[RFC,04/11] mm/mempolicy: create struct mempolicy_args for creating new mempolicies

Commit Message

Gregory Price Dec. 7, 2023, 12:27 a.m. UTC

This patch adds a new kernel structure `struct mempolicy_args`,
intended to be used for an extensible get/set_mempolicy interface.

This implements the fields required to support the existing syscall
interfaces interfaces, but does not expose any user-facing arg
structure.

mpol_new is refactored to take the argument structure so that future
mempolicy extensions can all be managed in the mempolicy constructor.

The get_mempolicy and mbind syscalls are refactored to utilize the
new argument structure, as are all the callers of mpol_new() and
do_set_mempolicy.

Signed-off-by: Gregory Price <[e-mail]>
---
 include/linux/mempolicy.h | 14 ++++++++
 mm/mempolicy.c            | 69 +++++++++++++++++++++++++++++----------
 2 files changed, 65 insertions(+), 18 deletions(-)

Patch

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index ba09167e80f7..117c5395c6eb 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -61,6 +61,20 @@  struct mempolicy {
 	} wil;
 };
 
+/*
+ * Describes settings of a mempolicy during set/get syscalls and
+ * kernel internal calls to do_set_mempolicy()
+ */
+struct mempolicy_args {
+	unsigned short mode;		/* policy mode */
+	unsigned short mode_flags;	/* policy mode flags */
+	nodemask_t *policy_nodes;	/* get/set/mbind */
+	int policy_node;		/* get: policy node information */
+	unsigned long addr;		/* get: vma address */
+	int addr_node;			/* get: node the address belongs to */
+	int home_node;			/* mbind: use MPOL_MF_HOME_NODE */
+};
+
 /*
  * Support for managing mempolicy data objects (clone, copy, destroy)
  * The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index eec807d0c6a1..4c343218c033 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -268,10 +268,12 @@  static int mpol_set_nodemask(struct mempolicy *pol,
  * This function just creates a new policy, does some check and simple
  * initialization. You must invoke mpol_set_nodemask() to set nodes.
  */
-static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
-				  nodemask_t *nodes)
+static struct mempolicy *mpol_new(struct mempolicy_args *args)
 {
 	struct mempolicy *policy;
+	unsigned short mode = args->mode;
+	unsigned short flags = args->mode_flags;
+	nodemask_t *nodes = args->policy_nodes;
 
 	if (mode == MPOL_DEFAULT) {
 		if (nodes && !nodes_empty(*nodes))
@@ -820,8 +822,7 @@  static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma,
 }
 
 /* Set the process memory policy */
-static long do_set_mempolicy(unsigned short mode, unsigned short flags,
-			     nodemask_t *nodes)
+static long do_set_mempolicy(struct mempolicy_args *args)
 {
 	struct mempolicy *new, *old;
 	NODEMASK_SCRATCH(scratch);
@@ -830,14 +831,14 @@  static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	if (!scratch)
 		return -ENOMEM;
 
-	new = mpol_new(mode, flags, nodes);
+	new = mpol_new(args);
 	if (IS_ERR(new)) {
 		ret = PTR_ERR(new);
 		goto out;
 	}
 
 	task_lock(current);
-	ret = mpol_set_nodemask(new, nodes, scratch);
+	ret = mpol_set_nodemask(new, args->policy_nodes, scratch);
 	if (ret) {
 		task_unlock(current);
 		mpol_put(new);
@@ -1235,8 +1236,7 @@  static struct folio *alloc_migration_target_by_mpol(struct folio *src,
 #endif
 
 static long do_mbind(unsigned long start, unsigned long len,
-		     unsigned short mode, unsigned short mode_flags,
-		     nodemask_t *nmask, unsigned long flags)
+		     struct mempolicy_args *margs, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -1256,7 +1256,7 @@  static long do_mbind(unsigned long start, unsigned long len,
 	if (start & ~PAGE_MASK)
 		return -EINVAL;
 
-	if (mode == MPOL_DEFAULT)
+	if (margs->mode == MPOL_DEFAULT)
 		flags &= ~MPOL_MF_STRICT;
 
 	len = PAGE_ALIGN(len);
@@ -1267,7 +1267,7 @@  static long do_mbind(unsigned long start, unsigned long len,
 	if (end == start)
 		return 0;
 
-	new = mpol_new(mode, mode_flags, nmask);
+	new = mpol_new(margs);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
@@ -1284,7 +1284,8 @@  static long do_mbind(unsigned long start, unsigned long len,
 		NODEMASK_SCRATCH(scratch);
 		if (scratch) {
 			mmap_write_lock(mm);
-			err = mpol_set_nodemask(new, nmask, scratch);
+			err = mpol_set_nodemask(new, margs->policy_nodes,
+						scratch);
 			if (err)
 				mmap_write_unlock(mm);
 		} else
@@ -1298,7 +1299,7 @@  static long do_mbind(unsigned long start, unsigned long len,
 	 * Lock the VMAs before scanning for pages to migrate,
 	 * to ensure we don't miss a concurrently inserted page.
 	 */
-	nr_failed = queue_pages_range(mm, start, end, nmask,
+	nr_failed = queue_pages_range(mm, start, end, margs->policy_nodes,
 			flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist);
 
 	if (nr_failed < 0) {
@@ -1503,6 +1504,7 @@  static long kernel_mbind(unsigned long start, unsigned long len,
 			 unsigned long mode, const unsigned long __user *nmask,
 			 unsigned long maxnode, unsigned int flags)
 {
+	struct mempolicy_args margs;
 	unsigned short mode_flags;
 	nodemask_t nodes;
 	int lmode = mode;
@@ -1517,7 +1519,12 @@  static long kernel_mbind(unsigned long start, unsigned long len,
 	if (err)
 		return err;
 
-	return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
+	memset(&margs, 0, sizeof(margs));
+	margs.mode = lmode;
+	margs.mode_flags = mode_flags;
+	margs.policy_nodes = &nodes;
+
+	return do_mbind(start, len, &margs, flags);
 }
 
 SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len,
@@ -1598,6 +1605,7 @@  SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
 				 unsigned long maxnode)
 {
+	struct mempolicy_args args;
 	unsigned short mode_flags;
 	nodemask_t nodes;
 	int lmode = mode;
@@ -1611,7 +1619,12 @@  static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
 	if (err)
 		return err;
 
-	return do_set_mempolicy(lmode, mode_flags, &nodes);
+	memset(&args, 0, sizeof(args));
+	args.mode = lmode;
+	args.mode_flags = mode_flags;
+	args.policy_nodes = &nodes;
+
+	return do_set_mempolicy(&args);
 }
 
 SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
@@ -2877,6 +2890,7 @@  static int shared_policy_replace(struct shared_policy *sp, pgoff_t start,
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 {
 	int ret;
+	struct mempolicy_args margs;
 
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
 	rwlock_init(&sp->lock);
@@ -2889,8 +2903,12 @@  void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 		if (!scratch)
 			goto put_mpol;
 
+		memset(&margs, 0, sizeof(margs));
+		margs.mode = mpol->mode;
+		margs.mode_flags = mpol->flags;
+		margs.policy_nodes = &mpol->w.user_nodemask;
 		/* contextualize the tmpfs mount point mempolicy to this file */
-		npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
+		npol = mpol_new(&margs);
 		if (IS_ERR(npol))
 			goto free_scratch; /* no valid nodemask intersection */
 
@@ -2998,6 +3016,7 @@  static inline void __init check_numabalancing_enable(void)
 
 void __init numa_policy_init(void)
 {
+	struct mempolicy_args args;
 	nodemask_t interleave_nodes;
 	unsigned long largest = 0;
 	int nid, prefer = 0;
@@ -3043,7 +3062,11 @@  void __init numa_policy_init(void)
 	if (unlikely(nodes_empty(interleave_nodes)))
 		node_set(prefer, interleave_nodes);
 
-	if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
+	memset(&args, 0, sizeof(args));
+	args.mode = MPOL_INTERLEAVE;
+	args.policy_nodes = &interleave_nodes;
+
+	if (do_set_mempolicy(&args))
 		pr_err("%s: interleaving failed\n", __func__);
 
 	check_numabalancing_enable();
@@ -3052,7 +3075,12 @@  void __init numa_policy_init(void)
 /* Reset policy of current process to default */
 void numa_default_policy(void)
 {
-	do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
+	struct mempolicy_args args;
+
+	memset(&args, 0, sizeof(args));
+	args.mode = MPOL_DEFAULT;
+
+	do_set_mempolicy(&args);
 }
 
 /*
@@ -3082,6 +3110,7 @@  static const char * const policy_modes[] =
  */
 int mpol_parse_str(char *str, struct mempolicy **mpol)
 {
+	struct mempolicy_args margs;
 	struct mempolicy *new = NULL;
 	unsigned short mode_flags;
 	nodemask_t nodes;
@@ -3168,7 +3197,11 @@  int mpol_parse_str(char *str, struct mempolicy **mpol)
 			goto out;
 	}
 
-	new = mpol_new(mode, mode_flags, &nodes);
+	memset(&margs, 0, sizeof(margs));
+	margs.mode = mode;
+	margs.mode_flags = mode_flags;
+	margs.policy_nodes = &nodes;
+	new = mpol_new(&margs);
 	if (IS_ERR(new))
 		goto out;