tcg/riscv: Support softmmu unaligned accesses

The system is required to emulate unaligned accesses, even if the
hardware does not support it.  The resulting trap may or may not
be more efficient than the qemu slow path.  There are linux kernel
patches in flight to allow userspace to query hardware support;
we can re-evaluate whether to enable this by default after that.

In the meantime, softmmu now matches useronly, where we already
assumed that unaligned accesses are supported.

Reviewed-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 28 insertions, 20 deletions

diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 19cd450..415e6c6 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -910,12 +910,13 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase,
 
 #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(mem_index);
     int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask);
     int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table);
-    TCGReg mask_base = TCG_AREG0, table_base = TCG_AREG0;
-    tcg_target_long compare_mask;
+    int compare_mask;
+    TCGReg addr_adj;
 
     ldst = new_ldst_label(s);
     ldst->is_ld = is_ld;
@@ -924,44 +925,51 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext *s, TCGReg *pbase,
 
     QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0);
     QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11));
-    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, mask_base, mask_ofs);
-    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, table_base, table_ofs);
+    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,
                     TARGET_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);
 
-    /* Load the tlb comparator and the addend.  */
-    tcg_out_ld(s, TCG_TYPE_TL, 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));
-
-    /* We don't support unaligned accesses. */
+    /*
+     * 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_bits < s_bits) {
-        a_bits = s_bits;
+        addr_adj = TCG_REG_TMP0;
+        tcg_out_opc_imm(s, TARGET_LONG_BITS == 32 ? OPC_ADDIW : OPC_ADDI,
+                        addr_adj, addr_reg, s_mask - a_mask);
     }
-    /* Clear the non-page, non-alignment bits from the address.  */
-    compare_mask = (tcg_target_long)TARGET_PAGE_MASK | a_mask;
+    compare_mask = TARGET_PAGE_MASK | a_mask;
     if (compare_mask == sextreg(compare_mask, 0, 12)) {
-        tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_reg, compare_mask);
+        tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_TMP1, addr_adj, compare_mask);
     } else {
         tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_TMP1, compare_mask);
-        tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addr_reg);
+        tcg_out_opc_reg(s, OPC_AND, TCG_REG_TMP1, TCG_REG_TMP1, addr_adj);
     }
 
+    /* Load the tlb comparator and the addend.  */
+    tcg_out_ld(s, TCG_TYPE_TL, 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.  */
+    addr_adj = addr_reg;
     if (TARGET_LONG_BITS == 32) {
-        tcg_out_ext32u(s, TCG_REG_TMP0, addr_reg);
-        addr_reg = TCG_REG_TMP0;
+        addr_adj = TCG_REG_TMP0;
+        tcg_out_ext32u(s, addr_adj, addr_reg);
     }
-    tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_REG_TMP2, addr_reg);
+    tcg_out_opc_reg(s, OPC_ADD, TCG_REG_TMP0, TCG_REG_TMP2, addr_adj);
     *pbase = TCG_REG_TMP0;
 #else
     if (a_mask) {