kernel/linux.git/mm, branch v4.9.331

mm: prevent page_frag_alloc() from corrupting the memory

2022-10-26T11:15:32+00:00

commit dac22531bbd4af2426c4e29e05594415ccfa365d upstream. A number of drivers call page_frag_alloc() with a fragment's size > PAGE_SIZE. In low memory conditions, __page_frag_cache_refill() may fail the order 3 cache allocation and fall back to order 0; In this case, the cache will be smaller than the fragment, causing memory corruptions. Prevent this from happening by checking if the newly allocated cache is large enough for the fragment; if not, the allocation will fail and page_frag_alloc() will return NULL. Link: https://lkml.kernel.org/r/20220715125013.247085-1-mlombard@redhat.com Fixes: b63ae8ca096d ("mm/net: Rename and move page fragment handling from net/ to mm/") Signed-off-by: Maurizio Lombardi Reviewed-by: Alexander Duyck Cc: Chen Lin Cc: Jakub Kicinski Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman

mm/slub: fix to return errno if kmalloc() fails

2022-09-28T08:55:45+00:00

commit 7e9c323c52b379d261a72dc7bd38120a761a93cd upstream. In create_unique_id(), kmalloc(, GFP_KERNEL) can fail due to out-of-memory, if it fails, return errno correctly rather than triggering panic via BUG_ON(); kernel BUG at mm/slub.c:5893! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Call trace: sysfs_slab_add+0x258/0x260 mm/slub.c:5973 __kmem_cache_create+0x60/0x118 mm/slub.c:4899 create_cache mm/slab_common.c:229 [inline] kmem_cache_create_usercopy+0x19c/0x31c mm/slab_common.c:335 kmem_cache_create+0x1c/0x28 mm/slab_common.c:390 f2fs_kmem_cache_create fs/f2fs/f2fs.h:2766 [inline] f2fs_init_xattr_caches+0x78/0xb4 fs/f2fs/xattr.c:808 f2fs_fill_super+0x1050/0x1e0c fs/f2fs/super.c:4149 mount_bdev+0x1b8/0x210 fs/super.c:1400 f2fs_mount+0x44/0x58 fs/f2fs/super.c:4512 legacy_get_tree+0x30/0x74 fs/fs_context.c:610 vfs_get_tree+0x40/0x140 fs/super.c:1530 do_new_mount+0x1dc/0x4e4 fs/namespace.c:3040 path_mount+0x358/0x914 fs/namespace.c:3370 do_mount fs/namespace.c:3383 [inline] __do_sys_mount fs/namespace.c:3591 [inline] __se_sys_mount fs/namespace.c:3568 [inline] __arm64_sys_mount+0x2f8/0x408 fs/namespace.c:3568 Cc: Fixes: 81819f0fc8285 ("SLUB core") Reported-by: syzbot+81684812ea68216e08c5@syzkaller.appspotmail.com Reviewed-by: Muchun Song Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Chao Yu Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Signed-off-by: Greg Kroah-Hartman

mm: Fix TLB flush for not-first PFNMAP mappings in unmap_region()

2022-09-20T09:50:16+00:00

This is a stable-specific patch. I botched the stable-specific rewrite of commit b67fbebd4cf98 ("mmu_gather: Force tlb-flush VM_PFNMAP vmas"): As Hugh pointed out, unmap_region() actually operates on a list of VMAs, and the variable "vma" merely points to the first VMA in that list. So if we want to check whether any of the VMAs we're operating on is PFNMAP or MIXEDMAP, we have to iterate through the list and check each VMA. Signed-off-by: Jann Horn Signed-off-by: Greg Kroah-Hartman

Revert "mm: kmemleak: take a full lowmem check in kmemleak_*_phys()"

2022-09-15T10:39:45+00:00

This reverts commit 23c2d497de21f25898fbea70aeb292ab8acc8c94. Commit 23c2d497de21 ("mm: kmemleak: take a full lowmem check in kmemleak_*_phys()") brought false leak alarms on some archs like arm64 that does not init pfn boundary in early booting. The final solution lands on linux-6.0: commit 0c24e061196c ("mm: kmemleak: add rbtree and store physical address for objects allocated with PA"). Revert this commit before linux-6.0. The original issue of invalid PA can be mitigated by additional check in devicetree. The false alarm report is as following: Kmemleak output: (Qemu/arm64) unreferenced object 0xffff0000c0170a00 (size 128): comm "swapper/0", pid 1, jiffies 4294892404 (age 126.208s) hex dump (first 32 bytes): 62 61 73 65 00 00 00 00 00 00 00 00 00 00 00 00 base............ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] __kmalloc_track_caller+0x1b0/0x2e4 [<(____ptrval____)>] kstrdup_const+0x8c/0xc4 [<(____ptrval____)>] kvasprintf_const+0xbc/0xec [<(____ptrval____)>] kobject_set_name_vargs+0x58/0xe4 [<(____ptrval____)>] kobject_add+0x84/0x100 [<(____ptrval____)>] __of_attach_node_sysfs+0x78/0xec [<(____ptrval____)>] of_core_init+0x68/0x104 [<(____ptrval____)>] driver_init+0x28/0x48 [<(____ptrval____)>] do_basic_setup+0x14/0x28 [<(____ptrval____)>] kernel_init_freeable+0x110/0x178 [<(____ptrval____)>] kernel_init+0x20/0x1a0 [<(____ptrval____)>] ret_from_fork+0x10/0x20 This pacth is also applicable to linux-5.17.y/linux-5.18.y/linux-5.19.y Cc: Signed-off-by: Yee Lee Signed-off-by: Greg Kroah-Hartman

mm/rmap: Fix anon_vma->degree ambiguity leading to double-reuse

2022-09-05T08:23:58+00:00

commit 2555283eb40df89945557273121e9393ef9b542b upstream. anon_vma->degree tracks the combined number of child anon_vmas and VMAs that use the anon_vma as their ->anon_vma. anon_vma_clone() then assumes that for any anon_vma attached to src->anon_vma_chain other than src->anon_vma, it is impossible for it to be a leaf node of the VMA tree, meaning that for such VMAs ->degree is elevated by 1 because of a child anon_vma, meaning that if ->degree equals 1 there are no VMAs that use the anon_vma as their ->anon_vma. This assumption is wrong because the ->degree optimization leads to leaf nodes being abandoned on anon_vma_clone() - an existing anon_vma is reused and no new parent-child relationship is created. So it is possible to reuse an anon_vma for one VMA while it is still tied to another VMA. This is an issue because is_mergeable_anon_vma() and its callers assume that if two VMAs have the same ->anon_vma, the list of anon_vmas attached to the VMAs is guaranteed to be the same. When this assumption is violated, vma_merge() can merge pages into a VMA that is not attached to the corresponding anon_vma, leading to dangling page->mapping pointers that will be dereferenced during rmap walks. Fix it by separately tracking the number of child anon_vmas and the number of VMAs using the anon_vma as their ->anon_vma. Fixes: 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy") Cc: stable@kernel.org Acked-by: Michal Hocko Acked-by: Vlastimil Babka Signed-off-by: Jann Horn Signed-off-by: Linus Torvalds [manually fixed up different indentation in stable] Signed-off-by: Jann Horn Signed-off-by: Greg Kroah-Hartman

mm: Force TLB flush for PFNMAP mappings before unlink_file_vma()

2022-09-05T08:23:56+00:00

commit b67fbebd4cf980aecbcc750e1462128bffe8ae15 upstream. Some drivers rely on having all VMAs through which a PFN might be accessible listed in the rmap for correctness. However, on X86, it was possible for a VMA with stale TLB entries to not be listed in the rmap. This was fixed in mainline with commit b67fbebd4cf9 ("mmu_gather: Force tlb-flush VM_PFNMAP vmas"), but that commit relies on preceding refactoring in commit 18ba064e42df3 ("mmu_gather: Let there be one tlb_{start,end}_vma() implementation") and commit 1e9fdf21a4339 ("mmu_gather: Remove per arch tlb_{start,end}_vma()"). This patch provides equivalent protection without needing that refactoring, by forcing a TLB flush between removing PTEs in unmap_vmas() and the call to unlink_file_vma() in free_pgtables(). [This is a stable-specific rewrite of the upstream commit!] Signed-off-by: Jann Horn Signed-off-by: Greg Kroah-Hartman

mm/hugetlb: fix hugetlb not supporting softdirty tracking

2022-09-05T08:23:56+00:00

commit f96f7a40874d7c746680c0b9f57cef2262ae551f upstream. Patch series "mm/hugetlb: fix write-fault handling for shared mappings", v2. I observed that hugetlb does not support/expect write-faults in shared mappings that would have to map the R/O-mapped page writable -- and I found two case where we could currently get such faults and would erroneously map an anon page into a shared mapping. Reproducers part of the patches. I propose to backport both fixes to stable trees. The first fix needs a small adjustment. This patch (of 2): Staring at hugetlb_wp(), one might wonder where all the logic for shared mappings is when stumbling over a write-protected page in a shared mapping. In fact, there is none, and so far we thought we could get away with that because e.g., mprotect() should always do the right thing and map all pages directly writable. Looks like we were wrong: -------------------------------------------------------------------------- #include #include #include #include #include #include #include #define HUGETLB_SIZE (2 * 1024 * 1024u) static void clear_softdirty(void) { int fd = open("/proc/self/clear_refs", O_WRONLY); const char *ctrl = "4"; int ret; if (fd < 0) { fprintf(stderr, "open(clear_refs) failed\n"); exit(1); } ret = write(fd, ctrl, strlen(ctrl)); if (ret != strlen(ctrl)) { fprintf(stderr, "write(clear_refs) failed\n"); exit(1); } close(fd); } int main(int argc, char **argv) { char *map; int fd; fd = open("/dev/hugepages/tmp", O_RDWR | O_CREAT); if (!fd) { fprintf(stderr, "open() failed\n"); return -errno; } if (ftruncate(fd, HUGETLB_SIZE)) { fprintf(stderr, "ftruncate() failed\n"); return -errno; } map = mmap(NULL, HUGETLB_SIZE, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); if (map == MAP_FAILED) { fprintf(stderr, "mmap() failed\n"); return -errno; } *map = 0; if (mprotect(map, HUGETLB_SIZE, PROT_READ)) { fprintf(stderr, "mmprotect() failed\n"); return -errno; } clear_softdirty(); if (mprotect(map, HUGETLB_SIZE, PROT_READ|PROT_WRITE)) { fprintf(stderr, "mmprotect() failed\n"); return -errno; } *map = 0; return 0; } -------------------------------------------------------------------------- Above test fails with SIGBUS when there is only a single free hugetlb page. # echo 1 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # ./test Bus error (core dumped) And worse, with sufficient free hugetlb pages it will map an anonymous page into a shared mapping, for example, messing up accounting during unmap and breaking MAP_SHARED semantics: # echo 2 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages # ./test # cat /proc/meminfo | grep HugePages_ HugePages_Total: 2 HugePages_Free: 1 HugePages_Rsvd: 18446744073709551615 HugePages_Surp: 0 Reason in this particular case is that vma_wants_writenotify() will return "true", removing VM_SHARED in vma_set_page_prot() to map pages write-protected. Let's teach vma_wants_writenotify() that hugetlb does not support softdirty tracking. Link: https://lkml.kernel.org/r/20220811103435.188481-1-david@redhat.com Link: https://lkml.kernel.org/r/20220811103435.188481-2-david@redhat.com Fixes: 64e455079e1b ("mm: softdirty: enable write notifications on VMAs after VM_SOFTDIRTY cleared") Signed-off-by: David Hildenbrand Reviewed-by: Mike Kravetz Cc: Peter Feiner Cc: Kirill A. Shutemov Cc: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: Jamie Liu Cc: Hugh Dickins Cc: Naoya Horiguchi Cc: Bjorn Helgaas Cc: Muchun Song Cc: Peter Xu Cc: [3.18+] Signed-off-by: Andrew Morton Signed-off-by: David Hildenbrand Signed-off-by: Greg Kroah-Hartman

mm/mempolicy: fix uninit-value in mpol_rebind_policy()

2022-07-29T15:05:46+00:00

commit 018160ad314d75b1409129b2247b614a9f35894c upstream. mpol_set_nodemask()(mm/mempolicy.c) does not set up nodemask when pol->mode is MPOL_LOCAL. Check pol->mode before access pol->w.cpuset_mems_allowed in mpol_rebind_policy()(mm/mempolicy.c). BUG: KMSAN: uninit-value in mpol_rebind_policy mm/mempolicy.c:352 [inline] BUG: KMSAN: uninit-value in mpol_rebind_task+0x2ac/0x2c0 mm/mempolicy.c:368 mpol_rebind_policy mm/mempolicy.c:352 [inline] mpol_rebind_task+0x2ac/0x2c0 mm/mempolicy.c:368 cpuset_change_task_nodemask kernel/cgroup/cpuset.c:1711 [inline] cpuset_attach+0x787/0x15e0 kernel/cgroup/cpuset.c:2278 cgroup_migrate_execute+0x1023/0x1d20 kernel/cgroup/cgroup.c:2515 cgroup_migrate kernel/cgroup/cgroup.c:2771 [inline] cgroup_attach_task+0x540/0x8b0 kernel/cgroup/cgroup.c:2804 __cgroup1_procs_write+0x5cc/0x7a0 kernel/cgroup/cgroup-v1.c:520 cgroup1_tasks_write+0x94/0xb0 kernel/cgroup/cgroup-v1.c:539 cgroup_file_write+0x4c2/0x9e0 kernel/cgroup/cgroup.c:3852 kernfs_fop_write_iter+0x66a/0x9f0 fs/kernfs/file.c:296 call_write_iter include/linux/fs.h:2162 [inline] new_sync_write fs/read_write.c:503 [inline] vfs_write+0x1318/0x2030 fs/read_write.c:590 ksys_write+0x28b/0x510 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __x64_sys_write+0xdb/0x120 fs/read_write.c:652 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Uninit was created at: slab_post_alloc_hook mm/slab.h:524 [inline] slab_alloc_node mm/slub.c:3251 [inline] slab_alloc mm/slub.c:3259 [inline] kmem_cache_alloc+0x902/0x11c0 mm/slub.c:3264 mpol_new mm/mempolicy.c:293 [inline] do_set_mempolicy+0x421/0xb70 mm/mempolicy.c:853 kernel_set_mempolicy mm/mempolicy.c:1504 [inline] __do_sys_set_mempolicy mm/mempolicy.c:1510 [inline] __se_sys_set_mempolicy+0x44c/0xb60 mm/mempolicy.c:1507 __x64_sys_set_mempolicy+0xd8/0x110 mm/mempolicy.c:1507 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae KMSAN: uninit-value in mpol_rebind_task (2) https://syzkaller.appspot.com/bug?id=d6eb90f952c2a5de9ea718a1b873c55cb13b59dc This patch seems to fix below bug too. KMSAN: uninit-value in mpol_rebind_mm (2) https://syzkaller.appspot.com/bug?id=f2fecd0d7013f54ec4162f60743a2b28df40926b The uninit-value is pol->w.cpuset_mems_allowed in mpol_rebind_policy(). When syzkaller reproducer runs to the beginning of mpol_new(), mpol_new() mm/mempolicy.c do_mbind() mm/mempolicy.c kernel_mbind() mm/mempolicy.c `mode` is 1(MPOL_PREFERRED), nodes_empty(*nodes) is `true` and `flags` is 0. Then mode = MPOL_LOCAL; ... policy->mode = mode; policy->flags = flags; will be executed. So in mpol_set_nodemask(), mpol_set_nodemask() mm/mempolicy.c do_mbind() kernel_mbind() pol->mode is 4 (MPOL_LOCAL), that `nodemask` in `pol` is not initialized, which will be accessed in mpol_rebind_policy(). Link: https://lkml.kernel.org/r/20220512123428.fq3wofedp6oiotd4@ppc.localdomain Signed-off-by: Wang Cheng Reported-by: Tested-by: Cc: David Rientjes Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman

mm: invalidate hwpoison page cache page in fault path

2022-07-21T18:40:33+00:00

commit e53ac7374e64dede04d745ff0e70ff5048378d1f upstream. Sometimes the page offlining code can leave behind a hwpoisoned clean page cache page. This can lead to programs being killed over and over and over again as they fault in the hwpoisoned page, get killed, and then get re-spawned by whatever wanted to run them. This is particularly embarrassing when the page was offlined due to having too many corrected memory errors. Now we are killing tasks due to them trying to access memory that probably isn't even corrupted. This problem can be avoided by invalidating the page from the page fault handler, which already has a branch for dealing with these kinds of pages. With this patch we simply pretend the page fault was successful if the page was invalidated, return to userspace, incur another page fault, read in the file from disk (to a new memory page), and then everything works again. Link: https://lkml.kernel.org/r/20220212213740.423efcea@imladris.surriel.com Signed-off-by: Rik van Riel Reviewed-by: Miaohe Lin Acked-by: Naoya Horiguchi Reviewed-by: Oscar Salvador Cc: John Hubbard Cc: Mel Gorman Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds [sudip: use int instead of vm_fault_t and adjust context] Signed-off-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman

mm/slub: add missing TID updates on slab deactivation

2022-07-12T14:26:24+00:00

commit eeaa345e128515135ccb864c04482180c08e3259 upstream. The fastpath in slab_alloc_node() assumes that c->slab is stable as long as the TID stays the same. However, two places in __slab_alloc() currently don't update the TID when deactivating the CPU slab. If multiple operations race the right way, this could lead to an object getting lost; or, in an even more unlikely situation, it could even lead to an object being freed onto the wrong slab's freelist, messing up the `inuse` counter and eventually causing a page to be freed to the page allocator while it still contains slab objects. (I haven't actually tested these cases though, this is just based on looking at the code. Writing testcases for this stuff seems like it'd be a pain...) The race leading to state inconsistency is (all operations on the same CPU and kmem_cache): - task A: begin do_slab_free(): - read TID - read pcpu freelist (==NULL) - check `slab == c->slab` (true) - [PREEMPT A->B] - task B: begin slab_alloc_node(): - fastpath fails (`c->freelist` is NULL) - enter __slab_alloc() - slub_get_cpu_ptr() (disables preemption) - enter ___slab_alloc() - take local_lock_irqsave() - read c->freelist as NULL - get_freelist() returns NULL - write `c->slab = NULL` - drop local_unlock_irqrestore() - goto new_slab - slub_percpu_partial() is NULL - get_partial() returns NULL - slub_put_cpu_ptr() (enables preemption) - [PREEMPT B->A] - task A: finish do_slab_free(): - this_cpu_cmpxchg_double() succeeds() - [CORRUPT STATE: c->slab==NULL, c->freelist!=NULL] From there, the object on c->freelist will get lost if task B is allowed to continue from here: It will proceed to the retry_load_slab label, set c->slab, then jump to load_freelist, which clobbers c->freelist. But if we instead continue as follows, we get worse corruption: - task A: run __slab_free() on object from other struct slab: - CPU_PARTIAL_FREE case (slab was on no list, is now on pcpu partial) - task A: run slab_alloc_node() with NUMA node constraint: - fastpath fails (c->slab is NULL) - call __slab_alloc() - slub_get_cpu_ptr() (disables preemption) - enter ___slab_alloc() - c->slab is NULL: goto new_slab - slub_percpu_partial() is non-NULL - set c->slab to slub_percpu_partial(c) - [CORRUPT STATE: c->slab points to slab-1, c->freelist has objects from slab-2] - goto redo - node_match() fails - goto deactivate_slab - existing c->freelist is passed into deactivate_slab() - inuse count of slab-1 is decremented to account for object from slab-2 At this point, the inuse count of slab-1 is 1 lower than it should be. This means that if we free all allocated objects in slab-1 except for one, SLUB will think that slab-1 is completely unused, and may free its page, leading to use-after-free. Fixes: c17dda40a6a4e ("slub: Separate out kmem_cache_cpu processing from deactivate_slab") Fixes: 03e404af26dc2 ("slub: fast release on full slab") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn Acked-by: Christoph Lameter Acked-by: David Rientjes Reviewed-by: Muchun Song Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/20220608182205.2945720-1-jannh@google.com Signed-off-by: Greg Kroah-Hartman