[Xen-devel] [PATCH v3] x86/mm: Suppresses vm_events caused by page-walks

[Alexandru Isaila <aisaila@xxxxxxxxxxxxxxx>]

This patch is adding a way to enable/disable inguest pagefault
events. It introduces the xc_monitor_inguest_pagefault function
and adds the inguest_pagefault_disabled in the monitor structure.
This is needed by the introspection so it will only get gla
faults and not get spammed with other faults.
In p2m_set_ad_bits the v->arch.sse_pg_dirty.eip and
v->arch.sse_pg_dirty.gla are used to mark that this is the
second time a fault occurs and the dirty bit is set.

Signed-off-by: Alexandru Isaila <aisaila@xxxxxxxxxxxxxxx>

---
Changes since V2:
        - Renamed nested_pagefault to inguest_pagefault
        - Add comment to inguest_pagefault_disabled
---
 tools/libxc/include/xenctrl.h |  2 ++
 tools/libxc/xc_monitor.c      | 14 ++++++++++++++
 xen/arch/x86/mm/mem_access.c  | 27 +++++++++++++++++++++++++++
 xen/arch/x86/monitor.c        | 13 +++++++++++++
 xen/include/asm-x86/domain.h  | 10 ++++++++++
 xen/include/asm-x86/monitor.h |  3 ++-
 xen/include/public/domctl.h   |  2 ++
 7 files changed, 70 insertions(+), 1 deletion(-)

diff --git a/tools/libxc/include/xenctrl.h b/tools/libxc/include/xenctrl.h
index 09e1363..20c2813 100644
--- a/tools/libxc/include/xenctrl.h
+++ b/tools/libxc/include/xenctrl.h
@@ -2056,6 +2056,8 @@ int xc_monitor_descriptor_access(xc_interface *xch, 
uint32_t domain_id,
                                  bool enable);
 int xc_monitor_guest_request(xc_interface *xch, uint32_t domain_id,
                              bool enable, bool sync, bool allow_userspace);
+int xc_monitor_inguest_pagefault(xc_interface *xch, uint32_t domain_id,
+                                 bool disable);
 int xc_monitor_debug_exceptions(xc_interface *xch, uint32_t domain_id,
                                 bool enable, bool sync);
 int xc_monitor_cpuid(xc_interface *xch, uint32_t domain_id, bool enable);
diff --git a/tools/libxc/xc_monitor.c b/tools/libxc/xc_monitor.c
index 0233b87..4ac823e 100644
--- a/tools/libxc/xc_monitor.c
+++ b/tools/libxc/xc_monitor.c
@@ -163,6 +163,20 @@ int xc_monitor_guest_request(xc_interface *xch, uint32_t 
domain_id, bool enable,
     return do_domctl(xch, &domctl);
 }
 
+int xc_monitor_inguest_pagefault(xc_interface *xch, uint32_t domain_id,
+                                bool disable)
+{
+    DECLARE_DOMCTL;
+
+    domctl.cmd = XEN_DOMCTL_monitor_op;
+    domctl.domain = domain_id;
+    domctl.u.monitor_op.op = disable ? XEN_DOMCTL_MONITOR_OP_ENABLE
+                                    : XEN_DOMCTL_MONITOR_OP_DISABLE;
+    domctl.u.monitor_op.event = XEN_DOMCTL_MONITOR_EVENT_INGUEST_PAGEFAULT;
+
+    return do_domctl(xch, &domctl);
+}
+
 int xc_monitor_emulate_each_rep(xc_interface *xch, uint32_t domain_id,
                                 bool enable)
 {
diff --git a/xen/arch/x86/mm/mem_access.c b/xen/arch/x86/mm/mem_access.c
index c0cd017..057f345 100644
--- a/xen/arch/x86/mm/mem_access.c
+++ b/xen/arch/x86/mm/mem_access.c
@@ -137,6 +137,23 @@ bool p2m_mem_access_emulate_check(struct vcpu *v,
     return violation;
 }
 
+static void p2m_set_ad_bits(struct vcpu *v, paddr_t ga)
+{
+    struct hvm_hw_cpu ctxt;
+    uint32_t pfec = 0;
+
+    hvm_funcs.save_cpu_ctxt(v, &ctxt);
+
+    if ( guest_cpu_user_regs()->eip == v->arch.pg_dirty.eip
+         && ga == v->arch.pg_dirty.gla )
+        pfec = PFEC_write_access;
+
+    paging_ga_to_gfn_cr3(v, ctxt.cr3, ga, &pfec, NULL);
+
+    v->arch.pg_dirty.eip = guest_cpu_user_regs()->eip;
+    v->arch.pg_dirty.gla = ga;
+}
+
 bool p2m_mem_access_check(paddr_t gpa, unsigned long gla,
                           struct npfec npfec,
                           vm_event_request_t **req_ptr)
@@ -208,6 +225,16 @@ bool p2m_mem_access_check(paddr_t gpa, unsigned long gla,
         }
     }
 
+    if ( vm_event_check_ring(d->vm_event_monitor) &&
+         d->arch.monitor.inguest_pagefault_disabled &&
+         npfec.kind != npfec_kind_with_gla ) /* don't send a mem_event */
+    {
+        v->arch.vm_event->emulate_flags = 0;
+        p2m_set_ad_bits(v, gla);
+
+        return true;
+    }
+
     *req_ptr = NULL;
     req = xzalloc(vm_event_request_t);
     if ( req )
diff --git a/xen/arch/x86/monitor.c b/xen/arch/x86/monitor.c
index f229e69..ce5d1ba 100644
--- a/xen/arch/x86/monitor.c
+++ b/xen/arch/x86/monitor.c
@@ -241,6 +241,19 @@ int arch_monitor_domctl_event(struct domain *d,
         break;
     }
 
+    case XEN_DOMCTL_MONITOR_EVENT_INGUEST_PAGEFAULT:
+    {
+        bool old_status = ad->monitor.inguest_pagefault_disabled;
+
+        if ( unlikely(old_status == requested_status) )
+            return -EEXIST;
+
+        domain_pause(d);
+        ad->monitor.inguest_pagefault_disabled = requested_status;
+        domain_unpause(d);
+        break;
+    }
+
     case XEN_DOMCTL_MONITOR_EVENT_DESC_ACCESS:
     {
         bool old_status = ad->monitor.descriptor_access_enabled;
diff --git a/xen/include/asm-x86/domain.h b/xen/include/asm-x86/domain.h
index 4679d54..37d04a2 100644
--- a/xen/include/asm-x86/domain.h
+++ b/xen/include/asm-x86/domain.h
@@ -412,6 +412,11 @@ struct arch_domain
         unsigned int descriptor_access_enabled                             : 1;
         unsigned int guest_request_userspace_enabled                       : 1;
         unsigned int emul_unimplemented_enabled                            : 1;
+        /*
+         * By default all events are sent.
+         * This is used to filter out pagefaults.
+         */
+        unsigned int inguest_pagefault_disabled                            : 1;
         struct monitor_msr_bitmap *msr_bitmap;
         uint64_t write_ctrlreg_mask[4];
     } monitor;
@@ -579,6 +584,11 @@ struct arch_vcpu
     /* A secondary copy of the vcpu time info. */
     XEN_GUEST_HANDLE(vcpu_time_info_t) time_info_guest;
 
+    struct {
+        unsigned long eip;
+        unsigned long gla;
+    } pg_dirty;
+
     struct arch_vm_event *vm_event;
 
     struct msr_vcpu_policy *msr;
diff --git a/xen/include/asm-x86/monitor.h b/xen/include/asm-x86/monitor.h
index a0444d1..647df4a 100644
--- a/xen/include/asm-x86/monitor.h
+++ b/xen/include/asm-x86/monitor.h
@@ -84,7 +84,8 @@ static inline uint32_t arch_monitor_get_capabilities(struct 
domain *d)
                    (1U << XEN_DOMCTL_MONITOR_EVENT_DEBUG_EXCEPTION) |
                    (1U << XEN_DOMCTL_MONITOR_EVENT_CPUID) |
                    (1U << XEN_DOMCTL_MONITOR_EVENT_INTERRUPT) |
-                   (1U << XEN_DOMCTL_MONITOR_EVENT_EMUL_UNIMPLEMENTED);
+                   (1U << XEN_DOMCTL_MONITOR_EVENT_EMUL_UNIMPLEMENTED) |
+                   (1U << XEN_DOMCTL_MONITOR_EVENT_INGUEST_PAGEFAULT);
 
     /* Since we know this is on VMX, we can just call the hvm func */
     if ( hvm_is_singlestep_supported() )
diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index 9ae72959..ab89f35 100644
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -1014,6 +1014,8 @@ struct xen_domctl_psr_cmt_op {
 #define XEN_DOMCTL_MONITOR_EVENT_INTERRUPT             8
 #define XEN_DOMCTL_MONITOR_EVENT_DESC_ACCESS           9
 #define XEN_DOMCTL_MONITOR_EVENT_EMUL_UNIMPLEMENTED    10
+/* Enabled by default */
+#define XEN_DOMCTL_MONITOR_EVENT_INGUEST_PAGEFAULT     11
 
 struct xen_domctl_monitor_op {
     uint32_t op; /* XEN_DOMCTL_MONITOR_OP_* */
-- 
2.7.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel