Merge tag 'pull-tcg-20231023' of https://gitlab.com/rth7680/qemu into staging

tcg: Drop unused tcg_temp_free define
tcg: Introduce tcg_use_softmmu
tcg: Optimize past conditional branches
tcg: Use constant zero when expanding with divu2
tcg: Add negsetcondi
tcg: Define MO_TL
tcg: Export tcg_gen_ext_{i32,i64,tl}
target/*: Use tcg_gen_ext_*
tcg/ppc: Enable direct branching tcg_out_goto_tb with TCG_REG_TB
tcg/ppc: Use ADDPCIS for power9
tcg/ppc: Use prefixed instructions for power10
tcg/ppc: Disable TCG_REG_TB for Power9/Power10
tcg/ppc: Enable direct branching tcg_out_goto_tb with TCG_REG_TB
tcg/ppc: Use ADDPCIS for power9
tcg/ppc: Use prefixed instructions for power10
tcg/ppc: Disable TCG_REG_TB for Power9/Power10

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmU2t18dHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV9uXQgAhT1mDy5sg7mfSWuc
# X7i54C3n6Ykyra0HDG47dt4G0gkACEs7tDkllHIxhqTPKCrzpevyZEoyigr2MEOa
# 3GCwxvJORb27Ql2aiM1K8cdlEbzcrx+RZbl4lwqZpZbmMUbz/ZQI4xPEAf2yKdfB
# jTzi+Iu6ziPVqVQrg6fTm1I7YgQI85qcfKxi5lBaXgSfxPXGSlLeDw9Y8QjLHXRx
# nSiGpWiUd5TkqZgLIctShDbK4NEHcvjXUTW4rMWU9l5Cjdf9ZIhxcCxgKTXtOxBi
# 9tUdGOiup2HudOFf+DpQorzWpwRwy3NGpUF7n+WmevQZ1Qh8uNKsveFB0uuqObLg
# zlTI2Q==
# =lgiT
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 23 Oct 2023 11:11:43 PDT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* tag 'pull-tcg-20231023' of https://gitlab.com/rth7680/qemu: (38 commits)
  target/xtensa: Use tcg_gen_sextract_i32
  target/tricore: Use tcg_gen_*extract_tl
  target/rx: Use tcg_gen_ext_i32
  target/m68k: Use tcg_gen_ext_i32
  target/i386: Use tcg_gen_ext_tl
  target/arm: Use tcg_gen_ext_i64
  tcg: Define MO_TL
  tcg: Export tcg_gen_ext_{i32,i64,tl}
  tcg: add negsetcondi
  target/i386: Use i128 for 128 and 256-bit loads and stores
  tcg: Add tcg_gen_{ld,st}_i128
  tcg: Optimize past conditional branches
  tcg: Use constant zero when expanding with divu2
  tcg: drop unused tcg_temp_free define
  tcg/s390x: Use tcg_use_softmmu
  tcg/riscv: Use tcg_use_softmmu
  tcg/riscv: Do not reserve TCG_GUEST_BASE_REG for guest_base zero
  tcg/ppc: Use tcg_use_softmmu
  tcg/mips: Use tcg_use_softmmu
  tcg/loongarch64: Use tcg_use_softmmu
  ...

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

1 files changed, 93 insertions, 88 deletions

diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index d6dbcaf..34e10e7 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -1245,105 +1245,110 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase,
     aa = atom_and_align_for_opc(s, opc, MO_ATOM_IFALIGN, false);
     a_mask = (1u << aa.align) - 1;
 
-#ifdef CONFIG_SOFTMMU
-    unsigned s_bits = opc & MO_SIZE;
-    unsigned s_mask = (1u << s_bits) - 1;
-    int mem_index = get_mmuidx(oi);
-    int fast_ofs = tlb_mask_table_ofs(s, mem_index);
-    int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask);
-    int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table);
-    int compare_mask;
-    TCGReg addr_adj;
-
-    ldst = new_ldst_label(s);
-    ldst->is_ld = is_ld;
-    ldst->oi = oi;
-    ldst->addrlo_reg = addr_reg;
-
-    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs);
-    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs);
-
-    tcg_out_opc_imm(s, OPC_SRLI, TCG_REG_TMP2, addr_reg,
-                    s->page_bits - CPU_TLB_ENTRY_BITS);
-    tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP0);
-    tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1);
+    if (tcg_use_softmmu) {
+        unsigned s_bits = opc & MO_SIZE;
+        unsigned s_mask = (1u << s_bits) - 1;
+        int mem_index = get_mmuidx(oi);
+        int fast_ofs = tlb_mask_table_ofs(s, mem_index);
+        int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask);
+        int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table);
+        int compare_mask;
+        TCGReg addr_adj;
 
-    /*
-     * For aligned accesses, we check the first byte and include the alignment
-     * bits within the address.  For unaligned access, we check that we don't
-     * cross pages using the address of the last byte of the access.
-     */
-    addr_adj = addr_reg;
-    if (a_mask < s_mask) {
-        addr_adj = TCG_REG_TMP0;
-        tcg_out_opc_imm(s, addr_type == TCG_TYPE_I32 ? OPC_ADDIW : OPC_ADDI,
-                        addr_adj, addr_reg, s_mask - a_mask);
-    }
-    compare_mask = s->page_mask | a_mask;
-    if (compare_mask == sextreg(compare_mask, 0, 12)) {
-        tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_adj, compare_mask);
-    } else {
-        tcg_out_movi(s, addr_type, TCG_REG_TMP1, compare_mask);
-        tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addr_adj);
-    }
-
-    /* Load the tlb comparator and the addend.  */
-    QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
-    tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2,
-               is_ld ? offsetof(CPUTLBEntry, addr_read)
-                     : offsetof(CPUTLBEntry, addr_write));
-    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP2,
-               offsetof(CPUTLBEntry, addend));
-
-    /* Compare masked address with the TLB entry. */
-    ldst->label_ptr[0] = s->code_ptr;
-    tcg_out_opc_branch(s, OPC_BNE, TCG_REG_TMP0, TCG_REG_TMP1, 0);
-
-    /* TLB Hit - translate address using addend.  */
-    if (addr_type != TCG_TYPE_I32) {
-        tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, addr_reg, TCG_REG_TMP2);
-    } else if (have_zba) {
-        tcg_out_opc_reg(s, OPC_ADD_UW, TCG_REG_TMP0, addr_reg, TCG_REG_TMP2);
-    } else {
-        tcg_out_ext32u(s, TCG_REG_TMP0, addr_reg);
-        tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_REG_TMP0, TCG_REG_TMP2);
-    }
-    *pbase = TCG_REG_TMP0;
-#else
-    TCGReg base;
-
-    if (a_mask) {
         ldst = new_ldst_label(s);
         ldst->is_ld = is_ld;
         ldst->oi = oi;
         ldst->addrlo_reg = addr_reg;
 
-        /* We are expecting alignment max 7, so we can always use andi. */
-        tcg_debug_assert(a_mask == sextreg(a_mask, 0, 12));
-        tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_reg, a_mask);
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_AREG0, mask_ofs);
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, TCG_AREG0, table_ofs);
+
+        tcg_out_opc_imm(s, OPC_SRLI, TCG_REG_TMP2, addr_reg,
+                        s->page_bits - CPU_TLB_ENTRY_BITS);
+        tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP0);
+        tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP2, TCG_REG_TMP2, TCG_REG_TMP1);
+
+        /*
+         * For aligned accesses, we check the first byte and include the
+         * alignment bits within the address.  For unaligned access, we
+         * check that we don't cross pages using the address of the last
+         * byte of the access.
+         */
+        addr_adj = addr_reg;
+        if (a_mask < s_mask) {
+            addr_adj = TCG_REG_TMP0;
+            tcg_out_opc_imm(s, addr_type == TCG_TYPE_I32 ? OPC_ADDIW : OPC_ADDI,
+                            addr_adj, addr_reg, s_mask - a_mask);
+        }
+        compare_mask = s->page_mask | a_mask;
+        if (compare_mask == sextreg(compare_mask, 0, 12)) {
+            tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_adj, compare_mask);
+        } else {
+            tcg_out_movi(s, addr_type, TCG_REG_TMP1, compare_mask);
+            tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addr_adj);
+        }
+
+        /* Load the tlb comparator and the addend.  */
+        QEMU_BUILD_BUG_ON(HOST_BIG_ENDIAN);
+        tcg_out_ld(s, addr_type, TCG_REG_TMP0, TCG_REG_TMP2,
+                   is_ld ? offsetof(CPUTLBEntry, addr_read)
+                         : offsetof(CPUTLBEntry, addr_write));
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP2, TCG_REG_TMP2,
+                   offsetof(CPUTLBEntry, addend));
 
+        /* Compare masked address with the TLB entry. */
         ldst->label_ptr[0] = s->code_ptr;
-        tcg_out_opc_branch(s, OPC_BNE, TCG_REG_TMP1, TCG_REG_ZERO, 0);
-    }
+        tcg_out_opc_branch(s, OPC_BNE, TCG_REG_TMP0, TCG_REG_TMP1, 0);
 
-    if (guest_base != 0) {
-        base = TCG_REG_TMP0;
+        /* TLB Hit - translate address using addend.  */
         if (addr_type != TCG_TYPE_I32) {
-            tcg_out_opc_reg(s, OPC_ADD, base, addr_reg, TCG_GUEST_BASE_REG);
+            tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, addr_reg, TCG_REG_TMP2);
         } else if (have_zba) {
-            tcg_out_opc_reg(s, OPC_ADD_UW, base, addr_reg, TCG_GUEST_BASE_REG);
+            tcg_out_opc_reg(s, OPC_ADD_UW, TCG_REG_TMP0,
+                            addr_reg, TCG_REG_TMP2);
         } else {
-            tcg_out_ext32u(s, base, addr_reg);
-            tcg_out_opc_reg(s, OPC_ADD, base, base, TCG_GUEST_BASE_REG);
+            tcg_out_ext32u(s, TCG_REG_TMP0, addr_reg);
+            tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0,
+                            TCG_REG_TMP0, TCG_REG_TMP2);
         }
-    } else if (addr_type != TCG_TYPE_I32) {
-        base = addr_reg;
+        *pbase = TCG_REG_TMP0;
     } else {
-        base = TCG_REG_TMP0;
-        tcg_out_ext32u(s, base, addr_reg);
+        TCGReg base;
+
+        if (a_mask) {
+            ldst = new_ldst_label(s);
+            ldst->is_ld = is_ld;
+            ldst->oi = oi;
+            ldst->addrlo_reg = addr_reg;
+
+            /* We are expecting alignment max 7, so we can always use andi. */
+            tcg_debug_assert(a_mask == sextreg(a_mask, 0, 12));
+            tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_reg, a_mask);
+
+            ldst->label_ptr[0] = s->code_ptr;
+            tcg_out_opc_branch(s, OPC_BNE, TCG_REG_TMP1, TCG_REG_ZERO, 0);
+        }
+
+        if (guest_base != 0) {
+            base = TCG_REG_TMP0;
+            if (addr_type != TCG_TYPE_I32) {
+                tcg_out_opc_reg(s, OPC_ADD, base, addr_reg,
+                                TCG_GUEST_BASE_REG);
+            } else if (have_zba) {
+                tcg_out_opc_reg(s, OPC_ADD_UW, base, addr_reg,
+                                TCG_GUEST_BASE_REG);
+            } else {
+                tcg_out_ext32u(s, base, addr_reg);
+                tcg_out_opc_reg(s, OPC_ADD, base, base, TCG_GUEST_BASE_REG);
+            }
+        } else if (addr_type != TCG_TYPE_I32) {
+            base = addr_reg;
+        } else {
+            base = TCG_REG_TMP0;
+            tcg_out_ext32u(s, base, addr_reg);
+        }
+        *pbase = base;
     }
-    *pbase = base;
-#endif
 
     return ldst;
 }
@@ -2075,10 +2080,10 @@ static void tcg_target_qemu_prologue(TCGContext *s)
                    TCG_REG_SP, SAVE_OFS + i * REG_SIZE);
     }
 
-#if !defined(CONFIG_SOFTMMU)
-    tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, guest_base);
-    tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
-#endif
+    if (!tcg_use_softmmu && guest_base) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, guest_base);
+        tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+    }
 
     /* Call generated code */
     tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);