mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 18:09:57 +00:00
![Axel Rasmussen](/assets/img/avatar_default.png)
This ioctl is how userspace ought to resolve "minor" userfaults. The idea is, userspace is notified that a minor fault has occurred. It might change the contents of the page using its second non-UFFD mapping, or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are correct, carry on setting up the mapping". Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in the minor fault case, we already have some pre-existing underlying page. Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping. We'd just use memcpy() or similar instead. It turns out hugetlb_mcopy_atomic_pte() already does very close to what we want, if an existing page is provided via `struct page **pagep`. We already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so just extend that design: add an enum for the three modes of operation, and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE case. (Basically, look up the existing page, and avoid adding the existing page to the page cache or calling set_page_huge_active() on it.) Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com Signed-off-by: Axel Rasmussen <axelrasmussen@google.com> Reviewed-by: Peter Xu <peterx@redhat.com> Cc: Adam Ruprecht <ruprecht@google.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Cannon Matthews <cannonmatthews@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chinwen Chang <chinwen.chang@mediatek.com> Cc: David Rientjes <rientjes@google.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Lokesh Gidra <lokeshgidra@google.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Michal Koutn" <mkoutny@suse.com> Cc: Michel Lespinasse <walken@google.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Oliver Upton <oupton@google.com> Cc: Shaohua Li <shli@fb.com> Cc: Shawn Anastasio <shawn@anastas.io> Cc: Steven Price <steven.price@arm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
234 lines
6.2 KiB
C
234 lines
6.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* include/linux/userfaultfd_k.h
|
|
*
|
|
* Copyright (C) 2015 Red Hat, Inc.
|
|
*
|
|
*/
|
|
|
|
#ifndef _LINUX_USERFAULTFD_K_H
|
|
#define _LINUX_USERFAULTFD_K_H
|
|
|
|
#ifdef CONFIG_USERFAULTFD
|
|
|
|
#include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */
|
|
|
|
#include <linux/fcntl.h>
|
|
#include <linux/mm.h>
|
|
#include <asm-generic/pgtable_uffd.h>
|
|
|
|
/* The set of all possible UFFD-related VM flags. */
|
|
#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR)
|
|
|
|
/*
|
|
* CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
|
|
* new flags, since they might collide with O_* ones. We want
|
|
* to re-use O_* flags that couldn't possibly have a meaning
|
|
* from userfaultfd, in order to leave a free define-space for
|
|
* shared O_* flags.
|
|
*/
|
|
#define UFFD_CLOEXEC O_CLOEXEC
|
|
#define UFFD_NONBLOCK O_NONBLOCK
|
|
|
|
#define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
|
|
#define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
|
|
|
|
extern int sysctl_unprivileged_userfaultfd;
|
|
|
|
extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
|
|
|
|
/*
|
|
* The mode of operation for __mcopy_atomic and its helpers.
|
|
*
|
|
* This is almost an implementation detail (mcopy_atomic below doesn't take this
|
|
* as a parameter), but it's exposed here because memory-kind-specific
|
|
* implementations (e.g. hugetlbfs) need to know the mode of operation.
|
|
*/
|
|
enum mcopy_atomic_mode {
|
|
/* A normal copy_from_user into the destination range. */
|
|
MCOPY_ATOMIC_NORMAL,
|
|
/* Don't copy; map the destination range to the zero page. */
|
|
MCOPY_ATOMIC_ZEROPAGE,
|
|
/* Just install pte(s) with the existing page(s) in the page cache. */
|
|
MCOPY_ATOMIC_CONTINUE,
|
|
};
|
|
|
|
extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
|
|
unsigned long src_start, unsigned long len,
|
|
bool *mmap_changing, __u64 mode);
|
|
extern ssize_t mfill_zeropage(struct mm_struct *dst_mm,
|
|
unsigned long dst_start,
|
|
unsigned long len,
|
|
bool *mmap_changing);
|
|
extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start,
|
|
unsigned long len, bool *mmap_changing);
|
|
extern int mwriteprotect_range(struct mm_struct *dst_mm,
|
|
unsigned long start, unsigned long len,
|
|
bool enable_wp, bool *mmap_changing);
|
|
|
|
/* mm helpers */
|
|
static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
|
|
struct vm_userfaultfd_ctx vm_ctx)
|
|
{
|
|
return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx;
|
|
}
|
|
|
|
/*
|
|
* Never enable huge pmd sharing on some uffd registered vmas:
|
|
*
|
|
* - VM_UFFD_WP VMAs, because write protect information is per pgtable entry.
|
|
*
|
|
* - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for
|
|
* VMAs which share huge pmds. (If you have two mappings to the same
|
|
* underlying pages, and fault in the non-UFFD-registered one with a write,
|
|
* with huge pmd sharing this would *also* setup the second UFFD-registered
|
|
* mapping, and we'd not get minor faults.)
|
|
*/
|
|
static inline bool uffd_disable_huge_pmd_share(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;
|
|
}
|
|
|
|
static inline bool userfaultfd_wp(struct vm_area_struct *vma)
|
|
{
|
|
return vma->vm_flags & VM_UFFD_WP;
|
|
}
|
|
|
|
static inline bool userfaultfd_minor(struct vm_area_struct *vma)
|
|
{
|
|
return vma->vm_flags & VM_UFFD_MINOR;
|
|
}
|
|
|
|
static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
|
|
pte_t pte)
|
|
{
|
|
return userfaultfd_wp(vma) && pte_uffd_wp(pte);
|
|
}
|
|
|
|
static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma,
|
|
pmd_t pmd)
|
|
{
|
|
return userfaultfd_wp(vma) && pmd_uffd_wp(pmd);
|
|
}
|
|
|
|
static inline bool userfaultfd_armed(struct vm_area_struct *vma)
|
|
{
|
|
return vma->vm_flags & __VM_UFFD_FLAGS;
|
|
}
|
|
|
|
extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
|
|
extern void dup_userfaultfd_complete(struct list_head *);
|
|
|
|
extern void mremap_userfaultfd_prep(struct vm_area_struct *,
|
|
struct vm_userfaultfd_ctx *);
|
|
extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
|
|
unsigned long from, unsigned long to,
|
|
unsigned long len);
|
|
|
|
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 void userfaultfd_unmap_complete(struct mm_struct *mm,
|
|
struct list_head *uf);
|
|
|
|
#else /* CONFIG_USERFAULTFD */
|
|
|
|
/* mm helpers */
|
|
static inline vm_fault_t handle_userfault(struct vm_fault *vmf,
|
|
unsigned long reason)
|
|
{
|
|
return VM_FAULT_SIGBUS;
|
|
}
|
|
|
|
static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
|
|
struct vm_userfaultfd_ctx vm_ctx)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline bool userfaultfd_missing(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool userfaultfd_wp(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool userfaultfd_minor(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma,
|
|
pte_t pte)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma,
|
|
pmd_t pmd)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
|
|
static inline bool userfaultfd_armed(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline int dup_userfaultfd(struct vm_area_struct *vma,
|
|
struct list_head *l)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void dup_userfaultfd_complete(struct list_head *l)
|
|
{
|
|
}
|
|
|
|
static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
|
|
struct vm_userfaultfd_ctx *ctx)
|
|
{
|
|
}
|
|
|
|
static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
|
|
unsigned long from,
|
|
unsigned long to,
|
|
unsigned long len)
|
|
{
|
|
}
|
|
|
|
static inline bool userfaultfd_remove(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end,
|
|
struct list_head *uf)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
|
|
struct list_head *uf)
|
|
{
|
|
}
|
|
|
|
#endif /* CONFIG_USERFAULTFD */
|
|
|
|
#endif /* _LINUX_USERFAULTFD_K_H */
|