8 files changed, 147 insertions, 64 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c
index cd89e956c322..b0d4e1908b22 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -416,7 +416,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
 #ifdef CONFIG_KALLSYMS
 /*
  * Provides a wchan file via kallsyms in a proper one-value-per-file format.
- * Returns the resolved symbol.  If that fails, simply return the address.
+ * Returns the resolved symbol to user space.
  */
 static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
@@ -1489,7 +1489,6 @@ static const struct file_operations proc_fail_nth_operations = {
 #endif
 
 
-#ifdef CONFIG_SCHED_DEBUG
 /*
  * Print out various scheduling related per-task fields:
  */
@@ -1539,8 +1538,6 @@ static const struct file_operations proc_pid_sched_operations = {
 	.release	= single_release,
 };
 
-#endif
-
 #ifdef CONFIG_SCHED_AUTOGROUP
 /*
  * Print out autogroup related information:
@@ -2497,11 +2494,9 @@ static const struct file_operations proc_map_files_operations = {
 
 #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
 struct timers_private {
-	struct pid *pid;
-	struct task_struct *task;
-	struct sighand_struct *sighand;
-	struct pid_namespace *ns;
-	unsigned long flags;
+	struct pid		*pid;
+	struct task_struct	*task;
+	struct pid_namespace	*ns;
 };
 
 static void *timers_start(struct seq_file *m, loff_t *pos)
@@ -2512,54 +2507,48 @@ static void *timers_start(struct seq_file *m, loff_t *pos)
 	if (!tp->task)
 		return ERR_PTR(-ESRCH);
 
-	tp->sighand = lock_task_sighand(tp->task, &tp->flags);
-	if (!tp->sighand)
-		return ERR_PTR(-ESRCH);
-
-	return seq_hlist_start(&tp->task->signal->posix_timers, *pos);
+	rcu_read_lock();
+	return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos);
 }
 
 static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct timers_private *tp = m->private;
-	return seq_hlist_next(v, &tp->task->signal->posix_timers, pos);
+
+	return seq_hlist_next_rcu(v, &tp->task->signal->posix_timers, pos);
 }
 
 static void timers_stop(struct seq_file *m, void *v)
 {
 	struct timers_private *tp = m->private;
 
-	if (tp->sighand) {
-		unlock_task_sighand(tp->task, &tp->flags);
-		tp->sighand = NULL;
-	}
-
 	if (tp->task) {
 		put_task_struct(tp->task);
 		tp->task = NULL;
+		rcu_read_unlock();
 	}
 }
 
 static int show_timer(struct seq_file *m, void *v)
 {
-	struct k_itimer *timer;
-	struct timers_private *tp = m->private;
-	int notify;
 	static const char * const nstr[] = {
-		[SIGEV_SIGNAL] = "signal",
-		[SIGEV_NONE] = "none",
-		[SIGEV_THREAD] = "thread",
+		[SIGEV_SIGNAL]	= "signal",
+		[SIGEV_NONE]	= "none",
+		[SIGEV_THREAD]	= "thread",
 	};
 
-	timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list);
-	notify = timer->it_sigev_notify;
+	struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list);
+	struct timers_private *tp = m->private;
+	int notify = timer->it_sigev_notify;
+
+	guard(spinlock_irq)(&timer->it_lock);
+	if (!posixtimer_valid(timer))
+		return 0;
 
 	seq_printf(m, "ID: %d\n", timer->it_id);
-	seq_printf(m, "signal: %d/%px\n",
-		   timer->sigq.info.si_signo,
+	seq_printf(m, "signal: %d/%px\n", timer->sigq.info.si_signo,
 		   timer->sigq.info.si_value.sival_ptr);
-	seq_printf(m, "notify: %s/%s.%d\n",
-		   nstr[notify & ~SIGEV_THREAD_ID],
+	seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID],
 		   (notify & SIGEV_THREAD_ID) ? "tid" : "pid",
 		   pid_nr_ns(timer->it_pid, tp->ns));
 	seq_printf(m, "ClockID: %d\n", timer->it_clock);
@@ -3331,9 +3320,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	ONE("status",     S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
 	ONE("limits",	  S_IRUGO, proc_pid_limits),
-#ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
-#endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
 #endif
@@ -3682,9 +3669,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	ONE("status",    S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
 	ONE("limits",	 S_IRUGO, proc_pid_limits),
-#ifdef CONFIG_SCHED_DEBUG
 	REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
-#endif
 	NOD("comm",      S_IFREG|S_IRUGO|S_IWUSR,
 			 &proc_tid_comm_inode_operations,
 			 &proc_pid_set_comm_operations, {}),
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8ec90826a49e..a3e22803cddf 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -559,10 +559,16 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
 	return p;
 }
 
-static inline void pde_set_flags(struct proc_dir_entry *pde)
+static void pde_set_flags(struct proc_dir_entry *pde)
 {
 	if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
 		pde->flags |= PROC_ENTRY_PERMANENT;
+	if (pde->proc_ops->proc_read_iter)
+		pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+	if (pde->proc_ops->proc_compat_ioctl)
+		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
 }
 
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
@@ -626,6 +632,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
 	p->proc_ops = &proc_seq_ops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
+	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_seq_private);
@@ -656,6 +663,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
 		return NULL;
 	p->proc_ops = &proc_single_ops;
 	p->single_show = show;
+	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_single_data);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 626ad7bd94f2..a3eb3b740f76 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -656,13 +656,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
-		if (de->proc_ops->proc_read_iter)
+		if (pde_has_proc_read_iter(de))
 			inode->i_fop = &proc_iter_file_ops;
 		else
 			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-		if (de->proc_ops->proc_compat_ioctl) {
-			if (de->proc_ops->proc_read_iter)
+		if (pde_has_proc_compat_ioctl(de)) {
+			if (pde_has_proc_read_iter(de))
 				inode->i_fop = &proc_iter_file_ops_compat;
 			else
 				inode->i_fop = &proc_reg_file_ops_compat;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 1695509370b8..96122e91c645 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -85,6 +85,20 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde)
 	pde->flags |= PROC_ENTRY_PERMANENT;
 }
 
+static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_proc_read_iter;
+}
+
+static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
+{
+#ifdef CONFIG_COMPAT
+	return pde->flags & PROC_ENTRY_proc_compat_ioctl;
+#else
+	return false;
+#endif
+}
+
 extern struct kmem_cache *proc_dir_entry_cache;
 void pde_free(struct proc_dir_entry *pde);
 
@@ -143,6 +157,7 @@ unsigned name_to_int(const struct qstr *qstr);
 /* Worst case buffer size needed for holding an integer. */
 #define PROC_NUMBUF 13
 
+#ifdef CONFIG_PAGE_MAPCOUNT
 /**
  * folio_precise_page_mapcount() - Number of mappings of this folio page.
  * @folio: The folio.
@@ -173,7 +188,49 @@ static inline int folio_precise_page_mapcount(struct folio *folio,
 
 	return mapcount;
 }
+#else /* !CONFIG_PAGE_MAPCOUNT */
+static inline int folio_precise_page_mapcount(struct folio *folio,
+		struct page *page)
+{
+	BUILD_BUG();
+}
+#endif /* CONFIG_PAGE_MAPCOUNT */
 
+/**
+ * folio_average_page_mapcount() - Average number of mappings per page in this
+ *				   folio
+ * @folio: The folio.
+ *
+ * The average number of user page table entries that reference each page in
+ * this folio as tracked via the RMAP: either referenced directly (PTE) or
+ * as part of a larger area that covers this page (e.g., PMD).
+ *
+ * The average is calculated by rounding to the nearest integer; however,
+ * to avoid duplicated code in current callers, the average is at least
+ * 1 if any page of the folio is mapped.
+ *
+ * Returns: The average number of mappings per page in this folio.
+ */
+static inline int folio_average_page_mapcount(struct folio *folio)
+{
+	int mapcount, entire_mapcount, avg;
+
+	if (!folio_test_large(folio))
+		return atomic_read(&folio->_mapcount) + 1;
+
+	mapcount = folio_large_mapcount(folio);
+	if (unlikely(mapcount <= 0))
+		return 0;
+	entire_mapcount = folio_entire_mapcount(folio);
+	if (mapcount <= entire_mapcount)
+		return entire_mapcount;
+	mapcount -= entire_mapcount;
+
+	/* Round to closest integer ... */
+	avg = ((unsigned int)mapcount + folio_large_nr_pages(folio) / 2) >> folio_large_order(folio);
+	/* ... but return at least 1. */
+	return max_t(int, avg + entire_mapcount, 1);
+}
 /*
  * array.c
  */
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 1cb33771bf9f..728630b10fdf 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -34,8 +34,6 @@
 #include <asm/sections.h>
 #include "internal.h"
 
-#define CORE_STR "CORE"
-
 #ifndef ELF_CORE_EFLAGS
 #define ELF_CORE_EFLAGS	0
 #endif
@@ -122,7 +120,9 @@ static void update_kcore_size(void)
 
 	kcore_phdrs_len = kcore_nphdr * sizeof(struct elf_phdr);
 	kcore_notes_len = (4 * sizeof(struct elf_note) +
-			   3 * ALIGN(sizeof(CORE_STR), 4) +
+			   ALIGN(sizeof(NN_PRSTATUS), 4) +
+			   ALIGN(sizeof(NN_PRPSINFO), 4) +
+			   ALIGN(sizeof(NN_TASKSTRUCT), 4) +
 			   VMCOREINFO_NOTE_NAME_BYTES +
 			   ALIGN(sizeof(struct elf_prstatus), 4) +
 			   ALIGN(sizeof(struct elf_prpsinfo), 4) +
@@ -443,11 +443,11 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
 			goto out;
 		}
 
-		append_kcore_note(notes, &i, CORE_STR, NT_PRSTATUS, &prstatus,
+		append_kcore_note(notes, &i, NN_PRSTATUS, NT_PRSTATUS, &prstatus,
 				  sizeof(prstatus));
-		append_kcore_note(notes, &i, CORE_STR, NT_PRPSINFO, &prpsinfo,
+		append_kcore_note(notes, &i, NN_PRPSINFO, NT_PRPSINFO, &prpsinfo,
 				  sizeof(prpsinfo));
-		append_kcore_note(notes, &i, CORE_STR, NT_TASKSTRUCT, current,
+		append_kcore_note(notes, &i, NN_TASKSTRUCT, NT_TASKSTRUCT, current,
 				  arch_task_struct_size);
 		/*
 		 * vmcoreinfo_size is mostly constant after init time, but it
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 8ba9b1472390..83be312159c9 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -162,6 +162,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "Unaccepted:     ",
 		    global_zone_page_state(NR_UNACCEPTED));
 #endif
+	show_val_kb(m, "Balloon:        ",
+		    global_node_page_state(NR_BALLOON_PAGES));
 
 	hugetlb_report_meminfo(m);
 
diff --git a/fs/proc/page.c b/fs/proc/page.c
index a55f5acefa97..23fc771100ae 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -67,9 +67,14 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 		 * memmaps that were actually initialized.
 		 */
 		page = pfn_to_online_page(pfn);
-		if (page)
-			mapcount = folio_precise_page_mapcount(page_folio(page),
-							       page);
+		if (page) {
+			struct folio *folio = page_folio(page);
+
+			if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+				mapcount = folio_precise_page_mapcount(folio, page);
+			else
+				mapcount = folio_average_page_mapcount(folio);
+		}
 
 		if (put_user(mapcount, out)) {
 			ret = -EFAULT;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f02cd362309a..994cde10e3f4 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -707,6 +707,8 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	struct folio *folio = page_folio(page);
 	int i, nr = compound ? compound_nr(page) : 1;
 	unsigned long size = nr * PAGE_SIZE;
+	bool exclusive;
+	int mapcount;
 
 	/*
 	 * First accumulate quantities that depend only on |size| and the type
@@ -747,18 +749,29 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 				      dirty, locked, present);
 		return;
 	}
+
+	if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) {
+		mapcount = folio_average_page_mapcount(folio);
+		exclusive = !folio_maybe_mapped_shared(folio);
+	}
+
 	/*
 	 * We obtain a snapshot of the mapcount. Without holding the folio lock
 	 * this snapshot can be slightly wrong as we cannot always read the
 	 * mapcount atomically.
 	 */
 	for (i = 0; i < nr; i++, page++) {
-		int mapcount = folio_precise_page_mapcount(folio, page);
 		unsigned long pss = PAGE_SIZE << PSS_SHIFT;
+
+		if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) {
+			mapcount = folio_precise_page_mapcount(folio, page);
+			exclusive = mapcount < 2;
+		}
+
 		if (mapcount >= 2)
 			pss /= mapcount;
 		smaps_page_accumulate(mss, folio, PAGE_SIZE, pss,
-				dirty, locked, mapcount < 2);
+				dirty, locked, exclusive);
 	}
 }
 
@@ -1023,7 +1036,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
 
 	if (folio) {
 		/* We treat non-present entries as "maybe shared". */
-		if (!present || folio_likely_mapped_shared(folio) ||
+		if (!present || folio_maybe_mapped_shared(folio) ||
 		    hugetlb_pmd_shared(pte))
 			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
 		else
@@ -1632,6 +1645,7 @@ struct pagemapread {
 #define PM_SOFT_DIRTY		BIT_ULL(55)
 #define PM_MMAP_EXCLUSIVE	BIT_ULL(56)
 #define PM_UFFD_WP		BIT_ULL(57)
+#define PM_GUARD_REGION		BIT_ULL(58)
 #define PM_FILE			BIT_ULL(61)
 #define PM_SWAP			BIT_ULL(62)
 #define PM_PRESENT		BIT_ULL(63)
@@ -1651,6 +1665,13 @@ static int add_to_pagemap(pagemap_entry_t *pme, struct pagemapread *pm)
 	return 0;
 }
 
+static bool __folio_page_mapped_exclusively(struct folio *folio, struct page *page)
+{
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		return folio_precise_page_mapcount(folio, page) == 1;
+	return !folio_maybe_mapped_shared(folio);
+}
+
 static int pagemap_pte_hole(unsigned long start, unsigned long end,
 			    __always_unused int depth, struct mm_walk *walk)
 {
@@ -1732,6 +1753,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 			page = pfn_swap_entry_to_page(entry);
 		if (pte_marker_entry_uffd_wp(entry))
 			flags |= PM_UFFD_WP;
+		if (is_guard_swp_entry(entry))
+			flags |=  PM_GUARD_REGION;
 	}
 
 	if (page) {
@@ -1739,7 +1762,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 		if (!folio_test_anon(folio))
 			flags |= PM_FILE;
 		if ((flags & PM_PRESENT) &&
-		    folio_precise_page_mapcount(folio, page) == 1)
+		    __folio_page_mapped_exclusively(folio, page))
 			flags |= PM_MMAP_EXCLUSIVE;
 	}
 	if (vma->vm_flags & VM_SOFTDIRTY)
@@ -1814,7 +1837,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			pagemap_entry_t pme;
 
 			if (folio && (flags & PM_PRESENT) &&
-			    folio_precise_page_mapcount(folio, page + idx) == 1)
+			    __folio_page_mapped_exclusively(folio, page))
 				cur_flags |= PM_MMAP_EXCLUSIVE;
 
 			pme = make_pme(frame, cur_flags);
@@ -1879,7 +1902,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
 		if (!folio_test_anon(folio))
 			flags |= PM_FILE;
 
-		if (!folio_likely_mapped_shared(folio) &&
+		if (!folio_maybe_mapped_shared(folio) &&
 		    !hugetlb_pmd_shared(ptep))
 			flags |= PM_MMAP_EXCLUSIVE;
 
@@ -1931,7 +1954,8 @@ static const struct mm_walk_ops pagemap_ops = {
  * Bit  55    pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst)
  * Bit  56    page exclusively mapped
  * Bit  57    pte is uffd-wp write-protected
- * Bits 58-60 zero
+ * Bit  58    pte is a guard region
+ * Bits 59-60 zero
  * Bit  61    page is file-page or shared-anon
  * Bit  62    page swapped
  * Bit  63    page present
@@ -2455,22 +2479,19 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
 	spinlock_t *ptl;
 	int ret;
 
-	arch_enter_lazy_mmu_mode();
-
 	ret = pagemap_scan_thp_entry(pmd, start, end, walk);
-	if (ret != -ENOENT) {
-		arch_leave_lazy_mmu_mode();
+	if (ret != -ENOENT)
 		return ret;
-	}
 
 	ret = 0;
 	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
 	if (!pte) {
-		arch_leave_lazy_mmu_mode();
 		walk->action = ACTION_AGAIN;
 		return 0;
 	}
 
+	arch_enter_lazy_mmu_mode();
+
 	if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
 		/* Fast path for performing exclusive WP */
 		for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
@@ -2539,8 +2560,8 @@ flush_and_return:
 	if (flush_end)
 		flush_tlb_range(vma, start, addr);
 
-	pte_unmap_unlock(start_pte, ptl);
 	arch_leave_lazy_mmu_mode();
+	pte_unmap_unlock(start_pte, ptl);
 
 	cond_resched();
 	return ret;
@@ -2855,7 +2876,12 @@ static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
 			unsigned long nr_pages)
 {
 	struct folio *folio = page_folio(page);
-	int count = folio_precise_page_mapcount(folio, page);
+	int count;
+
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		count = folio_precise_page_mapcount(folio, page);
+	else
+		count = folio_average_page_mapcount(folio);
 
 	md->pages += nr_pages;
 	if (pte_dirty || folio_test_dirty(folio))