| Message ID | 20200219014433.88424-2-minchan@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | introduce memory hinting API for external process | expand |
On Tue, Feb 18, 2020 at 5:44 PM Minchan Kim <minchan@kernel.org> wrote: > > In upcoming patches, do_madvise will be called from external process > context so we shouldn't asssume "current" is always hinted process's > task_struct. Furthermore, we couldn't access mm_struct via task->mm > once it's verified by access_mm which will be introduced in next > patch[1]. And let's pass *current* and current->mm as arguments of > do_madvise so it shouldn't change existing behavior but prepare > next patch to make review easy. > > Note: io_madvise pass NULL as target_task argument of do_madvise > because it couldn't know who is target. > > [1] http://lore.kernel.org/r/CAG48ez27=pwm5m_N_988xT1huO7g7h6arTQL44zev6TD-h-7Tg@mail.gmail.com > > Cc: Jens Axboe <axboe@kernel.dk> > Cc: Jann Horn <jannh@google.com> > Signed-off-by: Minchan Kim <minchan@kernel.org> > --- > fs/io_uring.c | 2 +- > include/linux/mm.h | 3 ++- > mm/madvise.c | 34 +++++++++++++++++++--------------- > 3 files changed, 22 insertions(+), 17 deletions(-) > > diff --git a/fs/io_uring.c b/fs/io_uring.c > index 63beda9bafc5..a858da2ae2f4 100644 > --- a/fs/io_uring.c > +++ b/fs/io_uring.c > @@ -2736,7 +2736,7 @@ static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt, > if (force_nonblock) > return -EAGAIN; > > - ret = do_madvise(ma->addr, ma->len, ma->advice); > + ret = do_madvise(NULL, req->work.mm, ma->addr, ma->len, ma->advice); > if (ret < 0) > req_set_fail_links(req); > io_cqring_add_event(req, ret); > diff --git a/include/linux/mm.h b/include/linux/mm.h > index 52269e56c514..bc16c8774328 100644 > --- a/include/linux/mm.h > +++ b/include/linux/mm.h > @@ -2323,7 +2323,8 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t, > struct list_head *uf, bool downgrade); > extern int do_munmap(struct mm_struct *, unsigned long, size_t, > struct list_head *uf); > -extern int do_madvise(unsigned long start, size_t len_in, int behavior); > +extern int do_madvise(struct task_struct *target_task, struct mm_struct *mm, > + unsigned long start, size_t len_in, int behavior); > > static inline unsigned long > do_mmap_pgoff(struct file *file, unsigned long addr, > diff --git a/mm/madvise.c b/mm/madvise.c > index 43b47d3fae02..f75c86b6c463 100644 > --- a/mm/madvise.c > +++ b/mm/madvise.c > @@ -254,6 +254,7 @@ static long madvise_willneed(struct vm_area_struct *vma, > struct vm_area_struct **prev, > unsigned long start, unsigned long end) > { > + struct mm_struct *mm = vma->vm_mm; > struct file *file = vma->vm_file; > loff_t offset; > > @@ -288,12 +289,12 @@ static long madvise_willneed(struct vm_area_struct *vma, > */ > *prev = NULL; /* tell sys_madvise we drop mmap_sem */ > get_file(file); > - up_read(¤t->mm->mmap_sem); > + up_read(&mm->mmap_sem); > offset = (loff_t)(start - vma->vm_start) > + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); > vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); > fput(file); > - down_read(¤t->mm->mmap_sem); > + down_read(&mm->mmap_sem); > return 0; > } > > @@ -676,7 +677,6 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, > if (nr_swap) { > if (current->mm == mm) > sync_mm_rss(mm); > - > add_mm_counter(mm, MM_SWAPENTS, nr_swap); > } > arch_leave_lazy_mmu_mode(); > @@ -756,6 +756,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, > unsigned long start, unsigned long end, > int behavior) > { > + struct mm_struct *mm = vma->vm_mm; > + > *prev = vma; > if (!can_madv_lru_vma(vma)) > return -EINVAL; > @@ -763,8 +765,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, > if (!userfaultfd_remove(vma, start, end)) { > *prev = NULL; /* mmap_sem has been dropped, prev is stale */ > > - down_read(¤t->mm->mmap_sem); > - vma = find_vma(current->mm, start); > + down_read(&mm->mmap_sem); > + vma = find_vma(mm, start); > if (!vma) > return -ENOMEM; > if (start < vma->vm_start) { > @@ -818,6 +820,7 @@ static long madvise_remove(struct vm_area_struct *vma, > loff_t offset; > int error; > struct file *f; > + struct mm_struct *mm = vma->vm_mm; > > *prev = NULL; /* tell sys_madvise we drop mmap_sem */ > > @@ -845,13 +848,13 @@ static long madvise_remove(struct vm_area_struct *vma, > get_file(f); > if (userfaultfd_remove(vma, start, end)) { > /* mmap_sem was not released by userfaultfd_remove() */ > - up_read(¤t->mm->mmap_sem); > + up_read(&mm->mmap_sem); > } > error = vfs_fallocate(f, > FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, > offset, end - start); > fput(f); > - down_read(¤t->mm->mmap_sem); > + down_read(&mm->mmap_sem); > return error; > } > > @@ -1044,7 +1047,8 @@ madvise_behavior_valid(int behavior) > * -EBADF - map exists, but area maps something that isn't a file. > * -EAGAIN - a kernel resource was temporarily unavailable. > */ > -int do_madvise(unsigned long start, size_t len_in, int behavior) > +int do_madvise(struct task_struct *target_task, struct mm_struct *mm, > + unsigned long start, size_t len_in, int behavior) > { > unsigned long end, tmp; > struct vm_area_struct *vma, *prev; > @@ -1082,10 +1086,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) > > write = madvise_need_mmap_write(behavior); > if (write) { > - if (down_write_killable(¤t->mm->mmap_sem)) > + if (down_write_killable(&mm->mmap_sem)) > return -EINTR; > } else { > - down_read(¤t->mm->mmap_sem); > + down_read(&mm->mmap_sem); > } > > /* > @@ -1093,7 +1097,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) > * ranges, just ignore them, but return -ENOMEM at the end. > * - different from the way of handling in mlock etc. > */ > - vma = find_vma_prev(current->mm, start, &prev); > + vma = find_vma_prev(mm, start, &prev); > if (vma && start > vma->vm_start) > prev = vma; > > @@ -1130,19 +1134,19 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) > if (prev) > vma = prev->vm_next; > else /* madvise_remove dropped mmap_sem */ > - vma = find_vma(current->mm, start); > + vma = find_vma(mm, start); > } > out: > blk_finish_plug(&plug); > if (write) > - up_write(¤t->mm->mmap_sem); > + up_write(&mm->mmap_sem); > else > - up_read(¤t->mm->mmap_sem); > + up_read(&mm->mmap_sem); > > return error; > } > > SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) > { > - return do_madvise(start, len_in, behavior); > + return do_madvise(current, current->mm, start, len_in, behavior); > } > -- > 2.25.0.265.gbab2e86ba0-goog > Reviewed-by: Suren Baghdasaryan <surenb@google.com>
diff --git a/fs/io_uring.c b/fs/io_uring.c index 63beda9bafc5..a858da2ae2f4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2736,7 +2736,7 @@ static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt, if (force_nonblock) return -EAGAIN; - ret = do_madvise(ma->addr, ma->len, ma->advice); + ret = do_madvise(NULL, req->work.mm, ma->addr, ma->len, ma->advice); if (ret < 0) req_set_fail_links(req); io_cqring_add_event(req, ret); diff --git a/include/linux/mm.h b/include/linux/mm.h index 52269e56c514..bc16c8774328 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2323,7 +2323,8 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); -extern int do_madvise(unsigned long start, size_t len_in, int behavior); +extern int do_madvise(struct task_struct *target_task, struct mm_struct *mm, + unsigned long start, size_t len_in, int behavior); static inline unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, diff --git a/mm/madvise.c b/mm/madvise.c index 43b47d3fae02..f75c86b6c463 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -254,6 +254,7 @@ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { + struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; loff_t offset; @@ -288,12 +289,12 @@ static long madvise_willneed(struct vm_area_struct *vma, */ *prev = NULL; /* tell sys_madvise we drop mmap_sem */ get_file(file); - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); - down_read(¤t->mm->mmap_sem); + down_read(&mm->mmap_sem); return 0; } @@ -676,7 +677,6 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, if (nr_swap) { if (current->mm == mm) sync_mm_rss(mm); - add_mm_counter(mm, MM_SWAPENTS, nr_swap); } arch_leave_lazy_mmu_mode(); @@ -756,6 +756,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, unsigned long start, unsigned long end, int behavior) { + struct mm_struct *mm = vma->vm_mm; + *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; @@ -763,8 +765,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, if (!userfaultfd_remove(vma, start, end)) { *prev = NULL; /* mmap_sem has been dropped, prev is stale */ - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, start); + down_read(&mm->mmap_sem); + vma = find_vma(mm, start); if (!vma) return -ENOMEM; if (start < vma->vm_start) { @@ -818,6 +820,7 @@ static long madvise_remove(struct vm_area_struct *vma, loff_t offset; int error; struct file *f; + struct mm_struct *mm = vma->vm_mm; *prev = NULL; /* tell sys_madvise we drop mmap_sem */ @@ -845,13 +848,13 @@ static long madvise_remove(struct vm_area_struct *vma, get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_sem was not released by userfaultfd_remove() */ - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); - down_read(¤t->mm->mmap_sem); + down_read(&mm->mmap_sem); return error; } @@ -1044,7 +1047,8 @@ madvise_behavior_valid(int behavior) * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. */ -int do_madvise(unsigned long start, size_t len_in, int behavior) +int do_madvise(struct task_struct *target_task, struct mm_struct *mm, + unsigned long start, size_t len_in, int behavior) { unsigned long end, tmp; struct vm_area_struct *vma, *prev; @@ -1082,10 +1086,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) write = madvise_need_mmap_write(behavior); if (write) { - if (down_write_killable(¤t->mm->mmap_sem)) + if (down_write_killable(&mm->mmap_sem)) return -EINTR; } else { - down_read(¤t->mm->mmap_sem); + down_read(&mm->mmap_sem); } /* @@ -1093,7 +1097,7 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) * ranges, just ignore them, but return -ENOMEM at the end. * - different from the way of handling in mlock etc. */ - vma = find_vma_prev(current->mm, start, &prev); + vma = find_vma_prev(mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; @@ -1130,19 +1134,19 @@ int do_madvise(unsigned long start, size_t len_in, int behavior) if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_sem */ - vma = find_vma(current->mm, start); + vma = find_vma(mm, start); } out: blk_finish_plug(&plug); if (write) - up_write(¤t->mm->mmap_sem); + up_write(&mm->mmap_sem); else - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { - return do_madvise(start, len_in, behavior); + return do_madvise(current, current->mm, start, len_in, behavior); }
In upcoming patches, do_madvise will be called from external process context so we shouldn't asssume "current" is always hinted process's task_struct. Furthermore, we couldn't access mm_struct via task->mm once it's verified by access_mm which will be introduced in next patch[1]. And let's pass *current* and current->mm as arguments of do_madvise so it shouldn't change existing behavior but prepare next patch to make review easy. Note: io_madvise pass NULL as target_task argument of do_madvise because it couldn't know who is target. [1] http://lore.kernel.org/r/CAG48ez27=pwm5m_N_988xT1huO7g7h6arTQL44zev6TD-h-7Tg@mail.gmail.com Cc: Jens Axboe <axboe@kernel.dk> Cc: Jann Horn <jannh@google.com> Signed-off-by: Minchan Kim <minchan@kernel.org> --- fs/io_uring.c | 2 +- include/linux/mm.h | 3 ++- mm/madvise.c | 34 +++++++++++++++++++--------------- 3 files changed, 22 insertions(+), 17 deletions(-)