Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20160304' into staging

target-arm queue:
 * Correct handling of writes to CPSR from gdbstub in user mode
 * virt: lift maximum RAM limit to 255GB
 * sdhci: implement reset
 * virt: if booting in Secure mode, provide secure-only RAM, make first
   flash device secure-only, and assume the EL3 boot rom will handle PSCI
 * bcm2835: use explicit endianness accessors rather than ldl/stl_phys
 * support big-endian in system mode for ARM
 * implement SETEND instruction
 * arm_gic: implement the GICv2 GICC_DIR register
 * fix SRS bug: only trap from S-EL1 to EL3 if specified mode is Mon

# gpg: Signature made Fri 04 Mar 2016 11:38:53 GMT using RSA key ID 14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"

* remotes/pmaydell/tags/pull-target-arm-20160304: (30 commits)
  target-arm: Only trap SRS from S-EL1 if specified mode is MON
  hw/intc/arm_gic.c: Implement GICv2 GICC_DIR
  arm: boot: Support big-endian elfs
  loader: Add data swap option to load-elf
  loader: load_elf(): Add doc comment
  loader: add API to load elf header
  target-arm: implement BE32 mode in system emulation
  target-arm: implement setend
  target-arm: introduce tbflag for endianness
  target-arm: a64: Add endianness support
  target-arm: introduce disas flag for endianness
  target-arm: pass DisasContext to gen_aa32_ld*/st*
  target-arm: implement SCTLR.EE
  linux-user: arm: handle CPSR.E correctly in strex emulation
  linux-user: arm: set CPSR.E/SCTLR.E0E correctly for BE mode
  arm: cpu: handle BE32 user-mode as BE
  target-arm: cpu: Move cpu_is_big_endian to header
  target-arm: implement SCTLR.B, drop bswap_code
  linux-user: arm: pass env to get_user_code_*
  linux-user: arm: fix coding style for some linux-user signal functions
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 34 insertions, 22 deletions

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 7f65aeab64..f0c73df5b0 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -723,7 +723,7 @@ static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source,
                              TCGv_i64 tcg_addr, int size, int memidx)
 {
     g_assert(size <= 3);
-    tcg_gen_qemu_st_i64(source, tcg_addr, memidx, MO_TE + size);
+    tcg_gen_qemu_st_i64(source, tcg_addr, memidx, s->be_data + size);
 }
 
 static void do_gpr_st(DisasContext *s, TCGv_i64 source,
@@ -738,7 +738,7 @@ static void do_gpr_st(DisasContext *s, TCGv_i64 source,
 static void do_gpr_ld_memidx(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
                              int size, bool is_signed, bool extend, int memidx)
 {
-    TCGMemOp memop = MO_TE + size;
+    TCGMemOp memop = s->be_data + size;
 
     g_assert(size <= 3);
 
@@ -770,13 +770,18 @@ static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
     TCGv_i64 tmp = tcg_temp_new_i64();
     tcg_gen_ld_i64(tmp, cpu_env, fp_reg_offset(s, srcidx, MO_64));
     if (size < 4) {
-        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TE + size);
+        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s),
+                            s->be_data + size);
     } else {
+        bool be = s->be_data == MO_BE;
         TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
-        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TEQ);
-        tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx));
+
         tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
-        tcg_gen_qemu_st_i64(tmp, tcg_hiaddr, get_mem_index(s), MO_TEQ);
+        tcg_gen_qemu_st_i64(tmp, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
+                            s->be_data | MO_Q);
+        tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx));
+        tcg_gen_qemu_st_i64(tmp, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
+                            s->be_data | MO_Q);
         tcg_temp_free_i64(tcg_hiaddr);
     }
 
@@ -793,17 +798,21 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
     TCGv_i64 tmphi;
 
     if (size < 4) {
-        TCGMemOp memop = MO_TE + size;
+        TCGMemOp memop = s->be_data + size;
         tmphi = tcg_const_i64(0);
         tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
     } else {
+        bool be = s->be_data == MO_BE;
         TCGv_i64 tcg_hiaddr;
+
         tmphi = tcg_temp_new_i64();
         tcg_hiaddr = tcg_temp_new_i64();
 
-        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), MO_TEQ);
         tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
-        tcg_gen_qemu_ld_i64(tmphi, tcg_hiaddr, get_mem_index(s), MO_TEQ);
+        tcg_gen_qemu_ld_i64(tmplo, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
+                            s->be_data | MO_Q);
+        tcg_gen_qemu_ld_i64(tmphi, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
+                            s->be_data | MO_Q);
         tcg_temp_free_i64(tcg_hiaddr);
     }
 
@@ -942,7 +951,7 @@ static void clear_vec_high(DisasContext *s, int rd)
 static void do_vec_st(DisasContext *s, int srcidx, int element,
                       TCGv_i64 tcg_addr, int size)
 {
-    TCGMemOp memop = MO_TE + size;
+    TCGMemOp memop = s->be_data + size;
     TCGv_i64 tcg_tmp = tcg_temp_new_i64();
 
     read_vec_element(s, tcg_tmp, srcidx, element, size);
@@ -955,7 +964,7 @@ static void do_vec_st(DisasContext *s, int srcidx, int element,
 static void do_vec_ld(DisasContext *s, int destidx, int element,
                       TCGv_i64 tcg_addr, int size)
 {
-    TCGMemOp memop = MO_TE + size;
+    TCGMemOp memop = s->be_data + size;
     TCGv_i64 tcg_tmp = tcg_temp_new_i64();
 
     tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);
@@ -1702,7 +1711,7 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                                TCGv_i64 addr, int size, bool is_pair)
 {
     TCGv_i64 tmp = tcg_temp_new_i64();
-    TCGMemOp memop = MO_TE + size;
+    TCGMemOp memop = s->be_data + size;
 
     g_assert(size <= 3);
     tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), memop);
@@ -1764,7 +1773,7 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
     tcg_gen_brcond_i64(TCG_COND_NE, addr, cpu_exclusive_addr, fail_label);
 
     tmp = tcg_temp_new_i64();
-    tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), MO_TE + size);
+    tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), s->be_data + size);
     tcg_gen_brcond_i64(TCG_COND_NE, tmp, cpu_exclusive_val, fail_label);
     tcg_temp_free_i64(tmp);
 
@@ -1773,7 +1782,8 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
         TCGv_i64 tmphi = tcg_temp_new_i64();
 
         tcg_gen_addi_i64(addrhi, addr, 1 << size);
-        tcg_gen_qemu_ld_i64(tmphi, addrhi, get_mem_index(s), MO_TE + size);
+        tcg_gen_qemu_ld_i64(tmphi, addrhi, get_mem_index(s),
+                            s->be_data + size);
         tcg_gen_brcond_i64(TCG_COND_NE, tmphi, cpu_exclusive_high, fail_label);
 
         tcg_temp_free_i64(tmphi);
@@ -1781,13 +1791,14 @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
     }
 
     /* We seem to still have the exclusive monitor, so do the store */
-    tcg_gen_qemu_st_i64(cpu_reg(s, rt), addr, get_mem_index(s), MO_TE + size);
+    tcg_gen_qemu_st_i64(cpu_reg(s, rt), addr, get_mem_index(s),
+                        s->be_data + size);
     if (is_pair) {
         TCGv_i64 addrhi = tcg_temp_new_i64();
 
         tcg_gen_addi_i64(addrhi, addr, 1 << size);
         tcg_gen_qemu_st_i64(cpu_reg(s, rt2), addrhi,
-                            get_mem_index(s), MO_TE + size);
+                            get_mem_index(s), s->be_data + size);
         tcg_temp_free_i64(addrhi);
     }
 
@@ -2602,7 +2613,7 @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
             TCGv_i64 tcg_tmp = tcg_temp_new_i64();
 
             tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr,
-                                get_mem_index(s), MO_TE + scale);
+                                get_mem_index(s), s->be_data + scale);
             switch (scale) {
             case 0:
                 mulconst = 0x0101010101010101ULL;
@@ -2632,9 +2643,9 @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
         } else {
             /* Load/store one element per register */
             if (is_load) {
-                do_vec_ld(s, rt, index, tcg_addr, MO_TE + scale);
+                do_vec_ld(s, rt, index, tcg_addr, s->be_data + scale);
             } else {
-                do_vec_st(s, rt, index, tcg_addr, MO_TE + scale);
+                do_vec_st(s, rt, index, tcg_addr, s->be_data + scale);
             }
         }
         tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
@@ -10966,7 +10977,7 @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s)
 {
     uint32_t insn;
 
-    insn = arm_ldl_code(env, s->pc, s->bswap_code);
+    insn = arm_ldl_code(env, s->pc, s->sctlr_b);
     s->insn = insn;
     s->pc += 4;
 
@@ -11031,7 +11042,8 @@ void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb)
     dc->secure_routed_to_el3 = arm_feature(env, ARM_FEATURE_EL3) &&
                                !arm_el_is_aa64(env, 3);
     dc->thumb = 0;
-    dc->bswap_code = 0;
+    dc->sctlr_b = 0;
+    dc->be_data = ARM_TBFLAG_BE_DATA(tb->flags) ? MO_BE : MO_LE;
     dc->condexec_mask = 0;
     dc->condexec_cond = 0;
     dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags);
@@ -11217,7 +11229,7 @@ done_generating:
         qemu_log("----------------\n");
         qemu_log("IN: %s\n", lookup_symbol(pc_start));
         log_target_disas(cs, pc_start, dc->pc - pc_start,
-                         4 | (dc->bswap_code << 1));
+                         4 | (bswap_code(dc->sctlr_b) ? 2 : 0));
         qemu_log("\n");
     }
 #endif