Received-SPF: pass (google.com: domain of linux-kernel+bounces-176188-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Fri, 10 May 2024 14:02:54 -0700
From: Charlie Jenkins <charlie@rivosinc.com>
To: Deepak Gupta <debug@rivosinc.com>
Cc: paul.walmsley@sifive.com, rick.p.edgecombe@intel.com,
	broonie@kernel.org, Szabolcs.Nagy@arm.com, kito.cheng@sifive.com,
	keescook@chromium.org, ajones@ventanamicro.com,
	conor.dooley@microchip.com, cleger@rivosinc.com,
	atishp@atishpatra.org, alex@ghiti.fr, bjorn@rivosinc.com,
	alexghiti@rivosinc.com, samuel.holland@sifive.com, conor@kernel.org,
	linux-doc@vger.kernel.org, linux-riscv@lists.infradead.org,
	linux-kernel@vger.kernel.org, devicetree@vger.kernel.org,
	linux-mm@kvack.org, linux-arch@vger.kernel.org,
	linux-kselftest@vger.kernel.org, corbet@lwn.net, palmer@dabbelt.com,
	aou@eecs.berkeley.edu, robh+dt@kernel.org,
	krzysztof.kozlowski+dt@linaro.org, oleg@redhat.com,
	akpm@linux-foundation.org, arnd@arndb.de, ebiederm@xmission.com,
	Liam.Howlett@oracle.com, vbabka@suse.cz, lstoakes@gmail.com,
	shuah@kernel.org, brauner@kernel.org, andy.chiu@sifive.com,
	jerry.shih@sifive.com, hankuan.chen@sifive.com,
	greentime.hu@sifive.com, evan@rivosinc.com, xiao.w.wang@intel.com,
	apatel@ventanamicro.com, mchitale@ventanamicro.com,
	dbarboza@ventanamicro.com, sameo@rivosinc.com,
	shikemeng@huaweicloud.com, willy@infradead.org,
	vincent.chen@sifive.com, guoren@kernel.org, samitolvanen@google.com,
	songshuaishuai@tinylab.org, gerg@kernel.org, heiko@sntech.de,
	bhe@redhat.com, jeeheng.sia@starfivetech.com, cyy@cyyself.name,
	maskray@google.com, ancientmodern4@gmail.com,
	mathis.salmen@matsal.de, cuiyunhui@bytedance.com,
	bgray@linux.ibm.com, mpe@ellerman.id.au, baruch@tkos.co.il,
	alx@kernel.org, david@redhat.com, catalin.marinas@arm.com,
	revest@chromium.org, josh@joshtriplett.org, shr@devkernel.io,
	deller@gmx.de, omosnace@redhat.com, ojeda@kernel.org,
	jhubbard@nvidia.com
Subject: Re: [PATCH v3 10/29] riscv/mm : ensure PROT_WRITE leads to VM_READ |
 VM_WRITE
Message-ID: <Zj6LfpQhOjTLEx2O@ghost>
References: <20240403234054.2020347-1-debug@rivosinc.com>
 <20240403234054.2020347-11-debug@rivosinc.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240403234054.2020347-11-debug@rivosinc.com>

On Wed, Apr 03, 2024 at 04:34:58PM -0700, Deepak Gupta wrote:
> `arch_calc_vm_prot_bits` is implemented on risc-v to return VM_READ |
> VM_WRITE if PROT_WRITE is specified. Similarly `riscv_sys_mmap` is
> updated to convert all incoming PROT_WRITE to (PROT_WRITE | PROT_READ).
> This is to make sure that any existing apps using PROT_WRITE still work.
> 
> Earlier `protection_map[VM_WRITE]` used to pick read-write PTE encodings.
> Now `protection_map[VM_WRITE]` will always pick PAGE_SHADOWSTACK PTE
> encodings for shadow stack. Above changes ensure that existing apps
> continue to work because underneath kernel will be picking
> `protection_map[VM_WRITE|VM_READ]` PTE encodings.
> 
> Signed-off-by: Deepak Gupta <debug@rivosinc.com>
> ---
>  arch/riscv/include/asm/mman.h    | 24 ++++++++++++++++++++++++
>  arch/riscv/include/asm/pgtable.h |  1 +
>  arch/riscv/kernel/sys_riscv.c    | 11 +++++++++++
>  arch/riscv/mm/init.c             |  2 +-
>  mm/mmap.c                        |  1 +
>  5 files changed, 38 insertions(+), 1 deletion(-)
>  create mode 100644 arch/riscv/include/asm/mman.h
> 
> diff --git a/arch/riscv/include/asm/mman.h b/arch/riscv/include/asm/mman.h
> new file mode 100644
> index 000000000000..ef9fedf32546
> --- /dev/null
> +++ b/arch/riscv/include/asm/mman.h
> @@ -0,0 +1,24 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef __ASM_MMAN_H__
> +#define __ASM_MMAN_H__
> +
> +#include <linux/compiler.h>
> +#include <linux/types.h>
> +#include <uapi/asm/mman.h>
> +
> +static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
> +	unsigned long pkey __always_unused)
> +{
> +	unsigned long ret = 0;
> +
> +	/*
> +	 * If PROT_WRITE was specified, force it to VM_READ | VM_WRITE.
> +	 * Only VM_WRITE means shadow stack.
> +	 */
> +	if (prot & PROT_WRITE)
> +		ret = (VM_READ | VM_WRITE);
> +	return ret;
> +}
> +#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
> +
> +#endif /* ! __ASM_MMAN_H__ */
> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
> index 6066822e7396..4d5983bc6766 100644
> --- a/arch/riscv/include/asm/pgtable.h
> +++ b/arch/riscv/include/asm/pgtable.h
> @@ -184,6 +184,7 @@ extern struct pt_alloc_ops pt_ops __initdata;
>  #define PAGE_READ_EXEC		__pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC)
>  #define PAGE_WRITE_EXEC		__pgprot(_PAGE_BASE | _PAGE_READ |	\
>  					 _PAGE_EXEC | _PAGE_WRITE)
> +#define PAGE_SHADOWSTACK       __pgprot(_PAGE_BASE | _PAGE_WRITE)
>  
>  #define PAGE_COPY		PAGE_READ
>  #define PAGE_COPY_EXEC		PAGE_READ_EXEC
> diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
> index f1c1416a9f1e..846c36b1b3d5 100644
> --- a/arch/riscv/kernel/sys_riscv.c
> +++ b/arch/riscv/kernel/sys_riscv.c
> @@ -8,6 +8,8 @@
>  #include <linux/syscalls.h>
>  #include <asm/cacheflush.h>
>  #include <asm-generic/mman-common.h>
> +#include <vdso/vsyscall.h>
> +#include <asm/mman.h>
>  
>  static long riscv_sys_mmap(unsigned long addr, unsigned long len,
>  			   unsigned long prot, unsigned long flags,
> @@ -17,6 +19,15 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
>  	if (unlikely(offset & (~PAGE_MASK >> page_shift_offset)))
>  		return -EINVAL;
>  
> +	/*
> +	 * If only PROT_WRITE is specified then extend that to PROT_READ
> +	 * protection_map[VM_WRITE] is now going to select shadow stack encodings.
> +	 * So specifying PROT_WRITE actually should select protection_map [VM_WRITE | VM_READ]
> +	 * If user wants to create shadow stack then they should use `map_shadow_stack` syscall.
> +	 */
> +	if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ)))

The comments says that this should extend to PROT_READ if only
PROT_WRITE is specified. This condition instead is checking if
PROT_WRITE is selected but PROT_READ is not. If prot is (VM_EXEC |
VM_WRITE) then it would be extended to (VM_EXEC | VM_WRITE | VM_READ).
This will not currently cause any issues because these both map to the
same value in the protection_map PAGE_COPY_EXEC, however this seems to
be not the intention of this change.

prot == PROT_WRITE better suits the condition explained in the comment.

> +		prot |= PROT_READ;
> +
>  	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
>  			       offset >> (PAGE_SHIFT - page_shift_offset));
>  }
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index fa34cf55037b..98e5ece4052a 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -299,7 +299,7 @@ pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
>  static const pgprot_t protection_map[16] = {
>  	[VM_NONE]					= PAGE_NONE,
>  	[VM_READ]					= PAGE_READ,
> -	[VM_WRITE]					= PAGE_COPY,
> +	[VM_WRITE]					= PAGE_SHADOWSTACK,
>  	[VM_WRITE | VM_READ]				= PAGE_COPY,
>  	[VM_EXEC]					= PAGE_EXEC,
>  	[VM_EXEC | VM_READ]				= PAGE_READ_EXEC,
> diff --git a/mm/mmap.c b/mm/mmap.c
> index d89770eaab6b..57a974f49b00 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -47,6 +47,7 @@
>  #include <linux/oom.h>
>  #include <linux/sched/mm.h>
>  #include <linux/ksm.h>
> +#include <linux/processor.h>

It doesn't seem like this is necessary for this patch.

- Charlie

>  
>  #include <linux/uaccess.h>
>  #include <asm/cacheflush.h>
> -- 
> 2.43.2
>