kernel/linux.git/include/linux/userfaultfd_k.h, branch v6.12.80

mm: clear uffd-wp PTE/PMD state on mremap()

2025-01-23T16:23:02+00:00

commit 0cef0bb836e3cfe00f08f9606c72abd72fe78ca3 upstream. When mremap()ing a memory region previously registered with userfaultfd as write-protected but without UFFD_FEATURE_EVENT_REMAP, an inconsistency in flag clearing leads to a mismatch between the vma flags (which have uffd-wp cleared) and the pte/pmd flags (which do not have uffd-wp cleared). This mismatch causes a subsequent mprotect(PROT_WRITE) to trigger a warning in page_table_check_pte_flags() due to setting the pte to writable while uffd-wp is still set. Fix this by always explicitly clearing the uffd-wp pte/pmd flags on any such mremap() so that the values are consistent with the existing clearing of VM_UFFD_WP. Be careful to clear the logical flag regardless of its physical form; a PTE bit, a swap PTE bit, or a PTE marker. Cover PTE, huge PMD and hugetlb paths. Link: https://lkml.kernel.org/r/20250107144755.1871363-2-ryan.roberts@arm.com Co-developed-by: Mikołaj Lenczewski Signed-off-by: Mikołaj Lenczewski Signed-off-by: Ryan Roberts Closes: https://lore.kernel.org/linux-mm/810b44a8-d2ae-4107-b665-5a42eae2d948@arm.com/ Fixes: 63b2d4174c4a ("userfaultfd: wp: add the writeprotect API to userfaultfd ioctl") Cc: David Hildenbrand Cc: Jann Horn Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Mark Rutland Cc: Muchun Song Cc: Peter Xu Cc: Shuah Khan Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman

fork: do not invoke uffd on fork if error occurs

2024-10-29T04:40:38+00:00

Patch series "fork: do not expose incomplete mm on fork". During fork we may place the virtual memory address space into an inconsistent state before the fork operation is complete. In addition, we may encounter an error during the fork operation that indicates that the virtual memory address space is invalidated. As a result, we should not be exposing it in any way to external machinery that might interact with the mm or VMAs, machinery that is not designed to deal with incomplete state. We specifically update the fork logic to defer khugepaged and ksm to the end of the operation and only to be invoked if no error arose, and disallow uffd from observing fork events should an error have occurred. This patch (of 2): Currently on fork we expose the virtual address space of a process to userland unconditionally if uffd is registered in VMAs, regardless of whether an error arose in the fork. This is performed in dup_userfaultfd_complete() which is invoked unconditionally, and performs two duties - invoking registered handlers for the UFFD_EVENT_FORK event via dup_fctx(), and clearing down userfaultfd_fork_ctx objects established in dup_userfaultfd(). This is problematic, because the virtual address space may not yet be correctly initialised if an error arose. The change in commit d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") makes this more pertinent as we may be in a state where entries in the maple tree are not yet consistent. We address this by, on fork error, ensuring that we roll back state that we would otherwise expect to clean up through the event being handled by userland and perform the memory freeing duty otherwise performed by dup_userfaultfd_complete(). We do this by implementing a new function, dup_userfaultfd_fail(), which performs the same loop, only decrementing reference counts. Note that we perform mmgrab() on the parent and child mm's, however userfaultfd_ctx_put() will mmdrop() this once the reference count drops to zero, so we will avoid memory leaks correctly here. Link: https://lkml.kernel.org/r/cover.1729014377.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/d3691d58bb58712b6fb3df2be441d175bd3cdf07.1729014377.git.lorenzo.stoakes@oracle.com Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") Signed-off-by: Lorenzo Stoakes Reported-by: Jann Horn Reviewed-by: Jann Horn Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: Linus Torvalds Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton

userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c

2024-09-02T03:25:53+00:00

Patch series "Make core VMA operations internal and testable", v4. There are a number of "core" VMA manipulation functions implemented in mm/mmap.c, notably those concerning VMA merging, splitting, modifying, expanding and shrinking, which logically don't belong there. More importantly this functionality represents an internal implementation detail of memory management and should not be exposed outside of mm/ itself. This patch series isolates core VMA manipulation functionality into its own file, mm/vma.c, and provides an API to the rest of the mm code in mm/vma.h. Importantly, it also carefully implements mm/vma_internal.h, which specifies which headers need to be imported by vma.c, leading to the very useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h. This means we can then re-implement vma_internal.h in userland, adding shims for kernel mechanisms as required, allowing us to unit test internal VMA functionality. This testing is useful as opposed to an e.g. kunit implementation as this way we can avoid all external kernel side-effects while testing, run tests VERY quickly, and iterate on and debug problems quickly. Excitingly this opens the door to, in the future, recreating precise problems observed in production in userland and very quickly debugging problems that might otherwise be very difficult to reproduce. This patch series takes advantage of existing shim logic and full userland maple tree support contained in tools/testing/radix-tree/ and tools/include/linux/, separating out shared components of the radix tree implementation to provide this testing. Kernel functionality is stubbed and shimmed as needed in tools/testing/vma/ which contains a fully functional userland vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly tested from userland. A simple, skeleton testing implementation is provided in tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA merge, modify (testing split), expand and shrink functionality work correctly. This patch (of 4): This patch forms part of a patch series intending to separate out VMA logic and render it testable from userspace, which requires that core manipulation functions be exposed in an mm/-internal header file. In order to do this, we must abstract APIs we wish to test, in this instance functions which ultimately invoke vma_modify(). This patch therefore moves all logic which ultimately invokes vma_modify() to mm/userfaultfd.c, trying to transfer code at a functional granularity where possible. [lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()] Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Alexander Viro Cc: Brendan Higgins Cc: Christian Brauner Cc: David Gow Cc: Eric W. Biederman Cc: Jan Kara Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Rae Moar Cc: SeongJae Park Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Pengfei Xu Signed-off-by: Andrew Morton

mm: add MAP_DROPPABLE for designating always lazily freeable mappings

2024-07-19T18:22:12+00:00

The vDSO getrandom() implementation works with a buffer allocated with a new system call that has certain requirements: - It shouldn't be written to core dumps. * Easy: VM_DONTDUMP. - It should be zeroed on fork. * Easy: VM_WIPEONFORK. - It shouldn't be written to swap. * Uh-oh: mlock is rlimited. * Uh-oh: mlock isn't inherited by forks. - It shouldn't reserve actual memory, but it also shouldn't crash when page faulting in memory if none is available * Uh-oh: VM_NORESERVE means segfaults. It turns out that the vDSO getrandom() function has three really nice characteristics that we can exploit to solve this problem: 1) Due to being wiped during fork(), the vDSO code is already robust to having the contents of the pages it reads zeroed out midway through the function's execution. 2) In the absolute worst case of whatever contingency we're coding for, we have the option to fallback to the getrandom() syscall, and everything is fine. 3) The buffers the function uses are only ever useful for a maximum of 60 seconds -- a sort of cache, rather than a long term allocation. These characteristics mean that we can introduce VM_DROPPABLE, which has the following semantics: a) It never is written out to swap. b) Under memory pressure, mm can just drop the pages (so that they're zero when read back again). c) It is inherited by fork. d) It doesn't count against the mlock budget, since nothing is locked. e) If there's not enough memory to service a page fault, it's not fatal, and no signal is sent. This way, allocations used by vDSO getrandom() can use: VM_DROPPABLE | VM_DONTDUMP | VM_WIPEONFORK | VM_NORESERVE And there will be no problem with OOMing, crashing on overcommitment, using memory when not in use, not wiping on fork(), coredumps, or writing out to swap. In order to let vDSO getrandom() use this, expose these via mmap(2) as MAP_DROPPABLE. Note that this involves removing the MADV_FREE special case from sort_folio(), which according to Yu Zhao is unnecessary and will simply result in an extra call to shrink_folio_list() in the worst case. The chunk removed reenables the swapbacked flag, which we don't want for VM_DROPPABLE, and we can't conditionalize it here because there isn't a vma reference available. Finally, the provided self test ensures that this is working as desired. Cc: linux-mm@kvack.org Acked-by: David Hildenbrand Signed-off-by: Jason A. Donenfeld

userfaultfd: use per-vma locks in userfaultfd operations

2024-02-22T23:27:20+00:00

All userfaultfd operations, except write-protect, opportunistically use per-vma locks to lock vmas. On failure, attempt again inside mmap_lock critical section. Write-protect operation requires mmap_lock as it iterates over multiple vmas. Link: https://lkml.kernel.org/r/20240215182756.3448972-5-lokeshgidra@google.com Signed-off-by: Lokesh Gidra Reviewed-by: Liam R. Howlett Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Brian Geffon Cc: David Hildenbrand Cc: Jann Horn Cc: Kalesh Singh Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport (IBM) Cc: Nicolas Geoffray Cc: Peter Xu Cc: Ryan Roberts Cc: Suren Baghdasaryan Cc: Tim Murray Signed-off-by: Andrew Morton

userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx

2024-02-22T23:27:20+00:00

Increments and loads to mmap_changing are always in mmap_lock critical section. This ensures that if userspace requests event notification for non-cooperative operations (e.g. mremap), userfaultfd operations don't occur concurrently. This can be achieved by using a separate read-write semaphore in userfaultfd_ctx such that increments are done in write-mode and loads in read-mode, thereby eliminating the dependency on mmap_lock for this purpose. This is a preparatory step before we replace mmap_lock usage with per-vma locks in fill/move ioctls. Link: https://lkml.kernel.org/r/20240215182756.3448972-3-lokeshgidra@google.com Signed-off-by: Lokesh Gidra Reviewed-by: Mike Rapoport (IBM) Reviewed-by: Liam R. Howlett Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Brian Geffon Cc: David Hildenbrand Cc: Jann Horn Cc: Kalesh Singh Cc: Matthew Wilcox (Oracle) Cc: Nicolas Geoffray Cc: Peter Xu Cc: Ryan Roberts Cc: Suren Baghdasaryan Cc: Tim Murray Signed-off-by: Andrew Morton

userfaultfd: move userfaultfd_ctx struct to header file

2024-02-22T23:27:20+00:00

Patch series "per-vma locks in userfaultfd", v7. Performing userfaultfd operations (like copy/move etc.) in critical section of mmap_lock (read-mode) causes significant contention on the lock when operations requiring the lock in write-mode are taking place concurrently. We can use per-vma locks instead to significantly reduce the contention issue. Android runtime's Garbage Collector uses userfaultfd for concurrent compaction. mmap-lock contention during compaction potentially causes jittery experience for the user. During one such reproducible scenario, we observed the following improvements with this patch-set: - Wall clock time of compaction phase came down from ~3s to <500ms - Uninterruptible sleep time (across all threads in the process) was ~10ms (none in mmap_lock) during compaction, instead of >20s This patch (of 4): Move the struct to userfaultfd_k.h to be accessible from mm/userfaultfd.c. There are no other changes in the struct. This is required to prepare for using per-vma locks in userfaultfd operations. Link: https://lkml.kernel.org/r/20240215182756.3448972-1-lokeshgidra@google.com Link: https://lkml.kernel.org/r/20240215182756.3448972-2-lokeshgidra@google.com Signed-off-by: Lokesh Gidra Reviewed-by: Mike Rapoport (IBM) Reviewed-by: Liam R. Howlett Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Brian Geffon Cc: David Hildenbrand Cc: Jann Horn Cc: Kalesh Singh Cc: Matthew Wilcox (Oracle) Cc: Nicolas Geoffray Cc: Peter Xu Cc: Ryan Roberts Cc: Suren Baghdasaryan Cc: Tim Murray Signed-off-by: Andrew Morton

userfaultfd: UFFDIO_MOVE uABI

2023-12-29T19:58:24+00:00

Implement the uABI of UFFDIO_MOVE ioctl. UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are available (in userspace) for recycling, as is usually the case in heap compaction algorithms, then we can avoid the page allocation and memcpy (done by UFFDIO_COPY). Also, since the pages are recycled in the userspace, we avoid the need to release (via madvise) the pages back to the kernel [2]. We see over 40% reduction (on a Google pixel 6 device) in the compacting thread's completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was measured using a benchmark that emulates a heap compaction implementation using userfaultfd (to allow concurrent accesses by application threads). More details of the usecase are explained in [2]. Furthermore, UFFDIO_MOVE enables moving swapped-out pages without touching them within the same vma. Today, it can only be done by mremap, however it forces splitting the vma. [1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/ [2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/ Update for the ioctl_userfaultfd(2) manpage: UFFDIO_MOVE (Since Linux xxx) Move a continuous memory chunk into the userfault registered range and optionally wake up the blocked thread. The source and destination addresses and the number of bytes to move are specified by the src, dst, and len fields of the uffdio_move structure pointed to by argp: struct uffdio_move { __u64 dst; /* Destination of move */ __u64 src; /* Source of move */ __u64 len; /* Number of bytes to move */ __u64 mode; /* Flags controlling behavior of move */ __s64 move; /* Number of bytes moved, or negated error */ }; The following value may be bitwise ORed in mode to change the behavior of the UFFDIO_MOVE operation: UFFDIO_MOVE_MODE_DONTWAKE Do not wake up the thread that waits for page-fault resolution UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES Allow holes in the source virtual range that is being moved. When not specified, the holes will result in ENOENT error. When specified, the holes will be accounted as successfully moved memory. This is mostly useful to move hugepage aligned virtual regions without knowing if there are transparent hugepages in the regions or not, but preventing the risk of having to split the hugepage during the operation. The move field is used by the kernel to return the number of bytes that was actually moved, or an error (a negated errno- style value). If the value returned in move doesn't match the value that was specified in len, the operation fails with the error EAGAIN. The move field is output-only; it is not read by the UFFDIO_MOVE operation. The operation may fail for various reasons. Usually, remapping of pages that are not exclusive to the given process fail; once KSM might deduplicate pages or fork() COW-shares pages during fork() with child processes, they are no longer exclusive. Further, the kernel might only perform lightweight checks for detecting whether the pages are exclusive, and return -EBUSY in case that check fails. To make the operation more likely to succeed, KSM should be disabled, fork() should be avoided or MADV_DONTFORK should be configured for the source VMA before fork(). This ioctl(2) operation returns 0 on success. In this case, the entire area was moved. On error, -1 is returned and errno is set to indicate the error. Possible errors include: EAGAIN The number of bytes moved (i.e., the value returned in the move field) does not equal the value that was specified in the len field. EINVAL Either dst or len was not a multiple of the system page size, or the range specified by src and len or dst and len was invalid. EINVAL An invalid bit was specified in the mode field. ENOENT The source virtual memory range has unmapped holes and UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set. EEXIST The destination virtual memory range is fully or partially mapped. EBUSY The pages in the source virtual memory range are either pinned or not exclusive to the process. The kernel might only perform lightweight checks for detecting whether the pages are exclusive. To make the operation more likely to succeed, KSM should be disabled, fork() should be avoided or MADV_DONTFORK should be configured for the source virtual memory area before fork(). ENOMEM Allocating memory needed for the operation failed. ESRCH The target process has exited at the time of a UFFDIO_MOVE operation. Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com Signed-off-by: Andrea Arcangeli Signed-off-by: Suren Baghdasaryan Cc: Al Viro Cc: Axel Rasmussen Cc: Brian Geffon Cc: Christian Brauner Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jann Horn Cc: Kalesh Singh Cc: Liam R. Howlett Cc: Lokesh Gidra Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport (IBM) Cc: Nicolas Geoffray Cc: Peter Xu Cc: Ryan Roberts Cc: Shuah Khan Cc: ZhangPeng Signed-off-by: Andrew Morton

fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs

2023-10-18T21:34:12+00:00

The PAGEMAP_SCAN IOCTL on the pagemap file can be used to get or optionally clear the info about page table entries. The following operations are supported in this IOCTL: - Scan the address range and get the memory ranges matching the provided criteria. This is performed when the output buffer is specified. - Write-protect the pages. The PM_SCAN_WP_MATCHING is used to write-protect the pages of interest. The PM_SCAN_CHECK_WPASYNC aborts the operation if non-Async Write Protected pages are found. The ``PM_SCAN_WP_MATCHING`` can be used with or without PM_SCAN_CHECK_WPASYNC. - Both of those operations can be combined into one atomic operation where we can get and write protect the pages as well. Following flags about pages are currently supported: - PAGE_IS_WPALLOWED - Page has async-write-protection enabled - PAGE_IS_WRITTEN - Page has been written to from the time it was write protected - PAGE_IS_FILE - Page is file backed - PAGE_IS_PRESENT - Page is present in the memory - PAGE_IS_SWAPPED - Page is in swapped - PAGE_IS_PFNZERO - Page has zero PFN - PAGE_IS_HUGE - Page is THP or Hugetlb backed This IOCTL can be extended to get information about more PTE bits. The entire address range passed by user [start, end) is scanned until either the user provided buffer is full or max_pages have been found. [akpm@linux-foundation.org: update it for "mm: hugetlb: add huge page size param to set_huge_pte_at()"] [akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n warning] [arnd@arndb.de: hide unused pagemap_scan_backout_range() function] Link: https://lkml.kernel.org/r/20230927060257.2975412-1-arnd@kernel.org [sfr@canb.auug.org.au: fix "fs/proc/task_mmu: hide unused pagemap_scan_backout_range() function"] Link: https://lkml.kernel.org/r/20230928092223.0625c6bf@canb.auug.org.au Link: https://lkml.kernel.org/r/20230821141518.870589-3-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum Signed-off-by: Michał Mirosław Signed-off-by: Arnd Bergmann Signed-off-by: Stephen Rothwell Reviewed-by: Andrei Vagin Reviewed-by: Michał Mirosław Cc: Alex Sierra Cc: Al Viro Cc: Axel Rasmussen Cc: Christian Brauner Cc: Cyrill Gorcunov Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: "Liam R. Howlett" Cc: Matthew Wilcox Cc: Michal Miroslaw Cc: Mike Rapoport (IBM) Cc: Nadav Amit Cc: Pasha Tatashin Cc: Paul Gofman Cc: Peter Xu Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yang Shi Cc: Yun Zhou Signed-off-by: Andrew Morton

userfaultfd: UFFD_FEATURE_WP_ASYNC

2023-10-18T21:34:12+00:00

Patch series "Implement IOCTL to get and optionally clear info about PTEs", v33. *Motivation* The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch() retrieves the addresses of the pages that are written to in a region of virtual memory. This syscall is used in Windows applications and games etc. This syscall is being emulated in pretty slow manner in userspace. Our purpose is to enhance the kernel such that we translate it efficiently in a better way. Currently some out of tree hack patches are being used to efficiently emulate it in some kernels. We intend to replace those with these patches. So the whole gaming on Linux can effectively get benefit from this. It means there would be tons of users of this code. CRIU use case [2] was mentioned by Andrei and Danylo: > Use cases for migrating sparse VMAs are binaries sanitized with ASAN, > MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of > shadow memory [4]. Being able to migrate such binaries allows to highly > reduce the amount of work needed to identify and fix post-migration > crashes, which happen constantly. Andrei defines the following uses of this code: * it is more granular and allows us to track changed pages more effectively. The current interface can clear dirty bits for the entire process only. In addition, reading info about pages is a separate operation. It means we must freeze the process to read information about all its pages, reset dirty bits, only then we can start dumping pages. The information about pages becomes more and more outdated, while we are processing pages. The new interface solves both these downsides. First, it allows us to read pte bits and clear the soft-dirty bit atomically. It means that CRIU will not need to freeze processes to pre-dump their memory. Second, it clears soft-dirty bits for a specified region of memory. It means CRIU will have actual info about pages to the moment of dumping them. * The new interface has to be much faster because basic page filtering is happening in the kernel. With the old interface, we have to read pagemap for each page. *Implementation Evolution (Short Summary)* From the definition of GetWriteWatch(), we feel like kernel's soft-dirty feature can be used under the hood with some additions like: * reset soft-dirty flag for only a specific region of memory instead of clearing the flag for the entire process * get and clear soft-dirty flag for a specific region atomically So we decided to use ioctl on pagemap file to read or/and reset soft-dirty flag. But using soft-dirty flag, sometimes we get extra pages which weren't even written. They had become soft-dirty because of VMA merging and VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were able to by-pass this short coming by ignoring VM_SOFTDIRTY until David reported that mprotect etc messes up the soft-dirty flag while ignoring VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We discussed if we can revert these patches. But we could not reach to any conclusion. So at this point, I made couple of tries to solve this whole VM_SOFTDIRTY issue by correcting the soft-dirty implementation: * [7] Correct the bug fixed wrongly back in 2014. It had potential to cause regression. We left it behind. * [8] Keep a list of soft-dirty part of a VMA across splits and merges. I got the reply don't increase the size of the VMA by 8 bytes. At this point, we left soft-dirty considering it is too much delicate and userfaultfd [9] seemed like the only way forward. From there onward, we have been basing soft-dirty emulation on userfaultfd wp feature where kernel resolves the faults itself when WP_ASYNC feature is used. It was straight forward to add WP_ASYNC feature in userfautlfd. Now we get only those pages dirty or written-to which are really written in reality. (PS There is another WP_UNPOPULATED userfautfd feature is required which is needed to avoid pre-faulting memory before write-protecting [9].) All the different masks were added on the request of CRIU devs to create interface more generic and better. [1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch [2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com [3] https://github.com/google/sanitizers [4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit [5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com [6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/ [7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com [8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com [9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com [10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com This patch (of 6): Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows userfaultfd wr-protect faults to be resolved by the kernel directly. It can be used like a high accuracy version of soft-dirty, without vma modifications during tracking, and also with ranged support by default rather than for a whole mm when reset the protections due to existence of ioctl(UFFDIO_WRITEPROTECT). Several goals of such a dirty tracking interface: 1. All types of memory should be supported and tracable. This is nature for soft-dirty but should mention when the context is userfaultfd, because it used to only support anon/shmem/hugetlb. The problem is for a dirty tracking purpose these three types may not be enough, and it's legal to track anything e.g. any page cache writes from mmap. 2. Protections can be applied to partial of a memory range, without vma split/merge fuss. The hope is that the tracking itself should not affect any vma layout change. It also helps when reset happens because the reset will not need mmap write lock which can block the tracee. 3. Accuracy needs to be maintained. This means we need pte markers to work on any type of VMA. One could question that, the whole concept of async dirty tracking is not really close to fundamentally what userfaultfd used to be: it's not "a fault to be serviced by userspace" anymore. However, using userfaultfd-wp here as a framework is convenient for us in at least: 1. VM_UFFD_WP vma flag, which has a very good name to suite something like this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new feature bit to identify from a sync version of uffd-wp registration. 2. PTE markers logic can be leveraged across the whole kernel to maintain the uffd-wp bit as long as an arch supports, this also applies to this case where uffd-wp bit will be a hint to dirty information and it will not go lost easily (e.g. when some page cache ptes got zapped). 3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or resetting a range of memory, while there's no counterpart in the old soft-dirty world, hence if this is wanted in a new design we'll need a new interface otherwise. We can somehow understand that commonality because uffd-wp was fundamentally a similar idea of write-protecting pages just like soft-dirty. This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also gives us chance to modify impl of WP_ASYNC just in case it could be not depending on WP_UNPOPULATED anymore in the future kernels. It's also fine to imply that because both features will rely on PTE_MARKER_UFFD_WP config option, so they'll show up together (or both missing) in an UFFDIO_API probe. vma_can_userfault() now allows any VMA if the userfaultfd registration is only about async uffd-wp. So we can track dirty for all kinds of memory including generic file systems (like XFS, EXT4 or BTRFS). One trick worth mention in do_wp_page() is that we need to manually update vmf->orig_pte here because it can be used later with a pte_same() check - this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags. The major defect of this approach of dirty tracking is we need to populate the pgtables when tracking starts. Soft-dirty doesn't do it like that. It's unwanted in the case where the range of memory to track is huge and unpopulated (e.g., tracking updates on a 10G file with mmap() on top, without having any page cache installed yet). One way to improve this is to allow pte markers exist for larger than PTE level for PMD+. That will not change the interface if to implemented, so we can leave that for later. Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com Signed-off-by: Peter Xu Co-developed-by: Muhammad Usama Anjum Signed-off-by: Muhammad Usama Anjum Cc: Alex Sierra Cc: Al Viro Cc: Andrei Vagin Cc: Axel Rasmussen Cc: Christian Brauner Cc: Cyrill Gorcunov Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Gustavo A. R. Silva Cc: "Liam R. Howlett" Cc: Matthew Wilcox Cc: Michal Miroslaw Cc: Mike Rapoport (IBM) Cc: Nadav Amit Cc: Pasha Tatashin Cc: Paul Gofman Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yang Shi Cc: Yun Zhou Cc: Michał Mirosław Signed-off-by: Andrew Morton