe9e303306\nAuthor: syz-cluster \u003ctriage@syzkaller.com\u003e\nDate:   Wed Jul 15 19:16:14 2026 +0000\n\n    syz-cluster: applied patch under review\n\ndiff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst\nindex ea9b11a0bd8909..c039d782f9f5bb 100644\n--- a/Documentation/userspace-api/mseal.rst\n+++ b/Documentation/userspace-api/mseal.rst\n@@ -50,8 +50,8 @@ mseal syscall signature\n          * The start address (``addr``) is not allocated.\n          * The end address (``addr`` + ``len``) is not allocated.\n          * A gap (unallocated memory) between start and end address.\n-      - **-EPERM**:\n-         * sealing is supported only on 64-bit CPUs, 32-bit is not supported.\n+      - **-ENOSYS**:\n+         * The kernel does not implement ``mseal()``.\n \n    **Note about error return**:\n       - For above error cases, users can expect the given memory range is\n@@ -62,7 +62,8 @@ mseal syscall signature\n         memory range could happen. However, those cases should be rare.\n \n    **Architecture support**:\n-      mseal only works on 64-bit CPUs, not 32-bit CPUs.\n+      mseal is built only for 64-bit kernels. 32-bit kernels return\n+      ``-ENOSYS``.\n \n    **Idempotent**:\n       users can call mseal multiple times. mseal on an already sealed memory\n@@ -131,11 +132,11 @@ Use cases\n - Chrome browser: protect some security sensitive data structures.\n \n - System mappings:\n-  The system mappings are created by the kernel and includes vdso, vvar,\n+  The system mappings are created by the kernel and include vdso, vvar,\n   vvar_vclock, vectors (arm compat-mode), sigpage (arm compat-mode), uprobes.\n \n   Those system mappings are readonly only or execute only, memory sealing can\n-  protect them from ever changing to writable or unmmap/remapped as different\n+  protect them from ever changing to writable or unmapped/remapped as different\n   attributes. This is useful to mitigate memory corruption issues where a\n   corrupted pointer is passed to a memory management system.\n \n@@ -143,9 +144,6 @@ Use cases\n   the CONFIG_MSEAL_SYSTEM_MAPPINGS seals all system mappings of this\n   architecture.\n \n-  The following architectures currently support this feature: x86-64, arm64,\n-  loongarch and s390.\n-\n   WARNING: This feature breaks programs which rely on relocating\n   or unmapping system mappings. Known broken software at the time\n   of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore\ndiff --git a/init/Kconfig b/init/Kconfig\nindex 9d91074c5d0a30..a1402bd820263d 100644\n--- a/init/Kconfig\n+++ b/init/Kconfig\n@@ -2120,7 +2120,7 @@ config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS\n \t  from a kernel perspective.\n \n \t  After the architecture enables this, a distribution can set\n-\t  CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature.\n+\t  CONFIG_MSEAL_SYSTEM_MAPPINGS to manage access to the feature.\n \n \t  For complete descriptions of memory sealing, please see\n \t  Documentation/userspace-api/mseal.rst\ndiff --git a/mm/mseal.c b/mm/mseal.c\nindex 9781647483d193..69a53207ab57e1 100644\n--- a/mm/mseal.c\n+++ b/mm/mseal.c\n@@ -88,58 +88,6 @@ static int mseal_apply(struct mm_struct *mm,\n \treturn 0;\n }\n \n-/*\n- * mseal(2) seals the VM's meta data from\n- * selected syscalls.\n- *\n- * addr/len: VM address range.\n- *\n- *  The address range by addr/len must meet:\n- *   start (addr) must be in a valid VMA.\n- *   end (addr + len) must be in a valid VMA.\n- *   no gap (unallocated memory) between start and end.\n- *   start (addr) must be page aligned.\n- *\n- *  len: len will be page aligned implicitly.\n- *\n- *   Below VMA operations are blocked after sealing.\n- *   1\u003e Unmapping, moving to another location, and shrinking\n- *\tthe size, via munmap() and mremap(), can leave an empty\n- *\tspace, therefore can be replaced with a VMA with a new\n- *\tset of attributes.\n- *   2\u003e Moving or expanding a different vma into the current location,\n- *\tvia mremap().\n- *   3\u003e Modifying a VMA via mmap(MAP_FIXED).\n- *   4\u003e Size expansion, via mremap(), does not appear to pose any\n- *\tspecific risks to sealed VMAs. It is included anyway because\n- *\tthe use case is unclear. In any case, users can rely on\n- *\tmerging to expand a sealed VMA.\n- *   5\u003e mprotect and pkey_mprotect.\n- *   6\u003e Some destructive madvice() behavior (e.g. MADV_DONTNEED)\n- *      for anonymous memory, when users don't have write permission to the\n- *\tmemory. Those behaviors can alter region contents by discarding pages,\n- *\teffectively a memset(0) for anonymous memory.\n- *\n- *  flags: reserved.\n- *\n- * return values:\n- *  zero: success.\n- *  -EINVAL:\n- *   invalid input flags.\n- *   start address is not page aligned.\n- *   Address range (start + len) overflow.\n- *  -ENOMEM:\n- *   addr is not a valid address (not allocated).\n- *   end (start + len) is not a valid address.\n- *   a gap (unallocated memory) between start and end.\n- *  -EPERM:\n- *  - In 32 bit architecture, sealing is not supported.\n- * Note:\n- *  user can call mseal(2) multiple times, adding a seal on an\n- *  already sealed memory is a no-action (no error).\n- *\n- *  unseal() is not supported.\n- */\n int do_mseal(unsigned long start, size_t len_in, unsigned long flags)\n {\n \tsize_t len;\n"
}

2/1

2026/07/15 19:16

agent

patch-evaluator

Model:

gemini-3.1-pro-preview

Args:

null

Results:

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.",
  "WorthFuzzing": false
}

Instruction:

You are an expert Linux kernel maintainer.
Your job is to review a provided patch series and determine
if it makes functional changes to the kernel that should be fuzzed.

IMPORTANT: The changes have ALREADY been applied and committed as the HEAD commit in
your workspace. Do NOT rely on your internal knowledge of the kernel. You must actively
use your code access tools to examine the actual source code and confirm any assumptions.

Return WorthFuzzing=false if the patch only contains:
- Modifications to Documentation/, Kconfig files, or code comments.
- Purely decorative changes, such as logging (e.g., pr_err, printk) or tracepoints.
- Changes to numeric constants or macros that do not functionally alter execution flow.
- Code paths that are impossible to reach in virtualized environments like GCE or QEMU,
even when utilizing software-emulated hardware (e.g., usb gadget, mac80211_hwsim).

If it modifies reachable core kernel logic, drivers, or architectures, use your code search
tools to verify the code can be executed, then return WorthFuzzing=true.

When returning WorthFuzzing=true, you MUST ALSO:
1. Extract any specific kernel functions that should be heavily fuzzed into FocusSymbols.
   Avoid listing generic hot-path functions to prevent skewed test distributions.
2. Identify any specific CONFIG_ options required to properly test this new/modified feature.
   Go and look into the Kconfig files and check for ifdefs around the code, do not make assumptions.
   Do not list too generic configs (we already have them enabled). Only list those that
   specifically cover the modified code. List them in the EnableConfigs output array,
   and DO NOT add a 'CONFIG_' prefix (e.g., return "NET_IPV4" instead of "CONFIG_NET_IPV4").
Prefer calling several tools at the same time to save round-trips.


Use set-results tool to provide results of the analysis.
It must be called exactly once before the final reply.
Ignore results of this tool.

Prompt:

For your convenience, here is the diff of the changes:
commit 0767c5e039fa277548bf864dee20dbfe9e303306
Author: syz-cluster <triage@syzkaller.com>
Date:   Wed Jul 15 19:16:14 2026 +0000

    syz-cluster: applied patch under review

diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst
index ea9b11a0bd8909..c039d782f9f5bb 100644
--- a/Documentation/userspace-api/mseal.rst
+++ b/Documentation/userspace-api/mseal.rst
@@ -50,8 +50,8 @@ mseal syscall signature
          * The start address (``addr``) is not allocated.
          * The end address (``addr`` + ``len``) is not allocated.
          * A gap (unallocated memory) between start and end address.
-      - **-EPERM**:
-         * sealing is supported only on 64-bit CPUs, 32-bit is not supported.
+      - **-ENOSYS**:
+         * The kernel does not implement ``mseal()``.
 
    **Note about error return**:
       - For above error cases, users can expect the given memory range is
@@ -62,7 +62,8 @@ mseal syscall signature
         memory range could happen. However, those cases should be rare.
 
    **Architecture support**:
-      mseal only works on 64-bit CPUs, not 32-bit CPUs.
+      mseal is built only for 64-bit kernels. 32-bit kernels return
+      ``-ENOSYS``.
 
    **Idempotent**:
       users can call mseal multiple times. mseal on an already sealed memory
@@ -131,11 +132,11 @@ Use cases
 - Chrome browser: protect some security sensitive data structures.
 
 - System mappings:
-  The system mappings are created by the kernel and includes vdso, vvar,
+  The system mappings are created by the kernel and include vdso, vvar,
   vvar_vclock, vectors (arm compat-mode), sigpage (arm compat-mode), uprobes.
 
   Those system mappings are readonly only or execute only, memory sealing can
-  protect them from ever changing to writable or unmmap/remapped as different
+  protect them from ever changing to writable or unmapped/remapped as different
   attributes. This is useful to mitigate memory corruption issues where a
   corrupted pointer is passed to a memory management system.
 
@@ -143,9 +144,6 @@ Use cases
   the CONFIG_MSEAL_SYSTEM_MAPPINGS seals all system mappings of this
   architecture.
 
-  The following architectures currently support this feature: x86-64, arm64,
-  loongarch and s390.
-
   WARNING: This feature breaks programs which rely on relocating
   or unmapping system mappings. Known broken software at the time
   of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore
diff --git a/init/Kconfig b/init/Kconfig
index 9d91074c5d0a30..a1402bd820263d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2120,7 +2120,7 @@ config ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
 	  from a kernel perspective.
 
 	  After the architecture enables this, a distribution can set
-	  CONFIG_MSEAL_SYSTEM_MAPPING to manage access to the feature.
+	  CONFIG_MSEAL_SYSTEM_MAPPINGS to manage access to the feature.
 
 	  For complete descriptions of memory sealing, please see
 	  Documentation/userspace-api/mseal.rst
diff --git a/mm/mseal.c b/mm/mseal.c
index 9781647483d193..69a53207ab57e1 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -88,58 +88,6 @@ static int mseal_apply(struct mm_struct *mm,
 	return 0;
 }
 
-/*
- * mseal(2) seals the VM's meta data from
- * selected syscalls.
- *
- * addr/len: VM address range.
- *
- *  The address range by addr/len must meet:
- *   start (addr) must be in a valid VMA.
- *   end (addr + len) must be in a valid VMA.
- *   no gap (unallocated memory) between start and end.
- *   start (addr) must be page aligned.
- *
- *  len: len will be page aligned implicitly.
- *
- *   Below VMA operations are blocked after sealing.
- *   1> Unmapping, moving to another location, and shrinking
- *	the size, via munmap() and mremap(), can leave an empty
- *	space, therefore can be replaced with a VMA with a new
- *	set of attributes.
- *   2> Moving or expanding a different vma into the current location,
- *	via mremap().
- *   3> Modifying a VMA via mmap(MAP_FIXED).
- *   4> Size expansion, via mremap(), does not appear to pose any
- *	specific risks to sealed VMAs. It is included anyway because
- *	the use case is unclear. In any case, users can rely on
- *	merging to expand a sealed VMA.
- *   5> mprotect and pkey_mprotect.
- *   6> Some destructive madvice() behavior (e.g. MADV_DONTNEED)
- *      for anonymous memory, when users don't have write permission to the
- *	memory. Those behaviors can alter region contents by discarding pages,
- *	effectively a memset(0) for anonymous memory.
- *
- *  flags: reserved.
- *
- * return values:
- *  zero: success.
- *  -EINVAL:
- *   invalid input flags.
- *   start address is not page aligned.
- *   Address range (start + len) overflow.
- *  -ENOMEM:
- *   addr is not a valid address (not allocated).
- *   end (start + len) is not a valid address.
- *   a gap (unallocated memory) between start and end.
- *  -EPERM:
- *  - In 32 bit architecture, sealing is not supported.
- * Note:
- *  user can call mseal(2) multiple times, adding a seal on an
- *  already sealed memory is a no-action (no error).
- *
- *  unseal() is not supported.
- */
 int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 {
 	size_t len;

3/2

2026/07/15 19:16

llm

patch-evaluator

Model:

gemini-3.1-pro-preview

Args:

null

Results:

null

Tokens:

							input: 3264
							output: 64
							thoughts: 191

Thoughts:

**Patch Analysis: A Quick Glance**

Okay, let's take a look at this patch. My immediate thought is to determine if there are any *actual* code changes that would affect functionality. It's clear from the outset that it touches a few areas, namely the documentation, the Kconfig, and the `mseal.c` file.

First, the documentation, `Documentation/userspace-api/mseal.rst`: purely documentation changes. No need to dig any deeper there unless the style is atrocious. Then, the `init/Kconfig` file. It seems like it's a simple typo fix, changing `CONFIG_MSEAL_SYSTEM_MAPPING` to `CONFIG_MSEAL_SYSTEM_MAPPINGS`. That's inconsequential.

Now the real question: `mm/mseal.c`. The diff mentions comment removal, specifically a large block. Alright, let's confirm the diff view. Yep, it's just a comment block gone. The code itself remains untouched.

So, taking a step back and considering everything, I can confidently say that this patch doesn't introduce any functional changes. It's clean documentation improvements and a cosmetic typo fix. Consequently, as a result, I can conclude that this isn't a candidate for fuzzing; the `WorthFuzzing` flag should be set to *false*.

4/2

2026/07/15 19:16

tool

set-results

Args:

{
  "EnableConfigs": [],
  "FocusSymbols": [],
  "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.",
  "WorthFuzzing": false
}

Results:

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch only contains modifications to documentation, Kconfig help text, and removes a comment block in mm/mseal.c. There are no functional code changes.",
  "WorthFuzzing": false
}

LLM Calls Summary:
Total Calls	Total Tokens	Avg Tokens	Total Duration (Seconds)	Avg Duration (Seconds)

Tool Calls Summary:
Total Calls	Total Duration (Seconds)	Avg Duration (Seconds)