From: Lokesh Gidra <lokeshgidra@google.com> mainline inclusion from mainline-v6.9-rc1 commit 5e4c24a57b0c126686534b5b159a406c5dd02400 category: bugfix bugzilla: https://atomgit.com/openeuler/kernel/issues/9183 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- 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 <lokeshgidra@google.com> Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Brian Geffon <bgeffon@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Kalesh Singh <kaleshsingh@google.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Nicolas Geoffray <ngeoffray@google.com> Cc: Peter Xu <peterx@redhat.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Tim Murray <timmurray@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: include/linux/userfaultfd_k_ext.h mm/userfaultfd.c [Conflicts due to uffd move not supported and kabi fix] Signed-off-by: Wupeng Ma <mawupeng1@huawei.com> --- fs/userfaultfd.c | 35 +++++++++-------- include/linux/userfaultfd_k.h | 24 +++++------- include/linux/userfaultfd_k_ext.h | 7 ++++ mm/userfaultfd.c | 63 ++++++++++++++++++------------- 4 files changed, 73 insertions(+), 56 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 0e713b5ab01fd..58a8ad01503a0 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -699,12 +699,15 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; + init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); + down_write(&octx->map_changing_lock); atomic_inc(&octx->mmap_changing); + up_write(&octx->map_changing_lock); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); @@ -779,7 +782,9 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); + down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); + up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ vma_start_write(vma); @@ -825,7 +830,9 @@ bool userfaultfd_remove(struct vm_area_struct *vma, return true; userfaultfd_ctx_get(ctx); + down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); + up_write(&ctx->map_changing_lock); mmap_read_unlock(mm); msg_init(&ewq.msg); @@ -867,7 +874,9 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, return -ENOMEM; userfaultfd_ctx_get(ctx); + down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); + up_write(&ctx->map_changing_lock); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; @@ -1807,9 +1816,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, (uffdio_copy.mode & UFFDIO_COPY_MODE_DIRECT_MAP)) flags |= MFILL_ATOMIC_DIRECT_MAP; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src, - uffdio_copy.len, &ctx->mmap_changing, - flags); + ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src, + uffdio_copy.len, flags); mmput(ctx->mm); } else { return -ESRCH; @@ -1859,9 +1867,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, goto out; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start, - uffdio_zeropage.range.len, - &ctx->mmap_changing); + ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start, + uffdio_zeropage.range.len); mmput(ctx->mm); } else { return -ESRCH; @@ -1916,9 +1923,8 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, return -EINVAL; if (mmget_not_zero(ctx->mm)) { - ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start, - uffdio_wp.range.len, mode_wp, - &ctx->mmap_changing); + ret = mwriteprotect_range(ctx, uffdio_wp.range.start, + uffdio_wp.range.len, mode_wp); mmput(ctx->mm); } else { return -ESRCH; @@ -1968,9 +1974,8 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start, - uffdio_continue.range.len, - &ctx->mmap_changing, flags); + ret = mfill_atomic_continue(ctx, uffdio_continue.range.start, + uffdio_continue.range.len, flags); mmput(ctx->mm); } else { return -ESRCH; @@ -2023,9 +2028,8 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long goto out; if (mmget_not_zero(ctx->mm)) { - ret = mfill_atomic_poison(ctx->mm, uffdio_poison.range.start, - uffdio_poison.range.len, - &ctx->mmap_changing, 0); + ret = mfill_atomic_poison(ctx, uffdio_poison.range.start, + uffdio_poison.range.len, 0); mmput(ctx->mm); } else { return -ESRCH; @@ -2236,6 +2240,7 @@ static int new_userfaultfd(int flags) ctx->flags = flags; ctx->features = 0; ctx->released = false; + init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index aa8e3725f1034..9c02eee21b917 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -79,22 +79,18 @@ extern int mfill_atomic_install_pte(pmd_t *dst_pmd, 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, +extern ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, 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, + uffd_flags_t flags); +extern ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx, 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); + unsigned long len); +extern ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start, + unsigned long len, uffd_flags_t flags); +extern ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, uffd_flags_t flags); +extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, bool enable_wp); extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); diff --git a/include/linux/userfaultfd_k_ext.h b/include/linux/userfaultfd_k_ext.h index 08d6c68933104..898895d9e11eb 100644 --- a/include/linux/userfaultfd_k_ext.h +++ b/include/linux/userfaultfd_k_ext.h @@ -37,6 +37,13 @@ struct userfaultfd_ctx { unsigned int features; /* released */ bool released; + /* + * Prevents userfaultfd operations (fill/move/wp) from happening while + * some non-cooperative event(s) is taking place. Increments are done + * in write-mode. Whereas, userfaultfd operations, which includes + * reading mmap_changing, is done under read-mode. + */ + struct rw_semaphore map_changing_lock; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 53afe2e97bc12..89d647037a5bd 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -12,6 +12,7 @@ #include <linux/swap.h> #include <linux/swapops.h> #include <linux/userfaultfd_k.h> +#include <linux/userfaultfd_k_ext.h> #include <linux/mmu_notifier.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> @@ -389,11 +390,11 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) * called with mmap_lock held, it will release mmap_lock before returning. */ static __always_inline ssize_t mfill_atomic_hugetlb( + struct userfaultfd_ctx *ctx, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -415,6 +416,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( * feature is not supported. */ if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) { + up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); return -EINVAL; } @@ -499,6 +501,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( cond_resched(); if (unlikely(err == -ENOENT)) { + up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); BUG_ON(!folio); @@ -509,12 +512,13 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out; } mmap_read_lock(dst_mm); + down_read(&ctx->map_changing_lock); /* * If memory mappings are changing because of non-cooperative * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ - if (mmap_changing && atomic_read(mmap_changing)) { + if (atomic_read(&ctx->mmap_changing)) { err = -EAGAIN; break; } @@ -537,6 +541,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( } out_unlock: + up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); out: if (folio) @@ -548,11 +553,11 @@ static __always_inline ssize_t mfill_atomic_hugetlb( } #else /* !CONFIG_HUGETLB_PAGE */ /* fail at build time if gcc attempts to use this */ -extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, +extern ssize_t mfill_atomic_hugetlb(struct userfaultfd_ctx *ctx, + struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ @@ -600,13 +605,13 @@ static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd, return err; } -static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, +static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, uffd_flags_t flags) { + struct mm_struct *dst_mm = ctx->mm; struct vm_area_struct *dst_vma; ssize_t err; pmd_t *dst_pmd; @@ -636,8 +641,9 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ + down_read(&ctx->map_changing_lock); err = -EAGAIN; - if (mmap_changing && atomic_read(mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out_unlock; /* @@ -673,8 +679,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, - len, mmap_changing, flags); + return mfill_atomic_hugetlb(ctx, dst_vma, dst_start, + src_start, len, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; @@ -743,6 +749,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, if (unlikely(err == -ENOENT)) { void *kaddr; + up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); BUG_ON(!folio); @@ -773,6 +780,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, } out_unlock: + up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); out: if (folio) @@ -783,34 +791,33 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, return copied ? copied : err; } -ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, +ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, uffd_flags_t flags) + uffd_flags_t flags) { - return mfill_atomic(dst_mm, dst_start, src_start, len, mmap_changing, + return mfill_atomic(ctx, dst_start, src_start, len, uffd_flags_set_mode(flags, MFILL_ATOMIC_COPY)); } -ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, atomic_t *mmap_changing) +ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx, + unsigned long start, + unsigned long len) { - return mfill_atomic(dst_mm, start, 0, len, mmap_changing, + return mfill_atomic(ctx, start, 0, len, uffd_flags_set_mode(0, MFILL_ATOMIC_ZEROPAGE)); } -ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, atomic_t *mmap_changing, - uffd_flags_t flags) +ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, uffd_flags_t flags) { - return mfill_atomic(dst_mm, start, 0, len, mmap_changing, + return mfill_atomic(ctx, start, 0, len, uffd_flags_set_mode(flags, MFILL_ATOMIC_CONTINUE)); } -ssize_t mfill_atomic_poison(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, atomic_t *mmap_changing, - uffd_flags_t flags) +ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, uffd_flags_t flags) { - return mfill_atomic(dst_mm, start, 0, len, mmap_changing, + return mfill_atomic(ctx, start, 0, len, uffd_flags_set_mode(flags, MFILL_ATOMIC_POISON)); } @@ -843,10 +850,10 @@ long uffd_wp_range(struct vm_area_struct *dst_vma, return ret; } -int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, bool enable_wp, - atomic_t *mmap_changing) +int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, + unsigned long len, bool enable_wp) { + struct mm_struct *dst_mm = ctx->mm; unsigned long end = start + len; unsigned long _start, _end; struct vm_area_struct *dst_vma; @@ -870,8 +877,9 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, * operation (e.g. mremap) running in parallel, bail out and * request the user to retry later */ + down_read(&ctx->map_changing_lock); err = -EAGAIN; - if (mmap_changing && atomic_read(mmap_changing)) + if (atomic_read(&ctx->mmap_changing)) goto out_unlock; err = -ENOENT; @@ -900,6 +908,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, err = 0; } out_unlock: + up_read(&ctx->map_changing_lock); mmap_read_unlock(dst_mm); return err; } -- 2.43.0