mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 01:10:04 +00:00
![Juergen Gross](/assets/img/avatar_default.png)
pte_clear() et al are based on two paravirt steps today: one step to create a page table entry with all zeroes, and one step to write this entry value. Drop the first step as it is completely useless. Signed-off-by: Juergen Gross <jgross@suse.com> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20200815100641.26362-7-jgross@suse.com
845 lines
20 KiB
C
845 lines
20 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_X86_PARAVIRT_H
|
|
#define _ASM_X86_PARAVIRT_H
|
|
/* Various instructions on x86 need to be replaced for
|
|
* para-virtualization: those hooks are defined here. */
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
#include <asm/pgtable_types.h>
|
|
#include <asm/asm.h>
|
|
#include <asm/nospec-branch.h>
|
|
|
|
#include <asm/paravirt_types.h>
|
|
|
|
#ifndef __ASSEMBLY__
|
|
#include <linux/bug.h>
|
|
#include <linux/types.h>
|
|
#include <linux/cpumask.h>
|
|
#include <asm/frame.h>
|
|
|
|
static inline unsigned long long paravirt_sched_clock(void)
|
|
{
|
|
return PVOP_CALL0(unsigned long long, time.sched_clock);
|
|
}
|
|
|
|
struct static_key;
|
|
extern struct static_key paravirt_steal_enabled;
|
|
extern struct static_key paravirt_steal_rq_enabled;
|
|
|
|
__visible void __native_queued_spin_unlock(struct qspinlock *lock);
|
|
bool pv_is_native_spin_unlock(void);
|
|
__visible bool __native_vcpu_is_preempted(long cpu);
|
|
bool pv_is_native_vcpu_is_preempted(void);
|
|
|
|
static inline u64 paravirt_steal_clock(int cpu)
|
|
{
|
|
return PVOP_CALL1(u64, time.steal_clock, cpu);
|
|
}
|
|
|
|
/* The paravirtualized I/O functions */
|
|
static inline void slow_down_io(void)
|
|
{
|
|
pv_ops.cpu.io_delay();
|
|
#ifdef REALLY_SLOW_IO
|
|
pv_ops.cpu.io_delay();
|
|
pv_ops.cpu.io_delay();
|
|
pv_ops.cpu.io_delay();
|
|
#endif
|
|
}
|
|
|
|
void native_flush_tlb_local(void);
|
|
void native_flush_tlb_global(void);
|
|
void native_flush_tlb_one_user(unsigned long addr);
|
|
void native_flush_tlb_others(const struct cpumask *cpumask,
|
|
const struct flush_tlb_info *info);
|
|
|
|
static inline void __flush_tlb_local(void)
|
|
{
|
|
PVOP_VCALL0(mmu.flush_tlb_user);
|
|
}
|
|
|
|
static inline void __flush_tlb_global(void)
|
|
{
|
|
PVOP_VCALL0(mmu.flush_tlb_kernel);
|
|
}
|
|
|
|
static inline void __flush_tlb_one_user(unsigned long addr)
|
|
{
|
|
PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
|
|
}
|
|
|
|
static inline void __flush_tlb_others(const struct cpumask *cpumask,
|
|
const struct flush_tlb_info *info)
|
|
{
|
|
PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
|
|
}
|
|
|
|
static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
|
|
{
|
|
PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
|
|
}
|
|
|
|
static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
|
|
{
|
|
PVOP_VCALL1(mmu.exit_mmap, mm);
|
|
}
|
|
|
|
#ifdef CONFIG_PARAVIRT_XXL
|
|
static inline void load_sp0(unsigned long sp0)
|
|
{
|
|
PVOP_VCALL1(cpu.load_sp0, sp0);
|
|
}
|
|
|
|
/* The paravirtualized CPUID instruction. */
|
|
static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
|
|
unsigned int *ecx, unsigned int *edx)
|
|
{
|
|
PVOP_VCALL4(cpu.cpuid, eax, ebx, ecx, edx);
|
|
}
|
|
|
|
/*
|
|
* These special macros can be used to get or set a debugging register
|
|
*/
|
|
static inline unsigned long paravirt_get_debugreg(int reg)
|
|
{
|
|
return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg);
|
|
}
|
|
#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
|
|
static inline void set_debugreg(unsigned long val, int reg)
|
|
{
|
|
PVOP_VCALL2(cpu.set_debugreg, reg, val);
|
|
}
|
|
|
|
static inline unsigned long read_cr0(void)
|
|
{
|
|
return PVOP_CALL0(unsigned long, cpu.read_cr0);
|
|
}
|
|
|
|
static inline void write_cr0(unsigned long x)
|
|
{
|
|
PVOP_VCALL1(cpu.write_cr0, x);
|
|
}
|
|
|
|
static inline unsigned long read_cr2(void)
|
|
{
|
|
return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
|
|
}
|
|
|
|
static inline void write_cr2(unsigned long x)
|
|
{
|
|
PVOP_VCALL1(mmu.write_cr2, x);
|
|
}
|
|
|
|
static inline unsigned long __read_cr3(void)
|
|
{
|
|
return PVOP_CALL0(unsigned long, mmu.read_cr3);
|
|
}
|
|
|
|
static inline void write_cr3(unsigned long x)
|
|
{
|
|
PVOP_VCALL1(mmu.write_cr3, x);
|
|
}
|
|
|
|
static inline void __write_cr4(unsigned long x)
|
|
{
|
|
PVOP_VCALL1(cpu.write_cr4, x);
|
|
}
|
|
|
|
static inline void arch_safe_halt(void)
|
|
{
|
|
PVOP_VCALL0(irq.safe_halt);
|
|
}
|
|
|
|
static inline void halt(void)
|
|
{
|
|
PVOP_VCALL0(irq.halt);
|
|
}
|
|
|
|
static inline void wbinvd(void)
|
|
{
|
|
PVOP_VCALL0(cpu.wbinvd);
|
|
}
|
|
|
|
static inline u64 paravirt_read_msr(unsigned msr)
|
|
{
|
|
return PVOP_CALL1(u64, cpu.read_msr, msr);
|
|
}
|
|
|
|
static inline void paravirt_write_msr(unsigned msr,
|
|
unsigned low, unsigned high)
|
|
{
|
|
PVOP_VCALL3(cpu.write_msr, msr, low, high);
|
|
}
|
|
|
|
static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
|
|
{
|
|
return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err);
|
|
}
|
|
|
|
static inline int paravirt_write_msr_safe(unsigned msr,
|
|
unsigned low, unsigned high)
|
|
{
|
|
return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high);
|
|
}
|
|
|
|
#define rdmsr(msr, val1, val2) \
|
|
do { \
|
|
u64 _l = paravirt_read_msr(msr); \
|
|
val1 = (u32)_l; \
|
|
val2 = _l >> 32; \
|
|
} while (0)
|
|
|
|
#define wrmsr(msr, val1, val2) \
|
|
do { \
|
|
paravirt_write_msr(msr, val1, val2); \
|
|
} while (0)
|
|
|
|
#define rdmsrl(msr, val) \
|
|
do { \
|
|
val = paravirt_read_msr(msr); \
|
|
} while (0)
|
|
|
|
static inline void wrmsrl(unsigned msr, u64 val)
|
|
{
|
|
wrmsr(msr, (u32)val, (u32)(val>>32));
|
|
}
|
|
|
|
#define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b)
|
|
|
|
/* rdmsr with exception handling */
|
|
#define rdmsr_safe(msr, a, b) \
|
|
({ \
|
|
int _err; \
|
|
u64 _l = paravirt_read_msr_safe(msr, &_err); \
|
|
(*a) = (u32)_l; \
|
|
(*b) = _l >> 32; \
|
|
_err; \
|
|
})
|
|
|
|
static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
|
|
{
|
|
int err;
|
|
|
|
*p = paravirt_read_msr_safe(msr, &err);
|
|
return err;
|
|
}
|
|
|
|
static inline unsigned long long paravirt_read_pmc(int counter)
|
|
{
|
|
return PVOP_CALL1(u64, cpu.read_pmc, counter);
|
|
}
|
|
|
|
#define rdpmc(counter, low, high) \
|
|
do { \
|
|
u64 _l = paravirt_read_pmc(counter); \
|
|
low = (u32)_l; \
|
|
high = _l >> 32; \
|
|
} while (0)
|
|
|
|
#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
|
|
|
|
static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
|
|
{
|
|
PVOP_VCALL2(cpu.alloc_ldt, ldt, entries);
|
|
}
|
|
|
|
static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
|
|
{
|
|
PVOP_VCALL2(cpu.free_ldt, ldt, entries);
|
|
}
|
|
|
|
static inline void load_TR_desc(void)
|
|
{
|
|
PVOP_VCALL0(cpu.load_tr_desc);
|
|
}
|
|
static inline void load_gdt(const struct desc_ptr *dtr)
|
|
{
|
|
PVOP_VCALL1(cpu.load_gdt, dtr);
|
|
}
|
|
static inline void load_idt(const struct desc_ptr *dtr)
|
|
{
|
|
PVOP_VCALL1(cpu.load_idt, dtr);
|
|
}
|
|
static inline void set_ldt(const void *addr, unsigned entries)
|
|
{
|
|
PVOP_VCALL2(cpu.set_ldt, addr, entries);
|
|
}
|
|
static inline unsigned long paravirt_store_tr(void)
|
|
{
|
|
return PVOP_CALL0(unsigned long, cpu.store_tr);
|
|
}
|
|
|
|
#define store_tr(tr) ((tr) = paravirt_store_tr())
|
|
static inline void load_TLS(struct thread_struct *t, unsigned cpu)
|
|
{
|
|
PVOP_VCALL2(cpu.load_tls, t, cpu);
|
|
}
|
|
|
|
static inline void load_gs_index(unsigned int gs)
|
|
{
|
|
PVOP_VCALL1(cpu.load_gs_index, gs);
|
|
}
|
|
|
|
static inline void write_ldt_entry(struct desc_struct *dt, int entry,
|
|
const void *desc)
|
|
{
|
|
PVOP_VCALL3(cpu.write_ldt_entry, dt, entry, desc);
|
|
}
|
|
|
|
static inline void write_gdt_entry(struct desc_struct *dt, int entry,
|
|
void *desc, int type)
|
|
{
|
|
PVOP_VCALL4(cpu.write_gdt_entry, dt, entry, desc, type);
|
|
}
|
|
|
|
static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
|
|
{
|
|
PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_IOPL_IOPERM
|
|
static inline void tss_invalidate_io_bitmap(void)
|
|
{
|
|
PVOP_VCALL0(cpu.invalidate_io_bitmap);
|
|
}
|
|
|
|
static inline void tss_update_io_bitmap(void)
|
|
{
|
|
PVOP_VCALL0(cpu.update_io_bitmap);
|
|
}
|
|
#endif
|
|
|
|
static inline void paravirt_activate_mm(struct mm_struct *prev,
|
|
struct mm_struct *next)
|
|
{
|
|
PVOP_VCALL2(mmu.activate_mm, prev, next);
|
|
}
|
|
|
|
static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
|
|
struct mm_struct *mm)
|
|
{
|
|
PVOP_VCALL2(mmu.dup_mmap, oldmm, mm);
|
|
}
|
|
|
|
static inline int paravirt_pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
return PVOP_CALL1(int, mmu.pgd_alloc, mm);
|
|
}
|
|
|
|
static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
PVOP_VCALL2(mmu.pgd_free, mm, pgd);
|
|
}
|
|
|
|
static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
|
|
{
|
|
PVOP_VCALL2(mmu.alloc_pte, mm, pfn);
|
|
}
|
|
static inline void paravirt_release_pte(unsigned long pfn)
|
|
{
|
|
PVOP_VCALL1(mmu.release_pte, pfn);
|
|
}
|
|
|
|
static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
|
|
{
|
|
PVOP_VCALL2(mmu.alloc_pmd, mm, pfn);
|
|
}
|
|
|
|
static inline void paravirt_release_pmd(unsigned long pfn)
|
|
{
|
|
PVOP_VCALL1(mmu.release_pmd, pfn);
|
|
}
|
|
|
|
static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
|
|
{
|
|
PVOP_VCALL2(mmu.alloc_pud, mm, pfn);
|
|
}
|
|
static inline void paravirt_release_pud(unsigned long pfn)
|
|
{
|
|
PVOP_VCALL1(mmu.release_pud, pfn);
|
|
}
|
|
|
|
static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn)
|
|
{
|
|
PVOP_VCALL2(mmu.alloc_p4d, mm, pfn);
|
|
}
|
|
|
|
static inline void paravirt_release_p4d(unsigned long pfn)
|
|
{
|
|
PVOP_VCALL1(mmu.release_p4d, pfn);
|
|
}
|
|
|
|
static inline pte_t __pte(pteval_t val)
|
|
{
|
|
return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) };
|
|
}
|
|
|
|
static inline pteval_t pte_val(pte_t pte)
|
|
{
|
|
return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
|
|
}
|
|
|
|
static inline pgd_t __pgd(pgdval_t val)
|
|
{
|
|
return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) };
|
|
}
|
|
|
|
static inline pgdval_t pgd_val(pgd_t pgd)
|
|
{
|
|
return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
|
|
}
|
|
|
|
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
|
|
static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
|
|
pte_t *ptep)
|
|
{
|
|
pteval_t ret;
|
|
|
|
ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep);
|
|
|
|
return (pte_t) { .pte = ret };
|
|
}
|
|
|
|
static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
|
|
pte_t *ptep, pte_t old_pte, pte_t pte)
|
|
{
|
|
|
|
PVOP_VCALL4(mmu.ptep_modify_prot_commit, vma, addr, ptep, pte.pte);
|
|
}
|
|
|
|
static inline void set_pte(pte_t *ptep, pte_t pte)
|
|
{
|
|
PVOP_VCALL2(mmu.set_pte, ptep, pte.pte);
|
|
}
|
|
|
|
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
|
|
{
|
|
PVOP_VCALL2(mmu.set_pmd, pmdp, native_pmd_val(pmd));
|
|
}
|
|
|
|
static inline pmd_t __pmd(pmdval_t val)
|
|
{
|
|
return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) };
|
|
}
|
|
|
|
static inline pmdval_t pmd_val(pmd_t pmd)
|
|
{
|
|
return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
|
|
}
|
|
|
|
static inline void set_pud(pud_t *pudp, pud_t pud)
|
|
{
|
|
PVOP_VCALL2(mmu.set_pud, pudp, native_pud_val(pud));
|
|
}
|
|
|
|
static inline pud_t __pud(pudval_t val)
|
|
{
|
|
pudval_t ret;
|
|
|
|
ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
|
|
|
|
return (pud_t) { ret };
|
|
}
|
|
|
|
static inline pudval_t pud_val(pud_t pud)
|
|
{
|
|
return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
|
|
}
|
|
|
|
static inline void pud_clear(pud_t *pudp)
|
|
{
|
|
set_pud(pudp, native_make_pud(0));
|
|
}
|
|
|
|
static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
|
|
{
|
|
p4dval_t val = native_p4d_val(p4d);
|
|
|
|
PVOP_VCALL2(mmu.set_p4d, p4dp, val);
|
|
}
|
|
|
|
#if CONFIG_PGTABLE_LEVELS >= 5
|
|
|
|
static inline p4d_t __p4d(p4dval_t val)
|
|
{
|
|
p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
|
|
|
|
return (p4d_t) { ret };
|
|
}
|
|
|
|
static inline p4dval_t p4d_val(p4d_t p4d)
|
|
{
|
|
return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
|
|
}
|
|
|
|
static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
|
|
{
|
|
PVOP_VCALL2(mmu.set_pgd, pgdp, native_pgd_val(pgd));
|
|
}
|
|
|
|
#define set_pgd(pgdp, pgdval) do { \
|
|
if (pgtable_l5_enabled()) \
|
|
__set_pgd(pgdp, pgdval); \
|
|
else \
|
|
set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \
|
|
} while (0)
|
|
|
|
#define pgd_clear(pgdp) do { \
|
|
if (pgtable_l5_enabled()) \
|
|
set_pgd(pgdp, native_make_pgd(0)); \
|
|
} while (0)
|
|
|
|
#endif /* CONFIG_PGTABLE_LEVELS == 5 */
|
|
|
|
static inline void p4d_clear(p4d_t *p4dp)
|
|
{
|
|
set_p4d(p4dp, native_make_p4d(0));
|
|
}
|
|
|
|
static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
|
|
{
|
|
set_pte(ptep, pte);
|
|
}
|
|
|
|
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep)
|
|
{
|
|
set_pte(ptep, native_make_pte(0));
|
|
}
|
|
|
|
static inline void pmd_clear(pmd_t *pmdp)
|
|
{
|
|
set_pmd(pmdp, native_make_pmd(0));
|
|
}
|
|
|
|
#define __HAVE_ARCH_START_CONTEXT_SWITCH
|
|
static inline void arch_start_context_switch(struct task_struct *prev)
|
|
{
|
|
PVOP_VCALL1(cpu.start_context_switch, prev);
|
|
}
|
|
|
|
static inline void arch_end_context_switch(struct task_struct *next)
|
|
{
|
|
PVOP_VCALL1(cpu.end_context_switch, next);
|
|
}
|
|
|
|
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
|
|
static inline void arch_enter_lazy_mmu_mode(void)
|
|
{
|
|
PVOP_VCALL0(mmu.lazy_mode.enter);
|
|
}
|
|
|
|
static inline void arch_leave_lazy_mmu_mode(void)
|
|
{
|
|
PVOP_VCALL0(mmu.lazy_mode.leave);
|
|
}
|
|
|
|
static inline void arch_flush_lazy_mmu_mode(void)
|
|
{
|
|
PVOP_VCALL0(mmu.lazy_mode.flush);
|
|
}
|
|
|
|
static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
|
|
phys_addr_t phys, pgprot_t flags)
|
|
{
|
|
pv_ops.mmu.set_fixmap(idx, phys, flags);
|
|
}
|
|
#endif
|
|
|
|
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
|
|
|
|
static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
|
|
u32 val)
|
|
{
|
|
PVOP_VCALL2(lock.queued_spin_lock_slowpath, lock, val);
|
|
}
|
|
|
|
static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
|
|
{
|
|
PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
|
|
}
|
|
|
|
static __always_inline void pv_wait(u8 *ptr, u8 val)
|
|
{
|
|
PVOP_VCALL2(lock.wait, ptr, val);
|
|
}
|
|
|
|
static __always_inline void pv_kick(int cpu)
|
|
{
|
|
PVOP_VCALL1(lock.kick, cpu);
|
|
}
|
|
|
|
static __always_inline bool pv_vcpu_is_preempted(long cpu)
|
|
{
|
|
return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
|
|
}
|
|
|
|
void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
|
|
bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
|
|
|
|
#endif /* SMP && PARAVIRT_SPINLOCKS */
|
|
|
|
#ifdef CONFIG_X86_32
|
|
/* save and restore all caller-save registers, except return value */
|
|
#define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;"
|
|
#define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;"
|
|
#else
|
|
/* save and restore all caller-save registers, except return value */
|
|
#define PV_SAVE_ALL_CALLER_REGS \
|
|
"push %rcx;" \
|
|
"push %rdx;" \
|
|
"push %rsi;" \
|
|
"push %rdi;" \
|
|
"push %r8;" \
|
|
"push %r9;" \
|
|
"push %r10;" \
|
|
"push %r11;"
|
|
#define PV_RESTORE_ALL_CALLER_REGS \
|
|
"pop %r11;" \
|
|
"pop %r10;" \
|
|
"pop %r9;" \
|
|
"pop %r8;" \
|
|
"pop %rdi;" \
|
|
"pop %rsi;" \
|
|
"pop %rdx;" \
|
|
"pop %rcx;"
|
|
#endif
|
|
|
|
/*
|
|
* Generate a thunk around a function which saves all caller-save
|
|
* registers except for the return value. This allows C functions to
|
|
* be called from assembler code where fewer than normal registers are
|
|
* available. It may also help code generation around calls from C
|
|
* code if the common case doesn't use many registers.
|
|
*
|
|
* When a callee is wrapped in a thunk, the caller can assume that all
|
|
* arg regs and all scratch registers are preserved across the
|
|
* call. The return value in rax/eax will not be saved, even for void
|
|
* functions.
|
|
*/
|
|
#define PV_THUNK_NAME(func) "__raw_callee_save_" #func
|
|
#define PV_CALLEE_SAVE_REGS_THUNK(func) \
|
|
extern typeof(func) __raw_callee_save_##func; \
|
|
\
|
|
asm(".pushsection .text;" \
|
|
".globl " PV_THUNK_NAME(func) ";" \
|
|
".type " PV_THUNK_NAME(func) ", @function;" \
|
|
PV_THUNK_NAME(func) ":" \
|
|
FRAME_BEGIN \
|
|
PV_SAVE_ALL_CALLER_REGS \
|
|
"call " #func ";" \
|
|
PV_RESTORE_ALL_CALLER_REGS \
|
|
FRAME_END \
|
|
"ret;" \
|
|
".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \
|
|
".popsection")
|
|
|
|
/* Get a reference to a callee-save function */
|
|
#define PV_CALLEE_SAVE(func) \
|
|
((struct paravirt_callee_save) { __raw_callee_save_##func })
|
|
|
|
/* Promise that "func" already uses the right calling convention */
|
|
#define __PV_IS_CALLEE_SAVE(func) \
|
|
((struct paravirt_callee_save) { func })
|
|
|
|
#ifdef CONFIG_PARAVIRT_XXL
|
|
static inline notrace unsigned long arch_local_save_flags(void)
|
|
{
|
|
return PVOP_CALLEE0(unsigned long, irq.save_fl);
|
|
}
|
|
|
|
static inline notrace void arch_local_irq_restore(unsigned long f)
|
|
{
|
|
PVOP_VCALLEE1(irq.restore_fl, f);
|
|
}
|
|
|
|
static inline notrace void arch_local_irq_disable(void)
|
|
{
|
|
PVOP_VCALLEE0(irq.irq_disable);
|
|
}
|
|
|
|
static inline notrace void arch_local_irq_enable(void)
|
|
{
|
|
PVOP_VCALLEE0(irq.irq_enable);
|
|
}
|
|
|
|
static inline notrace unsigned long arch_local_irq_save(void)
|
|
{
|
|
unsigned long f;
|
|
|
|
f = arch_local_save_flags();
|
|
arch_local_irq_disable();
|
|
return f;
|
|
}
|
|
#endif
|
|
|
|
|
|
/* Make sure as little as possible of this mess escapes. */
|
|
#undef PARAVIRT_CALL
|
|
#undef __PVOP_CALL
|
|
#undef __PVOP_VCALL
|
|
#undef PVOP_VCALL0
|
|
#undef PVOP_CALL0
|
|
#undef PVOP_VCALL1
|
|
#undef PVOP_CALL1
|
|
#undef PVOP_VCALL2
|
|
#undef PVOP_CALL2
|
|
#undef PVOP_VCALL3
|
|
#undef PVOP_CALL3
|
|
#undef PVOP_VCALL4
|
|
#undef PVOP_CALL4
|
|
|
|
extern void default_banner(void);
|
|
|
|
#else /* __ASSEMBLY__ */
|
|
|
|
#define _PVSITE(ptype, ops, word, algn) \
|
|
771:; \
|
|
ops; \
|
|
772:; \
|
|
.pushsection .parainstructions,"a"; \
|
|
.align algn; \
|
|
word 771b; \
|
|
.byte ptype; \
|
|
.byte 772b-771b; \
|
|
.popsection
|
|
|
|
|
|
#define COND_PUSH(set, mask, reg) \
|
|
.if ((~(set)) & mask); push %reg; .endif
|
|
#define COND_POP(set, mask, reg) \
|
|
.if ((~(set)) & mask); pop %reg; .endif
|
|
|
|
#ifdef CONFIG_X86_64
|
|
|
|
#define PV_SAVE_REGS(set) \
|
|
COND_PUSH(set, CLBR_RAX, rax); \
|
|
COND_PUSH(set, CLBR_RCX, rcx); \
|
|
COND_PUSH(set, CLBR_RDX, rdx); \
|
|
COND_PUSH(set, CLBR_RSI, rsi); \
|
|
COND_PUSH(set, CLBR_RDI, rdi); \
|
|
COND_PUSH(set, CLBR_R8, r8); \
|
|
COND_PUSH(set, CLBR_R9, r9); \
|
|
COND_PUSH(set, CLBR_R10, r10); \
|
|
COND_PUSH(set, CLBR_R11, r11)
|
|
#define PV_RESTORE_REGS(set) \
|
|
COND_POP(set, CLBR_R11, r11); \
|
|
COND_POP(set, CLBR_R10, r10); \
|
|
COND_POP(set, CLBR_R9, r9); \
|
|
COND_POP(set, CLBR_R8, r8); \
|
|
COND_POP(set, CLBR_RDI, rdi); \
|
|
COND_POP(set, CLBR_RSI, rsi); \
|
|
COND_POP(set, CLBR_RDX, rdx); \
|
|
COND_POP(set, CLBR_RCX, rcx); \
|
|
COND_POP(set, CLBR_RAX, rax)
|
|
|
|
#define PARA_PATCH(off) ((off) / 8)
|
|
#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
|
|
#define PARA_INDIRECT(addr) *addr(%rip)
|
|
#else
|
|
#define PV_SAVE_REGS(set) \
|
|
COND_PUSH(set, CLBR_EAX, eax); \
|
|
COND_PUSH(set, CLBR_EDI, edi); \
|
|
COND_PUSH(set, CLBR_ECX, ecx); \
|
|
COND_PUSH(set, CLBR_EDX, edx)
|
|
#define PV_RESTORE_REGS(set) \
|
|
COND_POP(set, CLBR_EDX, edx); \
|
|
COND_POP(set, CLBR_ECX, ecx); \
|
|
COND_POP(set, CLBR_EDI, edi); \
|
|
COND_POP(set, CLBR_EAX, eax)
|
|
|
|
#define PARA_PATCH(off) ((off) / 4)
|
|
#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4)
|
|
#define PARA_INDIRECT(addr) *%cs:addr
|
|
#endif
|
|
|
|
#ifdef CONFIG_PARAVIRT_XXL
|
|
#define INTERRUPT_RETURN \
|
|
PARA_SITE(PARA_PATCH(PV_CPU_iret), \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
|
|
|
|
#define DISABLE_INTERRUPTS(clobbers) \
|
|
PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
|
|
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \
|
|
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
|
|
|
|
#define ENABLE_INTERRUPTS(clobbers) \
|
|
PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \
|
|
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
|
|
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
|
|
#endif
|
|
|
|
#ifdef CONFIG_X86_64
|
|
#ifdef CONFIG_PARAVIRT_XXL
|
|
/*
|
|
* If swapgs is used while the userspace stack is still current,
|
|
* there's no way to call a pvop. The PV replacement *must* be
|
|
* inlined, or the swapgs instruction must be trapped and emulated.
|
|
*/
|
|
#define SWAPGS_UNSAFE_STACK \
|
|
PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs)
|
|
|
|
/*
|
|
* Note: swapgs is very special, and in practise is either going to be
|
|
* implemented with a single "swapgs" instruction or something very
|
|
* special. Either way, we don't need to save any registers for
|
|
* it.
|
|
*/
|
|
#define SWAPGS \
|
|
PARA_SITE(PARA_PATCH(PV_CPU_swapgs), \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \
|
|
)
|
|
|
|
#define USERGS_SYSRET64 \
|
|
PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
|
|
|
|
#ifdef CONFIG_DEBUG_ENTRY
|
|
#define SAVE_FLAGS(clobbers) \
|
|
PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \
|
|
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \
|
|
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
|
|
#endif
|
|
#endif /* CONFIG_PARAVIRT_XXL */
|
|
#endif /* CONFIG_X86_64 */
|
|
|
|
#ifdef CONFIG_PARAVIRT_XXL
|
|
|
|
#define GET_CR2_INTO_AX \
|
|
PARA_SITE(PARA_PATCH(PV_MMU_read_cr2), \
|
|
ANNOTATE_RETPOLINE_SAFE; \
|
|
call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2); \
|
|
)
|
|
|
|
#endif /* CONFIG_PARAVIRT_XXL */
|
|
|
|
|
|
#endif /* __ASSEMBLY__ */
|
|
#else /* CONFIG_PARAVIRT */
|
|
# define default_banner x86_init_noop
|
|
#endif /* !CONFIG_PARAVIRT */
|
|
|
|
#ifndef __ASSEMBLY__
|
|
#ifndef CONFIG_PARAVIRT_XXL
|
|
static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
|
|
struct mm_struct *mm)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifndef CONFIG_PARAVIRT
|
|
static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
|
|
{
|
|
}
|
|
#endif
|
|
#endif /* __ASSEMBLY__ */
|
|
#endif /* _ASM_X86_PARAVIRT_H */
|