!637 Introduce new memory policy for OLK-5.10

Merge Pull Request from: @ma-wupeng 
 
Introduce new syscall set_mempolicy_home_node and mempolicy
MPOL_PREFERRED_MANY.

This patch series introduces the concept of the MPOL_PREFERRED_MANY mempolicy.
This mempolicy mode can be used with either the set_mempolicy(2) or mbind(2)
interfaces. Like the MPOL_PREFERRED interface, it allows an application to set a
preference for nodes which will fulfil memory allocation requests. Unlike the
MPOL_PREFERRED mode, it takes a set of nodes. Like the MPOL_BIND interface, it
works over a set of nodes. Unlike MPOL_BIND, it will not cause a SIGSEGV or
invoke the OOM killer if those preferred nodes are not available.

mm: add new syscall set_mempolicy_home_node 
 
Link:https://gitee.com/openeuler/kernel/pulls/637 

Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com> 
Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> 

Documentation/admin-guide/mm/numa_memory_policy.rst

@@ -245,6 +245,13 @@ MPOL_INTERLEAVED
 	address range or file.  During system boot up, the temporary
 	interleaved system default policy works in this mode.
 
+MPOL_PREFERRED_MANY
+	This mode specifices that the allocation should be preferrably
+	satisfied from the nodemask specified in the policy. If there is
+	a memory pressure on all nodes in the nodemask, the allocation
+	can fall back to all existing numa nodes. This is effectively
+	MPOL_PREFERRED allowed for a mask rather than a single node.
+
 NUMA memory policy supports the following optional mode flags:
 
 MPOL_F_STATIC_NODES
@@ -253,10 +260,10 @@ MPOL_F_STATIC_NODES
 	nodes changes after the memory policy has been defined.
 
 	Without this flag, any time a mempolicy is rebound because of a
-	change in the set of allowed nodes, the node (Preferred) or
-	nodemask (Bind, Interleave) is remapped to the new set of
-	allowed nodes.  This may result in nodes being used that were
-	previously undesired.
+        change in the set of allowed nodes, the preferred nodemask (Preferred
+        Many), preferred node (Preferred) or nodemask (Bind, Interleave) is
+        remapped to the new set of allowed nodes.  This may result in nodes
+        being used that were previously undesired.
 
 	With this flag, if the user-specified nodes overlap with the
 	nodes allowed by the task's cpuset, then the memory policy is
@@ -401,7 +408,7 @@ follows:
 Memory Policy APIs
 ==================
 
-Linux supports 3 system calls for controlling memory policy.  These APIS
+Linux supports 4 system calls for controlling memory policy.  These APIS
 always affect only the calling task, the calling task's address space, or
 some shared object mapped into the calling task's address space.
 
@@ -453,6 +460,20 @@ requested via the 'flags' argument.
 
 See the mbind(2) man page for more details.
 
+Set home node for a Range of Task's Address Spacec::
+
+	long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
+					 unsigned long home_node,
+					 unsigned long flags);
+
+sys_set_mempolicy_home_node set the home node for a VMA policy present in the
+task's address range. The system call updates the home node only for the existing
+mempolicy range. Other address ranges are ignored. A home node is the NUMA node
+closest to which page allocation will come from. Specifying the home node override
+the default allocation policy to allocate memory close to the local node for an
+executing CPU.
+
+
 Memory Policy Command Line Interface
 ====================================
 

arch/alpha/kernel/syscalls/syscall.tbl

@@ -483,3 +483,4 @@
 554	common	landlock_create_ruleset		sys_landlock_create_ruleset
 555	common	landlock_add_rule		sys_landlock_add_rule
 556	common	landlock_restrict_self		sys_landlock_restrict_self
+560	common	set_mempolicy_home_node		sys_ni_syscall

arch/arm/tools/syscall.tbl

@@ -463,7 +463,7 @@
 447	common	kabi_reserved447		sys_ni_syscall
 448	common	kabi_reserved448		sys_ni_syscall
 449	common	kabi_reserved449		sys_ni_syscall
-450	common	kabi_reserved450		sys_ni_syscall
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	kabi_reserved451		sys_ni_syscall
 452	common	kabi_reserved452		sys_ni_syscall
 453	common	kabi_reserved453		sys_ni_syscall

arch/arm64/include/asm/unistd.h

@@ -42,7 +42,6 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE + 2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
-
 #define __NR_compat_syscalls		457
 #endif
 

arch/arm64/include/asm/unistd32.h

@@ -908,8 +908,8 @@ __SYSCALL(__NR_kabi_reserved447, sys_ni_syscall)
 __SYSCALL(__NR_kabi_reserved448, sys_ni_syscall)
 #define __NR_kabi_reserved449 449
 __SYSCALL(__NR_kabi_reserved449, sys_ni_syscall)
-#define __NR_kabi_reserved450 450
-__SYSCALL(__NR_kabi_reserved450, sys_ni_syscall)
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 #define __NR_kabi_reserved451 451
 __SYSCALL(__NR_kabi_reserved451, sys_ni_syscall)
 #define __NR_kabi_reserved452 452

arch/ia64/kernel/syscalls/syscall.tbl

@@ -364,3 +364,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/m68k/kernel/syscalls/syscall.tbl

@@ -443,3 +443,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/microblaze/kernel/syscalls/syscall.tbl

@@ -449,3 +449,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -382,3 +382,4 @@
 444 n32 landlock_create_ruleset     sys_landlock_create_ruleset
 445 n32 landlock_add_rule       sys_landlock_add_rule
 446 n32 landlock_restrict_self      sys_landlock_restrict_self
+450	n32	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/mips/kernel/syscalls/syscall_n64.tbl

@@ -358,3 +358,4 @@
 444 n64 landlock_create_ruleset     sys_landlock_create_ruleset
 445 n64 landlock_add_rule       sys_landlock_add_rule
 446 n64 landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/mips/kernel/syscalls/syscall_o32.tbl

@@ -431,3 +431,4 @@
 444 o32 landlock_create_ruleset     sys_landlock_create_ruleset
 445 o32 landlock_add_rule       sys_landlock_add_rule
 446 o32 landlock_restrict_self      sys_landlock_restrict_self
+450	o32	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/parisc/kernel/syscalls/syscall.tbl

@@ -441,3 +441,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -539,7 +539,7 @@
 447	common	kabi_reserved447		sys_ni_syscall
 448	common	kabi_reserved448		sys_ni_syscall
 449	common	kabi_reserved449		sys_ni_syscall
-450	common	kabi_reserved450		sys_ni_syscall
+450	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	kabi_reserved451		sys_ni_syscall
 452	common	kabi_reserved452		sys_ni_syscall
 453	common	kabi_reserved453		sys_ni_syscall

arch/s390/kernel/syscalls/syscall.tbl

@@ -446,3 +446,4 @@
 444  common    landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset
 445  common    landlock_add_rule   sys_landlock_add_rule       sys_landlock_add_rule
 446  common    landlock_restrict_self  sys_landlock_restrict_self  sys_landlock_restrict_self
+450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node

arch/sh/kernel/syscalls/syscall.tbl

@@ -446,3 +446,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/sparc/kernel/syscalls/syscall.tbl

@@ -489,3 +489,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

arch/x86/entry/syscalls/syscall_32.tbl

@@ -454,7 +454,7 @@
 447	i386	kabi_reserved447	sys_ni_syscall
 448	i386	kabi_reserved448	sys_ni_syscall
 449	i386	kabi_reserved449	sys_ni_syscall
-450	i386	kabi_reserved450	sys_ni_syscall
+450	i386	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	i386	kabi_reserved451	sys_ni_syscall
 452	i386	kabi_reserved452	sys_ni_syscall
 453	i386	kabi_reserved453	sys_ni_syscall

arch/x86/entry/syscalls/syscall_64.tbl

@@ -371,7 +371,7 @@
 447	common	kabi_reserved447	sys_ni_syscall
 448	common	kabi_reserved448	sys_ni_syscall
 449	common	kabi_reserved449	sys_ni_syscall
-450	common	kabi_reserved450	sys_ni_syscall
+450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	common	kabi_reserved451	sys_ni_syscall
 452	common	kabi_reserved452	sys_ni_syscall
 453	common	kabi_reserved453	sys_ni_syscall

arch/xtensa/kernel/syscalls/syscall.tbl

@@ -414,3 +414,4 @@
 444 common  landlock_create_ruleset     sys_landlock_create_ruleset
 445 common  landlock_add_rule       sys_landlock_add_rule
 446 common  landlock_restrict_self      sys_landlock_restrict_self
+450	common	set_mempolicy_home_node		sys_set_mempolicy_home_node

include/linux/mempolicy.h

@@ -57,6 +57,11 @@ struct mempolicy {
 	} w;
 };
 
+struct mempolicy_wrapper {
+	struct mempolicy policy;
+	int home_node;		/* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */
+};
+
 /*
  * Support for managing mempolicy data objects (clone, copy, destroy)
  * The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
@@ -154,13 +159,6 @@ extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
 extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
 
-static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
-{
-	struct mempolicy *mpol = get_task_policy(current);
-
-	return policy_nodemask(gfp, mpol);
-}
-
 extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
@@ -204,6 +202,14 @@ extern void mpol_put_task_policy(struct task_struct *);
 extern long __do_mbind(unsigned long start, unsigned long len,
 		       unsigned short mode, unsigned short mode_flags,
 		       nodemask_t *nmask, unsigned long flags, struct mm_struct *mm);
+
+static inline bool mpol_is_preferred_many(struct mempolicy *pol)
+{
+	return  (pol->mode == MPOL_PREFERRED_MANY);
+}
+
+extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone);
+
 #else
 
 struct mempolicy {};
@@ -315,9 +321,9 @@ static inline void mpol_put_task_policy(struct task_struct *task)
 {
 }
 
-static inline nodemask_t *policy_nodemask_current(gfp_t gfp)
+static inline bool mpol_is_preferred_many(struct mempolicy *pol)
 {
-	return NULL;
+	return  false;
 }
 #endif /* CONFIG_NUMA */
 #endif

include/linux/syscalls.h

@@ -1039,6 +1039,9 @@ asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr _
 asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type,
 		const void __user *rule_attr, __u32 flags);
 asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags);
+asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
+					    unsigned long home_node,
+					    unsigned long flags);
 
 /*
  * Architecture-specific system calls

include/uapi/asm-generic/unistd.h

@@ -878,8 +878,8 @@ __SYSCALL(__NR_kabi_reserved447, sys_ni_syscall)
 __SYSCALL(__NR_kabi_reserved448, sys_ni_syscall)
 #define __NR_kabi_reserved449 449
 __SYSCALL(__NR_kabi_reserved449, sys_ni_syscall)
-#define __NR_kabi_reserved450 450
-__SYSCALL(__NR_kabi_reserved450, sys_ni_syscall)
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 #define __NR_kabi_reserved451 451
 __SYSCALL(__NR_kabi_reserved451, sys_ni_syscall)
 #define __NR_kabi_reserved452 452

include/uapi/linux/mempolicy.h

@@ -22,6 +22,7 @@ enum {
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
 	MPOL_LOCAL,
+	MPOL_PREFERRED_MANY,
 	MPOL_MAX,	/* always last member of enum */
 };
 
@@ -58,7 +59,6 @@ enum {
  * are never OR'ed into the mode in mempolicy API arguments.
  */
 #define MPOL_F_SHARED  (1 << 0)	/* identify shared policies */
-#define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
 #define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
 #define MPOL_F_MORON	(1 << 4) /* Migrate On protnone Reference On Node */
 

kernel/sys_ni.c

@@ -298,6 +298,7 @@ COND_SYSCALL(migrate_pages);
 COND_SYSCALL_COMPAT(migrate_pages);
 COND_SYSCALL(move_pages);
 COND_SYSCALL_COMPAT(move_pages);
+COND_SYSCALL(set_mempolicy_home_node);
 
 COND_SYSCALL(perf_event_open);
 COND_SYSCALL(accept4);

mm/hugetlb.c

@@ -1154,7 +1154,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				unsigned long address, int avoid_reserve,
 				long chg)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	gfp_t gfp_mask;
 	nodemask_t *nodemask;
@@ -1175,7 +1175,19 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask, mpol);
+
+	if (mpol_is_preferred_many(mpol)) {
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask,
+						  mpol);
+
+		/* Fallback to all nodes if page==NULL */
+		nodemask = NULL;
+	}
+
+	if (!page)
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask,
+						  mpol);
+
 	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
 		SetHPageRestoreReserve(page);
 		h->resv_huge_pages--;
@@ -2200,16 +2212,26 @@ static
 struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	gfp_t gfp_mask = htlb_alloc_mask(h);
 	int nid;
 	nodemask_t *nodemask;
 
 	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
-	page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
-	mpol_cond_put(mpol);
+	if (mpol_is_preferred_many(mpol)) {
+		gfp_t gfp = gfp_mask | __GFP_NOWARN;
+
+		gfp &=  ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+		page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
+
+		/* Fallback to all nodes if page==NULL */
+		nodemask = NULL;
+	}
 
+	if (!page)
+		page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
+	mpol_cond_put(mpol);
 	return page;
 }
 
@@ -3850,19 +3872,35 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
+static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
+{
+#ifdef CONFIG_NUMA
+	struct mempolicy *mpol = get_task_policy(current);
+
+	/*
+	 * Only enforce MPOL_BIND policy which overlaps with cpuset policy
+	 * (from policy_nodemask) specifically for hugetlb case
+	 */
+	if (mpol->mode == MPOL_BIND &&
+		(apply_policy_zone(mpol, gfp_zone(gfp)) &&
+		 cpuset_nodemask_valid_mems_allowed(&mpol->v.nodes)))
+		return &mpol->v.nodes;
+#endif
+	return NULL;
+}
+
 static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;
 	unsigned int nr = 0;
-	nodemask_t *mpol_allowed;
+	nodemask_t *mbind_nodemask;
 	unsigned int *array = h->free_huge_pages_node;
 	gfp_t gfp_mask = htlb_alloc_mask(h);
 
-	mpol_allowed = policy_nodemask_current(gfp_mask);
-
+	mbind_nodemask = policy_mbind_nodemask(gfp_mask);
 	for_each_node_mask(node, cpuset_current_mems_allowed) {
-		if (!mpol_allowed ||
-		    (mpol_allowed && node_isset(node, *mpol_allowed)))
+		if (!mbind_nodemask ||
+		    (mbind_nodemask && node_isset(node, *mbind_nodemask)))
 			nr += array[node];
 	}
 

tools/include/uapi/asm-generic/unistd.h

@@ -878,8 +878,8 @@ __SYSCALL(__NR_kabi_reserved447, sys_ni_syscall)
 __SYSCALL(__NR_kabi_reserved448, sys_ni_syscall)
 #define __NR_kabi_reserved449 449
 __SYSCALL(__NR_kabi_reserved449, sys_ni_syscall)
-#define __NR_kabi_reserved450 450
-__SYSCALL(__NR_kabi_reserved450, sys_ni_syscall)
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 #define __NR_kabi_reserved451 451
 __SYSCALL(__NR_kabi_reserved451, sys_ni_syscall)
 #define __NR_kabi_reserved452 452
@@ -893,6 +893,9 @@ __SYSCALL(__NR_kabi_reserved455, sys_ni_syscall)
 #define __NR_kabi_reserved456 456
 __SYSCALL(__NR_kabi_reserved456, sys_ni_syscall)
 
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+
 #undef __NR_syscalls
 #define __NR_syscalls 457
 

tools/perf/arch/powerpc/entry/syscalls/syscall.tbl

@@ -539,7 +539,7 @@
 447	common	kabi_reserved447		sys_ni_syscall
 448	common	kabi_reserved448		sys_ni_syscall
 449	common	kabi_reserved449		sys_ni_syscall
-450	common	kabi_reserved450		sys_ni_syscall
+450	nospu	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	common	kabi_reserved451		sys_ni_syscall
 452	common	kabi_reserved452		sys_ni_syscall
 453	common	kabi_reserved453		sys_ni_syscall

tools/perf/arch/s390/entry/syscalls/syscall.tbl

@@ -388,3 +388,4 @@
 378  common	s390_guarded_storage	sys_s390_guarded_storage	compat_sys_s390_guarded_storage
 379  common	statx			sys_statx			compat_sys_statx
 380  common	s390_sthyi		sys_s390_sthyi			compat_sys_s390_sthyi
+450  common	set_mempolicy_home_node	sys_set_mempolicy_home_node	sys_set_mempolicy_home_node
\ No newline at end of file

tools/perf/arch/x86/entry/syscalls/syscall_64.tbl

@@ -371,7 +371,7 @@
 447	common	kabi_reserved447	sys_ni_syscall
 448	common	kabi_reserved448	sys_ni_syscall
 449	common	kabi_reserved449	sys_ni_syscall
-450	common	kabi_reserved450	sys_ni_syscall
+450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	common	kabi_reserved451	sys_ni_syscall
 452	common	kabi_reserved452	sys_ni_syscall
 453	common	kabi_reserved453	sys_ni_syscall