[Qemu-devel] [PATCH v4 01/14] Introduce TCGOpcode for memory barrier

[Pranith Kumar]

This commit introduces the TCGOpcode for memory barrier instruction.

This opcode takes an argument which is the type of memory barrier
which should be generated.

Signed-off-by: Pranith Kumar <address@hidden>
---
 tcg/README    | 17 +++++++++++++++++
 tcg/tcg-op.c  | 17 +++++++++++++++++
 tcg/tcg-op.h  |  2 ++
 tcg/tcg-opc.h |  2 ++
 tcg/tcg.h     | 19 +++++++++++++++++++
 5 files changed, 57 insertions(+)

diff --git a/tcg/README b/tcg/README
index ce8beba..1d48aa9 100644
--- a/tcg/README
+++ b/tcg/README
@@ -402,6 +402,23 @@ double-word product T0.  The later is returned in two 
single-word outputs.
 
 Similar to mulu2, except the two inputs T1 and T2 are signed.
 
+********* Memory Barrier support
+
+* mb <$arg>
+
+Generate a target memory barrier instruction to ensure memory ordering as being
+enforced by a corresponding guest memory barrier instruction. The ordering
+enforced by the backend may be stricter than the ordering required by the 
guest.
+It cannot be weaker. This opcode takes a constant argument which is required to
+generate the appropriate barrier instruction. The backend should take care to
+emit the target barrier instruction only when necessary i.e., for SMP guests 
and
+when MTTCG is enabled.
+
+The guest translators should generate this opcode for all guest instructions
+which have ordering side effects.
+
+Please see docs/atomics.txt for more information on memory barriers.
+
 ********* 64-bit guest on 32-bit host support
 
 The following opcodes are internal to TCG.  Thus they are to be implemented by
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index 293b854..149f4a9 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -148,6 +148,23 @@ void tcg_gen_op6(TCGContext *ctx, TCGOpcode opc, TCGArg 
a1, TCGArg a2,
     tcg_emit_op(ctx, opc, pi);
 }
 
+void tcg_gen_mb(TCGArg mb_type)
+{
+    bool emit_barriers = true;
+
+#ifndef CONFIG_USER_ONLY
+    /* TODO: When MTTCG is available for system mode, we will check
+     * the following condition and enable emit_barriers
+     * (qemu_tcg_mttcg_enabled() && smp_cpus > 1)
+     */
+    emit_barriers = false;
+#endif
+
+    if (emit_barriers) {
+        tcg_gen_op1(&tcg_ctx, INDEX_op_mb, mb_type);
+    }
+}
+
 /* 32 bit ops */
 
 void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index f217e80..41890cc 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -261,6 +261,8 @@ static inline void tcg_gen_br(TCGLabel *l)
     tcg_gen_op1(&tcg_ctx, INDEX_op_br, label_arg(l));
 }
 
+void tcg_gen_mb(TCGArg a);
+
 /* Helper calls. */
 
 /* 32 bit ops */
diff --git a/tcg/tcg-opc.h b/tcg/tcg-opc.h
index 6d0410c..45528d2 100644
--- a/tcg/tcg-opc.h
+++ b/tcg/tcg-opc.h
@@ -42,6 +42,8 @@ DEF(br, 0, 0, 1, TCG_OPF_BB_END)
 # define IMPL64  TCG_OPF_64BIT
 #endif
 
+DEF(mb, 0, 0, 1, 0)
+
 DEF(mov_i32, 1, 1, 0, TCG_OPF_NOT_PRESENT)
 DEF(movi_i32, 1, 0, 1, TCG_OPF_NOT_PRESENT)
 DEF(setcond_i32, 1, 2, 1, 0)
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 66ae0c7..639e30c 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -478,6 +478,25 @@ static inline intptr_t QEMU_ARTIFICIAL 
GET_TCGV_PTR(TCGv_ptr t)
 #define TCG_CALL_DUMMY_TCGV     MAKE_TCGV_I32(-1)
 #define TCG_CALL_DUMMY_ARG      ((TCGArg)(-1))
 
+/* used to indicate the type of accesses on which ordering is to be
+   ensured. Modeled after SPARC barriers */
+typedef enum {
+    TCG_MO_LD_LD    = 1,
+    TCG_MO_ST_LD    = 2,
+    TCG_MO_LD_ST    = 4,
+    TCG_MO_ST_ST    = 8,
+    TCG_MO_ALL      = 0xF, /* OR of all above */
+} TCGOrder;
+
+/* used to indicate the kind of ordering which is to be ensured by the
+   instruction. These types are derived from x86/aarch64 instructions.
+   It should be noted that these are different from C11 semantics */
+typedef enum {
+    TCG_BAR_LDAQ     = 0x10, /* generated for aarch64 load-acquire inst. */
+    TCG_BAR_STRL     = 0x20, /* generated for aarch64 store-rel inst. */
+    TCG_BAR_SC       = 0x40, /* generated for all other ordering inst. */
+} TCGBar;
+
 /* Conditions.  Note that these are laid out for easy manipulation by
    the functions below:
      bit 0 is used for inverting;
-- 
2.9.0