Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

Mostly bugfixes and cleanups from qemu-devel.  Yet another small patch from
the record/replay series, and a few SCSI and i386 patches as well.

# gpg: Signature made Wed 14 Jan 2015 09:39:14 GMT using RSA key ID 78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream:
  cpus: consistently use QEMU_CLOCK_VIRTUAL_RT for icount_warp_rt timer
  qemu-timer: rename timer_init to timer_init_tl
  scsi: fix cancellation when I/O was completed but DMA was not.
  rules.mak: Fix module build
  hw/scsi/lsi53c895a: add support for additional diag / debug registers
  qemu-common.h: optimise muldiv64 if int128 is available
  target-i386: do not memcpy in and out of xmm_regs
  target-i386: fix movntsd on big-endian hosts
  vl.c: fix regression when reading memory size from config file
  vl: Don't silently change topology when all -smp options were set
  vl: fix max_cpus check
  vl: Avoid unnecessary 'if' nesting
  9pfs: changed to use event_notifier instead of qemu_pipe
  vl.c: fix regression when reading machine type from config file
  char: restore stdio echo on resume from suspend.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

2 files changed, 30 insertions, 11 deletions

diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 54ccb890b5..36b1519f34 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1019,7 +1019,10 @@ static int kvm_put_fpu(X86CPU *cpu)
         fpu.ftwx |= (!env->fptags[i]) << i;
     }
     memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
-    memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
+    for (i = 0; i < CPU_NB_REGS; i++) {
+        stq_p(&fpu.xmm[i][0], env->xmm_regs[i].XMM_Q(0));
+        stq_p(&fpu.xmm[i][8], env->xmm_regs[i].XMM_Q(1));
+    }
     fpu.mxcsr = env->mxcsr;
 
     return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_FPU, &fpu);
@@ -1045,6 +1048,7 @@ static int kvm_put_xsave(X86CPU *cpu)
     CPUX86State *env = &cpu->env;
     struct kvm_xsave* xsave = env->kvm_xsave_buf;
     uint16_t cwd, swd, twd;
+    uint8_t *xmm;
     int i, r;
 
     if (!kvm_has_xsave()) {
@@ -1065,8 +1069,6 @@ static int kvm_put_xsave(X86CPU *cpu)
     memcpy(&xsave->region[XSAVE_CWD_RDP], &env->fpdp, sizeof(env->fpdp));
     memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
             sizeof env->fpregs);
-    memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
-            sizeof env->xmm_regs);
     xsave->region[XSAVE_MXCSR] = env->mxcsr;
     *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
     memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
@@ -1079,6 +1081,13 @@ static int kvm_put_xsave(X86CPU *cpu)
             sizeof env->opmask_regs);
     memcpy(&xsave->region[XSAVE_ZMM_Hi256], env->zmmh_regs,
             sizeof env->zmmh_regs);
+
+    xmm = (uint8_t *)&xsave->region[XSAVE_XMM_SPACE];
+    for (i = 0; i < CPU_NB_REGS; i++, xmm += 16) {
+        stq_p(xmm,     env->xmm_regs[i].XMM_Q(0));
+        stq_p(xmm+8,   env->xmm_regs[i].XMM_Q(1));
+    }
+
 #ifdef TARGET_X86_64
     memcpy(&xsave->region[XSAVE_Hi16_ZMM], env->hi16_zmm_regs,
             sizeof env->hi16_zmm_regs);
@@ -1384,7 +1393,10 @@ static int kvm_get_fpu(X86CPU *cpu)
         env->fptags[i] = !((fpu.ftwx >> i) & 1);
     }
     memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
-    memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
+    for (i = 0; i < CPU_NB_REGS; i++) {
+        env->xmm_regs[i].XMM_Q(0) = ldq_p(&fpu.xmm[i][0]);
+        env->xmm_regs[i].XMM_Q(1) = ldq_p(&fpu.xmm[i][8]);
+    }
     env->mxcsr = fpu.mxcsr;
 
     return 0;
@@ -1395,6 +1407,7 @@ static int kvm_get_xsave(X86CPU *cpu)
     CPUX86State *env = &cpu->env;
     struct kvm_xsave* xsave = env->kvm_xsave_buf;
     int ret, i;
+    const uint8_t *xmm;
     uint16_t cwd, swd, twd;
 
     if (!kvm_has_xsave()) {
@@ -1421,8 +1434,6 @@ static int kvm_get_xsave(X86CPU *cpu)
     env->mxcsr = xsave->region[XSAVE_MXCSR];
     memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
             sizeof env->fpregs);
-    memcpy(env->xmm_regs, &xsave->region[XSAVE_XMM_SPACE],
-            sizeof env->xmm_regs);
     env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
     memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
             sizeof env->ymmh_regs);
@@ -1434,6 +1445,13 @@ static int kvm_get_xsave(X86CPU *cpu)
             sizeof env->opmask_regs);
     memcpy(env->zmmh_regs, &xsave->region[XSAVE_ZMM_Hi256],
             sizeof env->zmmh_regs);
+
+    xmm = (const uint8_t *)&xsave->region[XSAVE_XMM_SPACE];
+    for (i = 0; i < CPU_NB_REGS; i++, xmm += 16) {
+        env->xmm_regs[i].XMM_Q(0) = ldq_p(xmm);
+        env->xmm_regs[i].XMM_Q(1) = ldq_p(xmm+8);
+    }
+
 #ifdef TARGET_X86_64
     memcpy(env->hi16_zmm_regs, &xsave->region[XSAVE_Hi16_ZMM],
             sizeof env->hi16_zmm_regs);
diff --git a/target-i386/translate.c b/target-i386/translate.c
index ebdc3500e5..9ebdf4b384 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -2621,10 +2621,10 @@ static inline void gen_sto_env_A0(DisasContext *s, int offset)
 
 static inline void gen_op_movo(int d_offset, int s_offset)
 {
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset);
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset);
-    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + 8);
-    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + 8);
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(XMMReg, XMM_Q(0)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(XMMReg, XMM_Q(0)));
+    tcg_gen_ld_i64(cpu_tmp1_i64, cpu_env, s_offset + offsetof(XMMReg, XMM_Q(1)));
+    tcg_gen_st_i64(cpu_tmp1_i64, cpu_env, d_offset + offsetof(XMMReg, XMM_Q(1)));
 }
 
 static inline void gen_op_movq(int d_offset, int s_offset)
@@ -3074,7 +3074,8 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
                 goto illegal_op;
             gen_lea_modrm(env, s, modrm);
             if (b1 & 1) {
-                gen_stq_env_A0(s, offsetof(CPUX86State, xmm_regs[reg]));
+                gen_stq_env_A0(s, offsetof(CPUX86State,
+                                           xmm_regs[reg].XMM_Q(0)));
             } else {
                 tcg_gen_ld32u_tl(cpu_T[0], cpu_env, offsetof(CPUX86State,
                     xmm_regs[reg].XMM_L(0)));