riscv: mm: add soft-dirty page tracking support

The Svrsw60t59b extension allows to free the PTE reserved bits 60 and 59
for software, this patch uses bit 59 for soft-dirty.

To add swap PTE soft-dirty tracking, we borrow bit 3 which is available
for swap PTEs on RISC-V systems.

Link: https://lkml.kernel.org/r/20251113072806.795029-5-zhangchunyan@iscas.ac.cn
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
Reviewed-by: Deepak Gupta <debug@rivosinc.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Jones <ajones@ventanamicro.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Conor Dooley <conor@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yuanchu Xie <yuanchu@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 93 insertions, 2 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 829d95d173cf..e5f070485bbe 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -142,6 +142,7 @@ config RISCV
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_SOFT_DIRTY if 64BIT && MMU && RISCV_ISA_SVRSW60T59B
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index 179bd4afece4..f3bac2bbc157 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -19,6 +19,25 @@
 #define _PAGE_SOFT      (3 << 8)    /* Reserved for software */
 
 #define _PAGE_SPECIAL   (1 << 8)    /* RSW: 0x1 */
+
+#ifdef CONFIG_MEM_SOFT_DIRTY
+
+/* ext_svrsw60t59b: bit 59 for soft-dirty tracking */
+#define _PAGE_SOFT_DIRTY						\
+	((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ?	\
+	 (1UL << 59) : 0)
+/*
+ * Bit 3 is always zero for swap entry computation, so we
+ * can borrow it for swap page soft-dirty tracking.
+ */
+#define _PAGE_SWP_SOFT_DIRTY						\
+	((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ?	\
+	 _PAGE_EXEC : 0)
+#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 5a08eb5fe99f..049ba0e64f94 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -428,7 +428,7 @@ 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)
@@ -456,6 +456,42 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+#define pgtable_supports_soft_dirty()				\
+	(IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) &&			\
+	 riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B))
+
+static inline bool 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 bool 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)) :\
@@ -805,6 +841,40 @@ static inline pud_t pud_mkspecial(pud_t pud)
 }
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
+static inline bool 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 bool 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)
 {
@@ -1003,7 +1073,8 @@ static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
  *
  * Format of swap PTE:
  *	bit            0:	_PAGE_PRESENT (zero)
- *	bit       1 to 3:       _PAGE_LEAF (zero)
+ *	bit       1 to 2:	(zero)
+ *	bit            3:	_PAGE_SWP_SOFT_DIRTY
  *	bit            5:	_PAGE_PROT_NONE (zero)
  *	bit            6:	exclusive marker
  *	bits      7 to 11:	swap type