aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/phys2virt.S
diff options
context:
space:
mode:
authorArd Biesheuvel <ardb@kernel.org>2020-09-20 23:02:25 +0200
committerArd Biesheuvel <ardb@kernel.org>2020-10-28 16:59:43 +0100
commite8e00f5afb087912fb3edb225ee373aa6499bb79 (patch)
treef1c38923210c3613c0118076f0216383913722c2 /arch/arm/kernel/phys2virt.S
parentARM: p2v: simplify __fixup_pv_table() (diff)
downloadlinux-dev-e8e00f5afb087912fb3edb225ee373aa6499bb79.tar.xz
linux-dev-e8e00f5afb087912fb3edb225ee373aa6499bb79.zip
ARM: p2v: switch to MOVW for Thumb2 and ARM/LPAE
In preparation for reducing the phys-to-virt minimum relative alignment from 16 MiB to 2 MiB, switch to patchable sequences involving MOVW instructions that can more easily be manipulated to carry a 12-bit immediate. Note that the non-LPAE ARM sequence is not updated: MOVW may not be supported on non-LPAE platforms, and the sequence itself can be updated more easily to apply the 12 bits of displacement. For Thumb2, which has many more versions of opcodes, switch to a sequence that can be patched by the same patching code for both versions. Note that the Thumb2 opcodes for MOVW and MVN are unambiguous, and have no rotation bits in their immediate fields, so there is no need to use placeholder constants in the asm blocks. While at it, drop the 'volatile' qualifiers from the asm blocks: the code does not have any side effects that are invisible to the compiler, so it is free to omit these sequences if the outputs are not used. Suggested-by: Russell King <linux@armlinux.org.uk> Acked-by: Nicolas Pitre <nico@fluxnic.net> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Diffstat (limited to 'arch/arm/kernel/phys2virt.S')
-rw-r--r--arch/arm/kernel/phys2virt.S147
1 files changed, 116 insertions, 31 deletions
diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S
index be8fb0d89877..a4e364689663 100644
--- a/arch/arm/kernel/phys2virt.S
+++ b/arch/arm/kernel/phys2virt.S
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 1994-2002 Russell King
- * Copyright (c) 2003 ARM Limited
+ * Copyright (c) 2003, 2020 ARM Limited
* All Rights Reserved
*/
@@ -58,55 +58,140 @@ __fixup_a_pv_table:
mov r6, r6, lsr #24
cmn r0, #1
#ifdef CONFIG_THUMB2_KERNEL
+ @
+ @ The Thumb-2 versions of the patchable sequences are
+ @
+ @ phys-to-virt: movw <reg>, #offset<31:24>
+ @ lsl <reg>, #24
+ @ sub <VA>, <PA>, <reg>
+ @
+ @ virt-to-phys (non-LPAE): movw <reg>, #offset<31:24>
+ @ lsl <reg>, #24
+ @ add <PA>, <VA>, <reg>
+ @
+ @ virt-to-phys (LPAE): movw <reg>, #offset<31:24>
+ @ lsl <reg>, #24
+ @ adds <PAlo>, <VA>, <reg>
+ @ mov <PAhi>, #offset<39:32>
+ @ adc <PAhi>, <PAhi>, #0
+ @
+ @ In the non-LPAE case, all patchable instructions are MOVW
+ @ instructions, where we need to patch in the offset into the
+ @ second halfword of the opcode (the 16-bit immediate is encoded
+ @ as imm4:i:imm3:imm8)
+ @
+ @ 15 11 10 9 4 3 0 15 14 12 11 8 7 0
+ @ +-----------+---+-------------+------++---+------+----+------+
+ @ MOVW | 1 1 1 1 0 | i | 1 0 0 1 0 0 | imm4 || 0 | imm3 | Rd | imm8 |
+ @ +-----------+---+-------------+------++---+------+----+------+
+ @
+ @ In the LPAE case, we also need to patch in the high word of the
+ @ offset into the immediate field of the MOV instruction, or patch it
+ @ to a MVN instruction if the offset is negative. In this case, we
+ @ need to inspect the first halfword of the opcode, to check whether
+ @ it is MOVW or MOV/MVN, and to perform the MOV to MVN patching if
+ @ needed. The encoding of the immediate is rather complex for values
+ @ of i:imm3 != 0b0000, but fortunately, we never need more than 8 lower
+ @ order bits, which can be patched into imm8 directly (and i:imm3
+ @ cleared)
+ @
+ @ 15 11 10 9 5 0 15 14 12 11 8 7 0
+ @ +-----------+---+---------------------++---+------+----+------+
+ @ MOV | 1 1 1 1 0 | i | 0 0 0 1 0 0 1 1 1 1 || 0 | imm3 | Rd | imm8 |
+ @ MVN | 1 1 1 1 0 | i | 0 0 0 1 1 0 1 1 1 1 || 0 | imm3 | Rd | imm8 |
+ @ +-----------+---+---------------------++---+------+----+------+
+ @
moveq r0, #0x200000 @ set bit 21, mov to mvn instruction
- lsls r6, #24
- beq .Lnext
- clz r7, r6
- lsr r6, #24
- lsl r6, r7
- bic r6, #0x0080
- lsrs r7, #1
- orrcs r6, #0x0080
- orr r6, r6, r7, lsl #12
- orr r6, #0x4000
b .Lnext
.Lloop: add r7, r4
- adds r4, #4
- ldrh ip, [r7, #2]
-ARM_BE8(rev16 ip, ip)
- tst ip, #0x4000
- and ip, #0x8f00
- orrne ip, r6 @ mask in offset bits 31-24
- orreq ip, r0 @ mask in offset bits 7-0
-ARM_BE8(rev16 ip, ip)
- strh ip, [r7, #2]
- bne .Lnext
+ adds r4, #4 @ clears Z flag
+#ifdef CONFIG_ARM_LPAE
ldrh ip, [r7]
ARM_BE8(rev16 ip, ip)
- bic ip, #0x20
- orr ip, ip, r0, lsr #16
+ tst ip, #0x200 @ MOVW has bit 9 set, MVN has it clear
+ bne 0f @ skip to MOVW handling (Z flag is clear)
+ bic ip, #0x20 @ clear bit 5 (MVN -> MOV)
+ orr ip, ip, r0, lsr #16 @ MOV -> MVN if offset < 0
ARM_BE8(rev16 ip, ip)
strh ip, [r7]
+ @ Z flag is set
+0:
+#endif
+ ldrh ip, [r7, #2]
+ARM_BE8(rev16 ip, ip)
+ and ip, #0xf00 @ clear everything except Rd field
+ orreq ip, r0 @ Z flag set -> MOV/MVN -> patch in high bits
+ orrne ip, r6 @ Z flag clear -> MOVW -> patch in low bits
+ARM_BE8(rev16 ip, ip)
+ strh ip, [r7, #2]
#else
#ifdef CONFIG_CPU_ENDIAN_BE8
@ in BE8, we load data in BE, but instructions still in LE
-#define PV_BIT22 0x00004000
+#define PV_BIT24 0x00000001
#define PV_IMM8_MASK 0xff000000
-#define PV_ROT_MASK 0x000f0000
#else
-#define PV_BIT22 0x00400000
+#define PV_BIT24 0x01000000
#define PV_IMM8_MASK 0x000000ff
-#define PV_ROT_MASK 0xf00
#endif
+ @
+ @ The ARM versions of the patchable sequences are
+ @
+ @ phys-to-virt: sub <VA>, <PA>, #offset<31:24>, lsl #24
+ @
+ @ virt-to-phys (non-LPAE): add <PA>, <VA>, #offset<31:24>, lsl #24
+ @
+ @ virt-to-phys (LPAE): movw <reg>, #offset<31:24>
+ @ adds <PAlo>, <VA>, <reg>, lsl #24
+ @ mov <PAhi>, #offset<39:32>
+ @ adc <PAhi>, <PAhi>, #0
+ @
+ @ In the non-LPAE case, all patchable instructions are ADD or SUB
+ @ instructions, where we need to patch in the offset into the
+ @ immediate field of the opcode, which is emitted with the correct
+ @ rotation value. (The effective value of the immediate is imm12<7:0>
+ @ rotated right by [2 * imm12<11:8>] bits)
+ @
+ @ 31 28 27 23 22 20 19 16 15 12 11 0
+ @ +------+-----------------+------+------+-------+
+ @ ADD | cond | 0 0 1 0 1 0 0 0 | Rn | Rd | imm12 |
+ @ SUB | cond | 0 0 1 0 0 1 0 0 | Rn | Rd | imm12 |
+ @ MOV | cond | 0 0 1 1 1 0 1 0 | Rn | Rd | imm12 |
+ @ MVN | cond | 0 0 1 1 1 1 1 0 | Rn | Rd | imm12 |
+ @ +------+-----------------+------+------+-------+
+ @
+ @ In the LPAE case, we use a MOVW instruction to carry the low offset
+ @ word, and patch in the high word of the offset into the immediate
+ @ field of the subsequent MOV instruction, or patch it to a MVN
+ @ instruction if the offset is negative. We can distinguish MOVW
+ @ instructions based on bits 23:22 of the opcode, and ADD/SUB can be
+ @ distinguished from MOV/MVN (all using the encodings above) using
+ @ bit 24.
+ @
+ @ 31 28 27 23 22 20 19 16 15 12 11 0
+ @ +------+-----------------+------+------+-------+
+ @ MOVW | cond | 0 0 1 1 0 0 0 0 | imm4 | Rd | imm12 |
+ @ +------+-----------------+------+------+-------+
+ @
moveq r0, #0x400000 @ set bit 22, mov to mvn instruction
b .Lnext
.Lloop: ldr ip, [r7, r4]
+#ifdef CONFIG_ARM_LPAE
+ tst ip, #PV_BIT24 @ ADD/SUB have bit 24 clear
+ beq 1f
+ARM_BE8(rev ip, ip)
+ tst ip, #0xc00000 @ MOVW has bits 23:22 clear
+ bic ip, ip, #0x400000 @ clear bit 22
+ bfc ip, #0, #12 @ clear imm12 field of MOV[W] instruction
+ orreq ip, ip, r6 @ MOVW -> mask in offset bits 31-24
+ orrne ip, ip, r0 @ MOV -> mask in offset bits 7-0 (or bit 22)
+ARM_BE8(rev ip, ip)
+ b 2f
+1:
+#endif
bic ip, ip, #PV_IMM8_MASK
- tst ip, #PV_ROT_MASK @ check the rotation field
- orrne ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24
- biceq ip, ip, #PV_BIT22 @ clear bit 22
- orreq ip, ip, r0 ARM_BE8(, ror #8) @ mask in offset bits 7-0 (or bit 22)
+ orr ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24
+2:
str ip, [r7, r4]
add r4, r4, #4
#endif