Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   David Hildenbrand <david@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Hugh Dickins <hughd@google.com>,
        John Hubbard <jhubbard@nvidia.com>,
        Jason Gunthorpe <jgg@nvidia.com>,
        Mike Rapoport <rppt@linux.ibm.com>,
        Yang Shi <shy828301@gmail.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Nadav Amit <namit@vmware.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Peter Xu <peterx@redhat.com>, linux-mm@kvack.org,
        x86@kernel.org, linux-alpha@vger.kernel.org,
        linux-snps-arc@lists.infradead.org,
        linux-arm-kernel@lists.infradead.org, linux-csky@vger.kernel.org,
        linux-hexagon@vger.kernel.org, linux-ia64@vger.kernel.org,
        loongarch@lists.linux.dev, linux-m68k@lists.linux-m68k.org,
        linux-mips@vger.kernel.org, openrisc@lists.librecores.org,
        linux-parisc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
        linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org,
        linux-sh@vger.kernel.org, sparclinux@vger.kernel.org,
        linux-um@lists.infradead.org, linux-xtensa@linux-xtensa.org,
        David Hildenbrand <david@redhat.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>
Subject: [PATCH mm-unstable v1 19/26] riscv/mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE
Date:   Fri, 13 Jan 2023 18:10:19 +0100
Message-Id: <20230113171026.582290-20-david@redhat.com>
In-Reply-To: <20230113171026.582290-1-david@redhat.com>
References: <20230113171026.582290-1-david@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Let's support __HAVE_ARCH_PTE_SWP_EXCLUSIVE by stealing one bit
from the offset. This reduces the maximum swap space per file: on 32bit
to 16 GiB (was 32 GiB).

Note that this bit does not conflict with swap PMDs and could also be used
in swap PMD context later.

While at it, mask the type in __swp_entry().

Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 arch/riscv/include/asm/pgtable-bits.h |  3 +++
 arch/riscv/include/asm/pgtable.h      | 29 ++++++++++++++++++++++-----
 2 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index b9e13a8fe2b7..f896708e8331 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -27,6 +27,9 @@
  */
 #define _PAGE_PROT_NONE _PAGE_GLOBAL
 
+/* Used for swap PTEs only. */
+#define _PAGE_SWP_EXCLUSIVE _PAGE_ACCESSED
+
 #define _PAGE_PFN_SHIFT 10
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 4eba9a98d0e3..03a4728db039 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -724,16 +724,18 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
- * Encode and decode a swap entry
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
  *
  * Format of swap PTE:
  *	bit            0:	_PAGE_PRESENT (zero)
  *	bit       1 to 3:       _PAGE_LEAF (zero)
  *	bit            5:	_PAGE_PROT_NONE (zero)
- *	bits      6 to 10:	swap type
- *	bits 10 to XLEN-1:	swap offset
+ *	bit            6:	exclusive marker
+ *	bits      7 to 11:	swap type
+ *	bits 11 to XLEN-1:	swap offset
  */
-#define __SWP_TYPE_SHIFT	6
+#define __SWP_TYPE_SHIFT	7
 #define __SWP_TYPE_BITS		5
 #define __SWP_TYPE_MASK		((1UL << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
@@ -744,11 +746,28 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 #define __swp_type(x)	(((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
 #define __swp_offset(x)	((x).val >> __SWP_OFFSET_SHIFT)
 #define __swp_entry(type, offset) ((swp_entry_t) \
-	{ ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
+	{ (((type) & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT) | \
+	  ((offset) << __SWP_OFFSET_SHIFT) })
 
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE);
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
+}
+
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
 #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) })
 #define __swp_entry_to_pmd(swp) __pmd((swp).val)
-- 
2.39.0