linux_dsm_epyc7002/arch/x86/xen/xen-asm_64.S
Andy Lutomirski 98f05b5138 x86/entry/64: Use the TSS sp2 slot for SYSCALL/SYSRET scratch space
In the non-trampoline SYSCALL64 path, a percpu variable is used to
temporarily store the user RSP value.

Instead of a separate variable, use the otherwise unused sp2 slot in the
TSS.  This will improve cache locality, as the sp1 slot is already used in
the same code to find the kernel stack.  It will also simplify a future
change to make the non-trampoline path work in PTI mode.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lkml.kernel.org/r/08e769a0023dbad4bac6f34f3631dbaf8ad59f4f.1536015544.git.luto@kernel.org
2018-09-08 11:20:11 +02:00

179 lines
3.8 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Asm versions of Xen pv-ops, suitable for direct use.
*
* We only bother with direct forms (ie, vcpu in pda) of the
* operations here; the indirect forms are better handled in C.
*/
#include <asm/errno.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <xen/interface/xen.h>
#include <linux/init.h>
#include <linux/linkage.h>
.macro xen_pv_trap name
ENTRY(xen_\name)
pop %rcx
pop %r11
jmp \name
END(xen_\name)
.endm
xen_pv_trap divide_error
xen_pv_trap debug
xen_pv_trap xendebug
xen_pv_trap int3
xen_pv_trap xenint3
xen_pv_trap xennmi
xen_pv_trap overflow
xen_pv_trap bounds
xen_pv_trap invalid_op
xen_pv_trap device_not_available
xen_pv_trap double_fault
xen_pv_trap coprocessor_segment_overrun
xen_pv_trap invalid_TSS
xen_pv_trap segment_not_present
xen_pv_trap stack_segment
xen_pv_trap general_protection
xen_pv_trap page_fault
xen_pv_trap spurious_interrupt_bug
xen_pv_trap coprocessor_error
xen_pv_trap alignment_check
#ifdef CONFIG_X86_MCE
xen_pv_trap machine_check
#endif /* CONFIG_X86_MCE */
xen_pv_trap simd_coprocessor_error
#ifdef CONFIG_IA32_EMULATION
xen_pv_trap entry_INT80_compat
#endif
xen_pv_trap hypervisor_callback
__INIT
ENTRY(xen_early_idt_handler_array)
i = 0
.rept NUM_EXCEPTION_VECTORS
pop %rcx
pop %r11
jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
i = i + 1
.fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
.endr
END(xen_early_idt_handler_array)
__FINIT
hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
/*
* Xen64 iret frame:
*
* ss
* rsp
* rflags
* cs
* rip <-- standard iret frame
*
* flags
*
* rcx }
* r11 }<-- pushed by hypercall page
* rsp->rax }
*/
ENTRY(xen_iret)
pushq $0
jmp hypercall_iret
ENTRY(xen_sysret64)
/*
* We're already on the usermode stack at this point, but
* still with the kernel gs, so we can easily switch back.
*
* tss.sp2 is scratch space.
*/
movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq $__USER_DS
pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
pushq %r11
pushq $__USER_CS
pushq %rcx
pushq $VGCF_in_syscall
jmp hypercall_iret
/*
* Xen handles syscall callbacks much like ordinary exceptions, which
* means we have:
* - kernel gs
* - kernel rsp
* - an iret-like stack frame on the stack (including rcx and r11):
* ss
* rsp
* rflags
* cs
* rip
* r11
* rsp->rcx
*/
/* Normal 64-bit system call target */
ENTRY(xen_syscall_target)
popq %rcx
popq %r11
/*
* Neither Xen nor the kernel really knows what the old SS and
* CS were. The kernel expects __USER_DS and __USER_CS, so
* report those values even though Xen will guess its own values.
*/
movq $__USER_DS, 4*8(%rsp)
movq $__USER_CS, 1*8(%rsp)
jmp entry_SYSCALL_64_after_hwframe
ENDPROC(xen_syscall_target)
#ifdef CONFIG_IA32_EMULATION
/* 32-bit compat syscall target */
ENTRY(xen_syscall32_target)
popq %rcx
popq %r11
/*
* Neither Xen nor the kernel really knows what the old SS and
* CS were. The kernel expects __USER32_DS and __USER32_CS, so
* report those values even though Xen will guess its own values.
*/
movq $__USER32_DS, 4*8(%rsp)
movq $__USER32_CS, 1*8(%rsp)
jmp entry_SYSCALL_compat_after_hwframe
ENDPROC(xen_syscall32_target)
/* 32-bit compat sysenter target */
ENTRY(xen_sysenter_target)
mov 0*8(%rsp), %rcx
mov 1*8(%rsp), %r11
mov 5*8(%rsp), %rsp
jmp entry_SYSENTER_compat
ENDPROC(xen_sysenter_target)
#else /* !CONFIG_IA32_EMULATION */
ENTRY(xen_syscall32_target)
ENTRY(xen_sysenter_target)
lea 16(%rsp), %rsp /* strip %rcx, %r11 */
mov $-ENOSYS, %rax
pushq $0
jmp hypercall_iret
ENDPROC(xen_syscall32_target)
ENDPROC(xen_sysenter_target)
#endif /* CONFIG_IA32_EMULATION */