diff mbox series

[v2,3/8] x86/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE

Message ID 20220329164329.208407-4-david@redhat.com (mailing list archive)
State New, archived
Headers show
Series mm: COW fixes part 3: reliable GUP R/W FOLL_GET of anonymous pages | expand

Commit Message

David Hildenbrand March 29, 2022, 4:43 p.m. UTC
Let's use bit 3 to remember PG_anon_exclusive in swap ptes.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 arch/x86/include/asm/pgtable.h       | 16 ++++++++++++++++
 arch/x86/include/asm/pgtable_64.h    |  4 +++-
 arch/x86/include/asm/pgtable_types.h |  5 +++++
 3 files changed, 24 insertions(+), 1 deletion(-)

Comments

David Hildenbrand April 19, 2022, 12:46 p.m. UTC | #1
On 29.03.22 18:43, David Hildenbrand wrote:
> Let's use bit 3 to remember PG_anon_exclusive in swap ptes.
> 
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---

Looks like I ignored that 32bit uses a different (undocumented) swap layout
and bit 3 falls into the swp type. We'll restrict this to x86-64 for now, just
like for the other architectures.

The following seems to fly. @Andrew, let me know if you prefer a v3.


From bafb5ba914e89ad20c46f4e841a36909e610b81e Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 9 Mar 2022 09:47:29 +0100
Subject: [PATCH] x86/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on x86_64

Let's use bit 3 to remember PG_anon_exclusive in swap ptes.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 arch/x86/include/asm/pgtable.h          | 17 +++++++++++++++++
 arch/x86/include/asm/pgtable_64.h       |  4 +++-
 arch/x86/include/asm/pgtable_64_types.h |  5 +++++
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 62ab07e24aef..a1c555abed26 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1291,6 +1291,23 @@ static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
 		unsigned long addr, pud_t *pud)
 {
 }
+#ifdef _PAGE_SWP_EXCLUSIVE
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE);
+}
+#endif /* _PAGE_SWP_EXCLUSIVE */
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 56d0399a0cd1..e479491da8d5 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -186,7 +186,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|F|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| E|F|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -203,6 +203,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
  * F (2) in swp entry is used to record when a pagetable is
  * writeprotected by userfaultfd WP support.
  *
+ * E (3) in swp entry is used to rememeber PG_anon_exclusive.
+ *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  *
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 91ac10654570..70e360a2e5fb 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -163,4 +163,9 @@ extern unsigned int ptrs_per_p4d;
 
 #define PGD_KERNEL_START	((PAGE_SIZE / 2) / sizeof(pgd_t))
 
+/*
+ * We borrow bit 3 to remember PG_anon_exclusive.
+ */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_PWT
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff mbox series

Patch

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 62ab07e24aef..e42e668153e9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1292,6 +1292,22 @@  static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
 {
 }
 
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE);
+}
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 56d0399a0cd1..e479491da8d5 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -186,7 +186,7 @@  static inline void native_pgd_clear(pgd_t *pgd)
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|F|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| E|F|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -203,6 +203,8 @@  static inline void native_pgd_clear(pgd_t *pgd)
  * F (2) in swp entry is used to record when a pagetable is
  * writeprotected by userfaultfd WP support.
  *
+ * E (3) in swp entry is used to rememeber PG_anon_exclusive.
+ *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  *
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 40497a9020c6..54a8f370046d 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -83,6 +83,11 @@ 
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
+/*
+ * We borrow bit 3 to remember PG_anon_exclusive.
+ */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_PWT
+
 /*
  * Tracking soft dirty bit when a page goes to a swap is tricky.
  * We need a bit which can be stored in pte _and_ not conflict