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:     charlie@rivosinc.com
Cc:     Jonathan Corbet <corbet@lwn.net>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Eric Biederman <ebiederm@xmission.com>,
        Kees Cook <keescook@chromium.org>,
        Shuah Khan <shuah@kernel.org>,
        Alexandre Ghiti <alexghiti@rivosinc.com>,
        =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>,
        Conor Dooley <conor.dooley@microchip.com>,
        Zong Li <zong.li@sifive.com>,
        Greentime Hu <greentime.hu@sifive.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Guo Ren <guoren@kernel.org>,
        David Hildenbrand <david@redhat.com>,
        Sergey Matyukevich <sergey.matyukevich@syntacore.com>,
        Juergen Gross <jgross@suse.com>,
        Qinglin Pan <panqinglin2020@iscas.ac.cn>,
        Anshuman Khandual <anshuman.khandual@arm.com>,
        Anup Patel <anup@brainfault.org>,
        Huacai Chen <chenhuacai@kernel.org>,
        Geert Uytterhoeven <geert@linux-m68k.org>,
        Sunil V L <sunilvl@ventanamicro.com>,
        Kefeng Wang <wangkefeng.wang@huawei.com>,
        Evan Green <evan@rivosinc.com>,
        Mark Brown <broonie@kernel.org>,
        Guillaume Tucker <guillaume.tucker@collabora.com>,
        Catalin Marinas <catalin.marinas@arm.com>,
        linux-doc@vger.kernel.org (open list:DOCUMENTATION),
        linux-riscv@lists.infradead.org (open list:RISC-V ARCHITECTURE),
        linux-kernel@vger.kernel.org (open list),
        linux-mm@kvack.org (open list:EXEC & BINFMT API),
        linux-kselftest@vger.kernel.org (open list:KERNEL SELFTEST FRAMEWORK)
Subject: [PATCH 1/2] RISC-V: mm: Restrict address space for sv39,sv48,sv57
Date:   Mon, 26 Jun 2023 11:36:03 -0700
Message-Id: <20230626183611.40479-2-charlie@rivosinc.com>
In-Reply-To: <20230626183611.40479-1-charlie@rivosinc.com>
References: <20230626183611.40479-1-charlie@rivosinc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Make sv39 the default address space for mmap as some applications
currently depend on this assumption. The RISC-V specification enforces
that bits outside of the virtual address range are not used, so
restricting the size of the default address space as such should be
temporary. 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, a 39-bit 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   | 13 +++++++++-
 arch/riscv/include/asm/processor.h | 41 +++++++++++++++++++++++++-----
 3 files changed, 47 insertions(+), 9 deletions(-)

diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index 30e7d2455960..1b57f13a1afd 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..e83912e97870 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -57,18 +57,29 @@
 #define MODULES_END		(PFN_ALIGN((unsigned long)&_start))
 #endif
 
+
 /*
  * Roughly size the vmemmap space to be large enough to fit enough
  * struct pages to map half the virtual address space. Then
  * position vmemmap directly below the VMALLOC region.
  */
 #ifdef CONFIG_64BIT
+#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))
 #else
 #define VA_BITS		32
 #endif
 
+#define DEFAULT_VA_BITS ((VA_BITS >= VA_BITS_SV39) ? VA_BITS_SV39 : VA_BITS)
+
 #define VMEMMAP_SHIFT \
 	(VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
 #define VMEMMAP_SIZE	BIT(VMEMMAP_SHIFT)
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 6fb8bbec8459..019dcd4ecae4 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -12,20 +12,47 @@
 
 #include <asm/ptrace.h>
 
-/*
- * 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 DEFAULT_MAP_WINDOW	(UL(1) << (DEFAULT_VA_BITS - 1))
 #define STACK_TOP_MAX		TASK_SIZE_64
+
+#define arch_get_mmap_end(addr, len, flags) \
+	((addr) == 0 || (addr) >= VA_USER_SV57 ? STACK_TOP_MAX :   \
+	 (((addr) >= VA_USER_SV48) && (VA_BITS >= VA_BITS_SV48)) ? \
+						 VA_USER_SV48 : \
+						 VA_USER_SV39)
+
+#define arch_get_mmap_base(addr, base) \
+	(((addr >= VA_USER_SV57) && (VA_BITS >= VA_BITS_SV57)) ?   \
+		 base + STACK_TOP_MAX - DEFAULT_MAP_WINDOW : \
+	 (((addr) >= VA_USER_SV48) && (VA_BITS >= VA_BITS_SV48)) ? \
+		 base + VA_USER_SV48 - DEFAULT_MAP_WINDOW : \
+		 base)
+
 #else
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
 #define STACK_TOP_MAX		TASK_SIZE
+
+#define arch_get_mmap_end(addr, len, flags) \
+	((addr) > DEFAULT_MAP_WINDOW ? STACK_TOP_MAX : DEFAULT_MAP_WINDOW)
+
+#define arch_get_mmap_base(addr, base) \
+	((addr > DEFAULT_MAP_WINDOW) ? \
+		base + STACK_TOP_MAX - DEFAULT_MAP_WINDOW : \
+		base)
+
 #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(DEFAULT_MAP_WINDOW / 3)
+
 #ifndef __ASSEMBLY__
 
 struct task_struct;
-- 
2.34.1