diff options
Diffstat (limited to 'arch/arm64/include/asm/assembler.h')
| -rw-r--r-- | arch/arm64/include/asm/assembler.h | 882 |
1 files changed, 817 insertions, 65 deletions
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 5aceb83b3f5c..f0ca7196f6fa 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -1,117 +1,869 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Based on arch/arm/include/asm/assembler.h + * Based on arch/arm/include/asm/assembler.h, arch/arm/mm/proc-macros.S * * Copyright (C) 1996-2000 Russell King * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #error "Only include this from assembly code" #endif +#ifndef __ASM_ASSEMBLER_H +#define __ASM_ASSEMBLER_H + +#include <linux/export.h> + +#include <asm/alternative.h> +#include <asm/asm-bug.h> +#include <asm/asm-extable.h> +#include <asm/asm-offsets.h> +#include <asm/cpufeature.h> +#include <asm/cputype.h> +#include <asm/debug-monitors.h> +#include <asm/page.h> +#include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> +#include <asm/thread_info.h> + + /* + * Provide a wxN alias for each wN register so what we can paste a xN + * reference after a 'w' to obtain the 32-bit version. + */ + .irp n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30 + wx\n .req w\n + .endr + + .macro disable_daif + msr daifset, #0xf + .endm /* - * Stack pushing/popping (register pairs only). Equivalent to store decrement - * before, load increment after. + * Save/restore interrupts. */ - .macro push, xreg1, xreg2 - stp \xreg1, \xreg2, [sp, #-16]! + .macro save_and_disable_daif, flags + mrs \flags, daif + msr daifset, #0xf + .endm + + .macro save_and_disable_irq, flags + mrs \flags, daif + msr daifset, #3 .endm - .macro pop, xreg1, xreg2 - ldp \xreg1, \xreg2, [sp], #16 + .macro restore_irq, flags + msr daif, \flags + .endm + + .macro disable_step_tsk, flgs, tmp + tbz \flgs, #TIF_SINGLESTEP, 9990f + mrs \tmp, mdscr_el1 + bic \tmp, \tmp, #MDSCR_EL1_SS + msr mdscr_el1, \tmp + isb // Take effect before a subsequent clear of DAIF.D +9990: + .endm + + /* call with daif masked */ + .macro enable_step_tsk, flgs, tmp + tbz \flgs, #TIF_SINGLESTEP, 9990f + mrs \tmp, mdscr_el1 + orr \tmp, \tmp, #MDSCR_EL1_SS + msr mdscr_el1, \tmp +9990: .endm /* - * Enable and disable interrupts. + * RAS Error Synchronization barrier */ - .macro disable_irq - msr daifset, #2 + .macro esb +#ifdef CONFIG_ARM64_RAS_EXTN + hint #16 +#else + nop +#endif .endm - .macro enable_irq - msr daifclr, #2 +/* + * Value prediction barrier + */ + .macro csdb + hint #20 .endm /* - * Save/disable and restore interrupts. + * Clear Branch History instruction */ - .macro save_and_disable_irqs, olddaif - mrs \olddaif, daif - disable_irq + .macro clearbhb + hint #22 .endm - .macro restore_irqs, olddaif - msr daif, \olddaif +/* + * Speculation barrier + */ + .macro sb +alternative_if_not ARM64_HAS_SB + dsb nsh + isb +alternative_else + SB_BARRIER_INSN + nop +alternative_endif .endm /* - * Enable and disable debug exceptions. + * NOP sequence */ - .macro disable_dbg - msr daifset, #8 + .macro nops, num + .rept \num + nop + .endr .endm - .macro enable_dbg - msr daifclr, #8 +/* + * Register aliases. + */ +lr .req x30 // link register + +/* + * Vector entry + */ + .macro ventry label + .align 7 + b \label .endm - .macro disable_step, tmp - mrs \tmp, mdscr_el1 - bic \tmp, \tmp, #1 - msr mdscr_el1, \tmp +/* + * Select code when configured for BE. + */ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CPU_BE(code...) code +#else +#define CPU_BE(code...) +#endif + +/* + * Select code when configured for LE. + */ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CPU_LE(code...) +#else +#define CPU_LE(code...) code +#endif + +/* + * Define a macro that constructs a 64-bit value by concatenating two + * 32-bit registers. Note that on big endian systems the order of the + * registers is swapped. + */ +#ifndef CONFIG_CPU_BIG_ENDIAN + .macro regs_to_64, rd, lbits, hbits +#else + .macro regs_to_64, rd, hbits, lbits +#endif + orr \rd, \lbits, \hbits, lsl #32 .endm - .macro enable_step, tmp - mrs \tmp, mdscr_el1 - orr \tmp, \tmp, #1 - msr mdscr_el1, \tmp +/* + * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where + * <symbol> is within the range +/- 4 GB of the PC. + */ + /* + * @dst: destination register (64 bit wide) + * @sym: name of the symbol + */ + .macro adr_l, dst, sym + adrp \dst, \sym + add \dst, \dst, :lo12:\sym .endm - .macro enable_dbg_if_not_stepping, tmp - mrs \tmp, mdscr_el1 - tbnz \tmp, #0, 9990f - enable_dbg -9990: + /* + * @dst: destination register (32 or 64 bit wide) + * @sym: name of the symbol + * @tmp: optional 64-bit scratch register to be used if <dst> is a + * 32-bit wide register, in which case it cannot be used to hold + * the address + */ + .macro ldr_l, dst, sym, tmp= + .ifb \tmp + adrp \dst, \sym + ldr \dst, [\dst, :lo12:\sym] + .else + adrp \tmp, \sym + ldr \dst, [\tmp, :lo12:\sym] + .endif + .endm + + /* + * @src: source register (32 or 64 bit wide) + * @sym: name of the symbol + * @tmp: mandatory 64-bit scratch register to calculate the address + * while <src> needs to be preserved. + */ + .macro str_l, src, sym, tmp + adrp \tmp, \sym + str \src, [\tmp, :lo12:\sym] + .endm + + /* + * @dst: destination register + */ +#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) + .macro get_this_cpu_offset, dst + mrs \dst, tpidr_el2 + .endm +#else + .macro get_this_cpu_offset, dst +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN + mrs \dst, tpidr_el1 +alternative_else + mrs \dst, tpidr_el2 +alternative_endif + .endm + + .macro set_this_cpu_offset, src +alternative_if_not ARM64_HAS_VIRT_HOST_EXTN + msr tpidr_el1, \src +alternative_else + msr tpidr_el2, \src +alternative_endif + .endm +#endif + + /* + * @dst: Result of per_cpu(sym, smp_processor_id()) (can be SP) + * @sym: The name of the per-cpu variable + * @tmp: scratch register + */ + .macro adr_this_cpu, dst, sym, tmp + adrp \tmp, \sym + add \dst, \tmp, #:lo12:\sym + get_this_cpu_offset \tmp + add \dst, \dst, \tmp + .endm + + /* + * @dst: Result of READ_ONCE(per_cpu(sym, smp_processor_id())) + * @sym: The name of the per-cpu variable + * @tmp: scratch register + */ + .macro ldr_this_cpu dst, sym, tmp + adr_l \dst, \sym + get_this_cpu_offset \tmp + ldr \dst, [\dst, \tmp] .endm /* - * SMP data memory barrier + * read_ctr - read CTR_EL0. If the system has mismatched register fields, + * provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val */ - .macro smp_dmb, opt -#ifdef CONFIG_SMP - dmb \opt + .macro read_ctr, reg +#ifndef __KVM_NVHE_HYPERVISOR__ +alternative_if_not ARM64_MISMATCHED_CACHE_TYPE + mrs \reg, ctr_el0 // read CTR + nop +alternative_else + ldr_l \reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL +alternative_endif +#else +alternative_if_not ARM64_KVM_PROTECTED_MODE + ASM_BUG() +alternative_else_nop_endif +alternative_cb ARM64_ALWAYS_SYSTEM, kvm_compute_final_ctr_el0 + movz \reg, #0 + movk \reg, #0, lsl #16 + movk \reg, #0, lsl #32 + movk \reg, #0, lsl #48 +alternative_cb_end #endif .endm -#define USER(l, x...) \ -9999: x; \ - .section __ex_table,"a"; \ - .align 3; \ - .quad 9999b,l; \ - .previous /* - * Register aliases. + * raw_dcache_line_size - get the minimum D-cache line size on this CPU + * from the CTR register. */ -lr .req x30 // link register + .macro raw_dcache_line_size, reg, tmp + mrs \tmp, ctr_el0 // read CTR + ubfm \tmp, \tmp, #16, #19 // cache line size encoding + mov \reg, #4 // bytes per word + lsl \reg, \reg, \tmp // actual cache line size + .endm /* - * Vector entry + * dcache_line_size - get the safe D-cache line size across all CPUs */ - .macro ventry label - .align 7 - b \label + .macro dcache_line_size, reg, tmp + read_ctr \tmp + ubfm \tmp, \tmp, #16, #19 // cache line size encoding + mov \reg, #4 // bytes per word + lsl \reg, \reg, \tmp // actual cache line size + .endm + +/* + * raw_icache_line_size - get the minimum I-cache line size on this CPU + * from the CTR register. + */ + .macro raw_icache_line_size, reg, tmp + mrs \tmp, ctr_el0 // read CTR + and \tmp, \tmp, #0xf // cache line size encoding + mov \reg, #4 // bytes per word + lsl \reg, \reg, \tmp // actual cache line size + .endm + +/* + * icache_line_size - get the safe I-cache line size across all CPUs + */ + .macro icache_line_size, reg, tmp + read_ctr \tmp + and \tmp, \tmp, #0xf // cache line size encoding + mov \reg, #4 // bytes per word + lsl \reg, \reg, \tmp // actual cache line size + .endm + +/* + * tcr_set_t0sz - update TCR.T0SZ so that we can load the ID map + */ + .macro tcr_set_t0sz, valreg, t0sz + bfi \valreg, \t0sz, #TCR_EL1_T0SZ_SHIFT, #TCR_EL1_T0SZ_WIDTH + .endm + +/* + * tcr_set_t1sz - update TCR.T1SZ + */ + .macro tcr_set_t1sz, valreg, t1sz + bfi \valreg, \t1sz, #TCR_EL1_T1SZ_SHIFT, #TCR_EL1_T1SZ_WIDTH + .endm + +/* + * tcr_compute_pa_size - set TCR.(I)PS to the highest supported + * ID_AA64MMFR0_EL1.PARange value + * + * tcr: register with the TCR_ELx value to be updated + * pos: IPS or PS bitfield position + * tmp{0,1}: temporary registers + */ + .macro tcr_compute_pa_size, tcr, pos, tmp0, tmp1 + mrs \tmp0, ID_AA64MMFR0_EL1 + // Narrow PARange to fit the PS field in TCR_ELx + ubfx \tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3 + mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX +#ifdef CONFIG_ARM64_LPA2 +alternative_if_not ARM64_HAS_VA52 + mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_48 +alternative_else_nop_endif +#endif + cmp \tmp0, \tmp1 + csel \tmp0, \tmp1, \tmp0, hi + bfi \tcr, \tmp0, \pos, #3 + .endm + + .macro __dcache_op_workaround_clean_cache, op, addr +alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE + dc \op, \addr +alternative_else + dc civac, \addr +alternative_endif + .endm + +/* + * Macro to perform a data cache maintenance for the interval + * [start, end) with dcache line size explicitly provided. + * + * op: operation passed to dc instruction + * domain: domain used in dsb instruction + * start: starting virtual address of the region + * end: end virtual address of the region + * linesz: dcache line size + * fixup: optional label to branch to on user fault + * Corrupts: start, end, tmp + */ + .macro dcache_by_myline_op op, domain, start, end, linesz, tmp, fixup + sub \tmp, \linesz, #1 + bic \start, \start, \tmp +.Ldcache_op\@: + .ifc \op, cvau + __dcache_op_workaround_clean_cache \op, \start + .else + .ifc \op, cvac + __dcache_op_workaround_clean_cache \op, \start + .else + .ifc \op, cvap + sys 3, c7, c12, 1, \start // dc cvap + .else + .ifc \op, cvadp + sys 3, c7, c13, 1, \start // dc cvadp + .else + dc \op, \start + .endif + .endif + .endif + .endif + add \start, \start, \linesz + cmp \start, \end + b.lo .Ldcache_op\@ + dsb \domain + + _cond_uaccess_extable .Ldcache_op\@, \fixup + .endm + +/* + * Macro to perform a data cache maintenance for the interval + * [start, end) + * + * op: operation passed to dc instruction + * domain: domain used in dsb instruction + * start: starting virtual address of the region + * end: end virtual address of the region + * fixup: optional label to branch to on user fault + * Corrupts: start, end, tmp1, tmp2 + */ + .macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup + dcache_line_size \tmp1, \tmp2 + dcache_by_myline_op \op, \domain, \start, \end, \tmp1, \tmp2, \fixup + .endm + +/* + * Macro to perform an instruction cache maintenance for the interval + * [start, end) + * + * start, end: virtual addresses describing the region + * fixup: optional label to branch to on user fault + * Corrupts: tmp1, tmp2 + */ + .macro invalidate_icache_by_line start, end, tmp1, tmp2, fixup + icache_line_size \tmp1, \tmp2 + sub \tmp2, \tmp1, #1 + bic \tmp2, \start, \tmp2 +.Licache_op\@: + ic ivau, \tmp2 // invalidate I line PoU + add \tmp2, \tmp2, \tmp1 + cmp \tmp2, \end + b.lo .Licache_op\@ + dsb ish + isb + + _cond_uaccess_extable .Licache_op\@, \fixup + .endm + +/* + * load_ttbr1 - install @pgtbl as a TTBR1 page table + * pgtbl preserved + * tmp1/tmp2 clobbered, either may overlap with pgtbl + */ + .macro load_ttbr1, pgtbl, tmp1, tmp2 + phys_to_ttbr \tmp1, \pgtbl + offset_ttbr1 \tmp1, \tmp2 + msr ttbr1_el1, \tmp1 + isb + .endm + +/* + * To prevent the possibility of old and new partial table walks being visible + * in the tlb, switch the ttbr to a zero page when we invalidate the old + * records. D4.7.1 'General TLB maintenance requirements' in ARM DDI 0487A.i + * Even switching to our copied tables will cause a changed output address at + * each stage of the walk. + */ + .macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2 + phys_to_ttbr \tmp, \zero_page + msr ttbr1_el1, \tmp + isb + tlbi vmalle1 + dsb nsh + load_ttbr1 \page_table, \tmp, \tmp2 + .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 + ubfx \tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4 + cmp \tmpreg, #ID_AA64DFR0_EL1_PMUVer_NI + ccmp \tmpreg, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne + b.eq 9000f // Skip if no PMU present or IMP_DEF + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm + +/* + * reset_amuserenr_el0 - reset AMUSERENR_EL0 if AMUv1 present + */ + .macro reset_amuserenr_el0, tmpreg + mrs \tmpreg, id_aa64pfr0_el1 // Check ID_AA64PFR0_EL1 + ubfx \tmpreg, \tmpreg, #ID_AA64PFR0_EL1_AMU_SHIFT, #4 + cbz \tmpreg, .Lskip_\@ // Skip if no AMU present + msr_s SYS_AMUSERENR_EL0, xzr // Disable AMU access from EL0 +.Lskip_\@: + .endm +/* + * copy_page - copy src to dest using temp registers t1-t8 + */ + .macro copy_page dest:req src:req t1:req t2:req t3:req t4:req t5:req t6:req t7:req t8:req +9998: ldp \t1, \t2, [\src] + ldp \t3, \t4, [\src, #16] + ldp \t5, \t6, [\src, #32] + ldp \t7, \t8, [\src, #48] + add \src, \src, #64 + stnp \t1, \t2, [\dest] + stnp \t3, \t4, [\dest, #16] + stnp \t5, \t6, [\dest, #32] + stnp \t7, \t8, [\dest, #48] + add \dest, \dest, #64 + tst \src, #(PAGE_SIZE - 1) + b.ne 9998b + .endm + +/* + * Annotate a function as being unsuitable for kprobes. + */ +#ifdef CONFIG_KPROBES +#define NOKPROBE(x) \ + .pushsection "_kprobe_blacklist", "aw"; \ + .quad x; \ + .popsection; +#else +#define NOKPROBE(x) +#endif + +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +#define EXPORT_SYMBOL_NOKASAN(name) +#else +#define EXPORT_SYMBOL_NOKASAN(name) EXPORT_SYMBOL(name) +#endif + + /* + * Emit a 64-bit absolute little endian symbol reference in a way that + * ensures that it will be resolved at build time, even when building a + * PIE binary. This requires cooperation from the linker script, which + * must emit the lo32/hi32 halves individually. + */ + .macro le64sym, sym + .long \sym\()_lo32 + .long \sym\()_hi32 + .endm + + /* + * mov_q - move an immediate constant into a 64-bit register using + * between 2 and 4 movz/movk instructions (depending on the + * magnitude and sign of the operand) + */ + .macro mov_q, reg, val + .if (((\val) >> 31) == 0 || ((\val) >> 31) == 0x1ffffffff) + movz \reg, :abs_g1_s:\val + .else + .if (((\val) >> 47) == 0 || ((\val) >> 47) == 0x1ffff) + movz \reg, :abs_g2_s:\val + .else + movz \reg, :abs_g3:\val + movk \reg, :abs_g2_nc:\val + .endif + movk \reg, :abs_g1_nc:\val + .endif + movk \reg, :abs_g0_nc:\val + .endm + +/* + * Return the current task_struct. + */ + .macro get_current_task, rd + mrs \rd, sp_el0 + .endm + +/* + * If the kernel is built for 52-bit virtual addressing but the hardware only + * supports 48 bits, we cannot program the pgdir address into TTBR1 directly, + * but we have to add an offset so that the TTBR1 address corresponds with the + * pgdir entry that covers the lowest 48-bit addressable VA. + * + * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an + * additional paging level, and on LPA2/16k pages, we would end up with a root + * level table with only 2 entries, which is suboptimal in terms of TLB + * utilization, so there we fall back to 47 bits of translation if LPA2 is not + * supported. + * + * orr is used as it can cover the immediate value (and is idempotent). + * ttbr: Value of ttbr to set, modified. + */ + .macro offset_ttbr1, ttbr, tmp +#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2) + mrs \tmp, tcr_el1 + and \tmp, \tmp, #TCR_EL1_T1SZ_MASK + cmp \tmp, #TCR_T1SZ(VA_BITS_MIN) + orr \tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET + csel \ttbr, \tmp, \ttbr, eq +#endif + .endm + +/* + * Arrange a physical address in a TTBR register, taking care of 52-bit + * addresses. + * + * phys: physical address, preserved + * ttbr: returns the TTBR value + */ + .macro phys_to_ttbr, ttbr, phys +#ifdef CONFIG_ARM64_PA_BITS_52 + orr \ttbr, \phys, \phys, lsr #46 + and \ttbr, \ttbr, #TTBR_BADDR_MASK_52 +#else + mov \ttbr, \phys +#endif + .endm + + .macro phys_to_pte, pte, phys +#ifdef CONFIG_ARM64_PA_BITS_52 + orr \pte, \phys, \phys, lsr #PTE_ADDR_HIGH_SHIFT + and \pte, \pte, #PHYS_TO_PTE_ADDR_MASK +#else + mov \pte, \phys +#endif + .endm + +/* + * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU. + */ + .macro tcr_clear_errata_bits, tcr, tmp1, tmp2 +#ifdef CONFIG_FUJITSU_ERRATUM_010001 + mrs \tmp1, midr_el1 + + mov_q \tmp2, MIDR_FUJITSU_ERRATUM_010001_MASK + and \tmp1, \tmp1, \tmp2 + mov_q \tmp2, MIDR_FUJITSU_ERRATUM_010001 + cmp \tmp1, \tmp2 + b.ne 10f + + mov_q \tmp2, TCR_CLEAR_FUJITSU_ERRATUM_010001 + bic \tcr, \tcr, \tmp2 +10: +#endif /* CONFIG_FUJITSU_ERRATUM_010001 */ + .endm + +/** + * Errata workaround prior to disable MMU. Insert an ISB immediately prior + * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. + */ + .macro pre_disable_mmu_workaround +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_E1041 + isb +#endif + .endm + + /* + * frame_push - Push @regcount callee saved registers to the stack, + * starting at x19, as well as x29/x30, and set x29 to + * the new value of sp. Add @extra bytes of stack space + * for locals. + */ + .macro frame_push, regcount:req, extra + __frame st, \regcount, \extra + .endm + + /* + * frame_pop - Pop the callee saved registers from the stack that were + * pushed in the most recent call to frame_push, as well + * as x29/x30 and any extra stack space that may have been + * allocated. + */ + .macro frame_pop + __frame ld + .endm + + .macro __frame_regs, reg1, reg2, op, num + .if .Lframe_regcount == \num + \op\()r \reg1, [sp, #(\num + 1) * 8] + .elseif .Lframe_regcount > \num + \op\()p \reg1, \reg2, [sp, #(\num + 1) * 8] + .endif + .endm + + .macro __frame, op, regcount, extra=0 + .ifc \op, st + .if (\regcount) < 0 || (\regcount) > 10 + .error "regcount should be in the range [0 ... 10]" + .endif + .if ((\extra) % 16) != 0 + .error "extra should be a multiple of 16 bytes" + .endif + .ifdef .Lframe_regcount + .if .Lframe_regcount != -1 + .error "frame_push/frame_pop may not be nested" + .endif + .endif + .set .Lframe_regcount, \regcount + .set .Lframe_extra, \extra + .set .Lframe_local_offset, ((\regcount + 3) / 2) * 16 + stp x29, x30, [sp, #-.Lframe_local_offset - .Lframe_extra]! + mov x29, sp + .endif + + __frame_regs x19, x20, \op, 1 + __frame_regs x21, x22, \op, 3 + __frame_regs x23, x24, \op, 5 + __frame_regs x25, x26, \op, 7 + __frame_regs x27, x28, \op, 9 + + .ifc \op, ld + .if .Lframe_regcount == -1 + .error "frame_push/frame_pop may not be nested" + .endif + ldp x29, x30, [sp], #.Lframe_local_offset + .Lframe_extra + .set .Lframe_regcount, -1 + .endif + .endm + +/* + * Set SCTLR_ELx to the @reg value, and invalidate the local icache + * in the process. This is called when setting the MMU on. + */ +.macro set_sctlr, sreg, reg + msr \sreg, \reg + isb + /* + * 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. + */ + ic iallu + dsb nsh + isb +.endm + +.macro set_sctlr_el1, reg + set_sctlr sctlr_el1, \reg +.endm + +.macro set_sctlr_el2, reg + set_sctlr sctlr_el2, \reg +.endm + + /* + * Check whether asm code should yield as soon as it is able. This is + * the case if we are currently running in task context, and the + * TIF_NEED_RESCHED flag is set. (Note that the TIF_NEED_RESCHED flag + * is stored negated in the top word of the thread_info::preempt_count + * field) + */ + .macro cond_yield, lbl:req, tmp:req, tmp2 +#ifdef CONFIG_PREEMPT_VOLUNTARY + get_current_task \tmp + ldr \tmp, [\tmp, #TSK_TI_PREEMPT] + /* + * If we are serving a softirq, there is no point in yielding: the + * softirq will not be preempted no matter what we do, so we should + * run to completion as quickly as we can. The preempt_count field will + * have BIT(SOFTIRQ_SHIFT) set in this case, so the zero check will + * catch this case too. + */ + cbz \tmp, \lbl +#endif + .endm + +/* + * Branch Target Identifier (BTI) + */ + .macro bti, targets + .equ .L__bti_targets_c, 34 + .equ .L__bti_targets_j, 36 + .equ .L__bti_targets_jc,38 + hint #.L__bti_targets_\targets + .endm + +/* + * This macro emits a program property note section identifying + * architecture features which require special handling, mainly for + * use in assembly files included in the VDSO. + */ + +#define NT_GNU_PROPERTY_TYPE_0 5 +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 + +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) +#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC (1U << 1) + +#ifdef CONFIG_ARM64_BTI_KERNEL +#define GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT \ + ((GNU_PROPERTY_AARCH64_FEATURE_1_BTI | \ + GNU_PROPERTY_AARCH64_FEATURE_1_PAC)) +#endif + +#ifdef GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT +.macro emit_aarch64_feature_1_and, feat=GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT + .pushsection .note.gnu.property, "a" + .align 3 + .long 2f - 1f + .long 6f - 3f + .long NT_GNU_PROPERTY_TYPE_0 +1: .string "GNU" +2: + .align 3 +3: .long GNU_PROPERTY_AARCH64_FEATURE_1_AND + .long 5f - 4f +4: + /* + * This is described with an array of char in the Linux API + * spec but the text and all other usage (including binutils, + * clang and GCC) treat this as a 32 bit value so no swizzling + * is required for big endian. + */ + .long \feat +5: + .align 3 +6: + .popsection +.endm + +#else +.macro emit_aarch64_feature_1_and, feat=0 +.endm + +#endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */ + + .macro __mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_loop_iter + mov \tmp, #32 // Patched to correct the immediate +alternative_cb_end +.Lspectre_bhb_loop\@: + b . + 4 + subs \tmp, \tmp, #1 + b.ne .Lspectre_bhb_loop\@ + sb +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_loop_mitigation_enable + b .L_spectre_bhb_loop_done\@ // Patched to NOP +alternative_cb_end + __mitigate_spectre_bhb_loop \tmp +.L_spectre_bhb_loop_done\@: +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + /* Save/restores x0-x3 to the stack */ + .macro __mitigate_spectre_bhb_fw +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_3 +alternative_cb ARM64_ALWAYS_SYSTEM, smccc_patch_fw_mitigation_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_clear_insn +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_clearbhb + /* Patched to NOP when not supported */ + clearbhb + isb +alternative_cb_end +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ .endm +#endif /* __ASM_ASSEMBLER_H */ |