x86, mm: Patch out arch_flush_lazy_mmu_mode() when running on bare metal

commit 511ba86e1d386f671084b5d0e6f110bb30b8eeb2 upstream.

Invoking arch_flush_lazy_mmu_mode() results in calls to
preempt_enable()/disable() which may have performance impact.

Since lazy MMU is not used on bare metal we can patch away
arch_flush_lazy_mmu_mode() so that it is never called in such
environment.

[ hpa: the previous patch "Fix vmalloc_fault oops during lazy MMU
  updates" may cause a minor performance regression on
  bare metal.  This patch resolves that performance regression.  It is
  somewhat unclear to me if this is a good -stable candidate. ]

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: http://lkml.kernel.org/r/1364045796-10720-2-git-send-email-konrad.wilk@oracle.com
Tested-by: Josh Boyer <jwboyer@redhat.com>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a7d2db9..91e758b 100644 (file)
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -740,7 +740,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
        PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
        PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 

-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+       PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}

 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
                                phys_addr_t phys, pgprot_t flags)
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
                                phys_addr_t phys, pgprot_t flags)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8e8b9a4..faf2c04 100644 (file)
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,6 +91,7 @@ struct pv_lazy_ops {
        /* Set deferred update mode, used for batching operations. */
        void (*enter)(void);
        void (*leave)(void);
        /* Set deferred update mode, used for batching operations. */
        void (*enter)(void);
        void (*leave)(void);

+       void (*flush)(void);

 };
 
 struct pv_time_ops {
 };
 
 struct pv_time_ops {


@@ -680,6 +681,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);

+void paravirt_flush_lazy_mmu(void);

 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index d90272e..84c938f 100644 (file)
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -261,6 +261,18 @@ void paravirt_leave_lazy_mmu(void)
        leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
        leave_lazy(PARAVIRT_LAZY_MMU);
 }
 

+void paravirt_flush_lazy_mmu(void)
+{
+       preempt_disable();
+
+       if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+               arch_leave_lazy_mmu_mode();
+               arch_enter_lazy_mmu_mode();
+       }
+
+       preempt_enable();
+}
+

 void paravirt_start_context_switch(struct task_struct *prev)
 {
        BUG_ON(preemptible());
 void paravirt_start_context_switch(struct task_struct *prev)
 {
        BUG_ON(preemptible());


@@ -290,18 +302,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
        return percpu_read(paravirt_lazy_mode);
 }
 
        return percpu_read(paravirt_lazy_mode);
 }
 

-void arch_flush_lazy_mmu_mode(void)
-{
-       preempt_disable();
-
-       if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-               arch_leave_lazy_mmu_mode();
-               arch_enter_lazy_mmu_mode();
-       }
-
-       preempt_enable();
-}
-

 struct pv_info pv_info = {
        .name = "bare hardware",
        .paravirt_enabled = 0,
 struct pv_info pv_info = {
        .name = "bare hardware",
        .paravirt_enabled = 0,


@@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = {
        .lazy_mode = {
                .enter = paravirt_nop,
                .leave = paravirt_nop,
        .lazy_mode = {
                .enter = paravirt_nop,
                .leave = paravirt_nop,

+               .flush = paravirt_nop,

        },
 
        .set_fixmap = native_set_fixmap,
        },
 
        .set_fixmap = native_set_fixmap,

diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index cf4603b..8f4fda4 100644 (file)
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1328,6 +1328,7 @@ __init void lguest_init(void)
        pv_mmu_ops.read_cr3 = lguest_read_cr3;
        pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
        pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
        pv_mmu_ops.read_cr3 = lguest_read_cr3;
        pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
        pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;

+       pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;

        pv_mmu_ops.pte_update = lguest_pte_update;
        pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
        pv_mmu_ops.pte_update = lguest_pte_update;
        pv_mmu_ops.pte_update_defer = lguest_pte_update;
 

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2b8b0de..fe00be6 100644 (file)
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2079,6 +2079,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
        .lazy_mode = {
                .enter = paravirt_enter_lazy_mmu,
                .leave = xen_leave_lazy_mmu,
        .lazy_mode = {
                .enter = paravirt_enter_lazy_mmu,
                .leave = xen_leave_lazy_mmu,

+               .flush = paravirt_flush_lazy_mmu,

        },
 
        .set_fixmap = xen_set_fixmap,
        },
 
        .set_fixmap = xen_set_fixmap,