mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 19:51:01 +07:00
7eb7ce4d2e
In xen_restore_fl_direct(), xen_force_evtchn_callback() was being called even if no events were pending. This resulted in (depending on workload) about a 100 times as many xen_version hypercalls as necessary. Fix this by correcting the sense of the conditional jump. This seems to give a significant performance benefit for some workloads. There is some subtle tricksy "..since the check here is trying to check both pending and masked in a single cmpw, but I think this is correct. It will call check_events now only when the combined mask+pending word is 0x0001 (aka unmasked, pending)." (Ian) CC: stable@kernel.org Acked-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: David Vrabel <david.vrabel@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
143 lines
3.6 KiB
ArmAsm
143 lines
3.6 KiB
ArmAsm
/*
|
|
* Asm versions of Xen pv-ops, suitable for either direct use or
|
|
* inlining. The inline versions are the same as the direct-use
|
|
* versions, with the pre- and post-amble chopped off.
|
|
*
|
|
* This code is encoded for size rather than absolute efficiency, with
|
|
* a view to being able to inline as much as possible.
|
|
*
|
|
* We only bother with direct forms (ie, vcpu in percpu data) of the
|
|
* operations here; the indirect forms are better handled in C, since
|
|
* they're generally too large to inline anyway.
|
|
*/
|
|
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/percpu.h>
|
|
#include <asm/processor-flags.h>
|
|
|
|
#include "xen-asm.h"
|
|
|
|
/*
|
|
* Enable events. This clears the event mask and tests the pending
|
|
* event status with one and operation. If there are pending events,
|
|
* then enter the hypervisor to get them handled.
|
|
*/
|
|
ENTRY(xen_irq_enable_direct)
|
|
/* Unmask events */
|
|
movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
|
|
|
|
/*
|
|
* Preempt here doesn't matter because that will deal with any
|
|
* pending interrupts. The pending check may end up being run
|
|
* on the wrong CPU, but that doesn't hurt.
|
|
*/
|
|
|
|
/* Test for pending */
|
|
testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
|
|
jz 1f
|
|
|
|
2: call check_events
|
|
1:
|
|
ENDPATCH(xen_irq_enable_direct)
|
|
ret
|
|
ENDPROC(xen_irq_enable_direct)
|
|
RELOC(xen_irq_enable_direct, 2b+1)
|
|
|
|
|
|
/*
|
|
* Disabling events is simply a matter of making the event mask
|
|
* non-zero.
|
|
*/
|
|
ENTRY(xen_irq_disable_direct)
|
|
movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
|
|
ENDPATCH(xen_irq_disable_direct)
|
|
ret
|
|
ENDPROC(xen_irq_disable_direct)
|
|
RELOC(xen_irq_disable_direct, 0)
|
|
|
|
/*
|
|
* (xen_)save_fl is used to get the current interrupt enable status.
|
|
* Callers expect the status to be in X86_EFLAGS_IF, and other bits
|
|
* may be set in the return value. We take advantage of this by
|
|
* making sure that X86_EFLAGS_IF has the right value (and other bits
|
|
* in that byte are 0), but other bits in the return value are
|
|
* undefined. We need to toggle the state of the bit, because Xen and
|
|
* x86 use opposite senses (mask vs enable).
|
|
*/
|
|
ENTRY(xen_save_fl_direct)
|
|
testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
|
|
setz %ah
|
|
addb %ah, %ah
|
|
ENDPATCH(xen_save_fl_direct)
|
|
ret
|
|
ENDPROC(xen_save_fl_direct)
|
|
RELOC(xen_save_fl_direct, 0)
|
|
|
|
|
|
/*
|
|
* In principle the caller should be passing us a value return from
|
|
* xen_save_fl_direct, but for robustness sake we test only the
|
|
* X86_EFLAGS_IF flag rather than the whole byte. After setting the
|
|
* interrupt mask state, it checks for unmasked pending events and
|
|
* enters the hypervisor to get them delivered if so.
|
|
*/
|
|
ENTRY(xen_restore_fl_direct)
|
|
#ifdef CONFIG_X86_64
|
|
testw $X86_EFLAGS_IF, %di
|
|
#else
|
|
testb $X86_EFLAGS_IF>>8, %ah
|
|
#endif
|
|
setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
|
|
/*
|
|
* Preempt here doesn't matter because that will deal with any
|
|
* pending interrupts. The pending check may end up being run
|
|
* on the wrong CPU, but that doesn't hurt.
|
|
*/
|
|
|
|
/* check for unmasked and pending */
|
|
cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
|
|
jnz 1f
|
|
2: call check_events
|
|
1:
|
|
ENDPATCH(xen_restore_fl_direct)
|
|
ret
|
|
ENDPROC(xen_restore_fl_direct)
|
|
RELOC(xen_restore_fl_direct, 2b+1)
|
|
|
|
|
|
/*
|
|
* Force an event check by making a hypercall, but preserve regs
|
|
* before making the call.
|
|
*/
|
|
check_events:
|
|
#ifdef CONFIG_X86_32
|
|
push %eax
|
|
push %ecx
|
|
push %edx
|
|
call xen_force_evtchn_callback
|
|
pop %edx
|
|
pop %ecx
|
|
pop %eax
|
|
#else
|
|
push %rax
|
|
push %rcx
|
|
push %rdx
|
|
push %rsi
|
|
push %rdi
|
|
push %r8
|
|
push %r9
|
|
push %r10
|
|
push %r11
|
|
call xen_force_evtchn_callback
|
|
pop %r11
|
|
pop %r10
|
|
pop %r9
|
|
pop %r8
|
|
pop %rdi
|
|
pop %rsi
|
|
pop %rdx
|
|
pop %rcx
|
|
pop %rax
|
|
#endif
|
|
ret
|