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:   Charlie Jenkins <charlie@rivosinc.com>
To:     linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org
Cc:     charlie@rivosinc.com, conor@kernel.org, paul.walmsley@sifive.com,
        palmer@rivosinc.com, aou@eecs.berkeley.edu, anup@brainfault.org,
        konstantin@linuxfoundation.org, linux-doc@vger.kernel.org,
        linux-kselftest@vger.kernel.org, linux-mm@kvack.org,
        mick@ics.forth.gr, jrtc27@jrtc27.com, rdunlap@infradead.org,
        alexghiti@rivosinc.com
Subject: [PATCH v9 1/4] RISC-V: mm: Restrict address space for sv39,sv48,sv57
Date:   Tue,  8 Aug 2023 18:51:07 -0700
Message-Id: <20230809015110.3290774-2-charlie@rivosinc.com>
In-Reply-To: <20230809015110.3290774-1-charlie@rivosinc.com>
References: <20230809015110.3290774-1-charlie@rivosinc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Make sv48 the default address space for mmap as some applications
currently depend on this assumption. A hint address passed to mmap will
cause the largest address space that fits entirely into the hint to be
used. If the hint is less than or equal to 1<<38, an sv39 address will
be used. An exception is that if the hint address is 0, then a sv48
address will be used. After an address space is completely full, the next
smallest address space will be used.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 arch/riscv/include/asm/elf.h       |  2 +-
 arch/riscv/include/asm/pgtable.h   | 21 +++++++++++-
 arch/riscv/include/asm/processor.h | 52 ++++++++++++++++++++++++++----
 3 files changed, 67 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index c24280774caf..5d3368d5585c 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -49,7 +49,7 @@ extern bool compat_elf_check_arch(Elf32_Ehdr *hdr);
  * the loader.  We need to make sure that it is out of the way of the program
  * that it will "exec", and that there is sufficient room for the brk.
  */
-#define ELF_ET_DYN_BASE		((TASK_SIZE / 3) * 2)
+#define ELF_ET_DYN_BASE		((DEFAULT_MAP_WINDOW / 3) * 2)
 
 #ifdef CONFIG_64BIT
 #ifdef CONFIG_COMPAT
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 75970ee2bda2..2611c1324a7c 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -63,8 +63,27 @@
  * position vmemmap directly below the VMALLOC region.
  */
 #ifdef CONFIG_64BIT
+#define VA_BITS_SV32 32
+#define VA_BITS_SV39 39
+#define VA_BITS_SV48 48
+#define VA_BITS_SV57 57
+
+#define VA_USER_SV39 (UL(1) << (VA_BITS_SV39 - 1))
+#define VA_USER_SV48 (UL(1) << (VA_BITS_SV48 - 1))
+#define VA_USER_SV57 (UL(1) << (VA_BITS_SV57 - 1))
+
 #define VA_BITS		(pgtable_l5_enabled ? \
-				57 : (pgtable_l4_enabled ? 48 : 39))
+				VA_BITS_SV57 : (pgtable_l4_enabled ? VA_BITS_SV48 : VA_BITS_SV39))
+
+#ifdef CONFIG_COMPAT
+#define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS)
+#define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39)
+#define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64)
+#define MMAP_MIN_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_MIN_VA_BITS_64)
+#else
+#define MMAP_VA_BITS ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS)
+#define MMAP_MIN_VA_BITS (VA_BITS_SV39)
+#endif
 #else
 #define VA_BITS		32
 #endif
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index c950a8d9edef..3e23e1786d05 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -13,19 +13,59 @@
 
 #include <asm/ptrace.h>
 
+#ifdef CONFIG_64BIT
+#define DEFAULT_MAP_WINDOW	(UL(1) << (MMAP_VA_BITS - 1))
+#define STACK_TOP_MAX		TASK_SIZE_64
+
+#define arch_get_mmap_end(addr, len, flags)			\
+({								\
+	unsigned long mmap_end;					\
+	typeof(addr) _addr = (addr);				\
+	if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
+		mmap_end = STACK_TOP_MAX;			\
+	else if ((_addr) >= VA_USER_SV57)			\
+		mmap_end = STACK_TOP_MAX;			\
+	else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
+		mmap_end = VA_USER_SV48;			\
+	else							\
+		mmap_end = VA_USER_SV39;			\
+	mmap_end;						\
+})
+
+#define arch_get_mmap_base(addr, base)				\
+({								\
+	unsigned long mmap_base;				\
+	typeof(addr) _addr = (addr);				\
+	typeof(base) _base = (base);				\
+	unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base);	\
+	if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())) \
+		mmap_base = (_base);				\
+	else if (((_addr) >= VA_USER_SV57) && (VA_BITS >= VA_BITS_SV57)) \
+		mmap_base = VA_USER_SV57 - rnd_gap;		\
+	else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= VA_BITS_SV48)) \
+		mmap_base = VA_USER_SV48 - rnd_gap;		\
+	else							\
+		mmap_base = VA_USER_SV39 - rnd_gap;		\
+	mmap_base;						\
+})
+
+#else
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
+#define STACK_TOP_MAX		TASK_SIZE
+#endif
+#define STACK_ALIGN		16
+
+#define STACK_TOP		DEFAULT_MAP_WINDOW
+
 /*
  * This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
-
-#define STACK_TOP		TASK_SIZE
 #ifdef CONFIG_64BIT
-#define STACK_TOP_MAX		TASK_SIZE_64
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN((UL(1) << MMAP_MIN_VA_BITS) / 3)
 #else
-#define STACK_TOP_MAX		TASK_SIZE
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
 #endif
-#define STACK_ALIGN		16
 
 #ifndef __ASSEMBLY__
 
-- 
2.34.1