diff options
Diffstat (limited to 'arch/arm64/kernel/head.S')
| -rw-r--r-- | arch/arm64/kernel/head.S | 201 |
1 files changed, 178 insertions, 23 deletions
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ffe9c2b6431b..4203d5f257bc 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -29,11 +29,14 @@ #include <asm/asm-offsets.h> #include <asm/cache.h> #include <asm/cputype.h> +#include <asm/elf.h> #include <asm/kernel-pgtable.h> +#include <asm/kvm_arm.h> #include <asm/memory.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable.h> #include <asm/page.h> +#include <asm/smp.h> #include <asm/sysreg.h> #include <asm/thread_info.h> #include <asm/virt.h> @@ -67,12 +70,11 @@ * in the entry routines. */ __HEAD - +_head: /* * 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. @@ -83,9 +85,9 @@ efi_head: b stext // branch to kernel start, magic .long 0 // reserved #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 + le64sym _kernel_offset_le // Image load offset from start of RAM, little-endian + le64sym _kernel_size_le // Effective size of kernel image, little-endian + le64sym _kernel_flags_le // Informative flags, little-endian .quad 0 // reserved .quad 0 // reserved .quad 0 // reserved @@ -94,14 +96,14 @@ efi_head: .byte 0x4d .byte 0x64 #ifdef CONFIG_EFI - .long pe_header - efi_head // Offset to the PE header. + .long pe_header - _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 + .set __efistub_stext_offset, stext - _head .align 3 pe_header: .ascii "PE" @@ -124,7 +126,7 @@ optional_header: .long _end - stext // SizeOfCode .long 0 // SizeOfInitializedData .long 0 // SizeOfUninitializedData - .long __efistub_entry - efi_head // AddressOfEntryPoint + .long __efistub_entry - _head // AddressOfEntryPoint .long __efistub_stext_offset // BaseOfCode extra_header_fields: @@ -139,7 +141,7 @@ extra_header_fields: .short 0 // MinorSubsystemVersion .long 0 // Win32VersionValue - .long _end - efi_head // SizeOfImage + .long _end - _head // SizeOfImage // Everything before the kernel image is considered part of the header .long __efistub_stext_offset // SizeOfHeaders @@ -210,6 +212,7 @@ section_table: ENTRY(stext) bl preserve_boot_args bl el2_setup // Drop to EL1, w20=cpu_boot_mode + mov x23, xzr // KASLR offset, defaults to 0 adrp x24, __PHYS_OFFSET bl set_cpu_boot_mode_flag bl __create_page_tables // x25=TTBR0, x26=TTBR1 @@ -219,11 +222,13 @@ ENTRY(stext) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ - ldr x27, =__mmap_switched // address to jump to after + ldr x27, 0f // address to jump to after // MMU has been enabled adr_l lr, __enable_mmu // return (PIC) address b __cpu_setup // initialise processor ENDPROC(stext) + .align 3 +0: .quad __mmap_switched - (_head - TEXT_OFFSET) + KIMAGE_VADDR /* * Preserve the arguments passed by the bootloader in x0 .. x3 @@ -311,7 +316,7 @@ ENDPROC(preserve_boot_args) __create_page_tables: adrp x25, idmap_pg_dir adrp x26, swapper_pg_dir - mov x27, lr + mov x28, lr /* * Invalidate the idmap and swapper page tables to avoid potential @@ -389,9 +394,11 @@ __create_page_tables: * Map the kernel image (starting with PHYS_OFFSET). */ mov x0, x26 // swapper_pg_dir - mov x5, #PAGE_OFFSET + ldr x5, =KIMAGE_VADDR + add x5, x5, x23 // add KASLR displacement create_pgd_entry x0, x5, x3, x6 - ldr x6, =KERNEL_END // __va(KERNEL_END) + ldr w6, kernel_img_size + add x6, x6, x5 mov x3, x24 // phys offset create_block_map x0, x7, x3, x5, x6 @@ -405,9 +412,11 @@ __create_page_tables: dmb sy bl __inval_cache_range - mov lr, x27 - ret + ret x28 ENDPROC(__create_page_tables) + +kernel_img_size: + .long _end - (_head - TEXT_OFFSET) .ltorg /* @@ -415,23 +424,81 @@ ENDPROC(__create_page_tables) */ .set initial_sp, init_thread_union + THREAD_START_SP __mmap_switched: + mov x28, lr // preserve LR + adr_l x8, vectors // load VBAR_EL1 with virtual + msr vbar_el1, x8 // vector table address + isb + // Clear BSS adr_l x0, __bss_start mov x1, xzr adr_l x2, __bss_stop sub x2, x2, x0 bl __pi_memset + dsb ishst // Make zero page visible to PTW + +#ifdef CONFIG_RELOCATABLE + + /* + * Iterate over each entry in the relocation table, and apply the + * relocations in place. + */ + adr_l x8, __dynsym_start // start of symbol table + adr_l x9, __reloc_start // start of reloc table + adr_l x10, __reloc_end // end of reloc table + +0: cmp x9, x10 + b.hs 2f + ldp x11, x12, [x9], #24 + ldr x13, [x9, #-8] + cmp w12, #R_AARCH64_RELATIVE + b.ne 1f + add x13, x13, x23 // relocate + str x13, [x11, x23] + b 0b + +1: cmp w12, #R_AARCH64_ABS64 + b.ne 0b + add x12, x12, x12, lsl #1 // symtab offset: 24x top word + add x12, x8, x12, lsr #(32 - 3) // ... shifted into bottom word + ldrsh w14, [x12, #6] // Elf64_Sym::st_shndx + ldr x15, [x12, #8] // Elf64_Sym::st_value + cmp w14, #-0xf // SHN_ABS (0xfff1) ? + add x14, x15, x23 // relocate + csel x15, x14, x15, ne + add x15, x13, x15 + str x15, [x11, x23] + b 0b + +2: adr_l x8, kimage_vaddr // make relocated kimage_vaddr + dc cvac, x8 // value visible to secondaries + dsb sy // with MMU off +#endif adr_l sp, initial_sp, x4 mov x4, sp and x4, x4, #~(THREAD_SIZE - 1) msr sp_el0, x4 // Save thread_info str_l x21, __fdt_pointer, x5 // Save FDT pointer - str_l x24, memstart_addr, x6 // Save PHYS_OFFSET + + ldr_l x4, kimage_vaddr // Save the offset between + sub x4, x4, x24 // the kernel virtual and + str_l x4, kimage_voffset, x5 // physical mappings + mov x29, #0 #ifdef CONFIG_KASAN bl kasan_early_init #endif +#ifdef CONFIG_RANDOMIZE_BASE + cbnz x23, 0f // already running randomized? + mov x0, x21 // pass FDT address in x0 + bl kaslr_early_init // parse FDT for KASLR options + cbz x0, 0f // KASLR disabled? just proceed + mov x23, x0 // record KASLR offset + ret x28 // we must enable KASLR, return + // to __enable_mmu() +0: +#endif b start_kernel ENDPROC(__mmap_switched) @@ -440,6 +507,10 @@ ENDPROC(__mmap_switched) * hotplug and needs to have the same protections as the text region */ .section ".text","ax" + +ENTRY(kimage_vaddr) + .quad _text - TEXT_OFFSET + /* * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. @@ -464,9 +535,27 @@ CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 isb ret +2: +#ifdef CONFIG_ARM64_VHE + /* + * Check for VHE being present. For the rest of the EL2 setup, + * x2 being non-zero indicates that we do have VHE, and that the + * kernel is intended to run at EL2. + */ + mrs x2, id_aa64mmfr1_el1 + ubfx x2, x2, #8, #4 +#else + mov x2, xzr +#endif + /* Hyp configuration. */ -2: mov x0, #(1 << 31) // 64-bit EL1 + mov x0, #HCR_RW // 64-bit EL1 + cbz x2, set_hcr + orr x0, x0, #HCR_TGE // Enable Host Extensions + orr x0, x0, #HCR_E2H +set_hcr: msr hcr_el2, x0 + isb /* Generic timers. */ mrs x0, cnthctl_el2 @@ -514,13 +603,25 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #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: /* Stage-2 translation */ msr vttbr_el2, xzr + cbz x2, install_el2_stub + + mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 + isb + ret + +install_el2_stub: /* Hypervisor stub */ adrp x0, __hyp_stub_vectors add x0, x0, #:lo12:__hyp_stub_vectors @@ -600,13 +701,20 @@ ENTRY(secondary_startup) 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 + ldr x8, kimage_vaddr + ldr w9, 0f + sub x27, x8, w9, sxtw // address to jump to after enabling the MMU b __enable_mmu ENDPROC(secondary_startup) +0: .long (_text - TEXT_OFFSET) - __secondary_switched ENTRY(__secondary_switched) - ldr x0, [x21] // get secondary_data.stack + adr_l x5, vectors + msr vbar_el1, x5 + isb + + adr_l x0, secondary_data + ldr x0, [x0, #CPU_BOOT_STACK] // get secondary_data.stack mov sp, x0 and x0, x0, #~(THREAD_SIZE - 1) msr sp_el0, x0 // save thread_info @@ -615,6 +723,29 @@ ENTRY(__secondary_switched) ENDPROC(__secondary_switched) /* + * The booting CPU updates the failed status @__early_cpu_boot_status, + * with MMU turned off. + * + * update_early_cpu_boot_status tmp, status + * - Corrupts tmp1, tmp2 + * - Writes 'status' to __early_cpu_boot_status and makes sure + * it is committed to memory. + */ + + .macro update_early_cpu_boot_status status, tmp1, tmp2 + mov \tmp2, #\status + str_l \tmp2, __early_cpu_boot_status, \tmp1 + dmb sy + dc ivac, \tmp1 // Invalidate potentially stale cache line + .endm + + .pushsection .data..cacheline_aligned + .align L1_CACHE_SHIFT +ENTRY(__early_cpu_boot_status) + .long 0 + .popsection + +/* * Enable the MMU. * * x0 = SCTLR_EL1 value for turning on the MMU. @@ -627,12 +758,12 @@ ENDPROC(__secondary_switched) */ .section ".idmap.text", "ax" __enable_mmu: + mrs x22, sctlr_el1 // preserve old SCTLR_EL1 value 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 + update_early_cpu_boot_status 0, x1, x2 msr ttbr0_el1, x25 // load TTBR0 msr ttbr1_el1, x26 // load TTBR1 isb @@ -646,10 +777,34 @@ __enable_mmu: ic iallu dsb nsh isb +#ifdef CONFIG_RANDOMIZE_BASE + mov x19, x0 // preserve new SCTLR_EL1 value + blr x27 + + /* + * If we return here, we have a KASLR displacement in x23 which we need + * to take into account by discarding the current kernel mapping and + * creating a new one. + */ + msr sctlr_el1, x22 // disable the MMU + isb + bl __create_page_tables // recreate kernel mapping + + msr sctlr_el1, x19 // re-enable the MMU + isb + ic iallu // flush instructions fetched + dsb nsh // via old mapping + isb + add x27, x27, x23 // relocated __mmap_switched +#endif br x27 ENDPROC(__enable_mmu) __no_granule_support: + /* Indicate that this CPU can't boot and is stuck in the kernel */ + update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2 +1: wfe - b __no_granule_support + wfi + b 1b ENDPROC(__no_granule_support) |