Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging

* configure: don't enable firmware for targets that are not built
* configure: don't use strings(1)
* scsi, target/i386: switch from device_legacy_reset() to device_cold_reset()
* target/i386: AVX support for TCG
* target/i386: fix SynIC SINT assertion failure on guest reset
* target/i386: Use atomic operations for pte updates and other cleanups
* tests/tcg: extend SSE tests to AVX
* virtio-scsi: send "REPORTED LUNS CHANGED" sense data upon disk hotplug events

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmNOlOcUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroNuvwgAj/Z5pI9KU33XiWKFR3bZf2lHh21P
# xmTzNtPmnP1WHDY1DNug/UB+BLg3c+carpTf5n3B8aKI4X3FfxGSJvYlXy4BONFD
# XqYMH3OZB5GaR8Wza9trNYjDs/9hOZus/0R6Hqdl/T38PlMjf8mmayULJIGdcFcJ
# WJvITVntbcCwwbpyJbRC5BNigG8ZXTNRoKBgtFVGz6Ox+n0YydwKX5qU5J7xRfCU
# lW41LjZ0Fk5lonH16+xuS4WD5EyrNt8cMKCGsxnyxhI7nehe/OGnYr9l+xZJclrh
# inQlSwJv0IpUJcrGCI4Xugwux4Z7ZXv3JQ37FzsdZcv/ZXpGonXMeXNJ9A==
# =o6x7
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 18 Oct 2022 07:58:31 EDT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# 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

* tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (53 commits)
  target/i386: remove old SSE decoder
  target/i386: move 3DNow to the new decoder
  tests/tcg: extend SSE tests to AVX
  target/i386: Enable AVX cpuid bits when using TCG
  target/i386: implement VLDMXCSR/VSTMXCSR
  target/i386: implement XSAVE and XRSTOR of AVX registers
  target/i386: reimplement 0x0f 0x28-0x2f, add AVX
  target/i386: reimplement 0x0f 0x10-0x17, add AVX
  target/i386: reimplement 0x0f 0xc2, 0xc4-0xc6, add AVX
  target/i386: reimplement 0x0f 0x38, add AVX
  target/i386: Use tcg gvec ops for pmovmskb
  target/i386: reimplement 0x0f 0x3a, add AVX
  target/i386: clarify (un)signedness of immediates from 0F3Ah opcodes
  target/i386: reimplement 0x0f 0xd0-0xd7, 0xe0-0xe7, 0xf0-0xf7, add AVX
  target/i386: reimplement 0x0f 0x70-0x77, add AVX
  target/i386: reimplement 0x0f 0x78-0x7f, add AVX
  target/i386: reimplement 0x0f 0x50-0x5f, add AVX
  target/i386: reimplement 0x0f 0xd8-0xdf, 0xe8-0xef, 0xf8-0xff, add AVX
  target/i386: reimplement 0x0f 0x60-0x6f, add AVX
  target/i386: Introduce 256-bit vector helpers
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 52 insertions, 16 deletions

diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 7edf5dfac3..dad2b2db8d 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -169,6 +169,7 @@ typedef enum X86Seg {
 #define HF_MPX_EN_SHIFT     25 /* MPX Enabled (CR4+XCR0+BNDCFGx) */
 #define HF_MPX_IU_SHIFT     26 /* BND registers in-use */
 #define HF_UMIP_SHIFT       27 /* CR4.UMIP */
+#define HF_AVX_EN_SHIFT     28 /* AVX Enabled (CR4+XCR0) */
 
 #define HF_CPL_MASK          (3 << HF_CPL_SHIFT)
 #define HF_INHIBIT_IRQ_MASK  (1 << HF_INHIBIT_IRQ_SHIFT)
@@ -195,6 +196,7 @@ typedef enum X86Seg {
 #define HF_MPX_EN_MASK       (1 << HF_MPX_EN_SHIFT)
 #define HF_MPX_IU_MASK       (1 << HF_MPX_IU_SHIFT)
 #define HF_UMIP_MASK         (1 << HF_UMIP_SHIFT)
+#define HF_AVX_EN_MASK       (1 << HF_AVX_EN_SHIFT)
 
 /* hflags2 */
 
@@ -1233,18 +1235,34 @@ typedef struct SegmentCache {
     uint32_t flags;
 } SegmentCache;
 
-#define MMREG_UNION(n, bits)        \
-    union n {                       \
-        uint8_t  _b_##n[(bits)/8];  \
-        uint16_t _w_##n[(bits)/16]; \
-        uint32_t _l_##n[(bits)/32]; \
-        uint64_t _q_##n[(bits)/64]; \
-        float32  _s_##n[(bits)/32]; \
-        float64  _d_##n[(bits)/64]; \
-    }
-
-typedef MMREG_UNION(ZMMReg, 512) ZMMReg;
-typedef MMREG_UNION(MMXReg, 64)  MMXReg;
+typedef union MMXReg {
+    uint8_t  _b_MMXReg[64 / 8];
+    uint16_t _w_MMXReg[64 / 16];
+    uint32_t _l_MMXReg[64 / 32];
+    uint64_t _q_MMXReg[64 / 64];
+    float32  _s_MMXReg[64 / 32];
+    float64  _d_MMXReg[64 / 64];
+} MMXReg;
+
+typedef union XMMReg {
+    uint64_t _q_XMMReg[128 / 64];
+} XMMReg;
+
+typedef union YMMReg {
+    uint64_t _q_YMMReg[256 / 64];
+    XMMReg   _x_YMMReg[256 / 128];
+} YMMReg;
+
+typedef union ZMMReg {
+    uint8_t  _b_ZMMReg[512 / 8];
+    uint16_t _w_ZMMReg[512 / 16];
+    uint32_t _l_ZMMReg[512 / 32];
+    uint64_t _q_ZMMReg[512 / 64];
+    float32  _s_ZMMReg[512 / 32];
+    float64  _d_ZMMReg[512 / 64];
+    XMMReg   _x_ZMMReg[512 / 128];
+    YMMReg   _y_ZMMReg[512 / 256];
+} ZMMReg;
 
 typedef struct BNDReg {
     uint64_t lb;
@@ -1267,6 +1285,13 @@ typedef struct BNDCSReg {
 #define ZMM_S(n) _s_ZMMReg[15 - (n)]
 #define ZMM_Q(n) _q_ZMMReg[7 - (n)]
 #define ZMM_D(n) _d_ZMMReg[7 - (n)]
+#define ZMM_X(n) _x_ZMMReg[3 - (n)]
+#define ZMM_Y(n) _y_ZMMReg[1 - (n)]
+
+#define XMM_Q(n) _q_XMMReg[1 - (n)]
+
+#define YMM_Q(n) _q_YMMReg[3 - (n)]
+#define YMM_X(n) _x_YMMReg[1 - (n)]
 
 #define MMX_B(n) _b_MMXReg[7 - (n)]
 #define MMX_W(n) _w_MMXReg[3 - (n)]
@@ -1279,6 +1304,13 @@ typedef struct BNDCSReg {
 #define ZMM_S(n) _s_ZMMReg[n]
 #define ZMM_Q(n) _q_ZMMReg[n]
 #define ZMM_D(n) _d_ZMMReg[n]
+#define ZMM_X(n) _x_ZMMReg[n]
+#define ZMM_Y(n) _y_ZMMReg[n]
+
+#define XMM_Q(n) _q_XMMReg[n]
+
+#define YMM_Q(n) _q_YMMReg[n]
+#define YMM_X(n) _x_YMMReg[n]
 
 #define MMX_B(n) _b_MMXReg[n]
 #define MMX_W(n) _w_MMXReg[n]
@@ -1556,8 +1588,8 @@ typedef struct CPUArchState {
     float_status mmx_status; /* for 3DNow! float ops */
     float_status sse_status;
     uint32_t mxcsr;
-    ZMMReg xmm_regs[CPU_NB_REGS == 8 ? 8 : 32];
-    ZMMReg xmm_t0;
+    ZMMReg xmm_regs[CPU_NB_REGS == 8 ? 8 : 32] QEMU_ALIGNED(16);
+    ZMMReg xmm_t0 QEMU_ALIGNED(16);
     MMXReg mmx_t0;
 
     uint64_t opmask_regs[NB_OPMASK_REGS];
@@ -2082,6 +2114,8 @@ typedef struct PropValue {
 } PropValue;
 void x86_cpu_apply_props(X86CPU *cpu, PropValue *props);
 
+void x86_cpu_after_reset(X86CPU *cpu);
+
 uint32_t cpu_x86_virtual_addr_width(CPUX86State *env);
 
 /* cpu.c other functions (cpuid) */
@@ -2094,6 +2128,7 @@ void host_cpuid(uint32_t function, uint32_t count,
 
 /* helper.c */
 void x86_cpu_set_a20(X86CPU *cpu, int a20_state);
+void cpu_sync_avx_hflag(CPUX86State *env);
 
 #ifndef CONFIG_USER_ONLY
 static inline int x86_asidx_from_attrs(CPUState *cs, MemTxAttrs attrs)
@@ -2147,6 +2182,9 @@ uint64_t cpu_get_tsc(CPUX86State *env);
 #define MMU_KSMAP_IDX   0
 #define MMU_USER_IDX    1
 #define MMU_KNOSMAP_IDX 2
+#define MMU_NESTED_IDX  3
+#define MMU_PHYS_IDX    4
+
 static inline int cpu_mmu_index(CPUX86State *env, bool ifetch)
 {
     return (env->hflags & HF_CPL_MASK) == 3 ? MMU_USER_IDX :
@@ -2382,8 +2420,6 @@ static inline bool ctl_has_irq(CPUX86State *env)
     return (env->int_ctl & V_IRQ_MASK) && (int_prio >= tpr);
 }
 
-hwaddr get_hphys(CPUState *cs, hwaddr gphys, MMUAccessType access_type,
-                        int *prot);
 #if defined(TARGET_X86_64) && \
     defined(CONFIG_USER_ONLY) && \
     defined(CONFIG_LINUX)