Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "190 patches.

  Subsystems affected by this patch series: mm (hugetlb, userfaultfd,
  vmscan, kconfig, proc, z3fold, zbud, ras, mempolicy, memblock,
  migration, thp, nommu, kconfig, madvise, memory-hotplug, zswap,
  zsmalloc, zram, cleanups, kfence, and hmm), procfs, sysctl, misc,
  core-kernel, lib, lz4, checkpatch, init, kprobes, nilfs2, hfs,
  signals, exec, kcov, selftests, compress/decompress, and ipc"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (190 commits)
  ipc/util.c: use binary search for max_idx
  ipc/sem.c: use READ_ONCE()/WRITE_ONCE() for use_global_lock
  ipc: use kmalloc for msg_queue and shmid_kernel
  ipc sem: use kvmalloc for sem_undo allocation
  lib/decompressors: remove set but not used variabled 'level'
  selftests/vm/pkeys: exercise x86 XSAVE init state
  selftests/vm/pkeys: refill shadow register after implicit kernel write
  selftests/vm/pkeys: handle negative sys_pkey_alloc() return code
  selftests/vm/pkeys: fix alloc_random_pkey() to make it really, really random
  kcov: add __no_sanitize_coverage to fix noinstr for all architectures
  exec: remove checks in __register_bimfmt()
  x86: signal: don't do sas_ss_reset() until we are certain that sigframe won't be abandoned
  hfsplus: report create_date to kstat.btime
  hfsplus: remove unnecessary oom message
  nilfs2: remove redundant continue statement in a while-loop
  kprobes: remove duplicated strong free_insn_page in x86 and s390
  init: print out unknown kernel parameters
  checkpatch: do not complain about positive return values starting with EPOLL
  checkpatch: improve the indented label test
  checkpatch: scripts/spdxcheck.py now requires python3
  ...

1 files changed, 38 insertions, 4 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8ba79dc64ab8..8e0f32f935bd 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -29,6 +29,23 @@ typedef struct { unsigned long pd; } hugepd_t;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+/*
+ * For HugeTLB page, there are more metadata to save in the struct page. But
+ * the head struct page cannot meet our needs, so we have to abuse other tail
+ * struct page to store the metadata. In order to avoid conflicts caused by
+ * subsequent use of more tail struct pages, we gather these discrete indexes
+ * of tail struct page here.
+ */
+enum {
+	SUBPAGE_INDEX_SUBPOOL = 1,	/* reuse page->private */
+#ifdef CONFIG_CGROUP_HUGETLB
+	SUBPAGE_INDEX_CGROUP,		/* reuse page->private */
+	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
+	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
+#endif
+	__NR_USED_SUBPAGE,
+};
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
@@ -515,12 +532,14 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
  *	modifications require hugetlb_lock.
  * HPG_freed - Set when page is on the free lists.
  *	Synchronization: hugetlb_lock held for examination and modification.
+ * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed.
  */
 enum hugetlb_page_flags {
 	HPG_restore_reserve = 0,
 	HPG_migratable,
 	HPG_temporary,
 	HPG_freed,
+	HPG_vmemmap_optimized,
 	__NR_HPAGEFLAGS,
 };
 
@@ -566,6 +585,7 @@ HPAGEFLAG(RestoreReserve, restore_reserve)
 HPAGEFLAG(Migratable, migratable)
 HPAGEFLAG(Temporary, temporary)
 HPAGEFLAG(Freed, freed)
+HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)
 
 #ifdef CONFIG_HUGETLB_PAGE
 
@@ -588,6 +608,9 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	unsigned int nr_free_vmemmap_pages;
+#endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
 	struct cftype cgroup_files_dfl[7];
@@ -635,13 +658,13 @@ extern unsigned int default_hstate_idx;
  */
 static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
 {
-	return (struct hugepage_subpool *)(hpage+1)->private;
+	return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL);
 }
 
 static inline void hugetlb_set_page_subpool(struct page *hpage,
 					struct hugepage_subpool *subpool)
 {
-	set_page_private(hpage+1, (unsigned long)subpool);
+	set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool);
 }
 
 static inline struct hstate *hstate_file(struct file *f)
@@ -718,8 +741,8 @@ static inline void arch_clear_hugepage_flags(struct page *page) { }
 #endif
 
 #ifndef arch_make_huge_pte
-static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
-				       struct page *page, int writable)
+static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
+				       vm_flags_t flags)
 {
 	return entry;
 }
@@ -875,6 +898,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage)
+{
+	return NULL;
+}
+
 static inline int isolate_or_dissolve_huge_page(struct page *page,
 						struct list_head *list)
 {
@@ -1028,6 +1056,12 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
 }
 #endif	/* CONFIG_HUGETLB_PAGE */
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+extern bool hugetlb_free_vmemmap_enabled;
+#else
+#define hugetlb_free_vmemmap_enabled	false
+#endif
+
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
 					struct mm_struct *mm, pte_t *pte)
 {