mm/madvise: pass task and mm to do_madvise

Patch series "introduce memory hinting API for external process", v7.

Now, we have MADV_PAGEOUT and MADV_COLD as madvise hinting API.  With
that, application could give hints to kernel what memory range are
preferred to be reclaimed.  However, in some platform(e.g., Android), the
information required to make the hinting decision is not known to the app.
Instead, it is known to a centralized userspace daemon(e.g.,
ActivityManagerService), and that daemon must be able to initiate reclaim
on its own without any app involvement.

To solve the concern, this patch introduces new syscall -
process_madvise(2).  Bascially, it's same with madvise(2) syscall but it
has some differences.

1. It needs pidfd of target process to provide the hint

2.  It supports only MADV_{COLD|PAGEOUT|MERGEABLE|UNMEREABLE} at this
   moment.  Other hints in madvise will be opened when there are explicit
   requests from community to prevent unexpected bugs we couldn't support.

3.  Only privileged processes can do something for other process's
   address space.

For more detail of the new API, please see "mm: introduce external memory
hinting API" description in this patchset.

This patch (of 7):

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

Link: http://lkml.kernel.org/r/20200302193630.68771-2-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jann Horn <jannh@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Daniel Colascione <dancol@google.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: John Dias <joaodias@google.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: <linux-man@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>

1 files changed, 19 insertions, 15 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 4bb30ed6c8d2..80f8a1839f70 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(&current->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(&current->mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	return 0;
 }
 
@@ -682,7 +683,6 @@ out:
 	if (nr_swap) {
 		if (current->mm == mm)
 			sync_mm_rss(mm);
-
 		add_mm_counter(mm, MM_SWAPENTS, nr_swap);
 	}
 	arch_leave_lazy_mmu_mode();
@@ -762,6 +762,8 @@ 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;
@@ -769,8 +771,8 @@ 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(&current->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) {
@@ -824,6 +826,7 @@ 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 */
 
@@ -851,13 +854,13 @@ 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(&current->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(&current->mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	return error;
 }
 
@@ -1050,7 +1053,8 @@ 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;
@@ -1088,10 +1092,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (down_write_killable(&current->mm->mmap_sem))
+		if (down_write_killable(&mm->mmap_sem))
 			return -EINTR;
 	} else {
-		down_read(&current->mm->mmap_sem);
+		down_read(&mm->mmap_sem);
 	}
 
 	/*
@@ -1099,7 +1103,7 @@ 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;
 
@@ -1136,19 +1140,19 @@ 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(&current->mm->mmap_sem);
+		up_write(&mm->mmap_sem);
 	else
-		up_read(&current->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);
 }