1 files changed, 100 insertions, 150 deletions

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 9223856c934b..999af26c7298 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -22,6 +22,12 @@
 #define KPMMASK (KPMSIZE - 1)
 #define KPMBITS (KPMSIZE * BITS_PER_BYTE)
 
+enum kpage_operation {
+	KPAGE_FLAGS,
+	KPAGE_COUNT,
+	KPAGE_CGROUP,
+};
+
 static inline unsigned long get_max_dump_pfn(void)
 {
 #ifdef CONFIG_SPARSEMEM
@@ -37,21 +43,17 @@ static inline unsigned long get_max_dump_pfn(void)
 #endif
 }
 
-/* /proc/kpagecount - an array exposing page counts
- *
- * Each entry is a u64 representing the corresponding
- * physical page count.
- */
-static ssize_t kpagecount_read(struct file *file, char __user *buf,
-			     size_t count, loff_t *ppos)
+static ssize_t kpage_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos,
+		enum kpage_operation op)
 {
 	const unsigned long max_dump_pfn = get_max_dump_pfn();
 	u64 __user *out = (u64 __user *)buf;
-	struct page *ppage;
+	struct page *page;
 	unsigned long src = *ppos;
 	unsigned long pfn;
 	ssize_t ret = 0;
-	u64 pcount;
+	u64 info;
 
 	pfn = src / KPMSIZE;
 	if (src & KPMMASK || count & KPMMASK)
@@ -65,14 +67,30 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 		 * TODO: ZONE_DEVICE support requires to identify
 		 * memmaps that were actually initialized.
 		 */
-		ppage = pfn_to_online_page(pfn);
-
-		if (!ppage)
-			pcount = 0;
-		else
-			pcount = page_mapcount(ppage);
-
-		if (put_user(pcount, out)) {
+		page = pfn_to_online_page(pfn);
+
+		if (page) {
+			switch (op) {
+			case KPAGE_FLAGS:
+				info = stable_page_flags(page);
+				break;
+			case KPAGE_COUNT:
+				if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+					info = folio_precise_page_mapcount(page_folio(page), page);
+				else
+					info = folio_average_page_mapcount(page_folio(page));
+				break;
+			case KPAGE_CGROUP:
+				info = page_cgroup_ino(page);
+				break;
+			default:
+				info = 0;
+				break;
+			}
+		} else
+			info = 0;
+
+		if (put_user(info, out)) {
 			ret = -EFAULT;
 			break;
 		}
@@ -90,27 +108,36 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 	return ret;
 }
 
+/* /proc/kpagecount - an array exposing page mapcounts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page mapcount.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_COUNT);
+}
+
 static const struct proc_ops kpagecount_proc_ops = {
 	.proc_flags	= PROC_ENTRY_PERMANENT,
 	.proc_lseek	= mem_lseek,
 	.proc_read	= kpagecount_read,
 };
 
-/* /proc/kpageflags - an array exposing page flags
- *
- * Each entry is a u64 representing the corresponding
- * physical page flags.
- */
 
 static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
 {
 	return ((kflags >> kbit) & 1) << ubit;
 }
 
-u64 stable_page_flags(struct page *page)
+u64 stable_page_flags(const struct page *page)
 {
-	u64 k;
-	u64 u;
+	const struct folio *folio;
+	unsigned long k;
+	unsigned long mapping;
+	bool is_anon;
+	u64 u = 0;
 
 	/*
 	 * pseudo flag: KPF_NOPAGE
@@ -118,48 +145,43 @@ u64 stable_page_flags(struct page *page)
 	 */
 	if (!page)
 		return 1 << KPF_NOPAGE;
+	folio = page_folio(page);
 
-	k = page->flags;
-	u = 0;
+	k = folio->flags;
+	mapping = (unsigned long)folio->mapping;
+	is_anon = mapping & PAGE_MAPPING_ANON;
 
 	/*
 	 * pseudo flags for the well known (anonymous) memory mapped pages
 	 */
 	if (page_mapped(page))
 		u |= 1 << KPF_MMAP;
-	if (PageAnon(page))
+	if (is_anon) {
 		u |= 1 << KPF_ANON;
-	if (PageKsm(page))
-		u |= 1 << KPF_KSM;
+		if (mapping & PAGE_MAPPING_KSM)
+			u |= 1 << KPF_KSM;
+	}
 
 	/*
 	 * compound pages: export both head/tail info
 	 * they together define a compound page's start/end pos and order
 	 */
-	if (PageHead(page))
-		u |= 1 << KPF_COMPOUND_HEAD;
-	if (PageTail(page))
+	if (page == &folio->page)
+		u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);
+	else
 		u |= 1 << KPF_COMPOUND_TAIL;
-	if (PageHuge(page))
+	if (folio_test_hugetlb(folio))
 		u |= 1 << KPF_HUGE;
-	/*
-	 * PageTransCompound can be true for non-huge compound pages (slab
-	 * pages or pages allocated by drivers with __GFP_COMP) because it
-	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
-	 * to make sure a given page is a thp, not a non-huge compound page.
-	 */
-	else if (PageTransCompound(page)) {
-		struct page *head = compound_head(page);
-
-		if (PageLRU(head) || PageAnon(head))
-			u |= 1 << KPF_THP;
-		else if (is_huge_zero_page(head)) {
-			u |= 1 << KPF_ZERO_PAGE;
-			u |= 1 << KPF_THP;
-		}
-	} else if (is_zero_pfn(page_to_pfn(page)))
+	else if (folio_test_large(folio) &&
+	         folio_test_large_rmappable(folio)) {
+		/* Note: we indicate any THPs here, not just PMD-sized ones */
+		u |= 1 << KPF_THP;
+	} else if (is_huge_zero_folio(folio)) {
 		u |= 1 << KPF_ZERO_PAGE;
-
+		u |= 1 << KPF_THP;
+	} else if (is_zero_folio(folio)) {
+		u |= 1 << KPF_ZERO_PAGE;
+	}
 
 	/*
 	 * Caveats on high order pages: PG_buddy and PG_slab will only be set
@@ -174,17 +196,17 @@ u64 stable_page_flags(struct page *page)
 		u |= 1 << KPF_OFFLINE;
 	if (PageTable(page))
 		u |= 1 << KPF_PGTABLE;
+	if (folio_test_slab(folio))
+		u |= 1 << KPF_SLAB;
 
-	if (page_is_idle(page))
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
+	u |= kpf_copy_bit(k, KPF_IDLE,          PG_idle);
+#else
+	if (folio_test_idle(folio))
 		u |= 1 << KPF_IDLE;
+#endif
 
 	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
-
-	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
-	if (PageTail(page) && PageSlab(page))
-		u |= 1 << KPF_SLAB;
-
-	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
 	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
 	u |= kpf_copy_bit(k, KPF_UPTODATE,	PG_uptodate);
 	u |= kpf_copy_bit(k, KPF_WRITEBACK,	PG_writeback);
@@ -194,7 +216,8 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
 	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);
 
-	if (PageSwapCache(page))
+#define SWAPCACHE ((1 << PG_swapbacked) | (1 << PG_swapcache))
+	if ((k & SWAPCACHE) == SWAPCACHE)
 		u |= 1 << KPF_SWAPCACHE;
 	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);
 
@@ -202,67 +225,37 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_MLOCKED,	PG_mlocked);
 
 #ifdef CONFIG_MEMORY_FAILURE
-	u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
-#endif
-
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
-	u |= kpf_copy_bit(k, KPF_UNCACHED,	PG_uncached);
+	if (u & (1 << KPF_HUGE))
+		u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
+	else
+		u |= kpf_copy_bit(page->flags, KPF_HWPOISON,	PG_hwpoison);
 #endif
 
 	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);
-	u |= kpf_copy_bit(k, KPF_MAPPEDTODISK,	PG_mappedtodisk);
+	u |= kpf_copy_bit(k, KPF_OWNER_2,	PG_owner_2);
 	u |= kpf_copy_bit(k, KPF_PRIVATE,	PG_private);
 	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
 	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
 	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
-#ifdef CONFIG_ARCH_USES_PG_ARCH_X
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
 	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
 	u |= kpf_copy_bit(k, KPF_ARCH_3,	PG_arch_3);
 #endif
 
 	return u;
-};
+}
 
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
 static ssize_t kpageflags_read(struct file *file, char __user *buf,
-			     size_t count, loff_t *ppos)
+		size_t count, loff_t *ppos)
 {
-	const unsigned long max_dump_pfn = get_max_dump_pfn();
-	u64 __user *out = (u64 __user *)buf;
-	struct page *ppage;
-	unsigned long src = *ppos;
-	unsigned long pfn;
-	ssize_t ret = 0;
-
-	pfn = src / KPMSIZE;
-	if (src & KPMMASK || count & KPMMASK)
-		return -EINVAL;
-	if (src >= max_dump_pfn * KPMSIZE)
-		return 0;
-	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
-
-	while (count > 0) {
-		/*
-		 * TODO: ZONE_DEVICE support requires to identify
-		 * memmaps that were actually initialized.
-		 */
-		ppage = pfn_to_online_page(pfn);
-
-		if (put_user(stable_page_flags(ppage), out)) {
-			ret = -EFAULT;
-			break;
-		}
-
-		pfn++;
-		out++;
-		count -= KPMSIZE;
-
-		cond_resched();
-	}
-
-	*ppos += (char __user *)out - buf;
-	if (!ret)
-		ret = (char __user *)out - buf;
-	return ret;
+	return kpage_read(file, buf, count, ppos, KPAGE_FLAGS);
 }
 
 static const struct proc_ops kpageflags_proc_ops = {
@@ -273,53 +266,10 @@ static const struct proc_ops kpageflags_proc_ops = {
 
 #ifdef CONFIG_MEMCG
 static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
-				size_t count, loff_t *ppos)
+		size_t count, loff_t *ppos)
 {
-	const unsigned long max_dump_pfn = get_max_dump_pfn();
-	u64 __user *out = (u64 __user *)buf;
-	struct page *ppage;
-	unsigned long src = *ppos;
-	unsigned long pfn;
-	ssize_t ret = 0;
-	u64 ino;
-
-	pfn = src / KPMSIZE;
-	if (src & KPMMASK || count & KPMMASK)
-		return -EINVAL;
-	if (src >= max_dump_pfn * KPMSIZE)
-		return 0;
-	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
-
-	while (count > 0) {
-		/*
-		 * TODO: ZONE_DEVICE support requires to identify
-		 * memmaps that were actually initialized.
-		 */
-		ppage = pfn_to_online_page(pfn);
-
-		if (ppage)
-			ino = page_cgroup_ino(ppage);
-		else
-			ino = 0;
-
-		if (put_user(ino, out)) {
-			ret = -EFAULT;
-			break;
-		}
-
-		pfn++;
-		out++;
-		count -= KPMSIZE;
-
-		cond_resched();
-	}
-
-	*ppos += (char __user *)out - buf;
-	if (!ret)
-		ret = (char __user *)out - buf;
-	return ret;
+	return kpage_read(file, buf, count, ppos, KPAGE_CGROUP);
 }
-
 static const struct proc_ops kpagecgroup_proc_ops = {
 	.proc_flags	= PROC_ENTRY_PERMANENT,
 	.proc_lseek	= mem_lseek,