[PATCH V5 2/3] riscv: mm: Add soft-dirty page tracking support

[Chunyan Zhang]

The PTE bit(9) is reserved for software, now used by devmap,
this patch reuses bit(9) for soft-dirty which is enabled only
if !CONFIG_ARCH_HAS_PTE_DEVMAP, in other words, soft-dirty
and devmap will be mutually exclusive on RISC-V.

To add swap PTE soft-dirty tracking, we borrow bit(4) which is
available for swap PTEs on RISC-V systems.

Reviewed-by: Alexandre Ghiti <alexghiti at rivosinc.com>
Signed-off-by: Chunyan Zhang <zhangchunyan at iscas.ac.cn>
---
 arch/riscv/Kconfig                    | 27 ++++++++++-
 arch/riscv/include/asm/pgtable-bits.h | 12 +++++
 arch/riscv/include/asm/pgtable.h      | 69 ++++++++++++++++++++++++++-
 3 files changed, 106 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index f4c570538d55..3bccdcae9445 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -40,7 +40,6 @@ config RISCV
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_PREPARE_SYNC_CORE_CMD
-	select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_DIRECT_MAP if MMU
 	select ARCH_HAS_SET_MEMORY if MMU
@@ -966,6 +965,32 @@ config RANDOMIZE_BASE
 
           If unsure, say N.
 
+choice
+	prompt "PTE RSW bit(9) usage"
+	default RISCV_HAS_PTE_DEVMAP
+	depends on MMU && 64BIT
+	help
+	  RISC-V PTE bit(9) is reserved for software, and used by more than
+	  one kernel feature which cannot be supported at the same time.
+	  So we have to select one for it.
+
+config RISCV_HAS_PTE_DEVMAP
+	bool "devmap"
+	select ARCH_HAS_PTE_DEVMAP
+	help
+	  The PTE bit(9) is used for devmap mark. ZONE_DEVICE pages need devmap
+	  PTEs support to function.
+
+	  So if you want to use ZONE_DEVICE, select this.
+
+config RISCV_HAS_SOFT_DIRTY
+	bool "soft-dirty"
+	select HAVE_ARCH_SOFT_DIRTY
+	help
+	  The PTE bit(9) is used for soft-dirty tracking.
+
+endchoice
+
 endmenu # "Kernel features"
 
 menu "Boot options"
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index 5bcc73430829..c6d51fe9fc6f 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -26,6 +26,18 @@
 #define _PAGE_DEVMAP	0
 #endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
 
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define _PAGE_SOFT_DIRTY	(1 << 9)    /* RSW: 0x2 for software dirty tracking */
+/*
+ * BIT 4 is not involved into swap entry computation, so we
+ * can borrow it for swap page soft-dirty tracking.
+ */
+#define _PAGE_SWP_SOFT_DIRTY	_PAGE_USER
+#else
+#define _PAGE_SOFT_DIRTY	0
+#define _PAGE_SWP_SOFT_DIRTY	0
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
 #define _PAGE_TABLE     _PAGE_PRESENT
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index e79f15293492..1779eae5cb49 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -424,7 +424,7 @@ static inline pte_t pte_mkwrite_novma(pte_t pte)
 
 static inline pte_t pte_mkdirty(pte_t pte)
 {
-	return __pte(pte_val(pte) | _PAGE_DIRTY);
+	return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
 }
 
 static inline pte_t pte_mkclean(pte_t pte)
@@ -457,6 +457,38 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline int pte_soft_dirty(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SOFT_DIRTY;
+}
+
+static inline pte_t pte_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
+}
+
+static inline pte_t pte_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_SOFT_DIRTY));
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~(_PAGE_SWP_SOFT_DIRTY));
+}
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
 #ifdef CONFIG_RISCV_ISA_SVNAPOT
 #define pte_leaf_size(pte)	(pte_napot(pte) ?				\
 					napot_cont_size(napot_cont_order(pte)) :\
@@ -757,6 +789,40 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 	return pte_pmd(pte_mkdevmap(pmd_pte(pmd)));
 }
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline int pmd_soft_dirty(pmd_t pmd)
+{
+	return pte_soft_dirty(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_mksoft_dirty(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd)));
+}
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+static inline int pmd_swp_soft_dirty(pmd_t pmd)
+{
+	return pte_swp_soft_dirty(pmd_pte(pmd));
+}
+
+static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd)));
+}
+
+static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
+{
+	return pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd)));
+}
+#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
+#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
+
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 				pmd_t *pmdp, pmd_t pmd)
 {
@@ -847,6 +913,7 @@ extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
  * Format of swap PTE:
  *	bit            0:	_PAGE_PRESENT (zero)
  *	bit       1 to 3:       _PAGE_LEAF (zero)
+ *	bit	       4:	_PAGE_SWP_SOFT_DIRTY
  *	bit            5:	_PAGE_PROT_NONE (zero)
  *	bit            6:	exclusive marker
  *	bits      7 to 11:	swap type
-- 
2.34.1