Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Peter Xu <peterx@redhat.com>
To:     linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc:     Mike Kravetz <mike.kravetz@oracle.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        David Hildenbrand <david@redhat.com>,
        Matthew Wilcox <willy@infradead.org>, peterx@redhat.com,
        Alistair Popple <apopple@nvidia.com>,
        Nadav Amit <nadav.amit@gmail.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        "Kirill A . Shutemov" <kirill@shutemov.name>,
        Hugh Dickins <hughd@google.com>,
        Jerome Glisse <jglisse@redhat.com>,
        Mike Rapoport <rppt@linux.vnet.ibm.com>
Subject: [PATCH v8 01/23] mm: Introduce PTE_MARKER swap entry
Date:   Mon,  4 Apr 2022 21:46:24 -0400
Message-Id: <20220405014646.13522-2-peterx@redhat.com>
In-Reply-To: <20220405014646.13522-1-peterx@redhat.com>
References: <20220405014646.13522-1-peterx@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This patch introduces a new swap entry type called PTE_MARKER.  It can be
installed for any pte that maps a file-backed memory when the pte is
temporarily zapped, so as to maintain per-pte information.

The information that kept in the pte is called a "marker".  Here we define the
marker as "unsigned long" just to match pgoff_t, however it will only work if
it still fits in swp_offset(), which is e.g. currently 58 bits on x86_64.

A new config CONFIG_PTE_MARKER is introduced too; it's by default off.  A bunch
of helpers are defined altogether to service the rest of the pte marker code.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/asm-generic/hugetlb.h |  9 ++++
 include/linux/swap.h          | 15 ++++++-
 include/linux/swapops.h       | 78 +++++++++++++++++++++++++++++++++++
 mm/Kconfig                    |  6 +++
 4 files changed, 107 insertions(+), 1 deletion(-)

diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 8e1e6244a89d..f39cad20ffc6 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -2,6 +2,9 @@
 #ifndef _ASM_GENERIC_HUGETLB_H
 #define _ASM_GENERIC_HUGETLB_H
 
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
 static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
 {
 	return mk_pte(page, pgprot);
@@ -80,6 +83,12 @@ static inline int huge_pte_none(pte_t pte)
 }
 #endif
 
+/* Please refer to comments above pte_none_mostly() for the usage */
+static inline int huge_pte_none_mostly(pte_t pte)
+{
+	return huge_pte_none(pte) || is_pte_marker(pte);
+}
+
 #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7daae5a4b3e1..5553189d0215 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -55,6 +55,19 @@ static inline int current_is_kswapd(void)
  * actions on faults.
  */
 
+/*
+ * PTE markers are used to persist information onto PTEs that are mapped with
+ * file-backed memories.  As its name "PTE" hints, it should only be applied to
+ * the leaves of pgtables.
+ */
+#ifdef CONFIG_PTE_MARKER
+#define SWP_PTE_MARKER_NUM 1
+#define SWP_PTE_MARKER     (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
+			    SWP_MIGRATION_NUM + SWP_DEVICE_NUM)
+#else
+#define SWP_PTE_MARKER_NUM 0
+#endif
+
 /*
  * Unaddressable device memory support. See include/linux/hmm.h and
  * Documentation/vm/hmm.rst. Short description is we need struct pages for
@@ -107,7 +120,7 @@ static inline int current_is_kswapd(void)
 
 #define MAX_SWAPFILES \
 	((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
-	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
+	SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM)
 
 /*
  * Magic header for a swap area. The first part of the union is
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 32d517a28969..7a00627845f0 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -274,6 +274,84 @@ static inline int is_readable_migration_entry(swp_entry_t entry)
 
 #endif
 
+typedef unsigned long pte_marker;
+
+#define  PTE_MARKER_MASK     (0)
+
+#ifdef CONFIG_PTE_MARKER
+
+static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
+{
+	return swp_entry(SWP_PTE_MARKER, marker);
+}
+
+static inline bool is_pte_marker_entry(swp_entry_t entry)
+{
+	return swp_type(entry) == SWP_PTE_MARKER;
+}
+
+static inline pte_marker pte_marker_get(swp_entry_t entry)
+{
+	return swp_offset(entry) & PTE_MARKER_MASK;
+}
+
+static inline bool is_pte_marker(pte_t pte)
+{
+	return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte));
+}
+
+#else /* CONFIG_PTE_MARKER */
+
+static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
+{
+	/* This should never be called if !CONFIG_PTE_MARKER */
+	WARN_ON_ONCE(1);
+	return swp_entry(0, 0);
+}
+
+static inline bool is_pte_marker_entry(swp_entry_t entry)
+{
+	return false;
+}
+
+static inline pte_marker pte_marker_get(swp_entry_t entry)
+{
+	return 0;
+}
+
+static inline bool is_pte_marker(pte_t pte)
+{
+	return false;
+}
+
+#endif /* CONFIG_PTE_MARKER */
+
+static inline pte_t make_pte_marker(pte_marker marker)
+{
+	return swp_entry_to_pte(make_pte_marker_entry(marker));
+}
+
+/*
+ * This is a special version to check pte_none() just to cover the case when
+ * the pte is a pte marker.  It existed because in many cases the pte marker
+ * should be seen as a none pte; it's just that we have stored some information
+ * onto the none pte so it becomes not-none any more.
+ *
+ * It should be used when the pte is file-backed, ram-based and backing
+ * userspace pages, like shmem.  It is not needed upon pgtables that do not
+ * support pte markers at all.  For example, it's not needed on anonymous
+ * memory, kernel-only memory (including when the system is during-boot),
+ * non-ram based generic file-system.  It's fine to be used even there, but the
+ * extra pte marker check will be pure overhead.
+ *
+ * For systems configured with !CONFIG_PTE_MARKER this will be automatically
+ * optimized to pte_none().
+ */
+static inline int pte_none_mostly(pte_t pte)
+{
+	return pte_none(pte) || is_pte_marker(pte);
+}
+
 static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
 {
 	struct page *p = pfn_to_page(swp_offset(entry));
diff --git a/mm/Kconfig b/mm/Kconfig
index 034d87953600..a1688b9314b2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -909,6 +909,12 @@ config ANON_VMA_NAME
 	  area from being merged with adjacent virtual memory areas due to the
 	  difference in their name.
 
+config PTE_MARKER
+	bool "Marker PTEs support"
+
+	help
+	  Allows to create marker PTEs for file-backed memory.
+
 source "mm/damon/Kconfig"
 
 endmenu
-- 
2.32.0