1 files changed, 136 insertions, 64 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index d4aa5f776543..416a56b8e757 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -17,6 +17,8 @@
 #include <linux/falloc.h>
 #include <linux/fadvise.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
+#include <linux/uio.h>
 #include <linux/ksm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
@@ -27,7 +29,6 @@
 #include <linux/swapops.h>
 #include <linux/shmem_fs.h>
 #include <linux/mmu_notifier.h>
-#include <linux/sched/mm.h>
 
 #include <asm/tlb.h>
 
@@ -224,25 +225,28 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end,
 		struct address_space *mapping)
 {
-	pgoff_t index;
+	XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
+	pgoff_t end_index = end / PAGE_SIZE;
 	struct page *page;
-	swp_entry_t swap;
 
-	for (; start < end; start += PAGE_SIZE) {
-		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
+	rcu_read_lock();
+	xas_for_each(&xas, page, end_index) {
+		swp_entry_t swap;
 
-		page = find_get_entry(mapping, index);
-		if (!xa_is_value(page)) {
-			if (page)
-				put_page(page);
+		if (!xa_is_value(page))
 			continue;
-		}
+		xas_pause(&xas);
+		rcu_read_unlock();
+
 		swap = radix_to_swp_entry(page);
 		page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE,
 							NULL, 0, false);
 		if (page)
 			put_page(page);
+
+		rcu_read_lock();
 	}
+	rcu_read_unlock();
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 }
@@ -255,6 +259,7 @@ 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;
 
@@ -291,10 +296,10 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	get_file(file);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-	mmap_read_unlock(current->mm);
+	mmap_read_unlock(mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return 0;
 }
 
@@ -381,9 +386,9 @@ huge_unlock:
 		return 0;
 	}
 
+regular_page:
 	if (pmd_trans_unstable(pmd))
 		return 0;
-regular_page:
 #endif
 	tlb_change_page_size(tlb, PAGE_SIZE);
 	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
@@ -763,6 +768,8 @@ 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;
@@ -770,8 +777,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (!userfaultfd_remove(vma, start, end)) {
 		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
 
-		mmap_read_lock(current->mm);
-		vma = find_vma(current->mm, start);
+		mmap_read_lock(mm);
+		vma = find_vma(mm, start);
 		if (!vma)
 			return -ENOMEM;
 		if (start < vma->vm_start) {
@@ -825,6 +832,7 @@ 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_lock */
 
@@ -852,13 +860,13 @@ static long madvise_remove(struct vm_area_struct *vma,
 	get_file(f);
 	if (userfaultfd_remove(vma, start, end)) {
 		/* mmap_lock was not released by userfaultfd_remove() */
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-	mmap_read_lock(current->mm);
+	mmap_read_lock(mm);
 	return error;
 }
 
@@ -869,7 +877,6 @@ static long madvise_remove(struct vm_area_struct *vma,
 static int madvise_inject_error(int behavior,
 		unsigned long start, unsigned long end)
 {
-	struct page *page;
 	struct zone *zone;
 	unsigned long size;
 
@@ -879,6 +886,7 @@ static int madvise_inject_error(int behavior,
 
 	for (; start < end; start += size) {
 		unsigned long pfn;
+		struct page *page;
 		int ret;
 
 		ret = get_user_pages_fast(start, 1, 0, &page);
@@ -893,32 +901,23 @@ static int madvise_inject_error(int behavior,
 		 */
 		size = page_size(compound_head(page));
 
-		if (PageHWPoison(page)) {
-			put_page(page);
-			continue;
-		}
-
 		if (behavior == MADV_SOFT_OFFLINE) {
 			pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
-					pfn, start);
-
+				 pfn, start);
 			ret = soft_offline_page(pfn, MF_COUNT_INCREASED);
-			if (ret)
-				return ret;
-			continue;
+		} else {
+			pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
+				 pfn, start);
+			/*
+			 * Drop the page reference taken by get_user_pages_fast(). In
+			 * the absence of MF_COUNT_INCREASED the memory_failure()
+			 * routine is responsible for pinning the page to prevent it
+			 * from being released back to the page allocator.
+			 */
+			put_page(page);
+			ret = memory_failure(pfn, 0);
 		}
 
-		pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
-				pfn, start);
-
-		/*
-		 * Drop the page reference taken by get_user_pages_fast(). In
-		 * the absence of MF_COUNT_INCREASED the memory_failure()
-		 * routine is responsible for pinning the page to prevent it
-		 * from being released back to the page allocator.
-		 */
-		put_page(page);
-		ret = memory_failure(pfn, 0);
 		if (ret)
 			return ret;
 	}
@@ -990,6 +989,18 @@ madvise_behavior_valid(int behavior)
 	}
 }
 
+static bool
+process_madvise_behavior_valid(int behavior)
+{
+	switch (behavior) {
+	case MADV_COLD:
+	case MADV_PAGEOUT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * The madvise(2) system call.
  *
@@ -1037,6 +1048,11 @@ madvise_behavior_valid(int behavior)
  *  MADV_DONTDUMP - the application wants to prevent pages in the given range
  *		from being included in its core dump.
  *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
+ *  MADV_COLD - the application is not expected to use this memory soon,
+ *		deactivate pages in this range so that they can be reclaimed
+ *		easily if memory pressure hanppens.
+ *  MADV_PAGEOUT - the application is not expected to use this memory soon,
+ *		page out the pages in this range immediately.
  *
  * return values:
  *  zero    - success
@@ -1051,7 +1067,7 @@ 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 mm_struct *mm, unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1089,27 +1105,10 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (mmap_write_lock_killable(current->mm))
-			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(current->mm)) {
-			mmap_write_unlock(current->mm);
+		if (mmap_write_lock_killable(mm))
 			return -EINTR;
-		}
 	} else {
-		mmap_read_lock(current->mm);
+		mmap_read_lock(mm);
 	}
 
 	/*
@@ -1117,7 +1116,7 @@ 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;
 
@@ -1154,19 +1153,92 @@ int do_madvise(unsigned long start, size_t len_in, int behavior)
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_lock */
-			vma = find_vma(current->mm, start);
+			vma = find_vma(mm, start);
 	}
 out:
 	blk_finish_plug(&plug);
 	if (write)
-		mmap_write_unlock(current->mm);
+		mmap_write_unlock(mm);
 	else
-		mmap_read_unlock(current->mm);
+		mmap_read_unlock(mm);
 
 	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->mm, start, len_in, behavior);
+}
+
+SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
+		size_t, vlen, int, behavior, unsigned int, flags)
+{
+	ssize_t ret;
+	struct iovec iovstack[UIO_FASTIOV], iovec;
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	struct pid *pid;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	size_t total_len;
+	unsigned int f_flags;
+
+	if (flags != 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret < 0)
+		goto out;
+
+	pid = pidfd_get_pid(pidfd, &f_flags);
+	if (IS_ERR(pid)) {
+		ret = PTR_ERR(pid);
+		goto free_iov;
+	}
+
+	task = get_pid_task(pid, PIDTYPE_PID);
+	if (!task) {
+		ret = -ESRCH;
+		goto put_pid;
+	}
+
+	if (task->mm != current->mm &&
+			!process_madvise_behavior_valid(behavior)) {
+		ret = -EINVAL;
+		goto release_task;
+	}
+
+	mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+	if (IS_ERR_OR_NULL(mm)) {
+		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+		goto release_task;
+	}
+
+	total_len = iov_iter_count(&iter);
+
+	while (iov_iter_count(&iter)) {
+		iovec = iov_iter_iovec(&iter);
+		ret = do_madvise(mm, (unsigned long)iovec.iov_base,
+					iovec.iov_len, behavior);
+		if (ret < 0)
+			break;
+		iov_iter_advance(&iter, iovec.iov_len);
+	}
+
+	if (ret == 0)
+		ret = total_len - iov_iter_count(&iter);
+
+	mmput(mm);
+	return ret;
+
+release_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+free_iov:
+	kfree(iov);
+out:
+	return ret;
 }