[Xen-devel] [PATCH v4 17/20] x86/HVM: do actual CMPXCHG in hvmemul_cmpxchg()

["Jan Beulich" <JBeulich@xxxxxxxx>]

..., at least as far as currently possible, i.e. when a mapping can be
obtained.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
Reviewed-by: Paul Durrant <paul.durrant@xxxxxxxxxx>
---
v4: Add ASSERT_UNREACHABLE() to hvmemul_cmpxchg()'s switch().
v3: New.

--- a/xen/arch/x86/hvm/emulate.c
+++ b/xen/arch/x86/hvm/emulate.c
@@ -1297,8 +1297,86 @@ static int hvmemul_cmpxchg(
     bool lock,
     struct x86_emulate_ctxt *ctxt)
 {
-    /* Fix this in case the guest is really relying on r-m-w atomicity. */
-    return hvmemul_write(seg, offset, p_new, bytes, ctxt);
+    struct hvm_emulate_ctxt *hvmemul_ctxt =
+        container_of(ctxt, struct hvm_emulate_ctxt, ctxt);
+    struct vcpu *curr = current;
+    unsigned long addr, reps = 1;
+    uint32_t pfec = PFEC_page_present | PFEC_write_access;
+    struct hvm_vcpu_io *vio = &curr->arch.hvm_vcpu.hvm_io;
+    int rc;
+    void *mapping = NULL;
+
+    rc = hvmemul_virtual_to_linear(
+        seg, offset, bytes, &reps, hvm_access_write, hvmemul_ctxt, &addr);
+    if ( rc != X86EMUL_OKAY )
+        return rc;
+
+    if ( is_x86_system_segment(seg) )
+        pfec |= PFEC_implicit;
+    else if ( hvmemul_ctxt->seg_reg[x86_seg_ss].dpl == 3 )
+        pfec |= PFEC_user_mode;
+
+    mapping = hvmemul_map_linear_addr(addr, bytes, pfec, hvmemul_ctxt);
+    if ( IS_ERR(mapping) )
+        return ~PTR_ERR(mapping);
+
+    if ( !mapping )
+    {
+        /* Fix this in case the guest is really relying on r-m-w atomicity. */
+        return hvmemul_linear_mmio_write(addr, bytes, p_new, pfec,
+                                         hvmemul_ctxt,
+                                         vio->mmio_access.write_access &&
+                                         vio->mmio_gla == (addr & PAGE_MASK));
+    }
+
+    switch ( bytes )
+    {
+    case 1: case 2: case 4: case 8:
+    {
+        unsigned long old = 0, new = 0, cur;
+
+        memcpy(&old, p_old, bytes);
+        memcpy(&new, p_new, bytes);
+        if ( lock )
+            cur = __cmpxchg(mapping, old, new, bytes);
+        else
+            cur = cmpxchg_local_(mapping, old, new, bytes);
+        if ( cur != old )
+        {
+            memcpy(p_old, &cur, bytes);
+            rc = X86EMUL_CMPXCHG_FAILED;
+        }
+        break;
+    }
+
+    case 16:
+        if ( cpu_has_cx16 )
+        {
+            __uint128_t *old = p_old, cur;
+
+            if ( lock )
+                cur = __cmpxchg16b(mapping, old, p_new);
+            else
+                cur = cmpxchg16b_local_(mapping, old, p_new);
+            if ( cur != *old )
+            {
+                *old = cur;
+                rc = X86EMUL_CMPXCHG_FAILED;
+            }
+        }
+        else
+            rc = X86EMUL_UNHANDLEABLE;
+        break;
+
+    default:
+        ASSERT_UNREACHABLE();
+        rc = X86EMUL_UNHANDLEABLE;
+        break;
+    }
+
+    hvmemul_unmap_linear_addr(mapping, addr, bytes, hvmemul_ctxt);
+
+    return rc;
 }
 
 static int hvmemul_validate(
--- a/xen/include/asm-x86/system.h
+++ b/xen/include/asm-x86/system.h
@@ -110,6 +110,38 @@ static always_inline unsigned long __cmp
     return old;
 }
 
+static always_inline unsigned long cmpxchg_local_(
+    void *ptr, unsigned long old, unsigned long new, unsigned int size)
+{
+    unsigned long prev = ~old;
+
+    switch ( size )
+    {
+    case 1:
+        asm volatile ( "cmpxchgb %b2, %1"
+                       : "=a" (prev), "+m" (*(uint8_t *)ptr)
+                       : "q" (new), "0" (old) );
+        break;
+    case 2:
+        asm volatile ( "cmpxchgw %w2, %1"
+                       : "=a" (prev), "+m" (*(uint16_t *)ptr)
+                       : "r" (new), "0" (old) );
+        break;
+    case 4:
+        asm volatile ( "cmpxchgl %k2, %1"
+                       : "=a" (prev), "+m" (*(uint32_t *)ptr)
+                       : "r" (new), "0" (old) );
+        break;
+    case 8:
+        asm volatile ( "cmpxchgq %2, %1"
+                       : "=a" (prev), "+m" (*(uint64_t *)ptr)
+                       : "r" (new), "0" (old) );
+        break;
+    }
+
+    return prev;
+}
+
 #define cmpxchgptr(ptr,o,n) ({                                          \
     const __typeof__(**(ptr)) *__o = (o);                               \
     __typeof__(**(ptr)) *__n = (n);                                     \
--- a/xen/include/asm-x86/x86_64/system.h
+++ b/xen/include/asm-x86/x86_64/system.h
@@ -31,6 +31,24 @@ static always_inline __uint128_t __cmpxc
     return prev.raw;
 }
 
+static always_inline __uint128_t cmpxchg16b_local_(
+    void *ptr, const __uint128_t *oldp, const __uint128_t *newp)
+{
+    union {
+        struct { uint64_t lo, hi; };
+        __uint128_t raw;
+    } new = { .raw = *newp }, old = { .raw = *oldp }, prev;
+
+    ASSERT(cpu_has_cx16);
+
+    /* Don't use "=A" here - clang can't deal with that. */
+    asm volatile ( "cmpxchg16b %2"
+                   : "=d" (prev.hi), "=a" (prev.lo), "+m" (*(__uint128_t *)ptr)
+                   : "c" (new.hi), "b" (new.lo), "0" (old.hi), "1" (old.lo) );
+
+    return prev.raw;
+}
+
 #define cmpxchg16b(ptr, o, n) ({                           \
     volatile void *_p = (ptr);                             \
     ASSERT(!((unsigned long)_p & 0xf));                    \



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