--- zzzz-none-000/linux-3.10.107/arch/arm64/kernel/head.S 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/arm64/kernel/head.S 2021-02-04 17:41:59.000000000 +0000 @@ -22,72 +22,36 @@ #include #include +#include #include #include #include +#include #include +#include #include -#include #include #include #include +#include +#include #include -/* - * swapper_pg_dir is the virtual address of the initial page table. We place - * the page tables 3 * PAGE_SIZE below KERNEL_RAM_VADDR. The idmap_pg_dir has - * 2 pages and is placed below swapper_pg_dir. - */ -#define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET) +#define __PHYS_OFFSET (KERNEL_START - TEXT_OFFSET) -#if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000 -#error KERNEL_RAM_VADDR must start at 0xXXX80000 +#if (TEXT_OFFSET & 0xfff) != 0 +#error TEXT_OFFSET must be at least 4KB aligned +#elif (PAGE_OFFSET & 0x1fffff) != 0 +#error PAGE_OFFSET must be at least 2MB aligned +#elif TEXT_OFFSET > 0x1fffff +#error TEXT_OFFSET must be less than 2MB #endif -#define SWAPPER_DIR_SIZE (3 * PAGE_SIZE) -#define IDMAP_DIR_SIZE (2 * PAGE_SIZE) - - .globl swapper_pg_dir - .equ swapper_pg_dir, KERNEL_RAM_VADDR - SWAPPER_DIR_SIZE - - .globl idmap_pg_dir - .equ idmap_pg_dir, swapper_pg_dir - IDMAP_DIR_SIZE - - .macro pgtbl, ttb0, ttb1, phys - add \ttb1, \phys, #TEXT_OFFSET - SWAPPER_DIR_SIZE - sub \ttb0, \ttb1, #IDMAP_DIR_SIZE - .endm - -#ifdef CONFIG_ARM64_64K_PAGES -#define BLOCK_SHIFT PAGE_SHIFT -#define BLOCK_SIZE PAGE_SIZE -#else -#define BLOCK_SHIFT SECTION_SHIFT -#define BLOCK_SIZE SECTION_SIZE -#endif - -#define KERNEL_START KERNEL_RAM_VADDR +#define KERNEL_START _text #define KERNEL_END _end /* - * Initial memory map attributes. - */ -#ifndef CONFIG_SMP -#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF -#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF -#else -#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF | PTE_SHARED -#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S -#endif - -#ifdef CONFIG_ARM64_64K_PAGES -#define MM_MMUFLAGS PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS -#else -#define MM_MMUFLAGS PMD_ATTRINDX(MT_NORMAL) | PMD_FLAGS -#endif - -/* * Kernel startup entry point. * --------------------------- * @@ -107,56 +71,409 @@ /* * DO NOT MODIFY. Image header expected by Linux boot-loaders. */ +#ifdef CONFIG_EFI +efi_head: + /* + * This add instruction has no meaningful effect except that + * its opcode forms the magic "MZ" signature required by UEFI. + */ + add x13, x18, #0x16 + b stext +#else b stext // branch to kernel start, magic .long 0 // reserved - .quad TEXT_OFFSET // Image load offset from start of RAM +#endif + .quad _kernel_offset_le // Image load offset from start of RAM, little-endian + .quad _kernel_size_le // Effective size of kernel image, little-endian + .quad _kernel_flags_le // Informative flags, little-endian .quad 0 // reserved .quad 0 // reserved + .quad 0 // reserved + .byte 0x41 // Magic number, "ARM\x64" + .byte 0x52 + .byte 0x4d + .byte 0x64 +#ifdef CONFIG_EFI + .long pe_header - efi_head // Offset to the PE header. +#else + .word 0 // reserved +#endif + +#ifdef CONFIG_EFI + .globl __efistub_stext_offset + .set __efistub_stext_offset, stext - efi_head + .align 3 +pe_header: + .ascii "PE" + .short 0 +coff_header: + .short 0xaa64 // AArch64 + .short 2 // nr_sections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 1 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short 0x206 // Characteristics. + // IMAGE_FILE_DEBUG_STRIPPED | + // IMAGE_FILE_EXECUTABLE_IMAGE | + // IMAGE_FILE_LINE_NUMS_STRIPPED +optional_header: + .short 0x20b // PE32+ format + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long _end - stext // SizeOfCode + .long 0 // SizeOfInitializedData + .long 0 // SizeOfUninitializedData + .long __efistub_entry - efi_head // AddressOfEntryPoint + .long __efistub_stext_offset // BaseOfCode + +extra_header_fields: + .quad 0 // ImageBase + .long 0x1000 // SectionAlignment + .long PECOFF_FILE_ALIGNMENT // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short 0 // MajorImageVersion + .short 0 // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _end - efi_head // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long __efistub_stext_offset // SizeOfHeaders + .long 0 // CheckSum + .short 0xa // Subsystem (EFI application) + .short 0 // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long 0x6 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + + /* + * The EFI application loader requires a relocation section + * because EFI applications must be relocatable. This is a + * dummy section as far as we are concerned. + */ + .ascii ".reloc" + .byte 0 + .byte 0 // end of 0 padding of section name + .long 0 + .long 0 + .long 0 // SizeOfRawData + .long 0 // PointerToRawData + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long 0x42100040 // Characteristics (section flags) + + + .ascii ".text" + .byte 0 + .byte 0 + .byte 0 // end of 0 padding of section name + .long _end - stext // VirtualSize + .long __efistub_stext_offset // VirtualAddress + .long _edata - stext // SizeOfRawData + .long __efistub_stext_offset // PointerToRawData + + .long 0 // PointerToRelocations (0 for executables) + .long 0 // PointerToLineNumbers (0 for executables) + .short 0 // NumberOfRelocations (0 for executables) + .short 0 // NumberOfLineNumbers (0 for executables) + .long 0xe0500020 // Characteristics (section flags) + + /* + * EFI will load stext onwards at the 4k section alignment + * described in the PE/COFF header. To ensure that instruction + * sequences using an adrp and a :lo12: immediate will function + * correctly at this alignment, we must ensure that stext is + * placed at a 4k boundary in the Image to begin with. + */ + .align 12 +#endif ENTRY(stext) - mov x21, x0 // x21=FDT - bl __calc_phys_offset // x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET - bl el2_setup // Drop to EL1 - mrs x22, midr_el1 // x22=cpuid - mov x0, x22 - bl lookup_processor_type - mov x23, x0 // x23=current cpu_table - cbz x23, __error_p // invalid processor (x23=0)? - bl __vet_fdt + bl preserve_boot_args + bl el2_setup // Drop to EL1, w20=cpu_boot_mode + adrp x24, __PHYS_OFFSET + bl set_cpu_boot_mode_flag bl __create_page_tables // x25=TTBR0, x26=TTBR1 /* - * The following calls CPU specific code in a position independent - * manner. See arch/arm64/mm/proc.S for details. x23 = base of - * cpu_info structure selected by lookup_processor_type above. + * The following calls CPU setup code, see arch/arm64/mm/proc.S for + * details. * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ - ldr x27, __switch_data // address to jump to after + ldr x27, =__mmap_switched // address to jump to after // MMU has been enabled - adr lr, __enable_mmu // return (PIC) address - ldr x12, [x23, #CPU_INFO_SETUP] - add x12, x12, x28 // __virt_to_phys - br x12 // initialise processor + adr_l lr, __enable_mmu // return (PIC) address + b __cpu_setup // initialise processor ENDPROC(stext) /* + * Preserve the arguments passed by the bootloader in x0 .. x3 + */ +preserve_boot_args: + mov x21, x0 // x21=FDT + + adr_l x0, boot_args // record the contents of + stp x21, x1, [x0] // x0 .. x3 at kernel entry + stp x2, x3, [x0, #16] + + dmb sy // needed before dc ivac with + // MMU off + + add x1, x0, #0x20 // 4 x 8 bytes + b __inval_cache_range // tail call +ENDPROC(preserve_boot_args) + +/* + * Macro to create a table entry to the next page. + * + * tbl: page table address + * virt: virtual address + * shift: #imm page table shift + * ptrs: #imm pointers per table page + * + * Preserves: virt + * Corrupts: tmp1, tmp2 + * Returns: tbl -> next level table page address + */ + .macro create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2 + lsr \tmp1, \virt, #\shift + and \tmp1, \tmp1, #\ptrs - 1 // table index + add \tmp2, \tbl, #PAGE_SIZE + orr \tmp2, \tmp2, #PMD_TYPE_TABLE // address of next table and entry type + str \tmp2, [\tbl, \tmp1, lsl #3] + add \tbl, \tbl, #PAGE_SIZE // next level table page + .endm + +/* + * Macro to populate the PGD (and possibily PUD) for the corresponding + * block entry in the next level (tbl) for the given virtual address. + * + * Preserves: tbl, next, virt + * Corrupts: tmp1, tmp2 + */ + .macro create_pgd_entry, tbl, virt, tmp1, tmp2 + create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2 +#if SWAPPER_PGTABLE_LEVELS > 3 + create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2 +#endif +#if SWAPPER_PGTABLE_LEVELS > 2 + create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2 +#endif + .endm + +/* + * Macro to populate block entries in the page table for the start..end + * virtual range (inclusive). + * + * Preserves: tbl, flags + * Corrupts: phys, start, end, pstate + */ + .macro create_block_map, tbl, flags, phys, start, end + lsr \phys, \phys, #SWAPPER_BLOCK_SHIFT + lsr \start, \start, #SWAPPER_BLOCK_SHIFT + and \start, \start, #PTRS_PER_PTE - 1 // table index + orr \phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT // table entry + lsr \end, \end, #SWAPPER_BLOCK_SHIFT + and \end, \end, #PTRS_PER_PTE - 1 // table end index +9999: str \phys, [\tbl, \start, lsl #3] // store the entry + add \start, \start, #1 // next entry + add \phys, \phys, #SWAPPER_BLOCK_SIZE // next block + cmp \start, \end + b.ls 9999b + .endm + +/* + * Setup the initial page tables. We only setup the barest amount which is + * required to get the kernel running. The following sections are required: + * - identity mapping to enable the MMU (low address, TTBR0) + * - first few MB of the kernel linear mapping to jump to once the MMU has + * been enabled + */ +__create_page_tables: + adrp x25, idmap_pg_dir + adrp x26, swapper_pg_dir + mov x27, lr + + /* + * Invalidate the idmap and swapper page tables to avoid potential + * dirty cache lines being evicted. + */ + mov x0, x25 + add x1, x26, #SWAPPER_DIR_SIZE + bl __inval_cache_range + + /* + * Clear the idmap and swapper page tables. + */ + mov x0, x25 + add x6, x26, #SWAPPER_DIR_SIZE +1: stp xzr, xzr, [x0], #16 + stp xzr, xzr, [x0], #16 + stp xzr, xzr, [x0], #16 + stp xzr, xzr, [x0], #16 + cmp x0, x6 + b.lo 1b + + ldr x7, =SWAPPER_MM_MMUFLAGS + + /* + * Create the identity mapping. + */ + mov x0, x25 // idmap_pg_dir + adrp x3, __idmap_text_start // __pa(__idmap_text_start) + +#ifndef CONFIG_ARM64_VA_BITS_48 +#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) +#define EXTRA_PTRS (1 << (48 - EXTRA_SHIFT)) + + /* + * If VA_BITS < 48, it may be too small to allow for an ID mapping to be + * created that covers system RAM if that is located sufficiently high + * in the physical address space. So for the ID map, use an extended + * virtual range in that case, by configuring an additional translation + * level. + * First, we have to verify our assumption that the current value of + * VA_BITS was chosen such that all translation levels are fully + * utilised, and that lowering T0SZ will always result in an additional + * translation level to be configured. + */ +#if VA_BITS != EXTRA_SHIFT +#error "Mismatch between VA_BITS and page size/number of translation levels" +#endif + + /* + * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the + * entire ID map region can be mapped. As T0SZ == (64 - #bits used), + * this number conveniently equals the number of leading zeroes in + * the physical address of __idmap_text_end. + */ + adrp x5, __idmap_text_end + clz x5, x5 + cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough? + b.ge 1f // .. then skip additional level + + adr_l x6, idmap_t0sz + str x5, [x6] + dmb sy + dc ivac, x6 // Invalidate potentially stale cache line + + create_table_entry x0, x3, EXTRA_SHIFT, EXTRA_PTRS, x5, x6 +1: +#endif + + create_pgd_entry x0, x3, x5, x6 + mov x5, x3 // __pa(__idmap_text_start) + adr_l x6, __idmap_text_end // __pa(__idmap_text_end) + create_block_map x0, x7, x3, x5, x6 + + /* + * Map the kernel image (starting with PHYS_OFFSET). + */ + mov x0, x26 // swapper_pg_dir + mov x5, #PAGE_OFFSET + create_pgd_entry x0, x5, x3, x6 + ldr x6, =KERNEL_END // __va(KERNEL_END) + mov x3, x24 // phys offset + create_block_map x0, x7, x3, x5, x6 + + /* + * Since the page tables have been populated with non-cacheable + * accesses (MMU disabled), invalidate the idmap and swapper page + * tables again to remove any speculatively loaded cache lines. + */ + mov x0, x25 + add x1, x26, #SWAPPER_DIR_SIZE + dmb sy + bl __inval_cache_range + + mov lr, x27 + ret +ENDPROC(__create_page_tables) + .ltorg + +/* + * The following fragment of code is executed with the MMU enabled. + */ + .set initial_sp, init_thread_union + THREAD_START_SP +__mmap_switched: + adr_l x6, __bss_start + adr_l x7, __bss_stop + +1: cmp x6, x7 + b.hs 2f + str xzr, [x6], #8 // Clear BSS + b 1b +2: +#ifdef CONFIG_THREAD_INFO_IN_TASK + adrp x4, init_thread_union + add sp, x4, #THREAD_SIZE + adr_l x5, init_task + msr sp_el0, x5 // Save thread_info +#else + adr_l sp, initial_sp, x4 + mov x4, sp + and x4, x4, #~(THREAD_SIZE - 1) + msr sp_el0, x4 // Save thread_info +#endif + str_l x21, __fdt_pointer, x5 // Save FDT pointer + str_l x24, memstart_addr, x6 // Save PHYS_OFFSET + mov x29, #0 +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif + b start_kernel +ENDPROC(__mmap_switched) + +/* + * end early head section, begin head code that is also used for + * hotplug and needs to have the same protections as the text region + */ + .section ".text","ax" +/* * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. + * + * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if + * booted in EL1 or EL2 respectively. */ ENTRY(el2_setup) mrs x0, CurrentEL - cmp x0, #PSR_MODE_EL2t - ccmp x0, #PSR_MODE_EL2h, #0x4, ne - ldr x0, =__boot_cpu_mode // Compute __boot_cpu_mode - add x0, x0, x28 - b.eq 1f - str wzr, [x0] // Remember we don't have EL2... + cmp x0, #CurrentEL_EL2 + b.ne 1f + mrs x0, sctlr_el2 +CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2 +CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2 + msr sctlr_el2, x0 + b 2f +1: mrs x0, sctlr_el1 +CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1 +CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 + msr sctlr_el1, x0 + mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1 + isb ret /* Hyp configuration. */ -1: ldr w1, =BOOT_CPU_MODE_EL2 - str w1, [x0, #4] // This CPU has EL2 - mov x0, #(1 << 31) // 64-bit EL1 +2: mov x0, #(1 << 31) // 64-bit EL1 msr hcr_el2, x0 /* Generic timers. */ @@ -165,6 +482,25 @@ msr cnthctl_el2, x0 msr cntvoff_el2, xzr // Clear virtual offset +#ifdef CONFIG_ARM_GIC_V3 + /* GICv3 system register access */ + mrs x0, id_aa64pfr0_el1 + ubfx x0, x0, #24, #4 + cmp x0, #1 + b.ne 3f + + mrs_s x0, ICC_SRE_EL2 + orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1 + orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1 + msr_s ICC_SRE_EL2, x0 + isb // Make sure SRE is now set + mrs_s x0, ICC_SRE_EL2 // Read SRE back, + tbz x0, #0, 3f // and check that it sticks + msr_s ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + +3: +#endif + /* Populate ID registers. */ mrs x0, midr_el1 mrs x1, mpidr_el1 @@ -173,7 +509,8 @@ /* sctlr_el1 */ mov x0, #0x0800 // Set/clear RES{1,0} bits - movk x0, #0x30d0, lsl #16 +CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems +CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems msr sctlr_el1, x0 /* Coprocessor traps. */ @@ -185,15 +522,22 @@ #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to - msr mdcr_el2, x0 // all PMU counters from EL1 +4: + csel x0, xzr, x0, lt // all PMU counters from EL1 + msr mdcr_el2, x0 // (if they exist) /* Stage-2 translation */ msr vttbr_el2, xzr /* Hypervisor stub */ - adr x0, __hyp_stub_vectors + adrp x0, __hyp_stub_vectors + add x0, x0, #:lo12:__hyp_stub_vectors msr vbar_el2, x0 /* spsr */ @@ -201,68 +545,74 @@ PSR_MODE_EL1h) msr spsr_el2, x0 msr elr_el2, lr + mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 eret ENDPROC(el2_setup) /* + * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed + * in x20. See arch/arm64/include/asm/virt.h for more info. + */ +ENTRY(set_cpu_boot_mode_flag) + adr_l x1, __boot_cpu_mode + cmp w20, #BOOT_CPU_MODE_EL2 + b.ne 1f + add x1, x1, #4 +1: str w20, [x1] // This CPU has booted in EL1 + dmb sy + dc ivac, x1 // Invalidate potentially stale cache line + ret +ENDPROC(set_cpu_boot_mode_flag) + +/* * We need to find out the CPU boot mode long after boot, so we need to * store it in a writable variable. * * This is not in .bss, because we set it sufficiently early that the boot-time * zeroing of .bss would clobber it. */ - .pushsection .data + .pushsection .data..cacheline_aligned + .align L1_CACHE_SHIFT ENTRY(__boot_cpu_mode) .long BOOT_CPU_MODE_EL2 - .long 0 + .long BOOT_CPU_MODE_EL1 .popsection - .align 3 -2: .quad . - .quad PAGE_OFFSET - -#ifdef CONFIG_SMP - .pushsection .smp.pen.text, "ax" - .align 3 -1: .quad . - .quad secondary_holding_pen_release - /* * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise. */ ENTRY(secondary_holding_pen) - bl __calc_phys_offset // x24=phys offset - bl el2_setup // Drop to EL1 + bl el2_setup // Drop to EL1, w20=cpu_boot_mode + bl set_cpu_boot_mode_flag mrs x0, mpidr_el1 ldr x1, =MPIDR_HWID_BITMASK and x0, x0, x1 - adr x1, 1b - ldp x2, x3, [x1] - sub x1, x1, x2 - add x3, x3, x1 + adr_l x3, secondary_holding_pen_release pen: ldr x4, [x3] cmp x4, x0 b.eq secondary_startup wfe b pen ENDPROC(secondary_holding_pen) - .popsection + + /* + * Secondary entry point that jumps straight into the kernel. Only to + * be used where CPUs are brought online dynamically by the kernel. + */ +ENTRY(secondary_entry) + bl el2_setup // Drop to EL1 + bl set_cpu_boot_mode_flag + b secondary_startup +ENDPROC(secondary_entry) ENTRY(secondary_startup) /* * Common entry point for secondary CPUs. */ - mrs x22, midr_el1 // x22=cpuid - mov x0, x22 - bl lookup_processor_type - mov x23, x0 // x23=current cpu_table - cbz x23, __error_p // invalid processor (x23=0)? - - pgtbl x25, x26, x24 // x25=TTBR0, x26=TTBR1 - ldr x12, [x23, #CPU_INFO_SETUP] - add x12, x12, x28 // __virt_to_phys - blr x12 // initialise processor + adrp x25, idmap_pg_dir + adrp x26, swapper_pg_dir + bl __cpu_setup // initialise processor ldr x21, =secondary_data ldr x27, =__secondary_switched // address to jump to after enabling the MMU @@ -270,283 +620,56 @@ ENDPROC(secondary_startup) ENTRY(__secondary_switched) +#ifdef CONFIG_THREAD_INFO_IN_TASK + ldr x0, [x21, #CPU_BOOT_STACK] // get secondary_data.stack + mov sp, x0 + ldr x0, [x21, #CPU_BOOT_TASK] +#else ldr x0, [x21] // get secondary_data.stack mov sp, x0 + and x0, x0, #~(THREAD_SIZE - 1) +#endif + msr sp_el0, x0 // save thread_info mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) -#endif /* CONFIG_SMP */ /* - * Setup common bits before finally enabling the MMU. Essentially this is just - * loading the page table pointer and vector base registers. + * Enable the MMU. * - * On entry to this code, x0 must contain the SCTLR_EL1 value for turning on - * the MMU. + * x0 = SCTLR_EL1 value for turning on the MMU. + * x27 = *virtual* address to jump to upon completion + * + * Other registers depend on the function called upon completion. + * + * Checks if the selected granule size is supported by the CPU. + * If it isn't, park the CPU */ + .section ".idmap.text", "ax" __enable_mmu: + mrs x1, ID_AA64MMFR0_EL1 + ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4 + cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED + b.ne __no_granule_support ldr x5, =vectors msr vbar_el1, x5 msr ttbr0_el1, x25 // load TTBR0 msr ttbr1_el1, x26 // load TTBR1 isb - b __turn_mmu_on -ENDPROC(__enable_mmu) - -/* - * Enable the MMU. This completely changes the structure of the visible memory - * space. You will not be able to trace execution through this. - * - * x0 = system control register - * x27 = *virtual* address to jump to upon completion - * - * other registers depend on the function called upon completion - */ - .align 6 -__turn_mmu_on: msr sctlr_el1, x0 isb - br x27 -ENDPROC(__turn_mmu_on) - -/* - * Calculate the start of physical memory. - */ -__calc_phys_offset: - adr x0, 1f - ldp x1, x2, [x0] - sub x28, x0, x1 // x28 = PHYS_OFFSET - PAGE_OFFSET - add x24, x2, x28 // x24 = PHYS_OFFSET - ret -ENDPROC(__calc_phys_offset) - - .align 3 -1: .quad . - .quad PAGE_OFFSET - -/* - * Macro to populate the PGD for the corresponding block entry in the next - * level (tbl) for the given virtual address. - * - * Preserves: pgd, tbl, virt - * Corrupts: tmp1, tmp2 - */ - .macro create_pgd_entry, pgd, tbl, virt, tmp1, tmp2 - lsr \tmp1, \virt, #PGDIR_SHIFT - and \tmp1, \tmp1, #PTRS_PER_PGD - 1 // PGD index - orr \tmp2, \tbl, #3 // PGD entry table type - str \tmp2, [\pgd, \tmp1, lsl #3] - .endm - -/* - * Macro to populate block entries in the page table for the start..end - * virtual range (inclusive). - * - * Preserves: tbl, flags - * Corrupts: phys, start, end, pstate - */ - .macro create_block_map, tbl, flags, phys, start, end, idmap=0 - lsr \phys, \phys, #BLOCK_SHIFT - .if \idmap - and \start, \phys, #PTRS_PER_PTE - 1 // table index - .else - lsr \start, \start, #BLOCK_SHIFT - and \start, \start, #PTRS_PER_PTE - 1 // table index - .endif - orr \phys, \flags, \phys, lsl #BLOCK_SHIFT // table entry - .ifnc \start,\end - lsr \end, \end, #BLOCK_SHIFT - and \end, \end, #PTRS_PER_PTE - 1 // table end index - .endif -9999: str \phys, [\tbl, \start, lsl #3] // store the entry - .ifnc \start,\end - add \start, \start, #1 // next entry - add \phys, \phys, #BLOCK_SIZE // next block - cmp \start, \end - b.ls 9999b - .endif - .endm - -/* - * Setup the initial page tables. We only setup the barest amount which is - * required to get the kernel running. The following sections are required: - * - identity mapping to enable the MMU (low address, TTBR0) - * - first few MB of the kernel linear mapping to jump to once the MMU has - * been enabled, including the FDT blob (TTBR1) - * - UART mapping if CONFIG_EARLY_PRINTK is enabled (TTBR1) - */ -__create_page_tables: - pgtbl x25, x26, x24 // idmap_pg_dir and swapper_pg_dir addresses - /* - * Clear the idmap and swapper page tables. + * Invalidate the local I-cache so that any instructions fetched + * speculatively from the PoC are discarded, since they may have + * been dynamically patched at the PoU. */ - mov x0, x25 - add x6, x26, #SWAPPER_DIR_SIZE -1: stp xzr, xzr, [x0], #16 - stp xzr, xzr, [x0], #16 - stp xzr, xzr, [x0], #16 - stp xzr, xzr, [x0], #16 - cmp x0, x6 - b.lo 1b - - ldr x7, =MM_MMUFLAGS - - /* - * Create the identity mapping. - */ - add x0, x25, #PAGE_SIZE // section table address - adr x3, __turn_mmu_on // virtual/physical address - create_pgd_entry x25, x0, x3, x5, x6 - create_block_map x0, x7, x3, x5, x5, idmap=1 - - /* - * Map the kernel image (starting with PHYS_OFFSET). - */ - add x0, x26, #PAGE_SIZE // section table address - mov x5, #PAGE_OFFSET - create_pgd_entry x26, x0, x5, x3, x6 - ldr x6, =KERNEL_END - 1 - mov x3, x24 // phys offset - create_block_map x0, x7, x3, x5, x6 - - /* - * Map the FDT blob (maximum 2MB; must be within 512MB of - * PHYS_OFFSET). - */ - mov x3, x21 // FDT phys address - and x3, x3, #~((1 << 21) - 1) // 2MB aligned - mov x6, #PAGE_OFFSET - sub x5, x3, x24 // subtract PHYS_OFFSET - tst x5, #~((1 << 29) - 1) // within 512MB? - csel x21, xzr, x21, ne // zero the FDT pointer - b.ne 1f - add x5, x5, x6 // __va(FDT blob) - add x6, x5, #1 << 21 // 2MB for the FDT blob - sub x6, x6, #1 // inclusive range - create_block_map x0, x7, x3, x5, x6 -1: -#ifdef CONFIG_EARLY_PRINTK - /* - * Create the pgd entry for the UART mapping. The full mapping is done - * later based earlyprintk kernel parameter. - */ - ldr x5, =EARLYCON_IOBASE // UART virtual address - add x0, x26, #2 * PAGE_SIZE // section table address - create_pgd_entry x26, x0, x5, x6, x7 -#endif - ret -ENDPROC(__create_page_tables) - .ltorg - - .align 3 - .type __switch_data, %object -__switch_data: - .quad __mmap_switched - .quad __data_loc // x4 - .quad _data // x5 - .quad __bss_start // x6 - .quad _end // x7 - .quad processor_id // x4 - .quad __fdt_pointer // x5 - .quad memstart_addr // x6 - .quad init_thread_union + THREAD_START_SP // sp - -/* - * The following fragment of code is executed with the MMU on in MMU mode, and - * uses absolute addresses; this is not position independent. - */ -__mmap_switched: - adr x3, __switch_data + 8 - - ldp x4, x5, [x3], #16 - ldp x6, x7, [x3], #16 - cmp x4, x5 // Copy data segment if needed -1: ccmp x5, x6, #4, ne - b.eq 2f - ldr x16, [x4], #8 - str x16, [x5], #8 - b 1b -2: -1: cmp x6, x7 - b.hs 2f - str xzr, [x6], #8 // Clear BSS - b 1b -2: - ldp x4, x5, [x3], #16 - ldr x6, [x3], #8 - ldr x16, [x3] - mov sp, x16 - str x22, [x4] // Save processor ID - str x21, [x5] // Save FDT pointer - str x24, [x6] // Save PHYS_OFFSET - mov x29, #0 - b start_kernel -ENDPROC(__mmap_switched) - -/* - * Exception handling. Something went wrong and we can't proceed. We ought to - * tell the user, but since we don't have any guarantee that we're even - * running on the right architecture, we do virtually nothing. - */ -__error_p: -ENDPROC(__error_p) - -__error: -1: nop - b 1b -ENDPROC(__error) - -/* - * This function gets the processor ID in w0 and searches the cpu_table[] for - * a match. It returns a pointer to the struct cpu_info it found. The - * cpu_table[] must end with an empty (all zeros) structure. - * - * This routine can be called via C code and it needs to work with the MMU - * both disabled and enabled (the offset is calculated automatically). - */ -ENTRY(lookup_processor_type) - adr x1, __lookup_processor_type_data - ldp x2, x3, [x1] - sub x1, x1, x2 // get offset between VA and PA - add x3, x3, x1 // convert VA to PA -1: - ldp w5, w6, [x3] // load cpu_id_val and cpu_id_mask - cbz w5, 2f // end of list? - and w6, w6, w0 - cmp w5, w6 - b.eq 3f - add x3, x3, #CPU_INFO_SZ - b 1b -2: - mov x3, #0 // unknown processor -3: - mov x0, x3 - ret -ENDPROC(lookup_processor_type) - - .align 3 - .type __lookup_processor_type_data, %object -__lookup_processor_type_data: - .quad . - .quad cpu_table - .size __lookup_processor_type_data, . - __lookup_processor_type_data + ic iallu + dsb nsh + isb + br x27 +ENDPROC(__enable_mmu) -/* - * Determine validity of the x21 FDT pointer. - * The dtb must be 8-byte aligned and live in the first 512M of memory. - */ -__vet_fdt: - tst x21, #0x7 - b.ne 1f - cmp x21, x24 - b.lt 1f - mov x0, #(1 << 29) - add x0, x0, x24 - cmp x21, x0 - b.ge 1f - ret -1: - mov x21, #0 - ret -ENDPROC(__vet_fdt) +__no_granule_support: + wfe + b __no_granule_support +ENDPROC(__no_granule_support)