[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [GIT PULL] x86/paravirt: allow preemption while doing lazy mmu update



This series allows preemption during lazy mmu updates.

No changes from previous postings, just rebased to a newer tip/master.

The following changes since commit 8c85122f33c5242e2f384b1f9f202f28e6bf4e61:
 Ingo Molnar (1):
       Merge branch 'core/locking'

are available in the git repository at:

 git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen.git push2/x86/paravirt

Jeremy Fitzhardinge (8):
     mm: disable preemption in apply_to_pte_range
     x86/paravirt: remove lazy mode in interrupts
     x86/pvops: replace arch_enter_lazy_cpu_mode with arch_start_context_switch
     x86/paravirt: flush pending mmu updates on context switch
     x86/paravirt: finish change from lazy cpu to context switch start/end
     x86/paravirt: allow preemption with lazy mmu mode
     mm: allow preemption in apply_to_pte_range
     x86/paravirt: use percpu_ rather than __get_cpu_var

arch/x86/include/asm/paravirt.h    |   22 +++++++-------
arch/x86/include/asm/pgtable.h     |    2 +
arch/x86/include/asm/thread_info.h |    2 +
arch/x86/kernel/kvm.c              |    2 +-
arch/x86/kernel/paravirt.c         |   56 ++++++++++++++++-------------------
arch/x86/kernel/process_32.c       |    2 +-
arch/x86/kernel/process_64.c       |    2 +-
arch/x86/kernel/vmi_32.c           |   20 ++++++++----
arch/x86/lguest/boot.c             |   16 +++++++---
arch/x86/mm/fault.c                |    6 +--
arch/x86/mm/highmem_32.c           |    2 -
arch/x86/mm/iomap_32.c             |    2 -
arch/x86/mm/pageattr.c             |   14 ---------
arch/x86/xen/enlighten.c           |   10 ++----
arch/x86/xen/mmu.c                 |   20 +++++--------
arch/x86/xen/xen-ops.h             |    1 -
include/asm-frv/pgtable.h          |    4 +-
include/asm-generic/pgtable.h      |   21 +++++++------
kernel/sched.c                     |    2 +-
19 files changed, 96 insertions(+), 110 deletions(-)

Overall diff:

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 7727aa8..bc384be 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -56,6 +56,7 @@ struct desc_ptr;
struct tss_struct;
struct mm_struct;
struct desc_struct;
+struct task_struct;

/*
 * Wrapper type for pointers to code which uses the non-standard
@@ -203,7 +204,8 @@ struct pv_cpu_ops {

        void (*swapgs)(void);

-       struct pv_lazy_ops lazy_mode;
+       void (*start_context_switch)(struct task_struct *prev);
+       void (*end_context_switch)(struct task_struct *next);
};

struct pv_irq_ops {
@@ -1399,25 +1401,23 @@ enum paravirt_lazy_mode {
};

enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
void paravirt_enter_lazy_mmu(void);
void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);

-#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define  __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
{
-       PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+       PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
}

-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
{
-       PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+       PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
}

-void arch_flush_lazy_cpu_mode(void);
-
#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f5ba6c1..205f6a9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -81,6 +81,8 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t 
*base)
#define pte_val(x)      native_pte_val(x)
#define __pte(x)        native_make_pte(x)

+#define arch_end_context_switch(prev)  do {} while(0)
+
#endif  /* CONFIG_PARAVIRT */

/*
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 8e45f44..aa34423 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -246,18 +246,16 @@ static DEFINE_PER_CPU(enum paravirt_lazy_mode, 
paravirt_lazy_mode) = PARAVIRT_LA

static inline void enter_lazy(enum paravirt_lazy_mode mode)
{
-       BUG_ON(__get_cpu_var(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-       BUG_ON(preemptible());
+       BUG_ON(percpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);

-       __get_cpu_var(paravirt_lazy_mode) = mode;
+       percpu_write(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());
+       BUG_ON(percpu_read(paravirt_lazy_mode) != mode);

-       __get_cpu_var(paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
+       percpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
}

void paravirt_enter_lazy_mmu(void)
@@ -267,22 +265,36 @@ 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)
+void paravirt_start_context_switch(struct task_struct *prev)
{
+       BUG_ON(preemptible());
+
+       if (percpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
+               arch_leave_lazy_mmu_mode();
+               set_ti_thread_flag(task_thread_info(prev), 
TIF_LAZY_MMU_UPDATES);
+       }
        enter_lazy(PARAVIRT_LAZY_CPU);
}

-void paravirt_leave_lazy_cpu(void)
+void paravirt_end_context_switch(struct task_struct *next)
{
-       paravirt_leave_lazy(PARAVIRT_LAZY_CPU);
+       BUG_ON(preemptible());
+
+       leave_lazy(PARAVIRT_LAZY_CPU);
+
+       if (test_and_clear_ti_thread_flag(task_thread_info(next), 
TIF_LAZY_MMU_UPDATES))
+               arch_enter_lazy_mmu_mode();
}

enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
{
-       return __get_cpu_var(paravirt_lazy_mode);
+       if (in_interrupt())
+               return PARAVIRT_LAZY_NONE;
+
+       return percpu_read(paravirt_lazy_mode);
}

void arch_flush_lazy_mmu_mode(void)
@@ -290,7 +302,6 @@ void arch_flush_lazy_mmu_mode(void)
        preempt_disable();

        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-               WARN_ON(preempt_count() == 1);
                arch_leave_lazy_mmu_mode();
                arch_enter_lazy_mmu_mode();
        }
@@ -298,19 +309,6 @@ void arch_flush_lazy_mmu_mode(void)
        preempt_enable();
}

-void arch_flush_lazy_cpu_mode(void)
-{
-       preempt_disable();
-
-       if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
-               WARN_ON(preempt_count() == 1);
-               arch_leave_lazy_cpu_mode();
-               arch_enter_lazy_cpu_mode();
-       }
-
-       preempt_enable();
-}
-
struct pv_info pv_info = {
        .name = "bare hardware",
        .paravirt_enabled = 0,
@@ -402,10 +400,8 @@ struct pv_cpu_ops pv_cpu_ops = {
        .set_iopl_mask = native_set_iopl_mask,
        .io_delay = native_io_delay,

-       .lazy_mode = {
-               .enter = paravirt_nop,
-               .leave = paravirt_nop,
-       },
+       .start_context_switch = paravirt_nop,
+       .end_context_switch = paravirt_nop,
};

struct pv_apic_ops pv_apic_ops = {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 14014d7..d766c76 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -407,7 +407,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct 
*next_p)
         * done before math_state_restore, so the TS bit is up
         * to date.
         */
-       arch_leave_lazy_cpu_mode();
+       arch_end_context_switch(next_p);

        /* If the task has used fpu the last 5 timeslices, just do a full
         * restore of the math state immediately to avoid the trap; the
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index abb7e6a..e8a9aaf 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -428,7 +428,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct 
*next_p)
         * done before math_state_restore, so the TS bit is up
         * to date.
         */
-       arch_leave_lazy_cpu_mode();
+       arch_end_context_switch(next_p);

        /*
         * Switch FS and GS.
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 95deb9f..b263423 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -462,22 +462,28 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long 
start_eip,
}
#endif

-static void vmi_enter_lazy_cpu(void)
+static void vmi_start_context_switch(struct task_struct *prev)
{
-       paravirt_enter_lazy_cpu();
+       paravirt_start_context_switch(prev);
        vmi_ops.set_lazy_mode(2);
}

+static void vmi_end_context_switch(struct task_struct *next)
+{
+       vmi_ops.set_lazy_mode(0);
+       paravirt_end_context_switch(next);
+}
+
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)
@@ -711,14 +717,14 @@ static inline int __init activate_vmi(void)
        para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
        para_fill(pv_cpu_ops.io_delay, IODelay);

-       para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu,
+       para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
                  set_lazy_mode, SetLazyMode);
-       para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy,
+       para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
                  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..25799f3 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_end_context_switch(struct task_struct *next)
+{
+       hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0);
+       paravirt_end_context_switch(next);
}

/*G:033
@@ -1025,8 +1031,8 @@ __init void lguest_init(void)
        pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
        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.start_context_switch = paravirt_start_context_switch;
+       pv_cpu_ops.end_context_switch = lguest_end_context_switch;

        /* 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/mm/fault.c b/arch/x86/mm/fault.c
index f70b901..09e6ae4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -227,12 +227,10 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, 
unsigned long address)
        if (!pmd_present(*pmd_k))
                return NULL;

-       if (!pmd_present(*pmd)) {
+       if (!pmd_present(*pmd))
                set_pmd(pmd, *pmd_k);
-               arch_flush_lazy_mmu_mode();
-       } else {
+       else
                BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-       }

        return pmd_k;
}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 522db5e..17d0103 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -87,7 +87,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, 
pgprot_t prot)
        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
        BUG_ON(!pte_none(*(kmap_pte-idx)));
        set_pte(kmap_pte-idx, mk_pte(page, prot));
-       arch_flush_lazy_mmu_mode();

        return (void *)vaddr;
}
@@ -117,7 +116,6 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
#endif
        }

-       arch_flush_lazy_mmu_mode();
        pagefault_enable();
}

diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 699c9b2..0c16a33 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -41,7 +41,6 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type 
type, pgprot_t prot)
        idx = type + KM_TYPE_NR * smp_processor_id();
        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
        set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
-       arch_flush_lazy_mmu_mode();

        return (void *)vaddr;
}
@@ -80,7 +79,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
        if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
                kpte_clear_flush(kmap_pte-idx, vaddr);

-       arch_flush_lazy_mmu_mode();
        pagefault_enable();
}
EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index b0e5adb..1224865 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -844,13 +844,6 @@ static int change_page_attr_set_clr(unsigned long *addr, 
int numpages,

        vm_unmap_aliases();

-       /*
-        * If we're called with lazy mmu updates enabled, the
-        * in-memory pte state may be stale.  Flush pending updates to
-        * bring them up to date.
-        */
-       arch_flush_lazy_mmu_mode();
-
        cpa.vaddr = addr;
        cpa.pages = pages;
        cpa.numpages = numpages;
@@ -895,13 +888,6 @@ static int change_page_attr_set_clr(unsigned long *addr, 
int numpages,
        } else
                cpa_flush_all(cache);

-       /*
-        * If we've been called with lazy mmu updates enabled, then
-        * make sure that everything gets flushed out before we
-        * return.
-        */
-       arch_flush_lazy_mmu_mode();
-
out:
        return ret;
}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 82cd39a..70b355d 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_end_context_switch(struct task_struct *next)
{
-       paravirt_leave_lazy(paravirt_get_lazy_mode());
        xen_mc_flush();
+       paravirt_end_context_switch(next);
}

static unsigned long xen_store_tr(void)
@@ -817,10 +817,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
        /* Xen takes care of %gs when switching to usermode for us */
        .swapgs = paravirt_nop,

-       .lazy_mode = {
-               .enter = paravirt_enter_lazy_cpu,
-               .leave = xen_leave_lazy,
-       },
+       .start_context_switch = paravirt_start_context_switch,
+       .end_context_switch = xen_end_context_switch,
};

static const struct pv_apic_ops xen_apic_ops __initdata = {
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index db3802f..e194f72 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -419,10 +419,6 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, 
pgprot_t flags)
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
                    pte_t *ptep, pte_t pteval)
{
-       /* updates to init_mm may be done without lock */
-       if (mm == &init_mm)
-               preempt_disable();
-
        ADD_STATS(set_pte_at, 1);
//      ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
        ADD_STATS(set_pte_at_current, mm == current->mm);
@@ -443,9 +439,7 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long 
addr,
        }
        xen_set_pte(ptep, pteval);

-out:
-       if (mm == &init_mm)
-               preempt_enable();
+out:   return;
}

pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
@@ -1119,10 +1113,8 @@ static void drop_other_mm_ref(void *info)

        /* If this cpu still has a stale cr3 reference, then make sure
           it has been flushed. */
-       if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+       if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
                load_cr3(swapper_pg_dir);
-               arch_flush_lazy_cpu_mode();
-       }
}

static void xen_drop_mm_ref(struct mm_struct *mm)
@@ -1135,7 +1127,6 @@ static void xen_drop_mm_ref(struct mm_struct *mm)
                        load_cr3(swapper_pg_dir);
                else
                        leave_mm(smp_processor_id());
-               arch_flush_lazy_cpu_mode();
        }

        /* Get the "official" set of cpus referring to our pagetable. */
@@ -1819,6 +1810,11 @@ __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,
@@ -1893,7 +1889,7 @@ 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);
diff --git a/include/asm-frv/pgtable.h b/include/asm-frv/pgtable.h
index e16fdb1..0988704 100644
--- a/include/asm-frv/pgtable.h
+++ b/include/asm-frv/pgtable.h
@@ -73,8 +73,8 @@ static inline int pte_file(pte_t pte) { return 0; }
#define pgtable_cache_init()            do {} while (0)
#define arch_enter_lazy_mmu_mode()      do {} while (0)
#define arch_leave_lazy_mmu_mode()      do {} while (0)
-#define arch_enter_lazy_cpu_mode()     do {} while (0)
-#define arch_leave_lazy_cpu_mode()     do {} while (0)
+
+#define arch_start_context_switch(prev)        do {} while (0)

#else /* !CONFIG_MMU */
/*****************************************************************************/
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e6d0ca..e410f60 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -280,17 +280,18 @@ static inline void ptep_modify_prot_commit(struct 
mm_struct *mm,
#endif

/*
- * A facility to provide batching of the reload of page tables with the
- * actual context switch code for paravirtualized guests.  By convention,
- * only one of the lazy modes (CPU, MMU) should be active at any given
- * time, entry should never be nested, and entry and exits should always
- * be paired.  This is for sanity of maintaining and reasoning about the
- * kernel code.
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests.  By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired.  This is for sanity of maintaining and reasoning about the
+ * kernel code.  In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
 */
-#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-#define arch_enter_lazy_cpu_mode()     do {} while (0)
-#define arch_leave_lazy_cpu_mode()     do {} while (0)
-#define arch_flush_lazy_cpu_mode()     do {} while (0)
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev)        do {} while (0)
#endif

#ifndef __HAVE_PFNMAP_TRACKING
diff --git a/kernel/sched.c b/kernel/sched.c
index 3e827b8..77b43e3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2804,7 +2804,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
         * combine the page table reload and the switch backend into
         * one hypercall.
         */
-       arch_enter_lazy_cpu_mode();
+       arch_start_context_switch(prev);

        if (unlikely(!mm)) {
                next->active_mm = oldmm;



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.