aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/include/linux/mm.h
diff options
context:
space:
mode:
authorLorenzo Stoakes <lorenzo.stoakes@oracle.com>2025-01-03 19:35:35 +0000
committerAndrew Morton <akpm@linux-foundation.org>2025-01-25 20:22:23 -0800
commitb0d66d82fce60161de6f3d57f87016c3a6f7a121 (patch)
treed392ee71a38c425b75869a2725c0d63880051e27 /include/linux/mm.h
parentlib/list_debug.c: add object information in case of invalid object (diff)
downloadwireguard-linux-b0d66d82fce60161de6f3d57f87016c3a6f7a121.tar.xz
wireguard-linux-b0d66d82fce60161de6f3d57f87016c3a6f7a121.zip
mm/debug: introduce VM_WARN_ON_VMG() to dump VMA merge state
Patch series "mm/debug: introduce and use VM_WARN_ON_VMG()". We use a number of asserts, enabled only when CONFIG_DEBUG_VM is set, during VMA merge operations to ensure state is as expected. However, when syzkaller or the like encounters these asserts, often the information provided by the report is insufficient to narrow down what the problem is. We noticed this recently in [0], where a non-repro issue resisted debugging due to simply not having sufficient information to go on. This series improves the situation by providing VM_WARN_ON_VMG() which acts like VM_WARN_ON() (i.e. only actually being invoked if CONFIG_DEBUG_VM is set), while dumping significant information about the VMA merge state, the mm_struct describing the virtual address space, all associated VMAs and, if CONFIG_DEBUG_VM_MAPLE_TREE is set, the associated maple tree. [0]:https://lore.kernel.org/all/6774c98f.050a0220.25abdd.0991.GAE@google.com/ This patch (of 2): We use a number of asserts, enabled only when CONFIG_DEBUG_VM is set, during VMA merge operations to ensure state is as expected. However, when syzkaller or the like encounters these asserts, often the information provided by the report is insufficient to narrow down what the problem is. This might not be so much of an issue if the reported problem is reproducible, but if it is a rarely encountered race or some other case which precludes a repro, it is a very big problem (see [0] for the motivating case). It is therefore sensible to provide a means by which we can easily and conveniently dump a lot more information in these circumstances. The aggregation of merge state into a single struct threaded through the operation makes this trivial - we can simply introduce a variant on VM_WARN_ON() which takes the VMA merge state object (vmg) and use that to dump information. This patch therefore introduces VM_WARN_ON_VMG() which provides this functionality. It additionally dumps full mm state, VMA state for each of the three VMAs the vmg contains (prev, next, vma) and if CONFIG_DEBUG_VM_MAPLE_TREE is enabled, dumps the maple tree from the provided VMA iterator if non-NULL. This patch has no functional impact if CONFIG_DEBUG_VM is not set. [0]:https://lore.kernel.org/all/6774c98f.050a0220.25abdd.0991.GAE@google.com/ Link: https://lkml.kernel.org/r/cover.1735932169.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/13b09b52d4d103ee86acaf0ae612539648ae29e0.1735932169.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Liam R. Howlett <Liam.Howlett@Oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'include/linux/mm.h')
0 files changed, 0 insertions, 0 deletions