diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fe2f17eb2b50..d8d62b8e72e4 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -243,7 +243,7 @@ config ARM_PATCH_PHYS_VIRT kernel in system memory. This can only be used with non-XIP MMU kernels where the base - of physical memory is at a 16MB boundary. + of physical memory is at a 2 MiB boundary. Only disable this option if you know that you do not require this feature (eg, building a kernel for a single machine) and diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index ccf55cef6ab9..2611be35f26b 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -173,6 +173,7 @@ extern unsigned long vectors_base; * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 +#define __PV_BITS_23_16 0x810000 #define __PV_BITS_7_0 0x81 extern unsigned long __pv_phys_pfn_offset; @@ -187,16 +188,18 @@ extern const void *__pv_table_begin, *__pv_table_end; #define __pv_stub(from,to,instr) \ __asm__("@ __pv_stub\n" \ "1: " instr " %0, %1, %2\n" \ + "2: " instr " %0, %0, %3\n" \ " .pushsection .pv_table,\"a\"\n" \ - " .long 1b - .\n" \ + " .long 1b - ., 2b - .\n" \ " .popsection\n" \ : "=r" (to) \ - : "r" (from), "I" (__PV_BITS_31_24)) + : "r" (from), "I" (__PV_BITS_31_24), \ + "I"(__PV_BITS_23_16)) #define __pv_add_carry_stub(x, y) \ __asm__("@ __pv_add_carry_stub\n" \ "0: movw %R0, #0\n" \ - " adds %Q0, %1, %R0, lsl #24\n" \ + " adds %Q0, %1, %R0, lsl #20\n" \ "1: mov %R0, %2\n" \ " adc %R0, %R0, #0\n" \ " .pushsection .pv_table,\"a\"\n" \ @@ -210,7 +213,7 @@ extern const void *__pv_table_begin, *__pv_table_end; #define __pv_stub(from,to,instr) \ __asm__("@ __pv_stub\n" \ "0: movw %0, #0\n" \ - " lsl %0, #24\n" \ + " lsl %0, #21\n" \ " " instr " %0, %1, %0\n" \ " .pushsection .pv_table,\"a\"\n" \ " .long 0b - .\n" \ @@ -221,7 +224,7 @@ extern const void *__pv_table_begin, *__pv_table_end; #define __pv_add_carry_stub(x, y) \ __asm__("@ __pv_add_carry_stub\n" \ "0: movw %R0, #0\n" \ - " lsls %R0, #24\n" \ + " lsls %R0, #21\n" \ " adds %Q0, %1, %R0\n" \ "1: mvn %R0, #0\n" \ " adc %R0, %R0, #0\n" \ diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S index a4e364689663..fb53db78fe78 100644 --- a/arch/arm/kernel/phys2virt.S +++ b/arch/arm/kernel/phys2virt.S @@ -21,7 +21,7 @@ /* * __fixup_pv_table - patch the stub instructions with the delta between * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be - * 16MiB aligned. + * 2 MiB aligned. * * Called from head.S, which expects the following registers to be preserved: * r1 = machine no, r2 = atags or dtb, @@ -38,8 +38,8 @@ ENTRY(__fixup_pv_table) strcc ip, [r0, #HIGH_OFFSET] @ save to __pv_offset high bits str r3, [r0, #LOW_OFFSET] @ save to __pv_offset low bits - mov r0, r3, lsr #24 @ constant for add/sub instructions - teq r3, r0, lsl #24 @ must be 16MiB aligned + mov r0, r3, lsr #21 @ constant for add/sub instructions + teq r3, r0, lsl #21 @ must be 2 MiB aligned bne 0f adr_l r4, __pv_table_begin @@ -55,22 +55,21 @@ __fixup_a_pv_table: adr_l r6, __pv_offset ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word - 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 , #offset<31:24> - @ lsl , #24 + @ phys-to-virt: movw , #offset<31:21> + @ lsl , #21 @ sub , , @ - @ virt-to-phys (non-LPAE): movw , #offset<31:24> - @ lsl , #24 + @ virt-to-phys (non-LPAE): movw , #offset<31:21> + @ lsl , #21 @ add , , @ - @ virt-to-phys (LPAE): movw , #offset<31:24> - @ lsl , #24 + @ virt-to-phys (LPAE): movw , #offset<31:21> + @ lsl , #21 @ adds , , @ mov , #offset<39:32> @ adc , , #0 @@ -102,6 +101,9 @@ __fixup_a_pv_table: @ +-----------+---+---------------------++---+------+----+------+ @ moveq r0, #0x200000 @ set bit 21, mov to mvn instruction + lsrs r3, r6, #29 @ isolate top 3 bits of displacement + ubfx r6, r6, #21, #8 @ put bits 28:21 into the MOVW imm8 field + bfi r6, r3, #12, #3 @ put bits 31:29 into the MOVW imm3 field b .Lnext .Lloop: add r7, r4 adds r4, #4 @ clears Z flag @@ -129,20 +131,24 @@ ARM_BE8(rev16 ip, ip) @ in BE8, we load data in BE, but instructions still in LE #define PV_BIT24 0x00000001 #define PV_IMM8_MASK 0xff000000 +#define PV_IMMR_MSB 0x00080000 #else #define PV_BIT24 0x01000000 #define PV_IMM8_MASK 0x000000ff +#define PV_IMMR_MSB 0x00000800 #endif @ @ The ARM versions of the patchable sequences are @ @ phys-to-virt: sub , , #offset<31:24>, lsl #24 + @ sub , , #offset<23:16>, lsl #16 @ @ virt-to-phys (non-LPAE): add , , #offset<31:24>, lsl #24 + @ add , , #offset<23:16>, lsl #16 @ - @ virt-to-phys (LPAE): movw , #offset<31:24> - @ adds , , , lsl #24 + @ virt-to-phys (LPAE): movw , #offset<31:20> + @ adds , , , lsl #20 @ mov , #offset<39:32> @ adc , , #0 @ @@ -174,6 +180,9 @@ ARM_BE8(rev16 ip, ip) @ +------+-----------------+------+------+-------+ @ moveq r0, #0x400000 @ set bit 22, mov to mvn instruction + mov r3, r6, lsr #16 @ put offset bits 31-16 into r3 + mov r6, r6, lsr #24 @ put offset bits 31-24 into r6 + and r3, r3, #0xf0 @ only keep offset bits 23-20 in r3 b .Lnext .Lloop: ldr ip, [r7, r4] #ifdef CONFIG_ARM_LPAE @@ -183,14 +192,17 @@ 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 + orreq ip, ip, r6, lsl #4 @ MOVW -> mask in offset bits 31-24 + orreq ip, ip, r3, lsr #4 @ MOVW -> mask in offset bits 23-20 orrne ip, ip, r0 @ MOV -> mask in offset bits 7-0 (or bit 22) ARM_BE8(rev ip, ip) b 2f 1: #endif + tst ip, #PV_IMMR_MSB @ rotation value >= 16 ? bic ip, ip, #PV_IMM8_MASK - orr ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 + orreq ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 + orrne ip, ip, r3 ARM_BE8(, lsl #24) @ mask in offset bits 23-20 2: str ip, [r7, r4] add r4, r4, #4