| Message ID | alpine.DEB.2.20.1708311057260.1874@nanos (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
* Thomas Gleixner <tglx@linutronix.de> wrote: > --- a/arch/x86/xen/enlighten_pv.c > +++ b/arch/x86/xen/enlighten_pv.c > @@ -586,6 +586,68 @@ static void xen_write_ldt_entry(struct d > preempt_enable(); > } > > +#ifdef CONFIG_X86_64 > +static struct { > + void (*orig)(void); > + void (*xen)(void); > + bool ist_okay; > +} trap_array[] = { > + { debug, xen_xendebug, true }, > + { int3, xen_xenint3, true }, > + { double_fault, xen_double_fault, true }, > +#ifdef CONFIG_X86_MCE > + { machine_check, xen_machine_check, true }, > +#endif > + { nmi, xen_nmi, true }, > + { overflow, xen_overflow, false }, > +#ifdef CONFIG_IA32_EMULATION > + { entry_INT80_compat, xen_entry_INT80_compat, false }, > +#endif > + { page_fault, xen_page_fault, false }, > + { divide_error, xen_divide_error, false }, > + { bounds, xen_bounds, false }, > + { invalid_op, xen_invalid_op, false }, > + { device_not_available, xen_device_not_available, false }, > + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, > + { invalid_TSS, xen_invalid_TSS, false }, > + { segment_not_present, xen_segment_not_present, false }, > + { stack_segment, xen_stack_segment, false }, > + { general_protection, xen_general_protection, false }, > + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, > + { coprocessor_error, xen_coprocessor_error, false }, > + { alignment_check, xen_alignment_check, false }, > + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, > +#ifdef CONFIG_TRACING > + { trace_page_fault, xen_trace_page_fault, false }, > +#endif > +}; Low prio nitpicking, could we please write such table based initializers in a vertically organized, tabular fashion: > + { debug, xen_xendebug, true }, > + { int3, xen_xenint3, true }, > + { double_fault, xen_double_fault, true }, > +#ifdef CONFIG_X86_MCE > + { machine_check, xen_machine_check, true }, > +#endif > + { nmi, xen_nmi, true }, > + { overflow, xen_overflow, false }, > +#ifdef CONFIG_IA32_EMULATION > + { entry_INT80_compat, xen_entry_INT80_compat, false }, > +#endif > + { page_fault, xen_page_fault, false }, > + { divide_error, xen_divide_error, false }, > + { bounds, xen_bounds, false }, > + { invalid_op, xen_invalid_op, false }, > + { device_not_available, xen_device_not_available, false }, > + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, > + { invalid_TSS, xen_invalid_TSS, false }, > + { segment_not_present, xen_segment_not_present, false }, > + { stack_segment, xen_stack_segment, false }, > + { general_protection, xen_general_protection, false }, > + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, > + { coprocessor_error, xen_coprocessor_error, false }, > + { alignment_check, xen_alignment_check, false }, > + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, > +#ifdef CONFIG_TRACING > + { trace_page_fault, xen_trace_page_fault, false }, > +#endif ... as to me such a table is 100 times more readable - YMMV. (If checkpatch whinges about col80 then ignore it.) > + > +static bool get_trap_addr(unsigned long *addr, unsigned int ist) > +{ > + unsigned int nr; > + bool ist_okay = false; > + > + /* > + * Replace trap handler addresses by Xen specific ones. > + * Check for known traps using IST and whitelist them. > + * The debugger ones are the only ones we care about. > + * Xen will handle faults like double_fault, * so we should never see > + * them. Warn if there's an unexpected IST-using fault handler. > + */ > + for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) > + if (*addr == (unsigned long)trap_array[nr].orig) { > + *addr = (unsigned long)trap_array[nr].xen; > + ist_okay = trap_array[nr].ist_okay; > + break; > + } And here I think we could do a more readable variant: static bool get_trap_addr(void **addr, unsigned int ist) ... struct trap_array_entry *entry = trap_array + nr; if (*addr == entry->orig) { *addr = entry->xen; ist_okay = entry->ist_okay; break; } I believe 'void **' is the natural type that avoids the type casts, and the 'trap_array_entry' name has to be defined in the array definition further above. Totally untested though. Thanks, Ingo
On 31/08/17 11:00, Thomas Gleixner wrote: > On Thu, 31 Aug 2017, Thomas Gleixner wrote: >> Hrm. For some reason I missed to remove these defines after getting rid of >> the tracing idt. >> >> I'll remove that now in tip and pull in the XEN stuff to see what needs to >> be done. > > I pushed out the removal of the trace leftovers. Talked to Juergen on IRC > and he suggested to revert the XEN patch in the xen tree and merge it > through tip. > > I've applied it on top of tip:x86/apic and fixed up the merge conflicts > mindlessly. Patch below. > > Juergen, can you please check the result? > > Thanks, > > tglx > > 8<------------- > Subject: xen: Get rid of paravirt op adjust_exception_frame > From: Juergen Gross <jgross@suse.com> > Date: Fri, 11 Aug 2017 16:54:48 +0200 > > When running as Xen pv-guest the exception frame on the stack contains > %r11 and %rcx additional to the other data pushed by the processor. > > Instead of having a paravirt op being called for each exception type > prepend the Xen specific code to each exception entry. When running as > Xen pv-guest just use the exception entry with prepended instructions, > otherwise use the entry without the Xen specific code. > > Signed-off-by: Juergen Gross <jgross@suse.com> > Cc: xen-devel@lists.xenproject.org > Cc: boris.ostrovsky@oracle.com > Cc: luto@amacapital.net > Link: http://lkml.kernel.org/r/20170811145448.5679-1-jgross@suse.com > > --- > arch/x86/entry/entry_64.S | 11 +-- > arch/x86/entry/entry_64_compat.S | 1 > arch/x86/include/asm/paravirt.h | 5 - > arch/x86/include/asm/paravirt_types.h | 4 - > arch/x86/include/asm/proto.h | 3 + > arch/x86/include/asm/traps.h | 3 - > arch/x86/kernel/asm-offsets_64.c | 1 > arch/x86/kernel/paravirt.c | 3 - > arch/x86/xen/enlighten_pv.c | 96 ++++++++++++++++++++++------------ > arch/x86/xen/irq.c | 3 - > arch/x86/xen/xen-ops.h | 1 > 11 files changed, 70 insertions(+), 61 deletions(-) > > --- a/arch/x86/entry/entry_64.S > +++ b/arch/x86/entry/entry_64.S > @@ -816,7 +816,6 @@ ENTRY(\sym) > .endif > > ASM_CLAC > - PARAVIRT_ADJUST_EXCEPTION_FRAME > > .ifeq \has_error_code > pushq $-1 /* ORIG_RAX: no syscall to restart */ > @@ -962,7 +961,7 @@ ENTRY(do_softirq_own_stack) > ENDPROC(do_softirq_own_stack) > > #ifdef CONFIG_XEN > -idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 > +idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 > > /* > * A note on the "critical region" in our callback handler. > @@ -1029,8 +1028,6 @@ ENTRY(xen_failsafe_callback) > movq 8(%rsp), %r11 > addq $0x30, %rsp > pushq $0 /* RIP */ > - pushq %r11 > - pushq %rcx > UNWIND_HINT_IRET_REGS offset=8 > jmp general_protection > 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ > @@ -1061,9 +1058,8 @@ idtentry int3 do_int3 has_error_code > idtentry stack_segment do_stack_segment has_error_code=1 > > #ifdef CONFIG_XEN > -idtentry xen_debug do_debug has_error_code=0 > -idtentry xen_int3 do_int3 has_error_code=0 > -idtentry xen_stack_segment do_stack_segment has_error_code=1 > +idtentry xendebug do_debug has_error_code=0 > +idtentry xenint3 do_int3 has_error_code=0 > #endif > > idtentry general_protection do_general_protection has_error_code=1 > @@ -1227,6 +1223,7 @@ ENTRY(error_exit) > END(error_exit) > > /* Runs on exception stack */ > +/* XXX: broken on Xen PV */ > ENTRY(nmi) > UNWIND_HINT_IRET_REGS > /* > --- a/arch/x86/entry/entry_64_compat.S > +++ b/arch/x86/entry/entry_64_compat.S > @@ -293,7 +293,6 @@ ENTRY(entry_INT80_compat) > /* > * Interrupts are off on entry. > */ > - PARAVIRT_ADJUST_EXCEPTION_FRAME > ASM_CLAC /* Do this early to minimize exposure */ > SWAPGS > > --- a/arch/x86/include/asm/paravirt.h > +++ b/arch/x86/include/asm/paravirt.h > @@ -960,11 +960,6 @@ extern void default_banner(void); > #define GET_CR2_INTO_RAX \ > call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) > > -#define PARAVIRT_ADJUST_EXCEPTION_FRAME \ > - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \ > - CLBR_NONE, \ > - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame)) > - > #define USERGS_SYSRET64 \ > PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ > CLBR_NONE, \ > --- a/arch/x86/include/asm/paravirt_types.h > +++ b/arch/x86/include/asm/paravirt_types.h > @@ -195,10 +195,6 @@ struct pv_irq_ops { > > void (*safe_halt)(void); > void (*halt)(void); > - > -#ifdef CONFIG_X86_64 > - void (*adjust_exception_frame)(void); > -#endif > } __no_randomize_layout; > > struct pv_mmu_ops { > --- a/arch/x86/include/asm/proto.h > +++ b/arch/x86/include/asm/proto.h > @@ -24,6 +24,9 @@ void entry_SYSENTER_compat(void); > void __end_entry_SYSENTER_compat(void); > void entry_SYSCALL_compat(void); > void entry_INT80_compat(void); > +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) > +void xen_entry_INT80_compat(void); > +#endif > #endif > > void x86_configure_nx(void); > --- a/arch/x86/include/asm/traps.h > +++ b/arch/x86/include/asm/traps.h > @@ -13,9 +13,6 @@ asmlinkage void divide_error(void); > asmlinkage void debug(void); > asmlinkage void nmi(void); > asmlinkage void int3(void); > -asmlinkage void xen_debug(void); > -asmlinkage void xen_int3(void); > -asmlinkage void xen_stack_segment(void); > asmlinkage void overflow(void); > asmlinkage void bounds(void); > asmlinkage void invalid_op(void); > --- a/arch/x86/kernel/asm-offsets_64.c > +++ b/arch/x86/kernel/asm-offsets_64.c > @@ -20,7 +20,6 @@ static char syscalls_ia32[] = { > int main(void) > { > #ifdef CONFIG_PARAVIRT > - OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); > OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); > OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); > BLANK(); > --- a/arch/x86/kernel/paravirt.c > +++ b/arch/x86/kernel/paravirt.c > @@ -319,9 +319,6 @@ struct pv_time_ops pv_time_ops = { > .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), > .safe_halt = native_safe_halt, > .halt = native_halt, > -#ifdef CONFIG_X86_64 > - .adjust_exception_frame = paravirt_nop, > -#endif > }; > > __visible struct pv_cpu_ops pv_cpu_ops = { > --- a/arch/x86/xen/enlighten_pv.c > +++ b/arch/x86/xen/enlighten_pv.c > @@ -586,6 +586,68 @@ static void xen_write_ldt_entry(struct d > preempt_enable(); > } > > +#ifdef CONFIG_X86_64 > +static struct { > + void (*orig)(void); > + void (*xen)(void); > + bool ist_okay; > +} trap_array[] = { > + { debug, xen_xendebug, true }, > + { int3, xen_xenint3, true }, > + { double_fault, xen_double_fault, true }, > +#ifdef CONFIG_X86_MCE > + { machine_check, xen_machine_check, true }, > +#endif > + { nmi, xen_nmi, true }, > + { overflow, xen_overflow, false }, > +#ifdef CONFIG_IA32_EMULATION > + { entry_INT80_compat, xen_entry_INT80_compat, false }, > +#endif > + { page_fault, xen_page_fault, false }, > + { divide_error, xen_divide_error, false }, > + { bounds, xen_bounds, false }, > + { invalid_op, xen_invalid_op, false }, > + { device_not_available, xen_device_not_available, false }, > + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, > + { invalid_TSS, xen_invalid_TSS, false }, > + { segment_not_present, xen_segment_not_present, false }, > + { stack_segment, xen_stack_segment, false }, > + { general_protection, xen_general_protection, false }, > + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, > + { coprocessor_error, xen_coprocessor_error, false }, > + { alignment_check, xen_alignment_check, false }, > + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, > +#ifdef CONFIG_TRACING > + { trace_page_fault, xen_trace_page_fault, false }, > +#endif > +}; > + > +static bool get_trap_addr(unsigned long *addr, unsigned int ist) > +{ > + unsigned int nr; > + bool ist_okay = false; > + > + /* > + * Replace trap handler addresses by Xen specific ones. > + * Check for known traps using IST and whitelist them. > + * The debugger ones are the only ones we care about. > + * Xen will handle faults like double_fault, * so we should never see > + * them. Warn if there's an unexpected IST-using fault handler. > + */ > + for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) > + if (*addr == (unsigned long)trap_array[nr].orig) { > + *addr = (unsigned long)trap_array[nr].xen; > + ist_okay = trap_array[nr].ist_okay; > + break; > + } > + > + if (WARN_ON(ist != 0 && !ist_okay)) > + return false; > + > + return true; > +} > +#endif > + > static int cvt_gate_to_trap(int vector, const gate_desc *val, > struct trap_info *info) > { > @@ -598,40 +660,8 @@ static int cvt_gate_to_trap(int vector, > > addr = gate_offset(val); > #ifdef CONFIG_X86_64 > - /* > - * Look for known traps using IST, and substitute them > - * appropriately. The debugger ones are the only ones we care > - * about. Xen will handle faults like double_fault, > - * so we should never see them. Warn if > - * there's an unexpected IST-using fault handler. > - */ > - if (addr == (unsigned long)debug) > - addr = (unsigned long)xen_debug; > - else if (addr == (unsigned long)int3) > - addr = (unsigned long)xen_int3; > - else if (addr == (unsigned long)stack_segment) > - addr = (unsigned long)xen_stack_segment; > - else if (addr == (unsigned long)double_fault) { > - /* Don't need to handle these */ > + if (!get_trap_addr(&addr, val->bits.ist)) > return 0; > -#ifdef CONFIG_X86_MCE > - } else if (addr == (unsigned long)machine_check) { > - /* > - * when xen hypervisor inject vMCE to guest, > - * use native mce handler to handle it > - */ > - ; > -#endif > - } else if (addr == (unsigned long)nmi) > - /* > - * Use the native version as well. > - */ > - ; > - else { > - /* Some other trap using IST? */ > - if (WARN_ON(val->bits.ist != 0)) > - return 0; > - } > #endif /* CONFIG_X86_64 */ > info->address = addr; > > --- a/arch/x86/xen/irq.c > +++ b/arch/x86/xen/irq.c > @@ -123,9 +123,6 @@ static const struct pv_irq_ops xen_irq_o > > .safe_halt = xen_safe_halt, > .halt = xen_halt, > -#ifdef CONFIG_X86_64 > - .adjust_exception_frame = xen_adjust_exception_frame, > -#endif > }; > > void __init xen_init_irq_ops(void) > --- a/arch/x86/xen/xen-ops.h > +++ b/arch/x86/xen/xen-ops.h > @@ -138,7 +138,6 @@ static inline void __init xen_efi_init(v > __visible void xen_iret(void); > __visible void xen_sysret32(void); > __visible void xen_sysret64(void); > -__visible void xen_adjust_exception_frame(void); > > extern int xen_panic_handler_init(void); > > You missed the updates to arch/x86/xen/xen-asm_64.S and the declarations of the xen specific trap entries in arch/x86/include/asm/traps.h Juergen
On Thu, 31 Aug 2017, Juergen Gross wrote: > > I've applied it on top of tip:x86/apic and fixed up the merge conflicts > > mindlessly. Patch below. > > > > Juergen, can you please check the result? > > You missed the updates to arch/x86/xen/xen-asm_64.S and the declarations > of the xen specific trap entries in arch/x86/include/asm/traps.h I'll try that again later today, unless you beat me to it. Thanks, tglx
On Thu, 2017-08-31 at 11:16 +0200, Ingo Molnar wrote: > * Thomas Gleixner <tglx@linutronix.de> wrote: > Low prio nitpicking, could we please write such table based initializers in a > vertically organized, tabular fashion: > > > + { debug, xen_xendebug, true }, > > + { int3, xen_xenint3, true }, > > + { double_fault, xen_double_fault, true }, > > +#ifdef CONFIG_X86_MCE > > + { machine_check, xen_machine_check, true }, > > +#endif > > + { nmi, xen_nmi, true }, > > + { overflow, xen_overflow, false }, > > +#ifdef CONFIG_IA32_EMULATION > > + { entry_INT80_compat, xen_entry_INT80_compat, false }, > > +#endif > > + { page_fault, xen_page_fault, false }, > > + { divide_error, xen_divide_error, false }, > > + { bounds, xen_bounds, false }, > > + { invalid_op, xen_invalid_op, false }, > > + { device_not_available, xen_device_not_available, false }, > > + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, > > + { invalid_TSS, xen_invalid_TSS, false }, > > + { segment_not_present, xen_segment_not_present, false }, > > + { stack_segment, xen_stack_segment, false }, > > + { general_protection, xen_general_protection, false }, > > + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, > > + { coprocessor_error, xen_coprocessor_error, false }, > > + { alignment_check, xen_alignment_check, false }, > > + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, > > +#ifdef CONFIG_TRACING > > + { trace_page_fault, xen_trace_page_fault, false }, > > +#endif > ,, > ... as to me such a table is 100 times more readable - YMMV. Yeah, kinda. It's a lot of whitespace and eyeball left/right scanning. And these tables require whitespace updating if a longer name is ever used. Given the near 1:1 mapping of <trap> to xen_<trap> perhaps adding a macro would be nice. #define xen_trap(trap, ist_ok) \ { trap, xen_##trap, ist_ok } { debug, xen_xendebug, true }, { int3, xen_xenint3, true }, #ifdef CONFIG_X86_MCE xen_trap(machine_check, true), #endif xen_trap(double_fault, true), xen_trap(nmi, true), xen_trap(overflow, false), ... ymmv. </bikeshedding>
On 08/31/2017 08:00 AM, Thomas Gleixner wrote: > On Thu, 31 Aug 2017, Juergen Gross wrote: >>> I've applied it on top of tip:x86/apic and fixed up the merge conflicts >>> mindlessly. Patch below. >>> >>> Juergen, can you please check the result? >> You missed the updates to arch/x86/xen/xen-asm_64.S and the declarations >> of the xen specific trap entries in arch/x86/include/asm/traps.h > I'll try that again later today, unless you beat me to it. > https://marc.info/?l=linux-kernel&m=150296063131595&w=2 should also be picked up by the tip tree then since it applies on top of the adjust_exception_frame patch. I will revert it from Xen tree as well. -boris
On 31/08/17 16:01, Boris Ostrovsky wrote: > On 08/31/2017 08:00 AM, Thomas Gleixner wrote: >> On Thu, 31 Aug 2017, Juergen Gross wrote: >>>> I've applied it on top of tip:x86/apic and fixed up the merge conflicts >>>> mindlessly. Patch below. >>>> >>>> Juergen, can you please check the result? >>> You missed the updates to arch/x86/xen/xen-asm_64.S and the declarations >>> of the xen specific trap entries in arch/x86/include/asm/traps.h >> I'll try that again later today, unless you beat me to it. >> > > https://marc.info/?l=linux-kernel&m=150296063131595&w=2 should also be > picked up by the tip tree then since it applies on top of the > adjust_exception_frame patch. I will revert it from Xen tree as well. I have included this patch in my rebase on top of the tip tree, so it is no longer needed. Juergen
On Thu, 31 Aug 2017, Boris Ostrovsky wrote: > On 08/31/2017 08:00 AM, Thomas Gleixner wrote: > > On Thu, 31 Aug 2017, Juergen Gross wrote: > >>> I've applied it on top of tip:x86/apic and fixed up the merge conflicts > >>> mindlessly. Patch below. > >>> > >>> Juergen, can you please check the result? > >> You missed the updates to arch/x86/xen/xen-asm_64.S and the declarations > >> of the xen specific trap entries in arch/x86/include/asm/traps.h > > I'll try that again later today, unless you beat me to it. > > > > https://marc.info/?l=linux-kernel&m=150296063131595&w=2 should also be > picked up by the tip tree then since it applies on top of the > adjust_exception_frame patch. I will revert it from Xen tree as well. Juergen folded that fix in and posted a version against tip:x86/apic. It's applied and pushed out now. Thanks to everyone helping with this. tglx
--- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -816,7 +816,6 @@ ENTRY(\sym) .endif ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME .ifeq \has_error_code pushq $-1 /* ORIG_RAX: no syscall to restart */ @@ -962,7 +961,7 @@ ENTRY(do_softirq_own_stack) ENDPROC(do_softirq_own_stack) #ifdef CONFIG_XEN -idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 /* * A note on the "critical region" in our callback handler. @@ -1029,8 +1028,6 @@ ENTRY(xen_failsafe_callback) movq 8(%rsp), %r11 addq $0x30, %rsp pushq $0 /* RIP */ - pushq %r11 - pushq %rcx UNWIND_HINT_IRET_REGS offset=8 jmp general_protection 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ @@ -1061,9 +1058,8 @@ idtentry int3 do_int3 has_error_code idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN -idtentry xen_debug do_debug has_error_code=0 -idtentry xen_int3 do_int3 has_error_code=0 -idtentry xen_stack_segment do_stack_segment has_error_code=1 +idtentry xendebug do_debug has_error_code=0 +idtentry xenint3 do_int3 has_error_code=0 #endif idtentry general_protection do_general_protection has_error_code=1 @@ -1227,6 +1223,7 @@ ENTRY(error_exit) END(error_exit) /* Runs on exception stack */ +/* XXX: broken on Xen PV */ ENTRY(nmi) UNWIND_HINT_IRET_REGS /* --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -293,7 +293,6 @@ ENTRY(entry_INT80_compat) /* * Interrupts are off on entry. */ - PARAVIRT_ADJUST_EXCEPTION_FRAME ASM_CLAC /* Do this early to minimize exposure */ SWAPGS --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -960,11 +960,6 @@ extern void default_banner(void); #define GET_CR2_INTO_RAX \ call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) -#define PARAVIRT_ADJUST_EXCEPTION_FRAME \ - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \ - CLBR_NONE, \ - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame)) - #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -195,10 +195,6 @@ struct pv_irq_ops { void (*safe_halt)(void); void (*halt)(void); - -#ifdef CONFIG_X86_64 - void (*adjust_exception_frame)(void); -#endif } __no_randomize_layout; struct pv_mmu_ops { --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -24,6 +24,9 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_INT80_compat(void); +#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +void xen_entry_INT80_compat(void); +#endif #endif void x86_configure_nx(void); --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -13,9 +13,6 @@ asmlinkage void divide_error(void); asmlinkage void debug(void); asmlinkage void nmi(void); asmlinkage void int3(void); -asmlinkage void xen_debug(void); -asmlinkage void xen_int3(void); -asmlinkage void xen_stack_segment(void); asmlinkage void overflow(void); asmlinkage void bounds(void); asmlinkage void invalid_op(void); --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -20,7 +20,6 @@ static char syscalls_ia32[] = { int main(void) { #ifdef CONFIG_PARAVIRT - OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -319,9 +319,6 @@ struct pv_time_ops pv_time_ops = { .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), .safe_halt = native_safe_halt, .halt = native_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = paravirt_nop, -#endif }; __visible struct pv_cpu_ops pv_cpu_ops = { --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -586,6 +586,68 @@ static void xen_write_ldt_entry(struct d preempt_enable(); } +#ifdef CONFIG_X86_64 +static struct { + void (*orig)(void); + void (*xen)(void); + bool ist_okay; +} trap_array[] = { + { debug, xen_xendebug, true }, + { int3, xen_xenint3, true }, + { double_fault, xen_double_fault, true }, +#ifdef CONFIG_X86_MCE + { machine_check, xen_machine_check, true }, +#endif + { nmi, xen_nmi, true }, + { overflow, xen_overflow, false }, +#ifdef CONFIG_IA32_EMULATION + { entry_INT80_compat, xen_entry_INT80_compat, false }, +#endif + { page_fault, xen_page_fault, false }, + { divide_error, xen_divide_error, false }, + { bounds, xen_bounds, false }, + { invalid_op, xen_invalid_op, false }, + { device_not_available, xen_device_not_available, false }, + { coprocessor_segment_overrun, xen_coprocessor_segment_overrun, false }, + { invalid_TSS, xen_invalid_TSS, false }, + { segment_not_present, xen_segment_not_present, false }, + { stack_segment, xen_stack_segment, false }, + { general_protection, xen_general_protection, false }, + { spurious_interrupt_bug, xen_spurious_interrupt_bug, false }, + { coprocessor_error, xen_coprocessor_error, false }, + { alignment_check, xen_alignment_check, false }, + { simd_coprocessor_error, xen_simd_coprocessor_error, false }, +#ifdef CONFIG_TRACING + { trace_page_fault, xen_trace_page_fault, false }, +#endif +}; + +static bool get_trap_addr(unsigned long *addr, unsigned int ist) +{ + unsigned int nr; + bool ist_okay = false; + + /* + * Replace trap handler addresses by Xen specific ones. + * Check for known traps using IST and whitelist them. + * The debugger ones are the only ones we care about. + * Xen will handle faults like double_fault, * so we should never see + * them. Warn if there's an unexpected IST-using fault handler. + */ + for (nr = 0; nr < ARRAY_SIZE(trap_array); nr++) + if (*addr == (unsigned long)trap_array[nr].orig) { + *addr = (unsigned long)trap_array[nr].xen; + ist_okay = trap_array[nr].ist_okay; + break; + } + + if (WARN_ON(ist != 0 && !ist_okay)) + return false; + + return true; +} +#endif + static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { @@ -598,40 +660,8 @@ static int cvt_gate_to_trap(int vector, addr = gate_offset(val); #ifdef CONFIG_X86_64 - /* - * Look for known traps using IST, and substitute them - * appropriately. The debugger ones are the only ones we care - * about. Xen will handle faults like double_fault, - * so we should never see them. Warn if - * there's an unexpected IST-using fault handler. - */ - if (addr == (unsigned long)debug) - addr = (unsigned long)xen_debug; - else if (addr == (unsigned long)int3) - addr = (unsigned long)xen_int3; - else if (addr == (unsigned long)stack_segment) - addr = (unsigned long)xen_stack_segment; - else if (addr == (unsigned long)double_fault) { - /* Don't need to handle these */ + if (!get_trap_addr(&addr, val->bits.ist)) return 0; -#ifdef CONFIG_X86_MCE - } else if (addr == (unsigned long)machine_check) { - /* - * when xen hypervisor inject vMCE to guest, - * use native mce handler to handle it - */ - ; -#endif - } else if (addr == (unsigned long)nmi) - /* - * Use the native version as well. - */ - ; - else { - /* Some other trap using IST? */ - if (WARN_ON(val->bits.ist != 0)) - return 0; - } #endif /* CONFIG_X86_64 */ info->address = addr; --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -123,9 +123,6 @@ static const struct pv_irq_ops xen_irq_o .safe_halt = xen_safe_halt, .halt = xen_halt, -#ifdef CONFIG_X86_64 - .adjust_exception_frame = xen_adjust_exception_frame, -#endif }; void __init xen_init_irq_ops(void) --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -138,7 +138,6 @@ static inline void __init xen_efi_init(v __visible void xen_iret(void); __visible void xen_sysret32(void); __visible void xen_sysret64(void); -__visible void xen_adjust_exception_frame(void); extern int xen_panic_handler_init(void);