Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/madvise.c b/mm/madvise.c
index 1107e99..24abc79 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>
@@ -39,7 +41,7 @@
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
- * take mmap_sem for writing. Others, which simply traverse vmas, need
+ * take mmap_lock for writing. Others, which simply traverse vmas, need
  * to only take it for reading.
  */
 static int madvise_need_mmap_write(int behavior)
@@ -164,7 +166,7 @@
 
 success:
 	/*
-	 * vm_flags is protected by the mmap_sem held in write mode.
+	 * vm_flags is protected by the mmap_lock held in write mode.
 	 */
 	vma->vm_flags = new_flags;
 
@@ -223,25 +225,28 @@
 		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 = linear_page_index(vma, end + PAGE_SIZE - 1);
 	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 */
 }
@@ -254,6 +259,7 @@
 			     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;
 
@@ -284,16 +290,16 @@
 	 * Filesystem's fadvise may need to take various locks.  We need to
 	 * explicitly grab a reference because the vma (and hence the
 	 * vma's reference to the file) can go away as soon as we drop
-	 * mmap_sem.
+	 * mmap_lock.
 	 */
-	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
+	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 	get_file(file);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(mm);
 	vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED);
 	fput(file);
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(mm);
 	return 0;
 }
 
@@ -762,15 +768,17 @@
 				  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;
 
 	if (!userfaultfd_remove(vma, start, end)) {
-		*prev = NULL; /* mmap_sem has been dropped, prev is stale */
+		*prev = NULL; /* mmap_lock has been dropped, prev is stale */
 
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma(current->mm, start);
+		mmap_read_lock(mm);
+		vma = find_vma(mm, start);
 		if (!vma)
 			return -ENOMEM;
 		if (start < vma->vm_start) {
@@ -790,7 +798,7 @@
 		if (end > vma->vm_end) {
 			/*
 			 * Don't fail if end > vma->vm_end. If the old
-			 * vma was splitted while the mmap_sem was
+			 * vma was splitted while the mmap_lock was
 			 * released the effect of the concurrent
 			 * operation may not cause madvise() to
 			 * have an undefined result. There may be an
@@ -824,8 +832,9 @@
 	loff_t offset;
 	int error;
 	struct file *f;
+	struct mm_struct *mm = vma->vm_mm;
 
-	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
+	*prev = NULL;	/* tell sys_madvise we drop mmap_lock */
 
 	if (vma->vm_flags & VM_LOCKED)
 		return -EINVAL;
@@ -846,18 +855,18 @@
 	 * Filesystem's fallocate may need to take i_mutex.  We need to
 	 * explicitly grab a reference because the vma (and hence the
 	 * vma's reference to the file) can go away as soon as we drop
-	 * mmap_sem.
+	 * mmap_lock.
 	 */
 	get_file(f);
 	if (userfaultfd_remove(vma, start, end)) {
-		/* mmap_sem was not released by userfaultfd_remove() */
-		up_read(&current->mm->mmap_sem);
+		/* mmap_lock was not released by userfaultfd_remove() */
+		mmap_read_unlock(mm);
 	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(mm);
 	return error;
 }
 
@@ -868,16 +877,16 @@
 static int madvise_inject_error(int behavior,
 		unsigned long start, unsigned long end)
 {
-	struct page *page;
 	struct zone *zone;
-	unsigned int order;
+	unsigned long size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
 
-	for (; start < end; start += PAGE_SIZE << order) {
+	for (; start < end; start += size) {
 		unsigned long pfn;
+		struct page *page;
 		int ret;
 
 		ret = get_user_pages_fast(start, 1, 0, &page);
@@ -888,36 +897,20 @@
 		/*
 		 * When soft offlining hugepages, after migrating the page
 		 * we dissolve it, therefore in the second loop "page" will
-		 * no longer be a compound page, and order will be 0.
+		 * no longer be a compound page.
 		 */
-		order = compound_order(compound_head(page));
-
-		if (PageHWPoison(page)) {
-			put_page(page);
-			continue;
-		}
+		size = page_size(compound_head(page));
 
 		if (behavior == MADV_SOFT_OFFLINE) {
 			pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n",
-					pfn, start);
-
-			ret = soft_offline_page(page, MF_COUNT_INCREASED);
-			if (ret)
-				return ret;
-			continue;
+				 pfn, start);
+			ret = soft_offline_page(pfn, MF_COUNT_INCREASED);
+		} else {
+			pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n",
+				 pfn, start);
+			ret = memory_failure(pfn, MF_COUNT_INCREASED);
 		}
 
-		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;
 	}
@@ -989,6 +982,18 @@
 	}
 }
 
+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.
  *
@@ -1036,6 +1041,11 @@
  *  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
@@ -1050,7 +1060,7 @@
  *  -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 mm_struct *mm, unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1065,9 +1075,9 @@
 	if (!madvise_behavior_valid(behavior))
 		return error;
 
-	if (start & ~PAGE_MASK)
+	if (!PAGE_ALIGNED(start))
 		return error;
-	len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+	len = PAGE_ALIGN(len_in);
 
 	/* Check to see whether len was rounded up from small -ve to zero */
 	if (len_in && !len)
@@ -1088,10 +1098,10 @@
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (down_write_killable(&current->mm->mmap_sem))
+		if (mmap_write_lock_killable(mm))
 			return -EINTR;
 	} else {
-		down_read(&current->mm->mmap_sem);
+		mmap_read_lock(mm);
 	}
 
 	/*
@@ -1099,7 +1109,7 @@
 	 * 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;
 
@@ -1135,15 +1145,101 @@
 			goto out;
 		if (prev)
 			vma = prev->vm_next;
-		else	/* madvise_remove dropped mmap_sem */
-			vma = find_vma(current->mm, start);
+		else	/* madvise_remove dropped mmap_lock */
+			vma = find_vma(mm, start);
 	}
 out:
 	blk_finish_plug(&plug);
 	if (write)
-		up_write(&current->mm->mmap_sem);
+		mmap_write_unlock(mm);
 	else
-		up_read(&current->mm->mmap_sem);
+		mmap_read_unlock(mm);
 
 	return error;
 }
+
+SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, 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 (!process_madvise_behavior_valid(behavior)) {
+		ret = -EINVAL;
+		goto release_task;
+	}
+
+	/* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
+	if (IS_ERR_OR_NULL(mm)) {
+		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
+		goto release_task;
+	}
+
+	/*
+	 * Require CAP_SYS_NICE for influencing process performance. Note that
+	 * only non-destructive hints are currently supported.
+	 */
+	if (!capable(CAP_SYS_NICE)) {
+		ret = -EPERM;
+		goto release_mm;
+	}
+
+	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);
+
+release_mm:
+	mmput(mm);
+release_task:
+	put_task_struct(task);
+put_pid:
+	put_pid(pid);
+free_iov:
+	kfree(iov);
+out:
+	return ret;
+}