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;
IronPort-SDR: x+Cqs+hkbgI9vuYjm5snrQn193WNpZGGT20l7DKmlWzlYk0QleaQb0KVdYPtDjWy19WsFwEb73
 UVjgCBDXW8CR0j41EQ3aeNrhLGa8VC6yROFiG/X/F8I6u0JzQDVB5Jo5p/2etnPujBU6kd6z7C
 lvLynZQENfFzF6+SAQ9+S5m/wPuS2DlZWyIKvqlqQvB8GOYnNqv3cBbEGzXrLrLP7hGb7zzCfB
 XR6PpyD3djR70Ellc0vmINDLkcxuDX1GnHxI13xV1/dun7fFAkZiXYV8uWsylxolqHdoIhdlxE
 LDTDhyCtd5OXmRG5mq6GRCib
IronPort-SDR: vucboqE6RKTKOV4ayKu7cGEJD8dnqhFaAOPTvogC1jyKg+q53X788/KKIeLQoSpiPKxh4IhT2z
 CsSnDVrBCt5Afw8Lq0wZIw4VrPwVYGllDWahJy5i7fHC9NtR2N1bn4b0vMl5rDwCxDyZrwXL5w
 KfkxiWuUSL62IDLMYgz3fzKHwTv1LQjvQI2rbq8BkJZUd755AVQ6bCLtrY5nEjqbKEIW9uI9tg
 YecbxXO2djZY8NsR4tiTZLHo76eywYB2zOZTOFOFE+0mkLaD8XNlV4FnPV8kRoZGtr9UQ5jznr
 Xr0=
WDCIronportException: Internal
From:   Alistair Francis <alistair.francis@opensource.wdc.com>
To:     linux-riscv@lists.infradead.org, palmer@dabbelt.com,
        paul.walmsley@sifive.com, aou@eecs.berkeley.edu
Cc:     linux-kernel@vger.kernel.org, atishp@rivosinc.com,
        guoren@kernel.org, anup@brainfault.org,
        Alistair Francis <alistair.francis@wdc.com>
Subject: [PATCH] riscv: Ensure only ASIDLEN is used for sfence.vma
Date:   Wed, 30 Mar 2022 17:33:47 +1000
Message-Id: <20220330073347.3898802-1-alistair.francis@opensource.wdc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

From: Alistair Francis <alistair.francis@wdc.com>

When we set the value of context.id using __new_context() we set both
the asid and the current_version with this return statement in
__new_context():

    return asid | ver;

This means that when local_flush_tlb_all_asid() is called with the asid
specified from context.id we can write the incorrect value.

We get away with this as hardware ignores the extra bits, as the RISC-V
specification states:

"bits SXLEN-1:ASIDMAX of the value held in rs2 are reserved for future
standard use. Until their use is defined by a standard extension, they
should be zeroed by software and ignored by current implementations."

but it is still a bug and worth addressing as we are incorrectly setting
extra bits.

This patch uses asid_mask when calling sfence.vma to ensure the asid is
always the correct len (ASIDLEN). This is similar to what we do in
arch/riscv/mm/context.c.

Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
---
 arch/riscv/mm/context.c  | 2 +-
 arch/riscv/mm/tlbflush.c | 4 ++--
 include/linux/mm_types.h | 2 ++
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index 7acbfbd14557..4329fe54176b 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -22,7 +22,7 @@ DEFINE_STATIC_KEY_FALSE(use_asid_allocator);
=20
 static unsigned long asid_bits;
 static unsigned long num_asids;
-static unsigned long asid_mask;
+unsigned long asid_mask;
=20
 static atomic_long_t current_version;
=20
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 37ed760d007c..4469615aa07f 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -10,7 +10,7 @@ static inline void local_flush_tlb_all_asid(unsigned lo=
ng asid)
 {
 	__asm__ __volatile__ ("sfence.vma x0, %0"
 			:
-			: "r" (asid)
+			: "r" (asid & asid_mask)
 			: "memory");
 }
=20
@@ -19,7 +19,7 @@ static inline void local_flush_tlb_page_asid(unsigned l=
ong addr,
 {
 	__asm__ __volatile__ ("sfence.vma %0, %1"
 			:
-			: "r" (addr), "r" (asid)
+			: "r" (addr), "r" (asid & asid_mask)
 			: "memory");
 }
=20
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8834e38c06a4..5fa7cc0af853 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -666,6 +666,8 @@ struct mm_struct {
=20
 extern struct mm_struct init_mm;
=20
+extern unsigned long asid_mask;
+
 /* Pointer magic because the dynamic array size confuses some compilers.=
 */
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
--=20
2.35.1