linux_dsm_epyc7002/arch/x86/xen/xen-asm_64.S
Zhenzhong Duan b23e5844df xen/pv: Fix a boot up hang revealed by int3 self test
Commit 7457c0da02 ("x86/alternatives: Add int3_emulate_call()
selftest") is used to ensure there is a gap setup in int3 exception stack
which could be used for inserting call return address.

This gap is missed in XEN PV int3 exception entry path, then below panic
triggered:

[    0.772876] general protection fault: 0000 [#1] SMP NOPTI
[    0.772886] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.2.0+ #11
[    0.772893] RIP: e030:int3_magic+0x0/0x7
[    0.772905] RSP: 3507:ffffffff82203e98 EFLAGS: 00000246
[    0.773334] Call Trace:
[    0.773334]  alternative_instructions+0x3d/0x12e
[    0.773334]  check_bugs+0x7c9/0x887
[    0.773334]  ? __get_locked_pte+0x178/0x1f0
[    0.773334]  start_kernel+0x4ff/0x535
[    0.773334]  ? set_init_arg+0x55/0x55
[    0.773334]  xen_start_kernel+0x571/0x57a

For 64bit PV guests, Xen's ABI enters the kernel with using SYSRET, with
%rcx/%r11 on the stack. To convert back to "normal" looking exceptions,
the xen thunks do 'xen_*: pop %rcx; pop %r11; jmp *'.

E.g. Extracting 'xen_pv_trap xenint3' we have:
xen_xenint3:
 pop %rcx;
 pop %r11;
 jmp xenint3

As xenint3 and int3 entry code are same except xenint3 doesn't generate
a gap, we can fix it by using int3 and drop useless xenint3.

Signed-off-by: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
2019-07-17 08:09:59 +02:00

180 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 <asm/asm.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)
_ASM_NOKPROBE(xen_\name)
.endm
xen_pv_trap divide_error
xen_pv_trap debug
xen_pv_trap xendebug
xen_pv_trap int3
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 */