[PULL 38/39] tcg/aarch64: Emit BTI insns at jump landing pads

[Richard Henderson]

The prologue is entered via "call"; the epilogue, each tb,
and each goto_tb continuation point are all reached via "jump".

As tcg_out_goto_long is only used by tcg_out_exit_tb, merge
the two functions.  Change the indirect register used to
TCG_REG_TMP1, aka X17, so that the BTI condition created
is "jump" instead of "jump or call".

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/aarch64/tcg-target.c.inc | 54 ++++++++++++++++++++++++++----------
 1 file changed, 39 insertions(+), 15 deletions(-)

diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc
index a0b65029d4..06ea3c7652 100644
--- a/tcg/aarch64/tcg-target.c.inc
+++ b/tcg/aarch64/tcg-target.c.inc
@@ -602,6 +602,10 @@ typedef enum {
     DMB_ISH         = 0xd50338bf,
     DMB_LD          = 0x00000100,
     DMB_ST          = 0x00000200,
+
+    BTI_C           = 0xd503245f,
+    BTI_J           = 0xd503249f,
+    BTI_JC          = 0xd50324df,
 } AArch64Insn;
 
 static inline uint32_t tcg_in32(TCGContext *s)
@@ -843,6 +847,17 @@ static void tcg_out_insn_3313(TCGContext *s, AArch64Insn 
insn,
               | rn << 5 | (rd & 0x1f));
 }
 
+static void tcg_out_bti(TCGContext *s, AArch64Insn insn)
+{
+    /*
+     * While BTI insns are nops on hosts without FEAT_BTI,
+     * there is no point in emitting them in that case either.
+     */
+    if (cpuinfo & CPUINFO_BTI) {
+        tcg_out32(s, insn);
+    }
+}
+
 /* Register to register move using ORR (shifted register with no shift). */
 static void tcg_out_movr(TCGContext *s, TCGType ext, TCGReg rd, TCGReg rm)
 {
@@ -1351,18 +1366,6 @@ static void tcg_out_goto(TCGContext *s, const 
tcg_insn_unit *target)
     tcg_out_insn(s, 3206, B, offset);
 }
 
-static void tcg_out_goto_long(TCGContext *s, const tcg_insn_unit *target)
-{
-    ptrdiff_t offset = tcg_pcrel_diff(s, target) >> 2;
-    if (offset == sextract64(offset, 0, 26)) {
-        tcg_out_insn(s, 3206, B, offset);
-    } else {
-        /* Choose X9 as a call-clobbered non-LR temporary. */
-        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X9, (intptr_t)target);
-        tcg_out_insn(s, 3207, BR, TCG_REG_X9);
-    }
-}
-
 static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *target)
 {
     ptrdiff_t offset = tcg_pcrel_diff(s, target) >> 2;
@@ -1947,12 +1950,28 @@ static const tcg_insn_unit *tb_ret_addr;
 
 static void tcg_out_exit_tb(TCGContext *s, uintptr_t a0)
 {
+    const tcg_insn_unit *target;
+    ptrdiff_t offset;
+
     /* Reuse the zeroing that exists for goto_ptr.  */
     if (a0 == 0) {
-        tcg_out_goto_long(s, tcg_code_gen_epilogue);
+        target = tcg_code_gen_epilogue;
     } else {
         tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
-        tcg_out_goto_long(s, tb_ret_addr);
+        target = tb_ret_addr;
+    }
+
+    offset = tcg_pcrel_diff(s, target) >> 2;
+    if (offset == sextract64(offset, 0, 26)) {
+        tcg_out_insn(s, 3206, B, offset);
+    } else {
+        /*
+         * Only x16/x17 generate BTI type Jump (2),
+         * other registers generate BTI type Jump|Call (3).
+         */
+        QEMU_BUILD_BUG_ON(TCG_REG_TMP0 != TCG_REG_X16);
+        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP0, (intptr_t)target);
+        tcg_out_insn(s, 3207, BR, TCG_REG_TMP0);
     }
 }
 
@@ -1970,6 +1989,7 @@ static void tcg_out_goto_tb(TCGContext *s, int which)
     tcg_out32(s, I3206_B);
     tcg_out_insn(s, 3207, BR, TCG_REG_TMP0);
     set_jmp_reset_offset(s, which);
+    tcg_out_bti(s, BTI_J);
 }
 
 void tb_target_set_jmp_target(const TranslationBlock *tb, int n,
@@ -3074,6 +3094,8 @@ static void tcg_target_qemu_prologue(TCGContext *s)
 {
     TCGReg r;
 
+    tcg_out_bti(s, BTI_C);
+
     /* Push (FP, LR) and allocate space for all saved registers.  */
     tcg_out_insn(s, 3314, STP, TCG_REG_FP, TCG_REG_LR,
                  TCG_REG_SP, -PUSH_SIZE, 1, 1);
@@ -3114,10 +3136,12 @@ static void tcg_target_qemu_prologue(TCGContext *s)
      * and fall through to the rest of the epilogue.
      */
     tcg_code_gen_epilogue = tcg_splitwx_to_rx(s->code_ptr);
+    tcg_out_bti(s, BTI_J);
     tcg_out_movi(s, TCG_TYPE_REG, TCG_REG_X0, 0);
 
     /* TB epilogue */
     tb_ret_addr = tcg_splitwx_to_rx(s->code_ptr);
+    tcg_out_bti(s, BTI_J);
 
     /* Remove TCG locals stack space.  */
     tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_SP, TCG_REG_SP,
@@ -3137,7 +3161,7 @@ static void tcg_target_qemu_prologue(TCGContext *s)
 
 static void tcg_out_tb_start(TCGContext *s)
 {
-    /* nothing to do */
+    tcg_out_bti(s, BTI_J);
 }
 
 static void tcg_out_nop_fill(tcg_insn_unit *p, int count)
-- 
2.34.1