From e71e2ace5721a8b921dca18b045069e7bb411277 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 23 Jul 2021 15:50:01 -0700 Subject: [PATCH 01/15] userfaultfd: do not untag user pointers Patch series "userfaultfd: do not untag user pointers", v5. If a user program uses userfaultfd on ranges of heap memory, it may end up passing a tagged pointer to the kernel in the range.start field of the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable allocator, or on Android if using the Tagged Pointers feature for MTE readiness [1]. When a fault subsequently occurs, the tag is stripped from the fault address returned to the application in the fault.address field of struct uffd_msg. However, from the application's perspective, the tagged address *is* the memory address, so if the application is unaware of memory tags, it may get confused by receiving an address that is, from its point of view, outside of the bounds of the allocation. We observed this behavior in the kselftest for userfaultfd [2] but other applications could have the same problem. Address this by not untagging pointers passed to the userfaultfd ioctls. Instead, let the system call fail. Also change the kselftest to use mmap so that it doesn't encounter this problem. [1] https://source.android.com/devices/tech/debug/tagged-pointers [2] tools/testing/selftests/vm/userfaultfd.c This patch (of 2): Do not untag pointers passed to the userfaultfd ioctls. Instead, let the system call fail. This will provide an early indication of problems with tag-unaware userspace code instead of letting the code get confused later, and is consistent with how we decided to handle brk/mmap/mremap in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in brk()/mmap()/mremap()"), as well as being consistent with the existing tagged address ABI documentation relating to how ioctl arguments are handled. The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag user pointers") plus some fixups to some additional calls to validate_range that have appeared since then. [1] https://source.android.com/devices/tech/debug/tagged-pointers [2] tools/testing/selftests/vm/userfaultfd.c Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI") Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Reviewed-by: Catalin Marinas Cc: Alistair Delva Cc: Andrea Arcangeli Cc: Dave Martin Cc: Evgenii Stepanov Cc: Lokesh Gidra Cc: Mitch Phillips Cc: Vincenzo Frascino Cc: Will Deacon Cc: William McVicker Cc: [5.4] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/arm64/tagged-address-abi.rst | 24 ++++++++++++++------ fs/userfaultfd.c | 26 ++++++++++------------ 2 files changed, 29 insertions(+), 21 deletions(-) diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst index 459e6b66ff68..0c9120ec58ae 100644 --- a/Documentation/arm64/tagged-address-abi.rst +++ b/Documentation/arm64/tagged-address-abi.rst @@ -45,14 +45,24 @@ how the user addresses are used by the kernel: 1. User addresses not accessed by the kernel but used for address space management (e.g. ``mprotect()``, ``madvise()``). The use of valid - tagged pointers in this context is allowed with the exception of - ``brk()``, ``mmap()`` and the ``new_address`` argument to - ``mremap()`` as these have the potential to alias with existing - user addresses. + tagged pointers in this context is allowed with these exceptions: - NOTE: This behaviour changed in v5.6 and so some earlier kernels may - incorrectly accept valid tagged pointers for the ``brk()``, - ``mmap()`` and ``mremap()`` system calls. + - ``brk()``, ``mmap()`` and the ``new_address`` argument to + ``mremap()`` as these have the potential to alias with existing + user addresses. + + NOTE: This behaviour changed in v5.6 and so some earlier kernels may + incorrectly accept valid tagged pointers for the ``brk()``, + ``mmap()`` and ``mremap()`` system calls. + + - The ``range.start``, ``start`` and ``dst`` arguments to the + ``UFFDIO_*`` ``ioctl()``s used on a file descriptor obtained from + ``userfaultfd()``, as fault addresses subsequently obtained by reading + the file descriptor will be untagged, which may otherwise confuse + tag-unaware programs. + + NOTE: This behaviour changed in v5.14 and so some earlier kernels may + incorrectly accept valid tagged pointers for this system call. 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI relaxation is disabled by default and the application thread needs to diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index f6e0f0c0d0e5..5c2d806e6ae5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1236,23 +1236,21 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, } static __always_inline int validate_range(struct mm_struct *mm, - __u64 *start, __u64 len) + __u64 start, __u64 len) { __u64 task_size = mm->task_size; - *start = untagged_addr(*start); - - if (*start & ~PAGE_MASK) + if (start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; - if (*start < mmap_min_addr) + if (start < mmap_min_addr) return -EINVAL; - if (*start >= task_size) + if (start >= task_size) return -EINVAL; - if (len > task_size - *start) + if (len > task_size - start) return -EINVAL; return 0; } @@ -1316,7 +1314,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vm_flags |= VM_UFFD_MINOR; } - ret = validate_range(mm, &uffdio_register.range.start, + ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; @@ -1522,7 +1520,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; - ret = validate_range(mm, &uffdio_unregister.start, + ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; @@ -1671,7 +1669,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; - ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len); + ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; @@ -1711,7 +1709,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, sizeof(uffdio_copy)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len); + ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* @@ -1768,7 +1766,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; - ret = validate_range(ctx->mm, &uffdio_zeropage.range.start, + ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; @@ -1818,7 +1816,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, sizeof(struct uffdio_writeprotect))) return -EFAULT; - ret = validate_range(ctx->mm, &uffdio_wp.range.start, + ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; @@ -1866,7 +1864,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; - ret = validate_range(ctx->mm, &uffdio_continue.range.start, + ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; From 0db282ba2c12c1515d490d14a1ff696643ab0f1b Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 23 Jul 2021 15:50:04 -0700 Subject: [PATCH 02/15] selftest: use mmap instead of posix_memalign to allocate memory This test passes pointers obtained from anon_allocate_area to the userfaultfd and mremap APIs. This causes a problem if the system allocator returns tagged pointers because with the tagged address ABI the kernel rejects tagged addresses passed to these APIs, which would end up causing the test to fail. To make this test compatible with such system allocators, stop using the system allocator to allocate memory in anon_allocate_area, and instead just use mmap. Link: https://lkml.kernel.org/r/20210714195437.118982-3-pcc@google.com Link: https://linux-review.googlesource.com/id/Icac91064fcd923f77a83e8e133f8631c5b8fc241 Fixes: c47174fc362a ("userfaultfd: selftest") Co-developed-by: Lokesh Gidra Signed-off-by: Lokesh Gidra Signed-off-by: Peter Collingbourne Reviewed-by: Catalin Marinas Cc: Vincenzo Frascino Cc: Dave Martin Cc: Will Deacon Cc: Andrea Arcangeli Cc: Alistair Delva Cc: William McVicker Cc: Evgenii Stepanov Cc: Mitch Phillips Cc: Andrey Konovalov Cc: [5.4] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index e363bdaff59d..2ea438e6b8b1 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area) static void anon_allocate_area(void **alloc_area) { - if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) - err("posix_memalign() failed"); + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (*alloc_area == MAP_FAILED) + err("mmap of anonymous memory failed"); } static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) From 32ae8a0669392248a92d7545a7363004543f3932 Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Fri, 23 Jul 2021 15:50:08 -0700 Subject: [PATCH 03/15] kfence: defer kfence_test_init to ensure that kunit debugfs is created kfence_test_init and kunit_init both use the same level late_initcall, which means if kfence_test_init linked ahead of kunit_init, kfence_test_init will get a NULL debugfs_rootdir as parent dentry, then kfence_test_init and kfence_debugfs_init both create a debugfs node named "kfence" under debugfs_mount->mnt_root, and it will throw out "debugfs: Directory 'kfence' with parent '/' already present!" with EEXIST. So kfence_test_init should be deferred. Link: https://lkml.kernel.org/r/20210714113140.2949995-1-o451686892@gmail.com Signed-off-by: Weizhao Ouyang Tested-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/kfence_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 7f24b9bcb2ec..942cbc16ad26 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -852,7 +852,7 @@ static void kfence_test_exit(void) tracepoint_synchronize_unregister(); } -late_initcall(kfence_test_init); +late_initcall_sync(kfence_test_init); module_exit(kfence_test_exit); MODULE_LICENSE("GPL v2"); From 235a85cb32bb123854ad31de46fdbf04c1d57cda Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 23 Jul 2021 15:50:11 -0700 Subject: [PATCH 04/15] kfence: move the size check to the beginning of __kfence_alloc() Check the allocation size before toggling kfence_allocation_gate. This way allocations that can't be served by KFENCE will not result in waiting for another CONFIG_KFENCE_SAMPLE_INTERVAL without allocating anything. Link: https://lkml.kernel.org/r/20210714092222.1890268-1-glider@google.com Signed-off-by: Alexander Potapenko Suggested-by: Marco Elver Reviewed-by: Marco Elver Cc: Dmitry Vyukov Cc: Marco Elver Cc: Greg Kroah-Hartman Cc: [5.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index d7666ace9d2e..2623ff401a10 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -733,6 +733,13 @@ void kfence_shutdown_cache(struct kmem_cache *s) void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { + /* + * Perform size check before switching kfence_allocation_gate, so that + * we don't disable KFENCE without making an allocation. + */ + if (size > PAGE_SIZE) + return NULL; + /* * allocation_gate only needs to become non-zero, so it doesn't make * sense to continue writing to it and pay the associated contention @@ -757,9 +764,6 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (!READ_ONCE(kfence_enabled)) return NULL; - if (size > PAGE_SIZE) - return NULL; - return kfence_guarded_alloc(s, size, flags); } From 236e9f1538523d3d380dda1cc99571d587058f37 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 23 Jul 2021 15:50:14 -0700 Subject: [PATCH 05/15] kfence: skip all GFP_ZONEMASK allocations Allocation requests outside ZONE_NORMAL (MOVABLE, HIGHMEM or DMA) cannot be fulfilled by KFENCE, because KFENCE memory pool is located in a zone different from the requested one. Because callers of kmem_cache_alloc() may actually rely on the allocation to reside in the requested zone (e.g. memory allocations done with __GFP_DMA must be DMAable), skip all allocations done with GFP_ZONEMASK and/or respective SLAB flags (SLAB_CACHE_DMA and SLAB_CACHE_DMA32). Link: https://lkml.kernel.org/r/20210714092222.1890268-2-glider@google.com Fixes: 0ce20dd84089 ("mm: add Kernel Electric-Fence infrastructure") Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Acked-by: Souptick Joarder Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Souptick Joarder Cc: [5.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/core.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 2623ff401a10..575c685aa642 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -740,6 +740,15 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) if (size > PAGE_SIZE) return NULL; + /* + * Skip allocations from non-default zones, including DMA. We cannot + * guarantee that pages in the KFENCE pool will have the requested + * properties (e.g. reside in DMAable memory). + */ + if ((flags & GFP_ZONEMASK) || + (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) + return NULL; + /* * allocation_gate only needs to become non-zero, so it doesn't make * sense to continue writing to it and pay the associated contention From 8dad53a11f8d94dceb540a5f8f153484f42be84b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Jul 2021 15:50:17 -0700 Subject: [PATCH 06/15] mm: call flush_dcache_page() in memcpy_to_page() and memzero_page() memcpy_to_page and memzero_page can write to arbitrary pages, which could be in the page cache or in high memory, so call flush_kernel_dcache_pages to flush the dcache. This is a problem when using these helpers on dcache challeneged architectures. Right now there are just a few users, chances are no one used the PC floppy driver, the aha1542 driver for an ISA SCSI HBA, and a few advanced and optional btrfs and ext4 features on those platforms yet since the conversion. Link: https://lkml.kernel.org/r/20210713055231.137602-2-hch@lst.de Fixes: bb90d4bc7b6a ("mm/highmem: Lift memcpy_[to|from]_page to core") Fixes: 28961998f858 ("iov_iter: lift memzero_page() to highmem.h") Signed-off-by: Christoph Hellwig Reviewed-by: Ira Weiny Cc: Chaitanya Kulkarni Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8c6e8e996c87..8e7e50a53a12 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -318,6 +318,7 @@ static inline void memcpy_to_page(struct page *page, size_t offset, VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); + flush_dcache_page(page); kunmap_local(to); } @@ -325,6 +326,7 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_atomic(page); memset(addr + offset, 0, len); + flush_dcache_page(page); kunmap_atomic(addr); } From d9a42b53bdf7b0329dc09a59fc1b092640b6da19 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 23 Jul 2021 15:50:20 -0700 Subject: [PATCH 07/15] mm: use kmap_local_page in memzero_page The commit message introducing the global memzero_page explicitly mentions switching to kmap_local_page in the commit log but doesn't actually do that. Link: https://lkml.kernel.org/r/20210713055231.137602-3-hch@lst.de Fixes: 28961998f858 ("iov_iter: lift memzero_page() to highmem.h") Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ira Weiny Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8e7e50a53a12..d9a606a9fc64 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -324,10 +324,10 @@ static inline void memcpy_to_page(struct page *page, size_t offset, static inline void memzero_page(struct page *page, size_t offset, size_t len) { - char *addr = kmap_atomic(page); + char *addr = kmap_local_page(page); memset(addr + offset, 0, len); flush_dcache_page(page); - kunmap_atomic(addr); + kunmap_local(addr); } #endif /* _LINUX_HIGHMEM_H */ From 69e5d322a2fb86173fde8bad26e8eb38cad1b1e9 Mon Sep 17 00:00:00 2001 From: Sergei Trofimovich Date: Fri, 23 Jul 2021 15:50:23 -0700 Subject: [PATCH 08/15] mm: page_alloc: fix page_poison=1 / INIT_ON_ALLOC_DEFAULT_ON interaction To reproduce the failure we need the following system: - kernel command: page_poison=1 init_on_free=0 init_on_alloc=0 - kernel config: * CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y * CONFIG_INIT_ON_FREE_DEFAULT_ON=y * CONFIG_PAGE_POISONING=y Resulting in: 0000000085629bdd: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 0000000022861832: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00000000c597f5b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ CPU: 11 PID: 15195 Comm: bash Kdump: loaded Tainted: G U O 5.13.1-gentoo-x86_64 #1 Hardware name: System manufacturer System Product Name/PRIME Z370-A, BIOS 2801 01/13/2021 Call Trace: dump_stack+0x64/0x7c __kernel_unpoison_pages.cold+0x48/0x84 post_alloc_hook+0x60/0xa0 get_page_from_freelist+0xdb8/0x1000 __alloc_pages+0x163/0x2b0 __get_free_pages+0xc/0x30 pgd_alloc+0x2e/0x1a0 mm_init+0x185/0x270 dup_mm+0x6b/0x4f0 copy_process+0x190d/0x1b10 kernel_clone+0xba/0x3b0 __do_sys_clone+0x8f/0xb0 do_syscall_64+0x68/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Before commit 51cba1ebc60d ("init_on_alloc: Optimize static branches") init_on_alloc never enabled static branch by default. It could only be enabed explicitly by init_mem_debugging_and_hardening(). But after commit 51cba1ebc60d, a static branch could already be enabled by default. There was no code to ever disable it. That caused page_poison=1 / init_on_free=1 conflict. This change extends init_mem_debugging_and_hardening() to also disable static branch disabling. Link: https://lkml.kernel.org/r/20210714031935.4094114-1-keescook@chromium.org Link: https://lore.kernel.org/r/20210712215816.1512739-1-slyfox@gentoo.org Fixes: 51cba1ebc60d ("init_on_alloc: Optimize static branches") Signed-off-by: Sergei Trofimovich Signed-off-by: Kees Cook Co-developed-by: Kees Cook Reported-by: Mikhail Morfikov Reported-by: Tested-by: Reviewed-by: David Hildenbrand Cc: Alexander Potapenko Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3e97e68aef7a..856b175c15a4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -840,21 +840,24 @@ void init_mem_debugging_and_hardening(void) } #endif - if (_init_on_alloc_enabled_early) { - if (page_poisoning_requested) - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc\n"); - else - static_branch_enable(&init_on_alloc); - } - if (_init_on_free_enabled_early) { - if (page_poisoning_requested) - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_free\n"); - else - static_branch_enable(&init_on_free); + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && + page_poisoning_requested) { + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " + "will take precedence over init_on_alloc and init_on_free\n"); + _init_on_alloc_enabled_early = false; + _init_on_free_enabled_early = false; } + if (_init_on_alloc_enabled_early) + static_branch_enable(&init_on_alloc); + else + static_branch_disable(&init_on_alloc); + + if (_init_on_free_enabled_early) + static_branch_enable(&init_on_free); + else + static_branch_disable(&init_on_free); + #ifdef CONFIG_DEBUG_PAGEALLOC if (!debug_pagealloc_enabled()) return; From 79e482e9c3ae86e849c701c846592e72baddda5a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 23 Jul 2021 15:50:26 -0700 Subject: [PATCH 09/15] memblock: make for_each_mem_range() traverse MEMBLOCK_HOTPLUG regions Commit b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()") didn't take into account that when there is movable_node parameter in the kernel command line, for_each_mem_range() would skip ranges marked with MEMBLOCK_HOTPLUG. The page table setup code in POWER uses for_each_mem_range() to create the linear mapping of the physical memory and since the regions marked as MEMORY_HOTPLUG are skipped, they never make it to the linear map. A later access to the memory in those ranges will fail: BUG: Unable to handle kernel data access on write at 0xc000000400000000 Faulting instruction address: 0xc00000000008a3c0 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 0 PID: 53 Comm: kworker/u2:0 Not tainted 5.13.0 #7 NIP: c00000000008a3c0 LR: c0000000003c1ed8 CTR: 0000000000000040 REGS: c000000008a57770 TRAP: 0300 Not tainted (5.13.0) MSR: 8000000002009033 CR: 84222202 XER: 20040000 CFAR: c0000000003c1ed4 DAR: c000000400000000 DSISR: 42000000 IRQMASK: 0 GPR00: c0000000003c1ed8 c000000008a57a10 c0000000019da700 c000000400000000 GPR04: 0000000000000280 0000000000000180 0000000000000400 0000000000000200 GPR08: 0000000000000100 0000000000000080 0000000000000040 0000000000000300 GPR12: 0000000000000380 c000000001bc0000 c0000000001660c8 c000000006337e00 GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR20: 0000000040000000 0000000020000000 c000000001a81990 c000000008c30000 GPR24: c000000008c20000 c000000001a81998 000fffffffff0000 c000000001a819a0 GPR28: c000000001a81908 c00c000001000000 c000000008c40000 c000000008a64680 NIP clear_user_page+0x50/0x80 LR __handle_mm_fault+0xc88/0x1910 Call Trace: __handle_mm_fault+0xc44/0x1910 (unreliable) handle_mm_fault+0x130/0x2a0 __get_user_pages+0x248/0x610 __get_user_pages_remote+0x12c/0x3e0 get_arg_page+0x54/0xf0 copy_string_kernel+0x11c/0x210 kernel_execve+0x16c/0x220 call_usermodehelper_exec_async+0x1b0/0x2f0 ret_from_kernel_thread+0x5c/0x70 Instruction dump: 79280fa4 79271764 79261f24 794ae8e2 7ca94214 7d683a14 7c893a14 7d893050 7d4903a6 60000000 60000000 60000000 <7c001fec> 7c091fec 7c081fec 7c051fec ---[ end trace 490b8c67e6075e09 ]--- Making for_each_mem_range() include MEMBLOCK_HOTPLUG regions in the traversal fixes this issue. Link: https://bugzilla.redhat.com/show_bug.cgi?id=1976100 Link: https://lkml.kernel.org/r/20210712071132.20902-1-rppt@kernel.org Fixes: b10d6bca8720 ("arch, drivers: replace for_each_membock() with for_each_mem_range()") Signed-off-by: Mike Rapoport Tested-by: Greg Kurz Reviewed-by: David Hildenbrand Cc: [5.10+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- mm/memblock.c | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index cbf46f56d105..4a53c3ca86bd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -209,7 +209,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_NONE, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG, p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -220,7 +220,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_NONE, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG, p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas diff --git a/mm/memblock.c b/mm/memblock.c index 0041ff62c584..de7b553baa50 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -947,7 +947,8 @@ static bool should_skip_region(struct memblock_type *type, return true; /* skip hotpluggable memory regions if needed */ - if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) + if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && + !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ From b43a9e76b4cc78cdaa8c809dd31cd452797b7661 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 23 Jul 2021 15:50:29 -0700 Subject: [PATCH 10/15] writeback, cgroup: remove wb from offline list before releasing refcnt Boyang reported that the commit c22d70a162d3 ("writeback, cgroup: release dying cgwbs by switching attached inodes") causes the kernel to crash while running xfstests generic/256 on ext4 on aarch64 and ppc64le. run fstests generic/256 at 2021-07-12 05:41:40 EXT4-fs (vda3): mounted filesystem with ordered data mode. Opts: . Quota mode: none. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 Mem abort info: ESR = 0x96000005 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 CM = 0, WnR = 0 user pgtable: 64k pages, 48-bit VAs, pgdp=00000000b0502000 [0000000000000000] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: dm_flakey dm_snapshot dm_bufio dm_zero dm_mod loop tls rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs rfkill sunrpc ext4 vfat fat mbcache jbd2 drm fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 sha1_ce virtio_blk virtio_net net_failover virtio_console failover virtio_mmio aes_neon_bs [last unloaded: scsi_debug] CPU: 0 PID: 408468 Comm: kworker/u8:5 Tainted: G X --------- --- 5.14.0-0.rc1.15.bx.el9.aarch64 #1 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Workqueue: events_unbound cleanup_offline_cgwbs_workfn pstate: 004000c5 (nzcv daIF +PAN -UAO -TCO BTYPE=--) pc : cleanup_offline_cgwbs_workfn+0x320/0x394 lr : cleanup_offline_cgwbs_workfn+0xe0/0x394 sp : ffff80001554fd10 x29: ffff80001554fd10 x28: 0000000000000000 x27: 0000000000000001 x26: 0000000000000000 x25: 00000000000000e0 x24: ffffd2a2fbe671a8 x23: ffff80001554fd88 x22: ffffd2a2fbe67198 x21: ffffd2a2fc25a730 x20: ffff210412bc3000 x19: ffff210412bc3280 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000030 x12: 0000000000000040 x11: ffff210481572238 x10: ffff21048157223a x9 : ffffd2a2fa276c60 x8 : ffff210484106b60 x7 : 0000000000000000 x6 : 000000000007d18a x5 : ffff210416a86400 x4 : ffff210412bc0280 x3 : 0000000000000000 x2 : ffff80001554fd88 x1 : ffff210412bc0280 x0 : 0000000000000003 Call trace: cleanup_offline_cgwbs_workfn+0x320/0x394 process_one_work+0x1f4/0x4b0 worker_thread+0x184/0x540 kthread+0x114/0x120 ret_from_fork+0x10/0x18 Code: d63f0020 97f99963 17ffffa6 f8588263 (f9400061) ---[ end trace e250fe289272792a ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs SMP: failed to stop secondary CPUs 0-2 Kernel Offset: 0x52a2e9fa0000 from 0xffff800010000000 PHYS_OFFSET: 0xfff0defca0000000 CPU features: 0x00200251,23200840 Memory Limit: none ---[ end Kernel panic - not syncing: Oops: Fatal exception ]--- The problem happens when cgwb_release_workfn() races with cleanup_offline_cgwbs_workfn(): wb_tryget() in cleanup_offline_cgwbs_workfn() can be called after percpu_ref_exit() is cgwb_release_workfn(), which is basically a use-after-free error. Fix the problem by making removing the writeback structure from the offline list before releasing the percpu reference counter. It will guarantee that cleanup_offline_cgwbs_workfn() will not see and not access writeback structures which are about to be released. Link: https://lkml.kernel.org/r/20210716201039.3762203-1-guro@fb.com Fixes: c22d70a162d3 ("writeback, cgroup: release dying cgwbs by switching attached inodes") Signed-off-by: Roman Gushchin Reported-by: Boyang Xue Suggested-by: Jan Kara Tested-by: Darrick J. Wong Cc: Will Deacon Cc: Dave Chinner Cc: Murphy Zhou Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/backing-dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 271f2ca862c8..f5561ea7d90a 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -398,12 +398,12 @@ static void cgwb_release_workfn(struct work_struct *work) blkcg_unpin_online(blkcg); fprop_local_destroy_percpu(&wb->memcg_completions); - percpu_ref_exit(&wb->refcnt); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); + percpu_ref_exit(&wb->refcnt); wb_exit(wb); WARN_ON_ONCE(!list_empty(&wb->b_attached)); kfree_rcu(wb, rcu); From 593311e85b26ecc6e4d45b6fb81b942b6672df09 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 23 Jul 2021 15:50:32 -0700 Subject: [PATCH 11/15] writeback, cgroup: do not reparent dax inodes The inode switching code is not suited for dax inodes. An attempt to switch a dax inode to a parent writeback structure (as a part of a writeback cleanup procedure) results in a panic like this: run fstests generic/270 at 2021-07-15 05:54:02 XFS (pmem0p2): EXPERIMENTAL big timestamp feature in use. Use at your own risk! XFS (pmem0p2): DAX enabled. Warning: EXPERIMENTAL, use at your own risk XFS (pmem0p2): EXPERIMENTAL inode btree counters feature in use. Use at your own risk! XFS (pmem0p2): Mounting V5 Filesystem XFS (pmem0p2): Ending clean mount XFS (pmem0p2): Quotacheck needed: Please wait. XFS (pmem0p2): Quotacheck: Done. XFS (pmem0p2): xlog_verify_grant_tail: space > BBTOB(tail_blocks) XFS (pmem0p2): xlog_verify_grant_tail: space > BBTOB(tail_blocks) XFS (pmem0p2): xlog_verify_grant_tail: space > BBTOB(tail_blocks) BUG: unable to handle page fault for address: 0000000005b0f669 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 13 PID: 10479 Comm: kworker/13:16 Not tainted 5.14.0-rc1-master-8096acd7442e+ #8 Hardware name: HP ProLiant DL360 Gen9/ProLiant DL360 Gen9, BIOS P89 09/13/2016 Workqueue: inode_switch_wbs inode_switch_wbs_work_fn RIP: 0010:inode_do_switch_wbs+0xaf/0x470 Code: 00 30 0f 85 c1 03 00 00 0f 1f 44 00 00 31 d2 48 c7 c6 ff ff ff ff 48 8d 7c 24 08 e8 eb 49 1a 00 48 85 c0 74 4a bb ff ff ff ff <48> 8b 50 08 48 8d 4a ff 83 e2 01 48 0f 45 c1 48 8b 00 a8 08 0f 85 RSP: 0018:ffff9c66691abdc8 EFLAGS: 00010002 RAX: 0000000005b0f661 RBX: 00000000ffffffff RCX: ffff89e6a21382b0 RDX: 0000000000000001 RSI: ffff89e350230248 RDI: ffffffffffffffff RBP: ffff89e681d19400 R08: 0000000000000000 R09: 0000000000000228 R10: ffffffffffffffff R11: ffffffffffffffc0 R12: ffff89e6a2138130 R13: ffff89e316af7400 R14: ffff89e316af6e78 R15: ffff89e6a21382b0 FS: 0000000000000000(0000) GS:ffff89ee5fb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000005b0f669 CR3: 0000000cb2410004 CR4: 00000000001706e0 Call Trace: inode_switch_wbs_work_fn+0xb6/0x2a0 process_one_work+0x1e6/0x380 worker_thread+0x53/0x3d0 kthread+0x10f/0x130 ret_from_fork+0x22/0x30 Modules linked in: xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nft_counter nf_tables nfnetlink bridge stp llc rfkill sunrpc intel_rapl_msr intel_rapl_common sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ipmi_ssif kvm mgag200 i2c_algo_bit iTCO_wdt irqbypass drm_kms_helper iTCO_vendor_support acpi_ipmi rapl syscopyarea sysfillrect intel_cstate ipmi_si sysimgblt ioatdma dax_pmem_compat fb_sys_fops ipmi_devintf device_dax i2c_i801 pcspkr intel_uncore hpilo nd_pmem cec dax_pmem_core dca i2c_smbus acpi_tad lpc_ich ipmi_msghandler acpi_power_meter drm fuse xfs libcrc32c sd_mod t10_pi crct10dif_pclmul crc32_pclmul crc32c_intel tg3 ghash_clmulni_intel serio_raw hpsa hpwdt scsi_transport_sas wmi dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000005b0f669 ---[ end trace ed2105faff8384f3 ]--- RIP: 0010:inode_do_switch_wbs+0xaf/0x470 Code: 00 30 0f 85 c1 03 00 00 0f 1f 44 00 00 31 d2 48 c7 c6 ff ff ff ff 48 8d 7c 24 08 e8 eb 49 1a 00 48 85 c0 74 4a bb ff ff ff ff <48> 8b 50 08 48 8d 4a ff 83 e2 01 48 0f 45 c1 48 8b 00 a8 08 0f 85 RSP: 0018:ffff9c66691abdc8 EFLAGS: 00010002 RAX: 0000000005b0f661 RBX: 00000000ffffffff RCX: ffff89e6a21382b0 RDX: 0000000000000001 RSI: ffff89e350230248 RDI: ffffffffffffffff RBP: ffff89e681d19400 R08: 0000000000000000 R09: 0000000000000228 R10: ffffffffffffffff R11: ffffffffffffffc0 R12: ffff89e6a2138130 R13: ffff89e316af7400 R14: ffff89e316af6e78 R15: ffff89e6a21382b0 FS: 0000000000000000(0000) GS:ffff89ee5fb40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000005b0f669 CR3: 0000000cb2410004 CR4: 00000000001706e0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x15200000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- The crash happens on an attempt to iterate over attached pagecache pages and check the dirty flag: a dax inode's xarray contains pfn's instead of generic struct page pointers. This happens for DAX and not for other kinds of non-page entries in the inodes because it's a tagged iteration, and shadow/swap entries are never tagged; only DAX entries get tagged. Fix the problem by bailing out (with the false return value) of inode_prepare_sbs_switch() if a dax inode is passed. [willy@infradead.org: changelog addition] Link: https://lkml.kernel.org/r/20210719171350.3876830-1-guro@fb.com Fixes: c22d70a162d3 ("writeback, cgroup: release dying cgwbs by switching attached inodes") Signed-off-by: Roman Gushchin Reported-by: Murphy Zhou Reported-by: Darrick J. Wong Tested-by: Darrick J. Wong Tested-by: Murphy Zhou Acked-by: Matthew Wilcox (Oracle) Cc: Jan Kara Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 06d04a74ab6c..4c3370548982 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -521,6 +521,9 @@ static bool inode_prepare_wbs_switch(struct inode *inode, */ smp_mb(); + if (IS_DAX(inode)) + return false; + /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || From af64237461910f4c7365d367291d1c4f20c18769 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 23 Jul 2021 15:50:35 -0700 Subject: [PATCH 12/15] mm/secretmem: wire up ->set_page_dirty Make secretmem up to date with the changes done in commit 0af573780b0b ("mm: require ->set_page_dirty to be explicitly wired up") so that unconditional call to this method won't cause crashes. Link: https://lkml.kernel.org/r/20210716063933.31633-1-rppt@kernel.org Fixes: 0af573780b0b ("mm: require ->set_page_dirty to be explicitly wired up") Signed-off-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/secretmem.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/secretmem.c b/mm/secretmem.c index f77d25467a14..030f02ddc7c1 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -152,6 +152,7 @@ static void secretmem_freepage(struct page *page) } const struct address_space_operations secretmem_aops = { + .set_page_dirty = __set_page_dirty_no_writeback, .freepage = secretmem_freepage, .migratepage = secretmem_migratepage, .isolate_page = secretmem_isolate_page, From e904c2ccf9b5cb356eec754ffea05c08984f6535 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 23 Jul 2021 15:50:38 -0700 Subject: [PATCH 13/15] mm: mmap_lock: fix disabling preemption directly Commit 832b50725373 ("mm: mmap_lock: use local locks instead of disabling preemption") fixed a bug by using local locks. But commit d01079f3d0c0 ("mm/mmap_lock: remove dead code for !CONFIG_TRACING configurations") changed those lines back to the original version. I guess it was introduced by fixing conflicts. Link: https://lkml.kernel.org/r/20210720074228.76342-1-songmuchun@bytedance.com Fixes: d01079f3d0c0 ("mm/mmap_lock: remove dead code for !CONFIG_TRACING configurations") Signed-off-by: Muchun Song Acked-by: Mel Gorman Reviewed-by: Yang Shi Reviewed-by: Pankaj Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap_lock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index f5852a058ce0..1854850b4b89 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -156,14 +156,14 @@ static inline void put_memcg_path_buf(void) #define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ do { \ const char *memcg_path; \ - preempt_disable(); \ + local_lock(&memcg_paths.lock); \ memcg_path = get_mm_memcg_path(mm); \ trace_mmap_lock_##type(mm, \ memcg_path != NULL ? memcg_path : "", \ ##__VA_ARGS__); \ if (likely(memcg_path != NULL)) \ put_memcg_path_buf(); \ - preempt_enable(); \ + local_unlock(&memcg_paths.lock); \ } while (0) #else /* !CONFIG_MEMCG */ From e4dc3489143f84f7ed30be58b886bb6772f229b9 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Fri, 23 Jul 2021 15:50:41 -0700 Subject: [PATCH 14/15] mm: fix the deadlock in finish_fault() Commit 63f3655f9501 ("mm, memcg: fix reclaim deadlock with writeback") fix the following ABBA deadlock by pre-allocating the pte page table without holding the page lock. lock_page(A) SetPageWriteback(A) unlock_page(A) lock_page(B) lock_page(B) pte_alloc_one shrink_page_list wait_on_page_writeback(A) SetPageWriteback(B) unlock_page(B) # flush A, B to clear the writeback Commit f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") reworked the relevant code but ignored this race. This will cause the deadlock above to appear again, so fix it. Link: https://lkml.kernel.org/r/20210721074849.57004-1-zhengqi.arch@bytedance.com Fixes: f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") Signed-off-by: Qi Zheng Acked-by: Kirill A. Shutemov Cc: Thomas Gleixner Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Muchun Song Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 747a01d495f2..25fc46e87214 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4026,8 +4026,17 @@ vm_fault_t finish_fault(struct vm_fault *vmf) return ret; } - if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) + if (vmf->prealloc_pte) { + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (likely(pmd_none(*vmf->pmd))) { + mm_inc_nr_ptes(vma->vm_mm); + pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); + vmf->prealloc_pte = NULL; + } + spin_unlock(vmf->ptl); + } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; + } } /* See comment in handle_pte_fault() */ From e0f7e2b2f7e7864238a4eea05cc77ae1be2bf784 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 23 Jul 2021 15:50:44 -0700 Subject: [PATCH 15/15] hugetlbfs: fix mount mode command line processing In commit 32021982a324 ("hugetlbfs: Convert to fs_context") processing of the mount mode string was changed from match_octal() to fsparam_u32. This changed existing behavior as match_octal does not require octal values to have a '0' prefix, but fsparam_u32 does. Use fsparam_u32oct which provides the same behavior as match_octal. Link: https://lkml.kernel.org/r/20210721183326.102716-1-mike.kravetz@oracle.com Fixes: 32021982a324 ("hugetlbfs: Convert to fs_context") Signed-off-by: Mike Kravetz Reported-by: Dennis Camera Reviewed-by: Matthew Wilcox (Oracle) Cc: David Howells Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 926eeb9bf4eb..cdfb1ae78a3f 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -77,7 +77,7 @@ enum hugetlb_param { static const struct fs_parameter_spec hugetlb_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_string("min_size", Opt_min_size), - fsparam_u32 ("mode", Opt_mode), + fsparam_u32oct("mode", Opt_mode), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("pagesize", Opt_pagesize), fsparam_string("size", Opt_size),