mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-29 22:02:02 +00:00
adef440691
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>
401 lines
11 KiB
C
401 lines
11 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 <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <asm-generic/pgtable_uffd.h>
|
|
#include <linux/hugetlb_inline.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 vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
|
|
|
|
/* A combined operation mode + behavior flags. */
|
|
typedef unsigned int __bitwise uffd_flags_t;
|
|
|
|
/* Mutually exclusive modes of operation. */
|
|
enum mfill_atomic_mode {
|
|
MFILL_ATOMIC_COPY,
|
|
MFILL_ATOMIC_ZEROPAGE,
|
|
MFILL_ATOMIC_CONTINUE,
|
|
MFILL_ATOMIC_POISON,
|
|
NR_MFILL_ATOMIC_MODES,
|
|
};
|
|
|
|
#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1)
|
|
#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr))
|
|
#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr))
|
|
#define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1))
|
|
|
|
static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected)
|
|
{
|
|
return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected);
|
|
}
|
|
|
|
static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode)
|
|
{
|
|
flags &= ~MFILL_ATOMIC_MODE_MASK;
|
|
return flags | ((__force uffd_flags_t) mode);
|
|
}
|
|
|
|
/* Flags controlling behavior. These behavior changes are mode-independent. */
|
|
#define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0)
|
|
|
|
extern int mfill_atomic_install_pte(pmd_t *dst_pmd,
|
|
struct vm_area_struct *dst_vma,
|
|
unsigned long dst_addr, struct page *page,
|
|
bool newly_allocated, uffd_flags_t flags);
|
|
|
|
extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start,
|
|
unsigned long src_start, unsigned long len,
|
|
atomic_t *mmap_changing, uffd_flags_t flags);
|
|
extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm,
|
|
unsigned long dst_start,
|
|
unsigned long len,
|
|
atomic_t *mmap_changing);
|
|
extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start,
|
|
unsigned long len, atomic_t *mmap_changing,
|
|
uffd_flags_t flags);
|
|
extern ssize_t mfill_atomic_poison(struct mm_struct *dst_mm, unsigned long start,
|
|
unsigned long len, atomic_t *mmap_changing,
|
|
uffd_flags_t flags);
|
|
extern int mwriteprotect_range(struct mm_struct *dst_mm,
|
|
unsigned long start, unsigned long len,
|
|
bool enable_wp, atomic_t *mmap_changing);
|
|
extern long uffd_wp_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long len, bool enable_wp);
|
|
|
|
/* move_pages */
|
|
void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
|
|
void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
|
|
ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
|
|
unsigned long dst_start, unsigned long src_start,
|
|
unsigned long len, __u64 flags);
|
|
int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
|
|
struct vm_area_struct *dst_vma,
|
|
struct vm_area_struct *src_vma,
|
|
unsigned long dst_addr, unsigned long src_addr);
|
|
|
|
/* 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);
|
|
}
|
|
|
|
/*
|
|
* 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;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
static inline bool vma_can_userfault(struct vm_area_struct *vma,
|
|
unsigned long vm_flags,
|
|
bool wp_async)
|
|
{
|
|
vm_flags &= __VM_UFFD_FLAGS;
|
|
|
|
if ((vm_flags & VM_UFFD_MINOR) &&
|
|
(!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
|
|
return false;
|
|
|
|
/*
|
|
* If wp async enabled, and WP is the only mode enabled, allow any
|
|
* memory type.
|
|
*/
|
|
if (wp_async && (vm_flags == VM_UFFD_WP))
|
|
return true;
|
|
|
|
#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
|
|
|
|
/* By default, allow any of anon|shmem|hugetlb */
|
|
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 *);
|
|
|
|
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);
|
|
extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma);
|
|
extern bool userfaultfd_wp_async(struct vm_area_struct *vma);
|
|
|
|
#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 long uffd_wp_range(struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long len,
|
|
bool enable_wp)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
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)
|
|
{
|
|
}
|
|
|
|
static inline bool uffd_disable_fault_around(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool userfaultfd_wp_async(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_USERFAULTFD */
|
|
|
|
static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma)
|
|
{
|
|
/* Only wr-protect mode uses pte markers */
|
|
if (!userfaultfd_wp(vma))
|
|
return false;
|
|
|
|
/* File-based uffd-wp always need markers */
|
|
if (!vma_is_anonymous(vma))
|
|
return true;
|
|
|
|
/*
|
|
* Anonymous uffd-wp only needs the markers if WP_UNPOPULATED
|
|
* enabled (to apply markers on zero pages).
|
|
*/
|
|
return userfaultfd_wp_unpopulated(vma);
|
|
}
|
|
|
|
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 */
|