Merge tag 'pull-tcg-20230502' of https://gitlab.com/rth7680/qemu into…

… staging

Misc tcg-related patch queue.

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmRQ8YwdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV+9rAf/RetCt2y/7VSlWBnP
# o/A5y8p6jQI+LjY0BIlG8V5DC1H/bLhCLD60/DyUwzWP6Zb9wYRQ5+WpsgBmUcql
# SkRA+mZLIGZWDSi6wIDN6IHixVkd/yVjn+05LQS8/GU7y/AEbjqsUevI5OX7aOkv
# 2LkDrzbZrBWcE/C1coZKUNDHac1+Wh4UBUqfxVWvBIQW+qXMXuwSraoOBHA9BvcH
# wGJjJ4eoLKoKBbu49rx+b2wvXiTRtIq2jfKAOEVoZy5uWrcXQTqZHJXejhB1JOFY
# 5i2qqGA9vX6HycDmq2xM3qwO2RtlyS2tGgXL0QX2D/4z1ysEzQUv7bPL9euGk13K
# neCv5w==
# =G9sH
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 02 May 2023 12:18:36 PM BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate]

* tag 'pull-tcg-20230502' of https://gitlab.com/rth7680/qemu:
  tcg: Introduce tcg_out_movext2
  tcg/mips: Conditionalize tcg_out_exts_i32_i64
  tcg/loongarch64: Conditionalize tcg_out_exts_i32_i64
  accel/tcg: Add cpu_ld*_code_mmu
  migration/xbzrle: Use __attribute__((target)) for avx512
  qemu/int128: Re-shuffle Int128Alias members
  tcg: Add tcg_gen_gvec_rotrs
  tcg: Add tcg_gen_gvec_andcs
  qemu/host-utils.h: Add clz and ctz functions for lower-bit integers
  qemu/bitops.h: Limit rotate amounts
  accel/tcg: Uncache the host address for instruction fetch when tlb size < 1
  softmmu: Tidy dirtylimit_dirty_ring_full_time

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

accel/tcg/cputlb.c

@@ -1696,6 +1696,11 @@ tb_page_addr_t get_page_addr_code_hostp(CPUArchState *env, target_ulong addr,
     if (p == NULL) {
         return -1;
     }
+
+    if (full->lg_page_size < TARGET_PAGE_BITS) {
+        return -1;
+    }
+
     if (hostp) {
         *hostp = p;
     }
@@ -2768,3 +2773,51 @@ uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr addr)
     MemOpIdx oi = make_memop_idx(MO_TEUQ, cpu_mmu_index(env, true));
     return full_ldq_code(env, addr, oi, 0);
 }
+
+uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr,
+                         MemOpIdx oi, uintptr_t retaddr)
+{
+    return full_ldub_code(env, addr, oi, retaddr);
+}
+
+uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t retaddr)
+{
+    MemOp mop = get_memop(oi);
+    int idx = get_mmuidx(oi);
+    uint16_t ret;
+
+    ret = full_lduw_code(env, addr, make_memop_idx(MO_TEUW, idx), retaddr);
+    if ((mop & MO_BSWAP) != MO_TE) {
+        ret = bswap16(ret);
+    }
+    return ret;
+}
+
+uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t retaddr)
+{
+    MemOp mop = get_memop(oi);
+    int idx = get_mmuidx(oi);
+    uint32_t ret;
+
+    ret = full_ldl_code(env, addr, make_memop_idx(MO_TEUL, idx), retaddr);
+    if ((mop & MO_BSWAP) != MO_TE) {
+        ret = bswap32(ret);
+    }
+    return ret;
+}
+
+uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t retaddr)
+{
+    MemOp mop = get_memop(oi);
+    int idx = get_mmuidx(oi);
+    uint64_t ret;
+
+    ret = full_ldq_code(env, addr, make_memop_idx(MO_TEUQ, idx), retaddr);
+    if ((mop & MO_BSWAP) != MO_TE) {
+        ret = bswap64(ret);
+    }
+    return ret;
+}

accel/tcg/tcg-runtime-gvec.c

@@ -550,6 +550,17 @@ void HELPER(gvec_ands)(void *d, void *a, uint64_t b, uint32_t desc)
     clear_high(d, oprsz, desc);
 }
 
+void HELPER(gvec_andcs)(void *d, void *a, uint64_t b, uint32_t desc)
+{
+    intptr_t oprsz = simd_oprsz(desc);
+    intptr_t i;
+
+    for (i = 0; i < oprsz; i += sizeof(uint64_t)) {
+        *(uint64_t *)(d + i) = *(uint64_t *)(a + i) & ~b;
+    }
+    clear_high(d, oprsz, desc);
+}
+
 void HELPER(gvec_xors)(void *d, void *a, uint64_t b, uint32_t desc)
 {
     intptr_t oprsz = simd_oprsz(desc);

accel/tcg/tcg-runtime.h

@@ -217,6 +217,7 @@ DEF_HELPER_FLAGS_4(gvec_nor, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_eqv, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(gvec_ands, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(gvec_andcs, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_xors, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 DEF_HELPER_FLAGS_4(gvec_ors, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 

accel/tcg/user-exec.c

@@ -1219,6 +1219,64 @@ uint64_t cpu_ldq_code(CPUArchState *env, abi_ptr ptr)
     return ret;
 }
 
+uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr,
+                         MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint8_t ret;
+
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_INST_FETCH);
+    ret = ldub_p(haddr);
+    clear_helper_retaddr();
+    return ret;
+}
+
+uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint16_t ret;
+
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_INST_FETCH);
+    ret = lduw_p(haddr);
+    clear_helper_retaddr();
+    if (get_memop(oi) & MO_BSWAP) {
+        ret = bswap16(ret);
+    }
+    return ret;
+}
+
+uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint32_t ret;
+
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_INST_FETCH);
+    ret = ldl_p(haddr);
+    clear_helper_retaddr();
+    if (get_memop(oi) & MO_BSWAP) {
+        ret = bswap32(ret);
+    }
+    return ret;
+}
+
+uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t ra)
+{
+    void *haddr;
+    uint64_t ret;
+
+    validate_memop(oi, MO_BEUQ);
+    haddr = cpu_mmu_lookup(env, addr, oi, ra, MMU_DATA_LOAD);
+    ret = ldq_p(haddr);
+    clear_helper_retaddr();
+    if (get_memop(oi) & MO_BSWAP) {
+        ret = bswap64(ret);
+    }
+    return ret;
+}
+
 #include "ldst_common.c.inc"
 
 /*

include/exec/cpu_ldst.h

@@ -445,6 +445,15 @@ static inline CPUTLBEntry *tlb_entry(CPUArchState *env, uintptr_t mmu_idx,
 # define cpu_stq_mmu          cpu_stq_le_mmu
 #endif
 
+uint8_t cpu_ldb_code_mmu(CPUArchState *env, abi_ptr addr,
+                         MemOpIdx oi, uintptr_t ra);
+uint16_t cpu_ldw_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t ra);
+uint32_t cpu_ldl_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t ra);
+uint64_t cpu_ldq_code_mmu(CPUArchState *env, abi_ptr addr,
+                          MemOpIdx oi, uintptr_t ra);
+
 uint32_t cpu_ldub_code(CPUArchState *env, abi_ptr addr);
 uint32_t cpu_lduw_code(CPUArchState *env, abi_ptr addr);
 uint32_t cpu_ldl_code(CPUArchState *env, abi_ptr addr);

include/qemu/bitops.h

@@ -218,7 +218,8 @@ static inline unsigned long find_first_zero_bit(const unsigned long *addr,
  */
 static inline uint8_t rol8(uint8_t word, unsigned int shift)
 {
-    return (word << shift) | (word >> ((8 - shift) & 7));
+    shift &= 7;
+    return (word << shift) | (word >> (8 - shift));
 }
 
 /**
@@ -228,7 +229,8 @@ static inline uint8_t rol8(uint8_t word, unsigned int shift)
  */
 static inline uint8_t ror8(uint8_t word, unsigned int shift)
 {
-    return (word >> shift) | (word << ((8 - shift) & 7));
+    shift &= 7;
+    return (word >> shift) | (word << (8 - shift));
 }
 
 /**
@@ -238,7 +240,8 @@ static inline uint8_t ror8(uint8_t word, unsigned int shift)
  */
 static inline uint16_t rol16(uint16_t word, unsigned int shift)
 {
-    return (word << shift) | (word >> ((16 - shift) & 15));
+    shift &= 15;
+    return (word << shift) | (word >> (16 - shift));
 }
 
 /**
@@ -248,7 +251,8 @@ static inline uint16_t rol16(uint16_t word, unsigned int shift)
  */
 static inline uint16_t ror16(uint16_t word, unsigned int shift)
 {
-    return (word >> shift) | (word << ((16 - shift) & 15));
+    shift &= 15;
+    return (word >> shift) | (word << (16 - shift));
 }
 
 /**
@@ -258,7 +262,8 @@ static inline uint16_t ror16(uint16_t word, unsigned int shift)
  */
 static inline uint32_t rol32(uint32_t word, unsigned int shift)
 {
-    return (word << shift) | (word >> ((32 - shift) & 31));
+    shift &= 31;
+    return (word << shift) | (word >> (32 - shift));
 }
 
 /**
@@ -268,7 +273,8 @@ static inline uint32_t rol32(uint32_t word, unsigned int shift)
  */
 static inline uint32_t ror32(uint32_t word, unsigned int shift)
 {
-    return (word >> shift) | (word << ((32 - shift) & 31));
+    shift &= 31;
+    return (word >> shift) | (word << (32 - shift));
 }
 
 /**
@@ -278,7 +284,8 @@ static inline uint32_t ror32(uint32_t word, unsigned int shift)
  */
 static inline uint64_t rol64(uint64_t word, unsigned int shift)
 {
-    return (word << shift) | (word >> ((64 - shift) & 63));
+    shift &= 63;
+    return (word << shift) | (word >> (64 - shift));
 }
 
 /**
@@ -288,7 +295,8 @@ static inline uint64_t rol64(uint64_t word, unsigned int shift)
  */
 static inline uint64_t ror64(uint64_t word, unsigned int shift)
 {
-    return (word >> shift) | (word << ((64 - shift) & 63));
+    shift &= 63;
+    return (word >> shift) | (word << (64 - shift));
 }
 
 /**

include/qemu/host-utils.h

@@ -107,6 +107,36 @@ static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
 }
 #endif
 
+/**
+ * clz8 - count leading zeros in a 8-bit value.
+ * @val: The value to search
+ *
+ * Returns 8 if the value is zero.  Note that the GCC builtin is
+ * undefined if the value is zero.
+ *
+ * Note that the GCC builtin will upcast its argument to an `unsigned int`
+ * so this function subtracts off the number of prepended zeroes.
+ */
+static inline int clz8(uint8_t val)
+{
+    return val ? __builtin_clz(val) - 24 : 8;
+}
+
+/**
+ * clz16 - count leading zeros in a 16-bit value.
+ * @val: The value to search
+ *
+ * Returns 16 if the value is zero.  Note that the GCC builtin is
+ * undefined if the value is zero.
+ *
+ * Note that the GCC builtin will upcast its argument to an `unsigned int`
+ * so this function subtracts off the number of prepended zeroes.
+ */
+static inline int clz16(uint16_t val)
+{
+    return val ? __builtin_clz(val) - 16 : 16;
+}
+
 /**
  * clz32 - count leading zeros in a 32-bit value.
  * @val: The value to search
@@ -153,6 +183,30 @@ static inline int clo64(uint64_t val)
     return clz64(~val);
 }
 
+/**
+ * ctz8 - count trailing zeros in a 8-bit value.
+ * @val: The value to search
+ *
+ * Returns 8 if the value is zero.  Note that the GCC builtin is
+ * undefined if the value is zero.
+ */
+static inline int ctz8(uint8_t val)
+{
+    return val ? __builtin_ctz(val) : 8;
+}
+
+/**
+ * ctz16 - count trailing zeros in a 16-bit value.
+ * @val: The value to search
+ *
+ * Returns 16 if the value is zero.  Note that the GCC builtin is
+ * undefined if the value is zero.
+ */
+static inline int ctz16(uint16_t val)
+{
+    return val ? __builtin_ctz(val) : 16;
+}
+
 /**
  * ctz32 - count trailing zeros in a 32-bit value.
  * @val: The value to search

include/qemu/int128.h

@@ -483,9 +483,9 @@ static inline void bswap128s(Int128 *s)
  */
 #ifdef CONFIG_INT128
 typedef union {
-    Int128 s;
-    __int128_t i;
     __uint128_t u;
+    __int128_t i;
+    Int128 s;
 } Int128Alias __attribute__((transparent_union));
 #else
 typedef Int128 Int128Alias;

include/tcg/tcg-op-gvec.h

@@ -330,6 +330,8 @@ void tcg_gen_gvec_ori(unsigned vece, uint32_t dofs, uint32_t aofs,
 
 void tcg_gen_gvec_ands(unsigned vece, uint32_t dofs, uint32_t aofs,
                        TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
+void tcg_gen_gvec_andcs(unsigned vece, uint32_t dofs, uint32_t aofs,
+                        TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
 void tcg_gen_gvec_xors(unsigned vece, uint32_t dofs, uint32_t aofs,
                        TCGv_i64 c, uint32_t oprsz, uint32_t maxsz);
 void tcg_gen_gvec_ors(unsigned vece, uint32_t dofs, uint32_t aofs,
@@ -369,6 +371,8 @@ void tcg_gen_gvec_sars(unsigned vece, uint32_t dofs, uint32_t aofs,
                        TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz);
 void tcg_gen_gvec_rotls(unsigned vece, uint32_t dofs, uint32_t aofs,
                         TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz);
+void tcg_gen_gvec_rotrs(unsigned vece, uint32_t dofs, uint32_t aofs,
+                        TCGv_i32 shift, uint32_t oprsz, uint32_t maxsz);
 
 /*
  * Perform vector shift by vector element, modulo the element size.

meson.build

@@ -2370,12 +2370,9 @@ config_host_data.set('CONFIG_AVX512F_OPT', get_option('avx512f') \
 config_host_data.set('CONFIG_AVX512BW_OPT', get_option('avx512bw') \
   .require(have_cpuid_h, error_message: 'cpuid.h not available, cannot enable AVX512BW') \
   .require(cc.links('''
-    #pragma GCC push_options
-    #pragma GCC target("avx512bw")
     #include <cpuid.h>
     #include <immintrin.h>
-    static int bar(void *a) {
-
+    static int __attribute__((target("avx512bw"))) bar(void *a) {
       __m512i *x = a;
       __m512i res= _mm512_abs_epi8(*x);
       return res[1];

migration/xbzrle.c

@@ -177,11 +177,11 @@ int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen)
 }
 
 #if defined(CONFIG_AVX512BW_OPT)
-#pragma GCC push_options
-#pragma GCC target("avx512bw")
 #include <immintrin.h>
-int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
-                             uint8_t *dst, int dlen)
+
+int __attribute__((target("avx512bw")))
+xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
+                            uint8_t *dst, int dlen)
 {
     uint32_t zrun_len = 0, nzrun_len = 0;
     int d = 0, i = 0, num = 0;
@@ -296,5 +296,4 @@ int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen,
     }
     return d;
 }
-#pragma GCC pop_options
 #endif