From 1db9dbc2ef05205bf1022f9b14aa29b1dd8efd7e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm/uffd: PTE_MARKER_UFFD_WP This patch introduces the 1st user of pte marker: the uffd-wp marker. When the pte marker is installed with the uffd-wp bit set, it means this pte was wr-protected by uffd. We will use this special pte to arm the ptes that got either unmapped or swapped out for a file-backed region that was previously wr-protected. This special pte could trigger a page fault just like swap entries. This idea is greatly inspired by Hugh and Andrea in the discussion, which is referenced in the links below. Some helpers are introduced to detect whether a swap pte is uffd wr-protected. After the pte marker introduced, one swap pte can be wr-protected in two forms: either it is a normal swap pte and it has _PAGE_SWP_UFFD_WP set, or it's a pte marker that has PTE_MARKER_UFFD_WP set. [peterx@redhat.com: fixup] Link: https://lkml.kernel.org/r/YkzKiM8tI4+qOfXF@xz-m1.local Link: https://lore.kernel.org/lkml/20201126222359.8120-1-peterx@redhat.com/ Link: https://lore.kernel.org/lkml/20201130230603.46187-1-peterx@redhat.com/ Link: https://lkml.kernel.org/r/20220405014838.14131-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Andrea Arcangeli Suggested-by: Hugh Dickins Cc: Alistair Popple Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 47 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux/userfaultfd_k.h') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 33cea484d1ad..3354d9ddc35f 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -15,6 +15,8 @@ #include #include +#include +#include #include /* The set of all possible UFFD-related VM flags. */ @@ -236,4 +238,49 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, #endif /* CONFIG_USERFAULTFD */ +static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); +#else + return false; +#endif +} + +static inline bool pte_marker_uffd_wp(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + swp_entry_t entry; + + if (!is_swap_pte(pte)) + return false; + + entry = pte_to_swp_entry(pte); + + return pte_marker_entry_uffd_wp(entry); +#else + return false; +#endif +} + +/* + * Returns true if this is a swap pte and was uffd-wp wr-protected in either + * forms (pte marker or a normal swap pte), false otherwise. + */ +static inline bool pte_swp_uffd_wp_any(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + if (!is_swap_pte(pte)) + return false; + + if (pte_swp_uffd_wp(pte)) + return true; + + if (pte_marker_uffd_wp(pte)) + return true; +#endif + return false; +} + #endif /* _LINUX_USERFAULTFD_K_H */ -- cgit v1.2.3 From 9c28a205c06123b9f0a0c4d819ece9f5f552d004 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:53 -0700 Subject: mm/shmem: handle uffd-wp special pte in page fault handler File-backed memories are prone to unmap/swap so the ptes are always unstable, because they can be easily faulted back later using the page cache. This could lead to uffd-wp getting lost when unmapping or swapping out such memory. One example is shmem. PTE markers are needed to store those information. This patch prepares it by handling uffd-wp pte markers first it is applied elsewhere, so that the page fault handler can recognize uffd-wp pte markers. The handling of uffd-wp pte markers is similar to missing fault, it's just that we'll handle this "missing fault" when we see the pte markers, meanwhile we need to make sure the marker information is kept during processing the fault. This is a slow path of uffd-wp handling, because zapping of wr-protected shmem ptes should be rare. So far it should only trigger in two conditions: (1) When trying to punch holes in shmem_fallocate(), there is an optimization to zap the pgtables before evicting the page. (2) When swapping out shmem pages. Because of this, the page fault handling is simplifed too by not sending the wr-protect message in the 1st page fault, instead the page will be installed read-only, so the uffd-wp message will be generated in the next fault, which will trigger the do_wp_page() path of general uffd-wp handling. Disable fault-around for all uffd-wp registered ranges for extra safety just like uffd-minor fault, and clean the code up. Link: https://lkml.kernel.org/r/20220405014844.14239-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux/userfaultfd_k.h') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3354d9ddc35f..e7afcdfd4b46 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -96,6 +96,18 @@ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } +/* + * Don't do fault around for either WP or MINOR registered uffd range. For + * MINOR registered range, fault around will be a total disaster and ptes can + * be installed without notifications; for WP it should mostly be fine as long + * as the fault around checks for pte_none() before the installation, however + * to be super safe we just forbid it. + */ +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -236,6 +248,11 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) -- cgit v1.2.3 From b1f9e876862d8f7176299ec4fb2108bc1045cbc8 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:56 -0700 Subject: mm/uffd: enable write protection for shmem & hugetlbfs We've had all the necessary changes ready for both shmem and hugetlbfs. Turn on all the shmem/hugetlbfs switches for userfaultfd-wp. We can expand UFFD_API_RANGE_IOCTLS_BASIC with _UFFDIO_WRITEPROTECT too because all existing types now support write protection mode. Since vma_can_userfault() will be used elsewhere, move into userfaultfd_k.h. Link: https://lkml.kernel.org/r/20220405014926.15101-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux/userfaultfd_k.h') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e7afcdfd4b46..732b522bacb7 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -18,6 +18,7 @@ #include #include #include +#include /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) @@ -140,6 +141,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return vma->vm_flags & __VM_UFFD_FLAGS; } +static inline bool vma_can_userfault(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + if (vm_flags & VM_UFFD_MINOR) + return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); + +#ifndef CONFIG_PTE_MARKER_UFFD_WP + /* + * If user requested uffd-wp but not enabled pte markers for + * uffd-wp, then shmem & hugetlbfs are not supported but only + * anonymous. + */ + if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) + return false; +#endif + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); -- cgit v1.2.3 From f369b07c861435bd812a9d14493f71b34132ed6f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 16:13:40 -0400 Subject: mm/uffd: reset write protection when unregister with wp-mode The motivation of this patch comes from a recent report and patchfix from David Hildenbrand on hugetlb shared handling of wr-protected page [1]. With the reproducer provided in commit message of [1], one can leverage the uffd-wp lazy-reset of ptes to trigger a hugetlb issue which can affect not only the attacker process, but also the whole system. The lazy-reset mechanism of uffd-wp was used to make unregister faster, meanwhile it has an assumption that any leftover pgtable entries should only affect the process on its own, so not only the user should be aware of anything it does, but also it should not affect outside of the process. But it seems that this is not true, and it can also be utilized to make some exploit easier. So far there's no clue showing that the lazy-reset is important to any userfaultfd users because normally the unregister will only happen once for a specific range of memory of the lifecycle of the process. Considering all above, what this patch proposes is to do explicit pte resets when unregister an uffd region with wr-protect mode enabled. It should be the same as calling ioctl(UFFDIO_WRITEPROTECT, wp=false) right before ioctl(UFFDIO_UNREGISTER) for the user. So potentially it'll make the unregister slower. From that pov it's a very slight abi change, but hopefully nothing should break with this change either. Regarding to the change itself - core of uffd write [un]protect operation is moved into a separate function (uffd_wp_range()) and it is reused in the unregister code path. Note that the new function will not check for anything, e.g. ranges or memory types, because they should have been checked during the previous UFFDIO_REGISTER or it should have failed already. It also doesn't check mmap_changing because we're with mmap write lock held anyway. I added a Fixes upon introducing of uffd-wp shmem+hugetlbfs because that's the only issue reported so far and that's the commit David's reproducer will start working (v5.19+). But the whole idea actually applies to not only file memories but also anonymous. It's just that we don't need to fix anonymous prior to v5.19- because there's no known way to exploit. IOW, this patch can also fix the issue reported in [1] as the patch 2 does. [1] https://lore.kernel.org/all/20220811103435.188481-3-david@redhat.com/ Link: https://lkml.kernel.org/r/20220811201340.39342-1-peterx@redhat.com Fixes: b1f9e876862d ("mm/uffd: enable write protection for shmem & hugetlbfs") Signed-off-by: Peter Xu Cc: David Hildenbrand Cc: Mike Rapoport Cc: Mike Kravetz Cc: Andrea Arcangeli Cc: Nadav Amit Cc: Axel Rasmussen Cc: Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/userfaultfd_k.h') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 732b522bacb7..e1b8a915e9e9 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -73,6 +73,8 @@ extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); +extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, + unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, -- cgit v1.2.3 From 69dbe6daf1041e32e003f966d71f70f20c63af53 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Tue, 6 Sep 2022 19:48:57 +0000 Subject: userfaultfd: use maple tree iterator to iterate VMAs Don't use the mm_struct linked list or the vma->vm_next in prep for removal. Link: https://lkml.kernel.org/r/20220906194824.2110408-45-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Tested-by: Yu Zhao Cc: Catalin Marinas Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: "Matthew Wilcox (Oracle)" Cc: SeongJae Park Cc: Sven Schnelle Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux/userfaultfd_k.h') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e1b8a915e9e9..f07e6998bb68 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -175,9 +175,8 @@ extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); -extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct list_head *uf); +extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, + unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); @@ -258,7 +257,7 @@ static inline bool userfaultfd_remove(struct vm_area_struct *vma, return true; } -static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, +static inline int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf) { -- cgit v1.2.3 From 67eae54bc227b30dedcce9db68b063ba1adb7838 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 24 Oct 2022 15:33:35 -0400 Subject: mm/uffd: fix vma check on userfault for wp We used to have a report that pte-marker code can be reached even when uffd-wp is not compiled in for file memories, here: https://lore.kernel.org/all/YzeR+R6b4bwBlBHh@x1n/T/#u I just got time to revisit this and found that the root cause is we simply messed up with the vma check, so that for !PTE_MARKER_UFFD_WP system, we will allow UFFDIO_REGISTER of MINOR & WP upon shmem as the check was wrong: if (vm_flags & VM_UFFD_MINOR) return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); Where we'll allow anything to pass on shmem as long as minor mode is requested. Axel did it right when introducing minor mode but I messed it up in b1f9e876862d when moving code around. Fix it. Link: https://lkml.kernel.org/r/20221024193336.1233616-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20221024193336.1233616-2-peterx@redhat.com Fixes: b1f9e876862d ("mm/uffd: enable write protection for shmem & hugetlbfs") Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: Andrea Arcangeli Cc: Nadav Amit Cc: Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/userfaultfd_k.h') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index f07e6998bb68..9df0b9a762cc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -146,9 +146,9 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { - if (vm_flags & VM_UFFD_MINOR) - return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); - + if ((vm_flags & VM_UFFD_MINOR) && + (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) + return false; #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for -- cgit v1.2.3