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

[Xen-devel] [PATCH 09/18] PVH xen: Support privileged op emulation for PVH



This patch changes mostly traps.c to support privileged op emulation for PVH.
A new function read_descriptor_sel() is introduced to read selectors for PVH.
Also, modify read_segment_register macro to return selector from
cpu_user_regs instead of reading natively.

Signed-off-by: Mukesh Rathor <mukesh.rathor@xxxxxxxxxx>
---
 xen/arch/x86/traps.c         |   86 ++++++++++++++++++++++++++++++++++++-----
 xen/include/asm-x86/system.h |   18 +++++++--
 2 files changed, 89 insertions(+), 15 deletions(-)

diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index d29136d..0caf73a 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -479,6 +479,10 @@ static unsigned int check_guest_io_breakpoint(struct vcpu 
*v,
     unsigned int width, i, match = 0;
     unsigned long start;
 
+    /* PVH fixme: support io breakpoint. */
+    if ( is_pvh_vcpu(v) )
+        return 0;
+
     if ( !(v->arch.debugreg[5]) ||
          !(v->arch.pv_vcpu.ctrlreg[4] & X86_CR4_DE) )
         return 0;
@@ -1524,6 +1528,49 @@ static int read_descriptor(unsigned int sel,
     return 1;
 }
 
+static int read_descriptor_sel(unsigned int sel,
+                               enum x86_segment which_sel,
+                               struct vcpu *v,
+                               const struct cpu_user_regs *regs,
+                               unsigned long *base,
+                               unsigned long *limit,
+                               unsigned int *ar,
+                               unsigned int vm86attr)
+{
+    struct segment_register seg;
+    unsigned int long_mode = 0;
+
+    if ( !is_pvh_vcpu(v) )
+        return read_descriptor(sel, v, regs, base, limit, ar, vm86attr);
+
+    hvm_get_segment_register(v, x86_seg_cs, &seg);
+    long_mode = seg.attr.fields.l;
+
+    if ( which_sel != x86_seg_cs )
+        hvm_get_segment_register(v, which_sel, &seg);
+
+    /* "ar" is returned packed as in segment_attributes_t. Fix it up. */
+    *ar = (unsigned int)seg.attr.bytes;
+    *ar = (*ar & 0xff ) | ((*ar & 0xf00) << 4);
+    *ar = *ar << 8;
+
+    if ( long_mode )
+    {
+        *limit = ~0UL;
+
+        if ( which_sel < x86_seg_fs )
+        {
+            *base = 0UL;
+            return 1;
+        }
+   }
+   else
+       *limit = (unsigned long)seg.limit;
+
+   *base = seg.base;
+    return 1;
+}
+
 static int read_gate_descriptor(unsigned int gate_sel,
                                 const struct vcpu *v,
                                 unsigned int *sel,
@@ -1589,6 +1636,13 @@ static int guest_io_okay(
     int user_mode = !(v->arch.flags & TF_kernel_mode);
 #define TOGGLE_MODE() if ( user_mode ) toggle_guest_mode(v)
 
+    /*
+     * For PVH we check this in vmexit for EXIT_REASON_IO_INSTRUCTION
+     * and so don't need to check again here.
+     */
+    if ( is_pvh_vcpu(v) )
+        return 1;
+
     if ( !vm86_mode(regs) &&
          (v->arch.pv_vcpu.iopl >= (guest_kernel_mode(v, regs) ? 1 : 3)) )
         return 1;
@@ -1834,7 +1888,7 @@ static inline uint64_t guest_misc_enable(uint64_t val)
         _ptr = (unsigned int)_ptr;                                          \
     if ( (limit) < sizeof(_x) - 1 || (eip) > (limit) - (sizeof(_x) - 1) )   \
         goto fail;                                                          \
-    if ( (_rc = copy_from_user(&_x, (type *)_ptr, sizeof(_x))) != 0 )       \
+    if ( (_rc = raw_copy_from_guest(&_x, (type *)_ptr, sizeof(_x))) != 0 )  \
     {                                                                       \
         propagate_page_fault(_ptr + sizeof(_x) - _rc, 0);                   \
         goto skip;                                                          \
@@ -1851,6 +1905,7 @@ static int is_cpufreq_controller(struct domain *d)
 
 static int emulate_privileged_op(struct cpu_user_regs *regs)
 {
+    enum x86_segment which_sel;
     struct vcpu *v = current;
     unsigned long *reg, eip = regs->eip;
     u8 opcode, modrm_reg = 0, modrm_rm = 0, rep_prefix = 0, lock = 0, rex = 0;
@@ -1873,9 +1928,10 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
     void (*io_emul)(struct cpu_user_regs *) __attribute__((__regparm__(1)));
     uint64_t val, msr_content;
 
-    if ( !read_descriptor(regs->cs, v, regs,
-                          &code_base, &code_limit, &ar,
-                          _SEGMENT_CODE|_SEGMENT_S|_SEGMENT_DPL|_SEGMENT_P) )
+    if ( !read_descriptor_sel(regs->cs, x86_seg_cs, v, regs,
+                              &code_base, &code_limit, &ar,
+                              _SEGMENT_CODE|_SEGMENT_S|
+                              _SEGMENT_DPL|_SEGMENT_P) )
         goto fail;
     op_default = op_bytes = (ar & (_SEGMENT_L|_SEGMENT_DB)) ? 4 : 2;
     ad_default = ad_bytes = (ar & _SEGMENT_L) ? 8 : op_default;
@@ -1886,6 +1942,7 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
 
     /* emulating only opcodes not allowing SS to be default */
     data_sel = read_segment_register(v, regs, ds);
+    which_sel = x86_seg_ds;
 
     /* Legacy prefixes. */
     for ( i = 0; i < 8; i++, rex == opcode || (rex = 0) )
@@ -1901,23 +1958,29 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
             continue;
         case 0x2e: /* CS override */
             data_sel = regs->cs;
+            which_sel = x86_seg_cs;
             continue;
         case 0x3e: /* DS override */
             data_sel = read_segment_register(v, regs, ds);
+            which_sel = x86_seg_ds;
             continue;
         case 0x26: /* ES override */
             data_sel = read_segment_register(v, regs, es);
+            which_sel = x86_seg_es;
             continue;
         case 0x64: /* FS override */
             data_sel = read_segment_register(v, regs, fs);
+            which_sel = x86_seg_fs;
             lm_ovr = lm_seg_fs;
             continue;
         case 0x65: /* GS override */
             data_sel = read_segment_register(v, regs, gs);
+            which_sel = x86_seg_gs;
             lm_ovr = lm_seg_gs;
             continue;
         case 0x36: /* SS override */
             data_sel = regs->ss;
+            which_sel = x86_seg_ss;
             continue;
         case 0xf0: /* LOCK */
             lock = 1;
@@ -1961,15 +2024,16 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
         if ( !(opcode & 2) )
         {
             data_sel = read_segment_register(v, regs, es);
+            which_sel = x86_seg_es;
             lm_ovr = lm_seg_none;
         }
 
         if ( !(ar & _SEGMENT_L) )
         {
-            if ( !read_descriptor(data_sel, v, regs,
-                                  &data_base, &data_limit, &ar,
-                                  _SEGMENT_WR|_SEGMENT_S|_SEGMENT_DPL|
-                                  _SEGMENT_P) )
+            if ( !read_descriptor_sel(data_sel, which_sel, v, regs,
+                                      &data_base, &data_limit, &ar,
+                                      _SEGMENT_WR|_SEGMENT_S|_SEGMENT_DPL|
+                                      _SEGMENT_P) )
                 goto fail;
             if ( !(ar & _SEGMENT_S) ||
                  !(ar & _SEGMENT_P) ||
@@ -1999,9 +2063,9 @@ static int emulate_privileged_op(struct cpu_user_regs 
*regs)
                 }
             }
             else
-                read_descriptor(data_sel, v, regs,
-                                &data_base, &data_limit, &ar,
-                                0);
+                read_descriptor_sel(data_sel, which_sel, v, regs,
+                                    &data_base, &data_limit, &ar,
+                                    0);
             data_limit = ~0UL;
             ar = _SEGMENT_WR|_SEGMENT_S|_SEGMENT_DPL|_SEGMENT_P;
         }
diff --git a/xen/include/asm-x86/system.h b/xen/include/asm-x86/system.h
index 9bb22cb..e29b6a3 100644
--- a/xen/include/asm-x86/system.h
+++ b/xen/include/asm-x86/system.h
@@ -4,10 +4,20 @@
 #include <xen/lib.h>
 #include <xen/bitops.h>
 
-#define read_segment_register(vcpu, regs, name)                 \
-({  u16 __sel;                                                  \
-    asm volatile ( "movw %%" STR(name) ",%0" : "=r" (__sel) );  \
-    __sel;                                                      \
+/*
+ * We need vcpu because during context switch, going from PVH to PV,
+ * in save_segments(), current has been updated to next, and no longer pointing
+ * to the PVH.
+ */
+#define read_segment_register(vcpu, regs, name)                   \
+({  u16 __sel;                                                    \
+    struct cpu_user_regs *_regs = (regs);                         \
+                                                                  \
+    if ( is_pvh_vcpu(vcpu) && guest_mode(regs) )                  \
+        __sel = _regs->name;                                      \
+    else                                                          \
+        asm volatile ( "movw %%" #name ",%0" : "=r" (__sel) );    \
+    __sel;                                                        \
 })
 
 #define wbinvd() \
-- 
1.7.2.3


_______________________________________________
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®.