Merge branch 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (42 commits)
  xen: cache cr0 value to avoid trap'n'emulate for read_cr0
  xen/x86-64: clean up warnings about IST-using traps
  xen/x86-64: fix breakpoints and hardware watchpoints
  xen: reserve Xen start_info rather than e820 reserving
  xen: add FIX_TEXT_POKE to fixmap
  lguest: update lazy mmu changes to match lguest's use of kvm hypercalls
  xen: honour VCPU availability on boot
  xen: add "capabilities" file
  xen: drop kexec bits from /sys/hypervisor since kexec isn't implemented yet
  xen/sys/hypervisor: change writable_pt to features
  xen: add /sys/hypervisor support
  xen/xenbus: export xenbus_dev_changed
  xen: use device model for suspending xenbus devices
  xen: remove suspend_cancel hook
  xen/dev-evtchn: clean up locking in evtchn
  xen: export ioctl headers to userspace
  xen: add /dev/xen/evtchn driver
  xen: add irq_from_evtchn
  xen: clean up gate trap/interrupt constants
  xen: set _PAGE_NX in __supported_pte_mask before pagetable construction
  ...

4 files changed, 71 insertions, 24 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f09e8c36ee80..0a1700a2be9c 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/start_kernel.h>
 #include <linux/sched.h>
+#include <linux/kprobes.h>
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -44,6 +45,7 @@
 #include <asm/processor.h>
 #include <asm/proto.h>
 #include <asm/msr-index.h>
+#include <asm/traps.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
@@ -240,10 +242,10 @@ 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)
@@ -428,11 +430,44 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
                             struct trap_info *info)
 {
+        unsigned long addr;
+
         if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
                 return 0;
 
         info->vector = vector;
-        info->address = gate_offset(*val);
+
+        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 and
+         * machine_check, 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 ||
+                 addr == (unsigned long)nmi) {
+                /* Don't need to handle these */
+                return 0;
+#ifdef CONFIG_X86_MCE
+        } else if (addr == (unsigned long)machine_check) {
+                return 0;
+#endif
+        } else {
+                /* Some other trap using IST? */
+                if (WARN_ON(val->ist != 0))
+                        return 0;
+        }
+#endif  /* CONFIG_X86_64 */
+        info->address = addr;
+
         info->cs = gate_segment(*val);
         info->flags = val->dpl;
         /* interrupt gates clear IF */
@@ -623,10 +658,26 @@ static void xen_clts(void)
         xen_mc_issue(PARAVIRT_LAZY_CPU);
 }
 
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+        unsigned long cr0 = percpu_read(xen_cr0_value);
+
+        if (unlikely(cr0 == 0)) {
+                cr0 = native_read_cr0();
+                percpu_write(xen_cr0_value, cr0);
+        }
+
+        return cr0;
+}
+
 static void xen_write_cr0(unsigned long cr0)
 {
         struct multicall_space mcs;
 
+        percpu_write(xen_cr0_value, cr0);
+
         /* Only pay attention to cr0.TS; everything else is
            ignored. */
         mcs = xen_mc_entry(0);
@@ -812,7 +863,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
 
         .clts = xen_clts,
 
-        .read_cr0 = native_read_cr0,
+        .read_cr0 = xen_read_cr0,
         .write_cr0 = xen_write_cr0,
 
         .read_cr4 = native_read_cr4,
@@ -860,10 +911,8 @@ 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 fba55b1a4021..4ceb28581652 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -452,10 +452,6 @@ 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);
@@ -476,9 +472,7 @@ 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,
@@ -1152,10 +1146,8 @@ 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)
@@ -1168,7 +1160,6 @@ 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. */
@@ -1876,6 +1867,14 @@ __init void xen_post_allocator_init(void)
         xen_mark_init_mm_pinned();
 }
 
+static void xen_leave_lazy_mmu(void)
+{
+        preempt_disable();
+        xen_mc_flush();
+        paravirt_leave_lazy_mmu();
+        preempt_enable();
+}
+
 const struct pv_mmu_ops xen_mmu_ops __initdata = {
         .pagetable_setup_start = xen_pagetable_setup_start,
         .pagetable_setup_done = xen_pagetable_setup_done,
@@ -1949,7 +1948,7 @@ 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/setup.c b/arch/x86/xen/setup.c
index 15c6c68db6a2..ad0047f47cd4 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -61,9 +61,9 @@ char * __init xen_memory_setup(void)
          *  - xen_start_info
          * See comment above "struct start_info" in <xen/interface/xen.h>
          */
-        e820_add_region(__pa(xen_start_info->mfn_list),
-                        xen_start_info->pt_base - xen_start_info->mfn_list,
-                        E820_RESERVED);
+        reserve_early(__pa(xen_start_info->mfn_list),
+                      __pa(xen_start_info->pt_base),
+                        "XEN START INFO");
 
         sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index ca6596b05d53..22494fd4c9b5 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);