linux/arch/arm64/include/asm/assembler.h
Linus Torvalds 15303ba5d1 KVM changes for 4.16
ARM:
 - Include icache invalidation optimizations, improving VM startup time
 
 - Support for forwarded level-triggered interrupts, improving
   performance for timers and passthrough platform devices
 
 - A small fix for power-management notifiers, and some cosmetic changes
 
 PPC:
 - Add MMIO emulation for vector loads and stores
 
 - Allow HPT guests to run on a radix host on POWER9 v2.2 CPUs without
   requiring the complex thread synchronization of older CPU versions
 
 - Improve the handling of escalation interrupts with the XIVE interrupt
   controller
 
 - Support decrement register migration
 
 - Various cleanups and bugfixes.
 
 s390:
 - Cornelia Huck passed maintainership to Janosch Frank
 
 - Exitless interrupts for emulated devices
 
 - Cleanup of cpuflag handling
 
 - kvm_stat counter improvements
 
 - VSIE improvements
 
 - mm cleanup
 
 x86:
 - Hypervisor part of SEV
 
 - UMIP, RDPID, and MSR_SMI_COUNT emulation
 
 - Paravirtualized TLB shootdown using the new KVM_VCPU_PREEMPTED bit
 
 - Allow guests to see TOPOEXT, GFNI, VAES, VPCLMULQDQ, and more AVX512
   features
 
 - Show vcpu id in its anonymous inode name
 
 - Many fixes and cleanups
 
 - Per-VCPU MSR bitmaps (already merged through x86/pti branch)
 
 - Stable KVM clock when nesting on Hyper-V (merged through x86/hyperv)
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABCAAGBQJafvMtAAoJEED/6hsPKofo6YcH/Rzf2RmshrWaC3q82yfIV0Qz
 Z8N8yJHSaSdc3Jo6cmiVj0zelwAxdQcyjwlT7vxt5SL2yML+/Q0st9Hc3EgGGXPm
 Il99eJEl+2MYpZgYZqV8ff3mHS5s5Jms+7BITAeh6Rgt+DyNbykEAvzt+MCHK9cP
 xtsIZQlvRF7HIrpOlaRzOPp3sK2/MDZJ1RBE7wYItK3CUAmsHim/LVYKzZkRTij3
 /9b4LP1yMMbziG+Yxt1o682EwJB5YIat6fmDG9uFeEVI5rWWN7WFubqs8gCjYy/p
 FX+BjpOdgTRnX+1m9GIj0Jlc/HKMXryDfSZS07Zy4FbGEwSiI5SfKECub4mDhuE=
 =C/uD
 -----END PGP SIGNATURE-----

Merge tag 'kvm-4.16-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "ARM:

   - icache invalidation optimizations, improving VM startup time

   - support for forwarded level-triggered interrupts, improving
     performance for timers and passthrough platform devices

   - a small fix for power-management notifiers, and some cosmetic
     changes

  PPC:

   - add MMIO emulation for vector loads and stores

   - allow HPT guests to run on a radix host on POWER9 v2.2 CPUs without
     requiring the complex thread synchronization of older CPU versions

   - improve the handling of escalation interrupts with the XIVE
     interrupt controller

   - support decrement register migration

   - various cleanups and bugfixes.

  s390:

   - Cornelia Huck passed maintainership to Janosch Frank

   - exitless interrupts for emulated devices

   - cleanup of cpuflag handling

   - kvm_stat counter improvements

   - VSIE improvements

   - mm cleanup

  x86:

   - hypervisor part of SEV

   - UMIP, RDPID, and MSR_SMI_COUNT emulation

   - paravirtualized TLB shootdown using the new KVM_VCPU_PREEMPTED bit

   - allow guests to see TOPOEXT, GFNI, VAES, VPCLMULQDQ, and more
     AVX512 features

   - show vcpu id in its anonymous inode name

   - many fixes and cleanups

   - per-VCPU MSR bitmaps (already merged through x86/pti branch)

   - stable KVM clock when nesting on Hyper-V (merged through
     x86/hyperv)"

* tag 'kvm-4.16-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (197 commits)
  KVM: PPC: Book3S: Add MMIO emulation for VMX instructions
  KVM: PPC: Book3S HV: Branch inside feature section
  KVM: PPC: Book3S HV: Make HPT resizing work on POWER9
  KVM: PPC: Book3S HV: Fix handling of secondary HPTEG in HPT resizing code
  KVM: PPC: Book3S PR: Fix broken select due to misspelling
  KVM: x86: don't forget vcpu_put() in kvm_arch_vcpu_ioctl_set_sregs()
  KVM: PPC: Book3S PR: Fix svcpu copying with preemption enabled
  KVM: PPC: Book3S HV: Drop locks before reading guest memory
  kvm: x86: remove efer_reload entry in kvm_vcpu_stat
  KVM: x86: AMD Processor Topology Information
  x86/kvm/vmx: do not use vm-exit instruction length for fast MMIO when running nested
  kvm: embed vcpu id to dentry of vcpu anon inode
  kvm: Map PFN-type memory regions as writable (if possible)
  x86/kvm: Make it compile on 32bit and with HYPYERVISOR_GUEST=n
  KVM: arm/arm64: Fixup userspace irqchip static key optimization
  KVM: arm/arm64: Fix userspace_irqchip_in_use counting
  KVM: arm/arm64: Fix incorrect timer_is_pending logic
  MAINTAINERS: update KVM/s390 maintainers
  MAINTAINERS: add Halil as additional vfio-ccw maintainer
  MAINTAINERS: add David as a reviewer for KVM/s390
  ...
2018-02-10 13:16:35 -08:00

599 lines
13 KiB
C

/*
* 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/asm-offsets.h>
#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
#include <asm/page.h>
#include <asm/pgtable-hwdef.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
.macro save_and_disable_daif, flags
mrs \flags, daif
msr daifset, #0xf
.endm
.macro disable_daif
msr daifset, #0xf
.endm
.macro enable_daif
msr daifclr, #0xf
.endm
.macro restore_daif, flags:req
msr daif, \flags
.endm
/* Only on aarch64 pstate, PSR_D_BIT is different for aarch32 */
.macro inherit_daif, pstate:req, tmp:req
and \tmp, \pstate, #(PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
msr daif, \tmp
.endm
/* IRQ is the lowest priority flag, unconditionally unmask the rest. */
.macro enable_da_f
msr daifclr, #(8 | 4 | 1)
.endm
/*
* 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
.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, #DBG_MDSCR_SS
msr mdscr_el1, \tmp
isb // Synchronise with enable_dbg
9990:
.endm
/* call with daif masked */
.macro enable_step_tsk, flgs, tmp
tbz \flgs, #TIF_SINGLESTEP, 9990f
mrs \tmp, mdscr_el1
orr \tmp, \tmp, #DBG_MDSCR_SS
msr mdscr_el1, \tmp
9990:
.endm
/*
* SMP data memory barrier
*/
.macro smp_dmb, opt
dmb \opt
.endm
/*
* RAS Error Synchronization barrier
*/
.macro esb
hint #16
.endm
/*
* Value prediction barrier
*/
.macro csdb
hint #20
.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
ldr_l \tmpreg, idmap_t0sz
bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_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_PARANGE_SHIFT, #3
mov \tmp1, #ID_AA64MMFR0_PARANGE_MAX
cmp \tmp0, \tmp1
csel \tmp0, \tmp1, \tmp0, hi
bfi \tcr, \tmp0, \pos, #3
.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_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:
.if (\op == cvau || \op == cvac)
alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
dc \op, \kaddr
alternative_else
dc civac, \kaddr
alternative_endif
.elseif (\op == cvap)
alternative_if ARM64_HAS_DCPOP
sys 3, c7, c12, 1, \kaddr // dc cvap
alternative_else
dc cvac, \kaddr
alternative_endif
.else
dc \op, \kaddr
.endif
add \kaddr, \kaddr, \tmp1
cmp \kaddr, \size
b.lo 9998b
dsb \domain
.endm
/*
* Macro to perform an instruction cache maintenance for the interval
* [start, end)
*
* start, end: virtual addresses describing the region
* label: A label to branch to on user fault.
* Corrupts: tmp1, tmp2
*/
.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
icache_line_size \tmp1, \tmp2
sub \tmp2, \tmp1, #1
bic \tmp2, \start, \tmp2
9997:
USER(\label, ic ivau, \tmp2) // invalidate I line PoU
add \tmp2, \tmp2, \tmp1
cmp \tmp2, \end
b.lo 9997b
dsb ish
isb
.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
/*
* 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
/*
* 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
/*
* We assume \phys is 64K aligned and this is guaranteed by only
* supporting this configuration with 64K pages.
*/
orr \pte, \phys, \phys, lsr #36
and \pte, \pte, #PTE_ADDR_MASK
#else
mov \pte, \phys
#endif
.endm
.macro pte_to_phys, phys, pte
#ifdef CONFIG_ARM64_PA_BITS_52
ubfiz \phys, \pte, #(48 - 16 - 12), #16
bfxil \phys, \pte, #16, #32
lsl \phys, \phys, #16
#else
and \phys, \pte, #PTE_ADDR_MASK
#endif
.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
#endif /* __ASM_ASSEMBLER_H */