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

[Xen-devel] [PATCH for-4.5 v7 4/7] xen: Add vmware_port support



This includes adding is_vmware_port_enabled

This is a new domain_create() flag, DOMCRF_vmware_port.  It is
passed to domctl as XEN_DOMCTL_CDF_vmware_port.

This enables limited support of VMware's hyper-call.

This is both a more complete support then in currently provided by
QEMU and/or KVM and less.  The missing part requires QEMU changes
and has been left out until the QEMU patches are accepted upstream.

VMware's hyper-call is also known as VMware Backdoor I/O Port.

Note: this support does not depend on vmware_hw being non-zero.

Summary is that VMware treats "in (%dx),%eax" (or "out %eax,(%dx)")
to port 0x5658 specially.  Note: since many operations return data
in EAX, "in (%dx),%eax" is the one to use.  The other lengths like
"in (%dx),%al" will still do things, only AL part of EAX will be
changed.  For "out %eax,(%dx)" of all lengths, EAX will remain
unchanged.

Also this instruction is allowed to be used from ring 3.  To
support this the vmexit for GP needs to be enabled.  I have not
fully tested that nested HVM is doing the right thing for this.

An open source example of using this is:

http://open-vm-tools.sourceforge.net/

Which only uses "inl (%dx)".  Also

http://kb.vmware.com/selfservice/microsites/search.do?language=en_US&cmd=displayKC&externalId=1009458

The support included is enough to allow VMware tools to install in a
HVM domU.

For AMD (svm) the max instruction length of 15 is hard coded.  This
is because __get_instruction_length_from_list() has issues that when
called from #GP handler NRIP is not available, or that NRIP may not
be available at all on a particular HW, leading to the need read the
instruction twice --- once in __get_instruction_length_from_list()
and then again in vmport_gp_check(). Which is bad because memory may
change between the reads.

Signed-off-by: Don Slutz <dslutz@xxxxxxxxxxx>
---
v7:
      More on AMD in the commit message.
      Switch to only change 32bit part of registers, what VMware
        does.
    Too much logging and tracing.
      Dropped a lot of it.  This includes vmport_debug=

v6:
      Dropped the attempt to use svm_nextrip_insn_length via
      __get_instruction_length (added in v2).  Just always look
      at upto 15 bytes on AMD.

v5:
      we should make sure that svm_vmexit_gp_intercept is not executed for
      any other guest.
        Added an ASSERT on is_vmware_port_enabled.
      magic integers?
        Added #define for them.
      I am fairly certain that you need some brackets here.
        Added brackets.

 xen/arch/x86/domain.c                 |   2 +
 xen/arch/x86/hvm/hvm.c                |   4 +
 xen/arch/x86/hvm/svm/emulate.c        |   2 +-
 xen/arch/x86/hvm/svm/svm.c            |  30 ++++
 xen/arch/x86/hvm/svm/vmcb.c           |   2 +
 xen/arch/x86/hvm/vmware/Makefile      |   1 +
 xen/arch/x86/hvm/vmware/vmport.c      | 274 ++++++++++++++++++++++++++++++++++
 xen/arch/x86/hvm/vmx/vmcs.c           |   2 +
 xen/arch/x86/hvm/vmx/vmx.c            |  63 +++++++-
 xen/arch/x86/hvm/vmx/vvmx.c           |   3 +
 xen/common/domctl.c                   |   3 +
 xen/include/asm-x86/hvm/domain.h      |   3 +
 xen/include/asm-x86/hvm/io.h          |   2 +-
 xen/include/asm-x86/hvm/svm/emulate.h |   1 +
 xen/include/asm-x86/hvm/vmport.h      |  52 +++++++
 xen/include/public/domctl.h           |   3 +
 xen/include/xen/sched.h               |   3 +
 17 files changed, 445 insertions(+), 5 deletions(-)
 create mode 100644 xen/arch/x86/hvm/vmware/vmport.c
 create mode 100644 xen/include/asm-x86/hvm/vmport.h

diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 8cfd1ca..a71da52 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -524,6 +524,8 @@ int arch_domain_create(struct domain *d, unsigned int 
domcr_flags)
     d->arch.hvm_domain.mem_sharing_enabled = 0;
 
     d->arch.s3_integrity = !!(domcr_flags & DOMCRF_s3_integrity);
+    d->arch.hvm_domain.is_vmware_port_enabled =
+        !!(domcr_flags & DOMCRF_vmware_port);
 
     INIT_LIST_HEAD(&d->arch.pdev_list);
 
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 4039061..1357079 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -61,6 +61,7 @@
 #include <asm/hvm/trace.h>
 #include <asm/hvm/nestedhvm.h>
 #include <asm/hvm/vmware.h>
+#include <asm/hvm/vmport.h>
 #include <asm/mtrr.h>
 #include <asm/apic.h>
 #include <public/sched.h>
@@ -1444,6 +1445,9 @@ int hvm_domain_initialise(struct domain *d)
         goto fail1;
     d->arch.hvm_domain.io_handler->num_slot = 0;
 
+    if ( d->arch.hvm_domain.is_vmware_port_enabled )
+        vmport_register(d);
+
     if ( is_pvh_domain(d) )
     {
         register_portio_handler(d, 0, 0x10003, handle_pvh_io);
diff --git a/xen/arch/x86/hvm/svm/emulate.c b/xen/arch/x86/hvm/svm/emulate.c
index 37a1ece..cfad9ab 100644
--- a/xen/arch/x86/hvm/svm/emulate.c
+++ b/xen/arch/x86/hvm/svm/emulate.c
@@ -50,7 +50,7 @@ static unsigned int is_prefix(u8 opc)
     return 0;
 }
 
-static unsigned long svm_rip2pointer(struct vcpu *v)
+unsigned long svm_rip2pointer(struct vcpu *v)
 {
     struct vmcb_struct *vmcb = v->arch.hvm_svm.vmcb;
     unsigned long p = vmcb->cs.base + guest_cpu_user_regs()->eip;
diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index e3e1565..d7f13d9 100644
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -59,6 +59,7 @@
 #include <public/sched.h>
 #include <asm/hvm/vpt.h>
 #include <asm/hvm/trace.h>
+#include <asm/hvm/vmport.h>
 #include <asm/hap.h>
 #include <asm/apic.h>
 #include <asm/debugger.h>
@@ -2111,6 +2112,31 @@ svm_vmexit_do_vmsave(struct vmcb_struct *vmcb,
     return;
 }
 
+static void svm_vmexit_gp_intercept(struct cpu_user_regs *regs,
+                                    struct vcpu *v)
+{
+    struct vmcb_struct *vmcb = v->arch.hvm_svm.vmcb;
+    /*
+     * Just use 15 for the instruction length; vmport_gp_check will
+     * adjust it.  This is because
+     * __get_instruction_length_from_list() has issues, and may
+     * require a double read of the instruction bytes.  At some
+     * point a new routine could be added that is based on the code
+     * in vmport_gp_check with extensions to make it more general.
+     * Since that routine is the only user of this code this can be
+     * done later.
+     */
+    unsigned long inst_len = 15;
+    unsigned long inst_addr = svm_rip2pointer(v);
+    int rc = vmport_gp_check(regs, v, &inst_len, inst_addr,
+                             vmcb->exitinfo1, vmcb->exitinfo2);
+
+    if ( !rc )
+        __update_guest_eip(regs, inst_len);
+    else
+        hvm_inject_hw_exception(TRAP_gp_fault, vmcb->exitinfo1);
+}
+
 static void svm_vmexit_ud_intercept(struct cpu_user_regs *regs)
 {
     struct hvm_emulate_ctxt ctxt;
@@ -2471,6 +2497,10 @@ void svm_vmexit_handler(struct cpu_user_regs *regs)
         break;
     }
 
+    case VMEXIT_EXCEPTION_GP:
+        svm_vmexit_gp_intercept(regs, v);
+        break;
+
     case VMEXIT_EXCEPTION_UD:
         svm_vmexit_ud_intercept(regs);
         break;
diff --git a/xen/arch/x86/hvm/svm/vmcb.c b/xen/arch/x86/hvm/svm/vmcb.c
index 21292bb..45ead61 100644
--- a/xen/arch/x86/hvm/svm/vmcb.c
+++ b/xen/arch/x86/hvm/svm/vmcb.c
@@ -195,6 +195,8 @@ static int construct_vmcb(struct vcpu *v)
         HVM_TRAP_MASK
         | (1U << TRAP_no_device);
 
+    if ( v->domain->arch.hvm_domain.is_vmware_port_enabled )
+        vmcb->_exception_intercepts |= 1U << TRAP_gp_fault;
     if ( paging_mode_hap(v->domain) )
     {
         vmcb->_np_enable = 1; /* enable nested paging */
diff --git a/xen/arch/x86/hvm/vmware/Makefile b/xen/arch/x86/hvm/vmware/Makefile
index 3fb2e0b..cd8815b 100644
--- a/xen/arch/x86/hvm/vmware/Makefile
+++ b/xen/arch/x86/hvm/vmware/Makefile
@@ -1 +1,2 @@
 obj-y += cpuid.o
+obj-y += vmport.o
diff --git a/xen/arch/x86/hvm/vmware/vmport.c b/xen/arch/x86/hvm/vmware/vmport.c
new file mode 100644
index 0000000..e73a5e6
--- /dev/null
+++ b/xen/arch/x86/hvm/vmware/vmport.c
@@ -0,0 +1,274 @@
+/*
+ * HVM VMPORT emulation
+ *
+ * Copyright (C) 2012 Verizon Corporation
+ *
+ * This file is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License Version 2 (GPLv2)
+ * as published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details. <http://www.gnu.org/licenses/>.
+ */
+
+#include <xen/config.h>
+#include <xen/lib.h>
+#include <asm/hvm/hvm.h>
+#include <asm/hvm/support.h>
+#include <asm/hvm/vmport.h>
+
+#include "backdoor_def.h"
+
+#define MAX_INST_LEN 15
+
+#ifndef NDEBUG
+unsigned int opt_vmport_debug __read_mostly;
+integer_param("vmport_debug", opt_vmport_debug);
+#endif
+
+/* More VMware defines */
+
+#define VMWARE_GUI_AUTO_GRAB              0x001
+#define VMWARE_GUI_AUTO_UNGRAB            0x002
+#define VMWARE_GUI_AUTO_SCROLL            0x004
+#define VMWARE_GUI_AUTO_RAISE             0x008
+#define VMWARE_GUI_EXCHANGE_SELECTIONS    0x010
+#define VMWARE_GUI_WARP_CURSOR_ON_UNGRAB  0x020
+#define VMWARE_GUI_FULL_SCREEN            0x040
+
+#define VMWARE_GUI_TO_FULL_SCREEN         0x080
+#define VMWARE_GUI_TO_WINDOW              0x100
+
+#define VMWARE_GUI_AUTO_RAISE_DISABLED    0x200
+
+#define VMWARE_GUI_SYNC_TIME              0x400
+
+/* When set, toolboxes should not show the cursor options page. */
+#define VMWARE_DISABLE_CURSOR_OPTIONS     0x800
+
+void vmport_register(struct domain *d)
+{
+    register_portio_handler(d, BDOOR_PORT, 4, vmport_ioport);
+}
+
+int vmport_ioport(int dir, uint32_t port, uint32_t bytes, uint32_t *val)
+{
+    struct cpu_user_regs *regs = guest_cpu_user_regs();
+    uint32_t cmd = regs->rcx & 0xffff;
+    uint32_t magic = regs->rax;
+    int rc = X86EMUL_OKAY;
+
+    if ( magic == BDOOR_MAGIC )
+    {
+        uint64_t saved_rax = regs->rax;
+        uint64_t value;
+        struct vcpu *curr = current;
+        struct domain *d = curr->domain;
+        struct segment_register sreg;
+
+        switch ( cmd )
+        {
+        case BDOOR_CMD_GETMHZ:
+            regs->rax = (uint32_t)(d->arch.tsc_khz / 1000);
+            break;
+        case BDOOR_CMD_GETVERSION:
+            /* MAGIC */
+            regs->rbx = (regs->rbx & 0xffffffff00000000ull) | BDOOR_MAGIC;
+            /* VERSION_MAGIC */
+            regs->rax = 6;
+            /* Claim we are an ESX. VMX_TYPE_SCALABLE_SERVER */
+            regs->rcx = (regs->rcx & 0xffffffff00000000ull) | 2;
+            break;
+        case BDOOR_CMD_GETSCREENSIZE:
+            /* We have no screen size */
+            regs->rax = -1;
+            break;
+        case BDOOR_CMD_GETHWVERSION:
+            /* vmware_hw */
+            regs->rax = 0;
+            if ( is_hvm_vcpu(curr) )
+            {
+                struct hvm_domain *hd = &d->arch.hvm_domain;
+
+                regs->rax = (uint32_t)hd->params[HVM_PARAM_VMWARE_HW];
+            }
+            if ( !regs->rax )
+                regs->rax = 4;  /* Act like version 4 */
+            break;
+        case BDOOR_CMD_GETHZ:
+            hvm_get_segment_register(curr, x86_seg_ss, &sreg);
+            if ( sreg.attr.fields.dpl == 0 )
+            {
+                value = d->arch.tsc_khz * 1000;
+                /* apic-frequency (bus speed) */
+                regs->rcx = (regs->rcx & 0xffffffff00000000ull) |
+                    (uint32_t)(1000000000ULL / APIC_BUS_CYCLE_NS);
+                /* High part of tsc-frequency */
+                regs->rbx = (regs->rbx & 0xffffffff00000000ull) |
+                    (uint32_t)(value >> 32);
+                /* Low part of tsc-frequency */
+                regs->rax = (uint32_t)value;
+            }
+            break;
+        case BDOOR_CMD_GETTIME:
+            value = get_localtime_us(d) - d->time_offset_seconds * 1000000ULL;
+            /* hostUsecs */
+            regs->rbx = (regs->rbx & 0xffffffff00000000ull) |
+                (uint32_t)(value % 1000000UL);
+            /* hostSecs */
+            regs->rax = (uint32_t)(value / 1000000ULL);
+            /* maxTimeLag */
+            regs->rcx = (regs->rcx & 0xffffffff00000000ull) | 1000000;
+            /* offset to GMT in minutes */
+            regs->rdx = (regs->rdx & 0xffffffff00000000ull) |
+                d->time_offset_seconds / 60;
+            break;
+        case BDOOR_CMD_GETTIMEFULL:
+            value = get_localtime_us(d) - d->time_offset_seconds * 1000000ULL;
+            /* ... */
+            regs->rax = BDOOR_MAGIC;
+            /* hostUsecs */
+            regs->rbx = (regs->rbx & 0xffffffff00000000ull) |
+                (uint32_t)(value % 1000000UL);
+            /* High part of hostSecs */
+            regs->rsi = (regs->rsi & 0xffffffff00000000ull) |
+                (uint32_t)((value / 1000000ULL) >> 32);
+            /* Low part of hostSecs */
+            regs->rdx = (regs->rdx & 0xffffffff00000000ull) |
+                (uint32_t)(value / 1000000ULL);
+            /* maxTimeLag */
+            regs->rcx = (regs->rcx & 0xffffffff00000000ull) | 1000000;
+            break;
+        case BDOOR_CMD_GETGUIOPTIONS:
+            regs->rax = VMWARE_GUI_AUTO_GRAB | VMWARE_GUI_AUTO_UNGRAB |
+                VMWARE_GUI_AUTO_RAISE_DISABLED | VMWARE_GUI_SYNC_TIME |
+                VMWARE_DISABLE_CURSOR_OPTIONS;
+            break;
+        case BDOOR_CMD_SETGUIOPTIONS:
+            regs->rax = 0x0;
+            break;
+        default:
+            regs->rax = (uint32_t)~0ul;
+            break;
+        }
+        if ( dir == IOREQ_READ )
+        {
+            switch ( bytes )
+            {
+            case 1:
+                regs->rax = (saved_rax & 0xffffff00) | (regs->rax & 0xff);
+                break;
+            case 2:
+                regs->rax = (saved_rax & 0xffff0000) | (regs->rax & 0xffff);
+                break;
+            case 4:
+                regs->rax = (uint32_t)regs->rax;
+                break;
+            }
+            *val = regs->rax;
+        }
+        else
+            regs->rax = saved_rax;
+    }
+    else
+        rc = X86EMUL_UNHANDLEABLE;
+
+    return rc;
+}
+
+int vmport_gp_check(struct cpu_user_regs *regs, struct vcpu *v,
+                    unsigned long *inst_len, unsigned long inst_addr,
+                    unsigned long ei1, unsigned long ei2)
+{
+    if ( !v->domain->arch.hvm_domain.is_vmware_port_enabled )
+        return X86EMUL_VMPORT_NOT_ENABLED;
+
+    if ( *inst_len && *inst_len <= MAX_INST_LEN &&
+         (regs->rdx & 0xffff) == BDOOR_PORT && ei1 == 0 && ei2 == 0 &&
+         (uint32_t)regs->rax == BDOOR_MAGIC )
+    {
+        int i = 0;
+        uint32_t val;
+        uint32_t byte_cnt = hvm_guest_x86_mode(v);
+        unsigned char bytes[MAX_INST_LEN];
+        unsigned int fetch_len;
+        int frc;
+
+        /* in or out are limited to 32bits */
+        if ( byte_cnt > 4 )
+            byte_cnt = 4;
+
+        /*
+         * Fetch up to the next page break; we'll fetch from the
+         * next page later if we have to.
+         */
+        fetch_len = min_t(unsigned int, *inst_len,
+                          PAGE_SIZE - (inst_addr  & ~PAGE_MASK));
+        frc = hvm_fetch_from_guest_virt_nofault(bytes, inst_addr, fetch_len,
+                                                PFEC_page_present);
+        if ( frc != HVMCOPY_okay )
+        {
+            gdprintk(XENLOG_WARNING,
+                     "Bad instruction fetch at %#lx (frc=%d il=%lu fl=%u)\n",
+                     (unsigned long) inst_addr, frc, *inst_len, fetch_len);
+            return X86EMUL_VMPORT_FETCH_ERROR_BYTE1;
+        }
+
+        /* Check for operand size prefix */
+        while ( (i < MAX_INST_LEN) && (bytes[i] == 0x66) )
+        {
+            i++;
+            if ( i >= fetch_len )
+            {
+                frc = hvm_fetch_from_guest_virt_nofault(
+                    &bytes[fetch_len], inst_addr + fetch_len,
+                    MAX_INST_LEN - fetch_len, PFEC_page_present);
+                if ( frc != HVMCOPY_okay )
+                {
+                    gdprintk(XENLOG_WARNING,
+                             "Bad instruction fetch at %#lx + %#x (frc=%d)\n",
+                             inst_addr, fetch_len, frc);
+                    return X86EMUL_VMPORT_FETCH_ERROR_BYTE2;
+                }
+                fetch_len = MAX_INST_LEN;
+            }
+        }
+        *inst_len = i + 1;
+
+        /* Only adjust byte_cnt 1 time */
+        if ( bytes[0] == 0x66 )     /* operand size prefix */
+        {
+            if ( byte_cnt == 4 )
+                byte_cnt = 2;
+            else
+                byte_cnt = 4;
+        }
+        if ( bytes[i] == 0xed )     /* in (%dx),%eax or in (%dx),%ax */
+            return vmport_ioport(IOREQ_READ, BDOOR_PORT, byte_cnt, &val);
+        else if ( bytes[i] == 0xec )     /* in (%dx),%al */
+            return vmport_ioport(IOREQ_READ, BDOOR_PORT, 1, &val);
+        else if ( bytes[i] == 0xef )     /* out %eax,(%dx) or out %ax,(%dx) */
+            return vmport_ioport(IOREQ_WRITE, BDOOR_PORT, byte_cnt, &val);
+        else if ( bytes[i] == 0xee )     /* out %al,(%dx) */
+            return vmport_ioport(IOREQ_WRITE, BDOOR_PORT, 1, &val);
+        else
+        {
+            *inst_len = 0; /* This is unknown. */
+            return X86EMUL_VMPORT_BAD_OPCODE;
+        }
+    }
+    *inst_len = 0; /* This is unknown. */
+    return X86EMUL_VMPORT_BAD_STATE;
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-set-style: "BSD"
+ * c-basic-offset: 4
+ * tab-width: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c
index 9d8033e..1bab216 100644
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -1102,6 +1102,8 @@ static int construct_vmcs(struct vcpu *v)
 
     v->arch.hvm_vmx.exception_bitmap = HVM_TRAP_MASK
               | (paging_mode_hap(d) ? 0 : (1U << TRAP_page_fault))
+              | (v->domain->arch.hvm_domain.is_vmware_port_enabled ?
+                 (1U << TRAP_gp_fault) : 0)
               | (1U << TRAP_no_device);
     vmx_update_exception_bitmap(v);
 
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 304aeea..300d804 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -44,6 +44,7 @@
 #include <asm/hvm/support.h>
 #include <asm/hvm/vmx/vmx.h>
 #include <asm/hvm/vmx/vmcs.h>
+#include <asm/hvm/vmport.h>
 #include <public/sched.h>
 #include <public/hvm/ioreq.h>
 #include <asm/hvm/vpic.h>
@@ -1276,9 +1277,11 @@ static void vmx_update_guest_cr(struct vcpu *v, unsigned 
int cr)
                         vmx_set_segment_register(
                             v, s, &v->arch.hvm_vmx.vm86_saved_seg[s]);
                 v->arch.hvm_vmx.exception_bitmap = HVM_TRAP_MASK
-                          | (paging_mode_hap(v->domain) ?
-                             0 : (1U << TRAP_page_fault))
-                          | (1U << TRAP_no_device);
+                    | (paging_mode_hap(v->domain) ?
+                       0 : (1U << TRAP_page_fault))
+                    | (v->domain->arch.hvm_domain.is_vmware_port_enabled ?
+                       (1U << TRAP_gp_fault) : 0)
+                    | (1U << TRAP_no_device);
                 vmx_update_exception_bitmap(v);
                 vmx_update_debug_state(v);
             }
@@ -2589,6 +2592,57 @@ static void vmx_idtv_reinject(unsigned long idtv_info)
     }
 }
 
+static unsigned long vmx_rip2pointer(struct cpu_user_regs *regs,
+                                     struct vcpu *v)
+{
+    struct segment_register cs;
+    unsigned long p;
+
+    vmx_get_segment_register(v, x86_seg_cs, &cs);
+    p = cs.base + regs->rip;
+    if ( !(cs.attr.fields.l && hvm_long_mode_enabled(v)) )
+        return (uint32_t)p; /* mask to 32 bits */
+    return p;
+}
+
+static void vmx_vmexit_gp_intercept(struct cpu_user_regs *regs,
+                                    struct vcpu *v)
+{
+    unsigned long exit_qualification;
+    unsigned long inst_len;
+    unsigned long inst_addr = vmx_rip2pointer(regs, v);
+    unsigned long ecode;
+    int rc;
+#ifndef NDEBUG
+    unsigned long orig_inst_len;
+    unsigned long vector;
+
+    __vmread(VM_EXIT_INTR_INFO, &vector);
+    BUG_ON(!(vector & INTR_INFO_VALID_MASK));
+    BUG_ON(!(vector & INTR_INFO_DELIVER_CODE_MASK));
+#endif
+
+    __vmread(EXIT_QUALIFICATION, &exit_qualification);
+    __vmread(VM_EXIT_INSTRUCTION_LEN, &inst_len);
+    __vmread(VM_EXIT_INTR_ERROR_CODE, &ecode);
+
+#ifndef NDEBUG
+    orig_inst_len = inst_len;
+#endif
+    rc = vmport_gp_check(regs, v, &inst_len, inst_addr,
+                         ecode, exit_qualification);
+#ifndef NDEBUG
+    if ( inst_len && orig_inst_len != inst_len )
+        gdprintk(XENLOG_WARNING,
+                 "Unexpected instruction length difference: %lu vs %lu\n",
+                 orig_inst_len, inst_len);
+#endif
+    if ( !rc )
+        update_guest_eip();
+    else
+        hvm_inject_hw_exception(TRAP_gp_fault, ecode);
+}
+
 static int vmx_handle_apic_write(void)
 {
     unsigned long exit_qualification;
@@ -2814,6 +2868,9 @@ void vmx_vmexit_handler(struct cpu_user_regs *regs)
             HVMTRACE_1D(TRAP, vector);
             vmx_fpu_dirty_intercept();
             break;
+        case TRAP_gp_fault:
+            vmx_vmexit_gp_intercept(regs, v);
+            break;
         case TRAP_page_fault:
             __vmread(EXIT_QUALIFICATION, &exit_qualification);
             __vmread(VM_EXIT_INTR_ERROR_CODE, &ecode);
diff --git a/xen/arch/x86/hvm/vmx/vvmx.c b/xen/arch/x86/hvm/vmx/vvmx.c
index 9ccc03f..8e07f92 100644
--- a/xen/arch/x86/hvm/vmx/vvmx.c
+++ b/xen/arch/x86/hvm/vmx/vvmx.c
@@ -24,6 +24,7 @@
 #include <asm/types.h>
 #include <asm/mtrr.h>
 #include <asm/p2m.h>
+#include <asm/hvm/vmport.h>
 #include <asm/hvm/vmx/vmx.h>
 #include <asm/hvm/vmx/vvmx.h>
 #include <asm/hvm/nestedhvm.h>
@@ -2182,6 +2183,8 @@ int nvmx_n2_vmexit_handler(struct cpu_user_regs *regs,
             if ( v->fpu_dirtied )
                 nvcpu->nv_vmexit_pending = 1;
         }
+        else if ( vector == TRAP_gp_fault )
+            nvcpu->nv_vmexit_pending = 1;
         else if ( (intr_info & valid_mask) == valid_mask )
         {
             exec_bitmap =__get_vvmcs(nvcpu->nv_vvmcx, EXCEPTION_BITMAP);
diff --git a/xen/common/domctl.c b/xen/common/domctl.c
index 30c9e50..fad55a2 100644
--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -543,6 +543,7 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) 
u_domctl)
              ~(XEN_DOMCTL_CDF_hvm_guest
                | XEN_DOMCTL_CDF_pvh_guest
                | XEN_DOMCTL_CDF_hap
+               | XEN_DOMCTL_CDF_vmware_port
                | XEN_DOMCTL_CDF_s3_integrity
                | XEN_DOMCTL_CDF_oos_off)) )
             break;
@@ -586,6 +587,8 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) 
u_domctl)
             domcr_flags |= DOMCRF_s3_integrity;
         if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_oos_off )
             domcr_flags |= DOMCRF_oos_off;
+        if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_vmware_port )
+            domcr_flags |= DOMCRF_vmware_port;
 
         d = domain_create(dom, domcr_flags, op->u.createdomain.ssidref);
         if ( IS_ERR(d) )
diff --git a/xen/include/asm-x86/hvm/domain.h b/xen/include/asm-x86/hvm/domain.h
index 2757c7f..d4718df 100644
--- a/xen/include/asm-x86/hvm/domain.h
+++ b/xen/include/asm-x86/hvm/domain.h
@@ -121,6 +121,9 @@ struct hvm_domain {
     spinlock_t             uc_lock;
     bool_t                 is_in_uc_mode;
 
+    /* VMware backdoor port available */
+    bool_t                 is_vmware_port_enabled;
+
     /* Pass-through */
     struct hvm_iommu       hvm_iommu;
 
diff --git a/xen/include/asm-x86/hvm/io.h b/xen/include/asm-x86/hvm/io.h
index 886a9d6..d257161 100644
--- a/xen/include/asm-x86/hvm/io.h
+++ b/xen/include/asm-x86/hvm/io.h
@@ -25,7 +25,7 @@
 #include <public/hvm/ioreq.h>
 #include <public/event_channel.h>
 
-#define MAX_IO_HANDLER             16
+#define MAX_IO_HANDLER             17
 
 #define HVM_PORTIO                  0
 #define HVM_BUFFERED_IO             2
diff --git a/xen/include/asm-x86/hvm/svm/emulate.h 
b/xen/include/asm-x86/hvm/svm/emulate.h
index ccc2d3c..d9a9dc5 100644
--- a/xen/include/asm-x86/hvm/svm/emulate.h
+++ b/xen/include/asm-x86/hvm/svm/emulate.h
@@ -44,6 +44,7 @@ enum instruction_index {
 
 struct vcpu;
 
+unsigned long svm_rip2pointer(struct vcpu *v);
 int __get_instruction_length_from_list(
     struct vcpu *, const enum instruction_index *, unsigned int list_count);
 
diff --git a/xen/include/asm-x86/hvm/vmport.h b/xen/include/asm-x86/hvm/vmport.h
new file mode 100644
index 0000000..d037d55
--- /dev/null
+++ b/xen/include/asm-x86/hvm/vmport.h
@@ -0,0 +1,52 @@
+/*
+ * asm/hvm/vmport.h: HVM VMPORT emulation
+ *
+ *
+ * Copyright (C) 2012 Verizon Corporation
+ *
+ * This file is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License Version 2 (GPLv2)
+ * as published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details. <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef ASM_X86_HVM_VMPORT_H__
+#define ASM_X86_HVM_VMPORT_H__
+
+void vmport_register(struct domain *d);
+int vmport_ioport(int dir, uint32_t port, uint32_t bytes, uint32_t *val);
+int vmport_gp_check(struct cpu_user_regs *regs, struct vcpu *v,
+                    unsigned long *inst_len, unsigned long inst_addr,
+                    unsigned long ei1, unsigned long ei2);
+/*
+ * Additional return values from vmport_gp_check.
+ *
+ * Note: return values include:
+ *   X86EMUL_OKAY
+ *   X86EMUL_UNHANDLEABLE
+ *   X86EMUL_EXCEPTION
+ *   X86EMUL_RETRY
+ *   X86EMUL_CMPXCHG_FAILED
+ *
+ * The additional do not overlap any of the above.
+ */
+#define X86EMUL_VMPORT_NOT_ENABLED              10
+#define X86EMUL_VMPORT_FETCH_ERROR_BYTE1        11
+#define X86EMUL_VMPORT_FETCH_ERROR_BYTE2        12
+#define X86EMUL_VMPORT_BAD_OPCODE               13
+#define X86EMUL_VMPORT_BAD_STATE                14
+
+#endif /* ASM_X86_HVM_VMPORT_H__ */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index 61f7555..2b38515 100644
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -63,6 +63,9 @@ struct xen_domctl_createdomain {
  /* Is this a PVH guest (as opposed to an HVM or PV guest)? */
 #define _XEN_DOMCTL_CDF_pvh_guest     4
 #define XEN_DOMCTL_CDF_pvh_guest      (1U<<_XEN_DOMCTL_CDF_pvh_guest)
+ /* Is VMware backdoor port available? */
+#define _XEN_DOMCTL_CDF_vmware_port   5
+#define XEN_DOMCTL_CDF_vmware_port    (1U<<_XEN_DOMCTL_CDF_vmware_port)
     uint32_t flags;
 };
 typedef struct xen_domctl_createdomain xen_domctl_createdomain_t;
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index c5157e6..d741978 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -546,6 +546,9 @@ struct domain *domain_create(
  /* DOMCRF_pvh: Create PV domain in HVM container. */
 #define _DOMCRF_pvh             5
 #define DOMCRF_pvh              (1U<<_DOMCRF_pvh)
+ /* DOMCRF_vmware_port: Enable use of vmware backdoor port. */
+#define _DOMCRF_vmware_port     6
+#define DOMCRF_vmware_port      (1U<<_DOMCRF_vmware_port)
 
 /*
  * rcu_lock_domain_by_id() is more efficient than get_domain_by_id().
-- 
1.8.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

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