Merge "mm/madvise: pass task and mm to do_madvise"

include/linux/mm.h

@@ -2350,6 +2350,8 @@ 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(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,

mm/madvise.c

@@ -22,11 +22,14 @@
 #include <linux/file.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/compat.h>
 #include <linux/pagewalk.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
+#include <linux/sched/mm.h>
+#include <linux/uio.h>
 
 #include <asm/tlb.h>
 
@@ -254,6 +257,7 @@ 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 +292,12 @@ 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 +686,6 @@ 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 +765,8 @@ 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 +774,8 @@ 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 +829,7 @@ 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 +857,13 @@ 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 +1056,8 @@ madvise_behavior_valid(int behavior)
  *  -EBADF  - map exists, but area maps something that isn't a file.
  *  -EAGAIN - a kernel resource was temporarily unavailable.
  */
-SYSCALL_DEFINE3(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 +1095,27 @@ SYSCALL_DEFINE3(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;
+
+		/*
+		 * We may have stolen the mm from another process
+		 * that is undergoing core dumping.
+		 *
+		 * Right now that's io_ring, in the future it may
+		 * be remote process management and not "current"
+		 * at all.
+		 *
+		 * We need to fix core dumping to not do this,
+		 * but for now we have the mmget_still_valid()
+		 * model.
+		 */
+		if (!mmget_still_valid(mm)) {
+			up_write(&mm->mmap_sem);
+			return -EINTR;
+		}
 	} else {
-		down_read(&current->mm->mmap_sem);
+		down_read(&mm->mmap_sem);
 	}
 
 	/*
@@ -1099,7 +1123,7 @@ SYSCALL_DEFINE3(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;
 
@@ -1136,14 +1160,19 @@ SYSCALL_DEFINE3(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(current, current->mm, start, len_in, behavior);
+}