summaryrefslogtreecommitdiff
path: root/fs/userfaultfd.c
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2023-12-06 02:36:56 -0800
committerAndrew Morton <akpm@linux-foundation.org>2023-12-29 11:58:24 -0800
commitadef440691bab824e39c1b17382322d195e1fab0 (patch)
treecad70a0fbf34893e2102a49d6ecd7b35b0a40e9b /fs/userfaultfd.c
parent880a99b60d467eefd96322e27b0a8c0b805dfa43 (diff)
userfaultfd: UFFDIO_MOVE uABI
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 <aarcange@redhat.com> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: Christian Brauner <brauner@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jann Horn <jannh@google.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Nicolas Geoffray <ngeoffray@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shuah Khan <shuah@kernel.org> Cc: ZhangPeng <zhangpeng362@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'fs/userfaultfd.c')
-rw-r--r--fs/userfaultfd.c72
1 files changed, 72 insertions, 0 deletions
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e8af40b05549..6e2a4d6a0d8f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -2005,6 +2005,75 @@ static inline unsigned int uffd_ctx_features(__u64 user_features)
return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
}
+static int userfaultfd_move(struct userfaultfd_ctx *ctx,
+ unsigned long arg)
+{
+ __s64 ret;
+ struct uffdio_move uffdio_move;
+ struct uffdio_move __user *user_uffdio_move;
+ struct userfaultfd_wake_range range;
+ struct mm_struct *mm = ctx->mm;
+
+ user_uffdio_move = (struct uffdio_move __user *) arg;
+
+ if (atomic_read(&ctx->mmap_changing))
+ return -EAGAIN;
+
+ if (copy_from_user(&uffdio_move, user_uffdio_move,
+ /* don't copy "move" last field */
+ sizeof(uffdio_move)-sizeof(__s64)))
+ return -EFAULT;
+
+ /* Do not allow cross-mm moves. */
+ if (mm != current->mm)
+ return -EINVAL;
+
+ ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
+ if (ret)
+ return ret;
+
+ ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
+ if (ret)
+ return ret;
+
+ if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
+ UFFDIO_MOVE_MODE_DONTWAKE))
+ return -EINVAL;
+
+ if (mmget_not_zero(mm)) {
+ mmap_read_lock(mm);
+
+ /* Re-check after taking mmap_lock */
+ if (likely(!atomic_read(&ctx->mmap_changing)))
+ ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src,
+ uffdio_move.len, uffdio_move.mode);
+ else
+ ret = -EINVAL;
+
+ mmap_read_unlock(mm);
+ mmput(mm);
+ } else {
+ return -ESRCH;
+ }
+
+ if (unlikely(put_user(ret, &user_uffdio_move->move)))
+ return -EFAULT;
+ if (ret < 0)
+ goto out;
+
+ /* len == 0 would wake all */
+ VM_WARN_ON(!ret);
+ range.len = ret;
+ if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
+ range.start = uffdio_move.dst;
+ wake_userfault(ctx, &range);
+ }
+ ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
+
+out:
+ return ret;
+}
+
/*
* userland asks for a certain API version and we return which bits
* and ioctl commands are implemented in this kernel for such API
@@ -2097,6 +2166,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
case UFFDIO_ZEROPAGE:
ret = userfaultfd_zeropage(ctx, arg);
break;
+ case UFFDIO_MOVE:
+ ret = userfaultfd_move(ctx, arg);
+ break;
case UFFDIO_WRITEPROTECT:
ret = userfaultfd_writeprotect(ctx, arg);
break;