blob: a38c502dd4b7a5c7126aa039a82a4b9919fc5ad8 [file] [log] [blame]
/*
* 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__
#error "Only include this from assembly code"
#endif
#ifndef __ASM_ASSEMBLER_H
#define __ASM_ASSEMBLER_H
#include <asm-generic/export.h>
#include <asm/asm-offsets.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/page.h>
#include <asm/pgtable-hwdef.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
/*
* Enable and disable interrupts.
*/
.macro disable_irq
msr daifset, #2
.endm
.macro enable_irq
msr daifclr, #2
.endm
.macro save_and_disable_irq, flags
mrs \flags, daif
msr daifset, #2
.endm
.macro restore_irq, flags
msr daif, \flags
.endm
/*
* Save/disable and restore interrupts.
*/
.macro save_and_disable_irqs, olddaif
mrs \olddaif, daif
disable_irq
.endm
.macro restore_irqs, olddaif
msr daif, \olddaif
.endm
/*
* Enable and disable debug exceptions.
*/
.macro disable_dbg
msr daifset, #8
.endm
.macro enable_dbg
msr daifclr, #8
.endm
.macro disable_step_tsk, flgs, tmp
tbz \flgs, #TIF_SINGLESTEP, 9990f
mrs \tmp, mdscr_el1
bic \tmp, \tmp, #1
msr mdscr_el1, \tmp
isb // Synchronise with enable_dbg
9990:
.endm
.macro enable_step_tsk, flgs, tmp
tbz \flgs, #TIF_SINGLESTEP, 9990f
disable_dbg
mrs \tmp, mdscr_el1
orr \tmp, \tmp, #1
msr mdscr_el1, \tmp
9990:
.endm
/*
* Enable both debug exceptions and interrupts. This is likely to be
* faster than two daifclr operations, since writes to this register
* are self-synchronising.
*/
.macro enable_dbg_and_irq
msr daifclr, #(8 | 2)
.endm
/*
* SMP data memory barrier
*/
.macro smp_dmb, opt
dmb \opt
.endm
/*
* Value prediction barrier
*/
.macro csdb
hint #20
.endm
/*
* Clear Branch History instruction
*/
.macro clearbhb
hint #22
.endm
/*
* Sanitise a 64-bit bounded index wrt speculation, returning zero if out
* of bounds.
*/
.macro mask_nospec64, idx, limit, tmp
sub \tmp, \idx, \limit
bic \tmp, \tmp, \idx
and \idx, \idx, \tmp, asr #63
csdb
.endm
/*
* NOP sequence
*/
.macro nops, num
.rept \num
nop
.endr
.endm
/*
* Emit an entry into the exception table
*/
.macro _asm_extable, from, to
.pushsection __ex_table, "a"
.align 3
.long (\from - .), (\to - .)
.popsection
.endm
#define USER(l, x...) \
9999: x; \
_asm_extable 9999b, l
/*
* Register aliases.
*/
lr .req x30 // link register
/*
* Vector entry
*/
.macro ventry label
.align 7
b \label
.endm
/*
* 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
/*
* Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
* <symbol> is within the range +/- 4 GB of the PC when running
* in core kernel context. In module context, a movz/movk sequence
* is used, since modules may be loaded far away from the kernel
* when KASLR is in effect.
*/
/*
* @dst: destination register (64 bit wide)
* @sym: name of the symbol
*/
.macro adr_l, dst, sym
#ifndef MODULE
adrp \dst, \sym
add \dst, \dst, :lo12:\sym
#else
movz \dst, #:abs_g3:\sym
movk \dst, #:abs_g2_nc:\sym
movk \dst, #:abs_g1_nc:\sym
movk \dst, #:abs_g0_nc:\sym
#endif
.endm
/*
* @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=
#ifndef MODULE
.ifb \tmp
adrp \dst, \sym
ldr \dst, [\dst, :lo12:\sym]
.else
adrp \tmp, \sym
ldr \dst, [\tmp, :lo12:\sym]
.endif
#else
.ifb \tmp
adr_l \dst, \sym
ldr \dst, [\dst]
.else
adr_l \tmp, \sym
ldr \dst, [\tmp]
.endif
#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
#ifndef MODULE
adrp \tmp, \sym
str \src, [\tmp, :lo12:\sym]
#else
adr_l \tmp, \sym
str \src, [\tmp]
#endif
.endm
/*
* @dst: Result of per_cpu(sym, smp_processor_id()), can be SP for
* non-module code
* @sym: The name of the per-cpu variable
* @tmp: scratch register
*/
.macro adr_this_cpu, dst, sym, tmp
#ifndef MODULE
adrp \tmp, \sym
add \dst, \tmp, #:lo12:\sym
#else
adr_l \dst, \sym
#endif
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
mrs \tmp, tpidr_el1
alternative_else
mrs \tmp, tpidr_el2
alternative_endif
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
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
mrs \tmp, tpidr_el1
alternative_else
mrs \tmp, tpidr_el2
alternative_endif
ldr \dst, [\dst, \tmp]
.endm
/*
* vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
*/
.macro vma_vm_mm, rd, rn
ldr \rd, [\rn, #VMA_VM_MM]
.endm
/*
* mmid - get context id from mm pointer (mm->context.id)
*/
.macro mmid, rd, rn
ldr \rd, [\rn, #MM_CONTEXT_ID]
.endm
/*
* read_ctr - read CTR_EL0. If the system has mismatched
* cache line sizes, provide the system wide safe value
* from arm64_ftr_reg_ctrel0.sys_val
*/
.macro read_ctr, reg
alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
mrs \reg, ctr_el0 // read CTR
nop
alternative_else
ldr_l \reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL
alternative_endif
.endm
/*
* raw_dcache_line_size - get the minimum D-cache line size on this CPU
* from the CTR 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
/*
* dcache_line_size - get the safe D-cache line size across all CPUs
*/
.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_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
*/
.macro tcr_set_idmap_t0sz, valreg, tmpreg
#ifndef CONFIG_ARM64_VA_BITS_48
ldr_l \tmpreg, idmap_t0sz
bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
#endif
.endm
/*
* Macro to perform a data cache maintenance for the interval
* [kaddr, kaddr + size)
*
* op: operation passed to dc instruction
* domain: domain used in dsb instruciton
* kaddr: starting virtual address of the region
* size: size of the region
* Corrupts: kaddr, size, tmp1, tmp2
*/
.macro __dcache_op_workaround_clean_cache, op, kaddr
alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
dc \op, \kaddr
alternative_else
dc civac, \kaddr
alternative_endif
.endm
.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
dcache_line_size \tmp1, \tmp2
add \size, \kaddr, \size
sub \tmp2, \tmp1, #1
bic \kaddr, \kaddr, \tmp2
9998:
.ifc \op, cvau
__dcache_op_workaround_clean_cache \op, \kaddr
.else
.ifc \op, cvac
__dcache_op_workaround_clean_cache \op, \kaddr
.else
.ifc \op, cvap
sys 3, c7, c12, 1, \kaddr // dc cvap
.else
dc \op, \kaddr
.endif
.endif
.endif
add \kaddr, \kaddr, \tmp1
cmp \kaddr, \size
b.lo 9998b
dsb \domain
.endm
/*
* reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
*/
.macro reset_pmuserenr_el0, tmpreg
mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer
sbfx \tmpreg, \tmpreg, #8, #4
cmp \tmpreg, #1 // Skip if no PMU present
b.lt 9000f
msr pmuserenr_el0, xzr // Disable PMU access from EL0
9000:
.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 position independent, i.e., safe to be called before
* the kernel virtual mapping is activated.
*/
#define ENDPIPROC(x) \
.globl __pi_##x; \
.type __pi_##x, %function; \
.set __pi_##x, x; \
.size __pi_##x, . - x; \
ENDPROC(x)
/*
* 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
#ifdef CONFIG_KASAN
#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 thread_info.
*/
.macro get_thread_info, rd
mrs \rd, sp_el0
.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
.macro pte_to_phys, phys, pte
and \phys, \pte, #(((1 << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
.endm
/*
* Check the MIDR_EL1 of the current CPU for a given model and a range of
* variant/revision. See asm/cputype.h for the macros used below.
*
* model: MIDR_CPU_MODEL of CPU
* rv_min: Minimum of MIDR_CPU_VAR_REV()
* rv_max: Maximum of MIDR_CPU_VAR_REV()
* res: Result register.
* tmp1, tmp2, tmp3: Temporary registers
*
* Corrupts: res, tmp1, tmp2, tmp3
* Returns: 0, if the CPU id doesn't match. Non-zero otherwise
*/
.macro cpu_midr_match model, rv_min, rv_max, res, tmp1, tmp2, tmp3
mrs \res, midr_el1
mov_q \tmp1, (MIDR_REVISION_MASK | MIDR_VARIANT_MASK)
mov_q \tmp2, MIDR_CPU_MODEL_MASK
and \tmp3, \res, \tmp2 // Extract model
and \tmp1, \res, \tmp1 // rev & variant
mov_q \tmp2, \model
cmp \tmp3, \tmp2
cset \res, eq
cbz \res, .Ldone\@ // Model matches ?
.if (\rv_min != 0) // Skip min check if rv_min == 0
mov_q \tmp3, \rv_min
cmp \tmp1, \tmp3
cset \res, ge
.endif // \rv_min != 0
/* Skip rv_max check if rv_min == rv_max && rv_min != 0 */
.if ((\rv_min != \rv_max) || \rv_min == 0)
mov_q \tmp2, \rv_max
cmp \tmp1, \tmp2
cset \tmp2, le
and \res, \res, \tmp2
.endif
.Ldone\@:
.endm
.macro __mitigate_spectre_bhb_loop tmp
#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
alternative_cb 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\@
dsb nsh
isb
#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_update_smccc_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
#endif /* __ASM_ASSEMBLER_H */