[PATCH 4/8] x86/paravirt: flush pending mmu updates on context switch

From: Jeremy Fitzhardinge
Date: Fri Mar 27 2009 - 14:04:20 EST

Next message: Jeremy Fitzhardinge: "[PATCH 7/8] mm: allow preemption in apply_to_pte_range"
Previous message: Jeremy Fitzhardinge: "[PATCH 2/8] x86/paravirt: remove lazy mode in interrupts"
In reply to: Jeremy Fitzhardinge: "[PATCH 2/8] x86/paravirt: remove lazy mode in interrupts"
Next in thread: Jeremy Fitzhardinge: "[PATCH 7/8] mm: allow preemption in apply_to_pte_range"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>

Impact: allow preemption during lazy mmu updates

If we're in lazy mmu mode when context switching, leave
lazy mmu mode, but remember the task's state in
TIF_LAZY_MMU_UPDATES. When we resume the task, check this
flag and re-enter lazy mmu mode if its set.

This sets things up for allowing lazy mmu mode while preemptible,
though that won't actually be active until the next change.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
---
arch/x86/include/asm/paravirt.h | 1 -
arch/x86/include/asm/thread_info.h | 2 ++
arch/x86/kernel/kvm.c | 2 +-
arch/x86/kernel/paravirt.c | 13 ++++++++++---
arch/x86/kernel/vmi_32.c | 14 ++++++++++----
arch/x86/lguest/boot.c | 14 ++++++++++----
arch/x86/xen/enlighten.c | 6 +++---
arch/x86/xen/mmu.c | 7 ++++++-
arch/x86/xen/xen-ops.h | 1 -
9 files changed, 42 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f79dc89..5ecd16e 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -1403,7 +1403,6 @@ void paravirt_enter_lazy_cpu(void);
void paravirt_leave_lazy_cpu(void);
void paravirt_enter_lazy_mmu(void);
void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);

#define __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(void)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 83d2b73..e6b4beb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -96,6 +96,7 @@ struct thread_info {
#define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */
#define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */
#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */
+#define TIF_LAZY_MMU_UPDATES 28 /* task is updating the mmu lazily */

#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
@@ -119,6 +120,7 @@ struct thread_info {
#define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR)
#define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR)
#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE)
+#define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES)

/* work to do in syscall_trace_enter() */
#define _TIF_WORK_SYSCALL_ENTRY \
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33019dd..6551ded 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -195,7 +195,7 @@ static void kvm_leave_lazy_mmu(void)
struct kvm_para_state *state = kvm_para_state();

mmu_queue_flush(state);
- paravirt_leave_lazy(paravirt_get_lazy_mode());
+ paravirt_leave_lazy_mmu();
state->mode = paravirt_get_lazy_mode();
}

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index a53e4fb..eca40de 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -252,7 +252,7 @@ static inline void enter_lazy(enum paravirt_lazy_mode mode)
__get_cpu_var(paravirt_lazy_mode) = mode;
}

-void paravirt_leave_lazy(enum paravirt_lazy_mode mode)
+static void leave_lazy(enum paravirt_lazy_mode mode)
{
BUG_ON(__get_cpu_var(paravirt_lazy_mode) != mode);
BUG_ON(preemptible());
@@ -267,17 +267,24 @@ void paravirt_enter_lazy_mmu(void)

void paravirt_leave_lazy_mmu(void)
{
- paravirt_leave_lazy(PARAVIRT_LAZY_MMU);
+ leave_lazy(PARAVIRT_LAZY_MMU);
}

void paravirt_enter_lazy_cpu(void)
{
+ if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+ arch_leave_lazy_mmu_mode();
+ set_thread_flag(TIF_LAZY_MMU_UPDATES);
+ }
enter_lazy(PARAVIRT_LAZY_CPU);
}

void paravirt_leave_lazy_cpu(void)
{
- paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+ leave_lazy(PARAVIRT_LAZY_CPU);
+
+ if (test_and_clear_thread_flag(TIF_LAZY_MMU_UPDATES))
+ arch_enter_lazy_mmu_mode();
}

enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 95deb9f..d74122f 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -468,16 +468,22 @@ static void vmi_enter_lazy_cpu(void)
vmi_ops.set_lazy_mode(2);
}

+static void vmi_leave_lazy_cpu(void)
+{
+ vmi_ops.set_lazy_mode(0);
+ paravirt_leave_lazy_cpu();
+}
+
static void vmi_enter_lazy_mmu(void)
{
paravirt_enter_lazy_mmu();
vmi_ops.set_lazy_mode(1);
}

-static void vmi_leave_lazy(void)
+static void vmi_leave_lazy_mmu(void)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
vmi_ops.set_lazy_mode(0);
+ paravirt_leave_lazy_mmu();
}

static inline int __init check_vmi_rom(struct vrom_header *rom)
@@ -713,12 +719,12 @@ static inline int __init activate_vmi(void)

para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
set_lazy_mode, SetLazyMode);
- para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+ para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy_cpu,
set_lazy_mode, SetLazyMode);

para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
set_lazy_mode, SetLazyMode);
- para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy,
+ para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
set_lazy_mode, SetLazyMode);

/* user and kernel flush are just handled with different flags to FlushTLB */
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 90e44a1..70d412a 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -147,10 +147,16 @@ static void lazy_hcall(unsigned long call,

/* When lazy mode is turned off reset the per-cpu lazy mode variable and then
* issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
+ paravirt_leave_lazy_mmu();
+}
+
+static void lguest_leave_lazy_cpu_mode(void)
+{
+ hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
+ paravirt_leave_lazy_cpu();
}

/*G:033
@@ -1026,7 +1032,7 @@ __init void lguest_init(void)
pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
pv_cpu_ops.wbinvd = lguest_wbinvd;
pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
- pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+ pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_cpu_mode;

/* pagetable management */
pv_mmu_ops.write_cr3 = lguest_write_cr3;
@@ -1039,7 +1045,7 @@ __init void lguest_init(void)
pv_mmu_ops.read_cr2 = lguest_read_cr2;
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_mode;
+ pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;

#ifdef CONFIG_X86_LOCAL_APIC
/* apic read/write intercepts */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 82cd39a..f586e63 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -203,10 +203,10 @@ static unsigned long xen_get_debugreg(int reg)
return HYPERVISOR_get_debugreg(reg);
}

-void xen_leave_lazy(void)
+static void xen_leave_lazy_cpu(void)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
xen_mc_flush();
+ paravirt_leave_lazy_cpu();
}

static unsigned long xen_store_tr(void)
@@ -819,7 +819,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {

.lazy_mode = {
.enter = paravirt_enter_lazy_cpu,
- .leave = xen_leave_lazy,
+ .leave = xen_leave_lazy_cpu,
},
};

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 4702c79..aba3b20 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1816,6 +1816,11 @@ __init void xen_post_allocator_init(void)
xen_mark_init_mm_pinned();
}

+static void xen_leave_lazy_mmu(void)
+{
+ xen_mc_flush();
+ paravirt_leave_lazy_mmu();
+}

const struct pv_mmu_ops xen_mmu_ops __initdata = {
.pagetable_setup_start = xen_pagetable_setup_start,
@@ -1890,7 +1895,7 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {

.lazy_mode = {
.enter = paravirt_enter_lazy_mmu,
- .leave = xen_leave_lazy,
+ .leave = xen_leave_lazy_mmu,
},

.set_fixmap = xen_set_fixmap,
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 2f5ef26..f897cdf 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -30,7 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
void xen_ident_map_ISA(void);
void xen_reserve_top(void);

-void xen_leave_lazy(void);
void xen_post_allocator_init(void);

char * __init xen_memory_setup(void);
--
1.6.0.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Jeremy Fitzhardinge: "[PATCH 7/8] mm: allow preemption in apply_to_pte_range"
Previous message: Jeremy Fitzhardinge: "[PATCH 2/8] x86/paravirt: remove lazy mode in interrupts"
In reply to: Jeremy Fitzhardinge: "[PATCH 2/8] x86/paravirt: remove lazy mode in interrupts"
Next in thread: Jeremy Fitzhardinge: "[PATCH 7/8] mm: allow preemption in apply_to_pte_range"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]