@@ -173,15 +173,6 @@
#define MEM_STORE8(VA, DATA, SLOT) \
MEM_STORE8_FUNC(DATA)(cpu_env, VA, DATA, SLOT)
#else
-#define MEM_LOAD1s(VA) ((int8_t)mem_load1(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD1u(VA) ((uint8_t)mem_load1(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD2s(VA) ((int16_t)mem_load2(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD2u(VA) ((uint16_t)mem_load2(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD4s(VA) ((int32_t)mem_load4(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD4u(VA) ((uint32_t)mem_load4(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD8s(VA) ((int64_t)mem_load8(env, pkt_has_store_s1, slot, VA))
-#define MEM_LOAD8u(VA) ((uint64_t)mem_load8(env, pkt_has_store_s1, slot, VA))
-
#define MEM_STORE1(VA, DATA, SLOT) log_store32(env, VA, DATA, 1, SLOT)
#define MEM_STORE2(VA, DATA, SLOT) log_store32(env, VA, DATA, 2, SLOT)
#define MEM_STORE4(VA, DATA, SLOT) log_store32(env, VA, DATA, 4, SLOT)
@@ -530,8 +521,16 @@ static inline TCGv gen_read_ireg(TCGv result, TCGv val, int shift)
#ifdef QEMU_GENERATE
#define fLOAD(NUM, SIZE, SIGN, EA, DST) MEM_LOAD##SIZE##SIGN(DST, EA)
#else
+#define MEM_LOAD1 cpu_ldub_data_ra
+#define MEM_LOAD2 cpu_lduw_data_ra
+#define MEM_LOAD4 cpu_ldl_data_ra
+#define MEM_LOAD8 cpu_ldq_data_ra
+
#define fLOAD(NUM, SIZE, SIGN, EA, DST) \
- DST = (size##SIZE##SIGN##_t)MEM_LOAD##SIZE##SIGN(EA)
+ do { \
+ check_noshuf(env, pkt_has_store_s1, slot, EA, SIZE, GETPC()); \
+ DST = (size##SIZE##SIGN##_t)MEM_LOAD##SIZE(env, EA, GETPC()); \
+ } while (0)
#endif
#define fMEMOP(NUM, SIZE, SIGN, EA, FNTYPE, VALUE)
@@ -19,15 +19,8 @@
#define HEXAGON_OP_HELPER_H
/* Misc functions */
-uint8_t mem_load1(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr);
-uint16_t mem_load2(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr);
-uint32_t mem_load4(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr);
-uint64_t mem_load8(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr);
-
+void check_noshuf(CPUHexagonState *env, bool pkt_has_store_s1,
+ uint32_t slot, target_ulong vaddr, int size, uintptr_t ra);
void log_store64(CPUHexagonState *env, target_ulong addr,
int64_t val, int width, int slot);
void log_store32(CPUHexagonState *env, target_ulong addr,
@@ -95,9 +95,8 @@ void HELPER(debug_check_store_width)(CPUHexagonState *env, int slot, int check)
}
}
-void HELPER(commit_store)(CPUHexagonState *env, int slot_num)
+static inline void commit_store(CPUHexagonState *env, int slot_num, uintptr_t ra)
{
- uintptr_t ra = GETPC();
uint8_t width = env->mem_log_stores[slot_num].width;
target_ulong va = env->mem_log_stores[slot_num].va;
@@ -119,6 +118,12 @@ void HELPER(commit_store)(CPUHexagonState *env, int slot_num)
}
}
+void HELPER(commit_store)(CPUHexagonState *env, int slot_num)
+{
+ uintptr_t ra = GETPC();
+ commit_store(env, slot_num, ra);
+}
+
void HELPER(gather_store)(CPUHexagonState *env, uint32_t addr, int slot)
{
mem_gather_store(env, addr, slot);
@@ -467,13 +472,12 @@ int32_t HELPER(cabacdecbin_pred)(int64_t RssV, int64_t RttV)
}
static void probe_store(CPUHexagonState *env, int slot, int mmu_idx,
- bool is_predicated)
+ bool is_predicated, uintptr_t retaddr)
{
if (!is_predicated || !(env->slot_cancelled & (1 << slot))) {
size1u_t width = env->mem_log_stores[slot].width;
target_ulong va = env->mem_log_stores[slot].va;
- uintptr_t ra = GETPC();
- probe_write(env, va, width, mmu_idx, ra);
+ probe_write(env, va, width, mmu_idx, retaddr);
}
}
@@ -494,12 +498,13 @@ void HELPER(probe_pkt_scalar_store_s0)(CPUHexagonState *env, int args)
int mmu_idx = FIELD_EX32(args, PROBE_PKT_SCALAR_STORE_S0, MMU_IDX);
bool is_predicated =
FIELD_EX32(args, PROBE_PKT_SCALAR_STORE_S0, IS_PREDICATED);
- probe_store(env, 0, mmu_idx, is_predicated);
+ uintptr_t ra = GETPC();
+ probe_store(env, 0, mmu_idx, is_predicated, ra);
}
-void HELPER(probe_hvx_stores)(CPUHexagonState *env, int mmu_idx)
+static inline void probe_hvx_stores(CPUHexagonState *env, int mmu_idx,
+ uintptr_t retaddr)
{
- uintptr_t retaddr = GETPC();
int i;
/* Normal (possibly masked) vector store */
@@ -538,6 +543,12 @@ void HELPER(probe_hvx_stores)(CPUHexagonState *env, int mmu_idx)
}
}
+void HELPER(probe_hvx_stores)(CPUHexagonState *env, int mmu_idx)
+{
+ uintptr_t retaddr = GETPC();
+ probe_hvx_stores(env, mmu_idx, retaddr);
+}
+
void HELPER(probe_pkt_scalar_hvx_stores)(CPUHexagonState *env, int mask)
{
bool has_st0 = FIELD_EX32(mask, PROBE_PKT_SCALAR_HVX_STORES, HAS_ST0);
@@ -547,15 +558,16 @@ void HELPER(probe_pkt_scalar_hvx_stores)(CPUHexagonState *env, int mask)
bool s0_is_pred = FIELD_EX32(mask, PROBE_PKT_SCALAR_HVX_STORES, S0_IS_PRED);
bool s1_is_pred = FIELD_EX32(mask, PROBE_PKT_SCALAR_HVX_STORES, S1_IS_PRED);
int mmu_idx = FIELD_EX32(mask, PROBE_PKT_SCALAR_HVX_STORES, MMU_IDX);
+ uintptr_t ra = GETPC();
if (has_st0) {
- probe_store(env, 0, mmu_idx, s0_is_pred);
+ probe_store(env, 0, mmu_idx, s0_is_pred, ra);
}
if (has_st1) {
- probe_store(env, 1, mmu_idx, s1_is_pred);
+ probe_store(env, 1, mmu_idx, s1_is_pred, ra);
}
if (has_hvx_stores) {
- HELPER(probe_hvx_stores)(env, mmu_idx);
+ probe_hvx_stores(env, mmu_idx, ra);
}
}
@@ -566,48 +578,16 @@ void HELPER(probe_pkt_scalar_hvx_stores)(CPUHexagonState *env, int mask)
* If the load is in slot 0 and there is a store in slot1 (that
* wasn't cancelled), we have to do the store first.
*/
-static void check_noshuf(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr, int size)
+void check_noshuf(CPUHexagonState *env, bool pkt_has_store_s1,
+ uint32_t slot, target_ulong vaddr, int size, uintptr_t ra)
{
if (slot == 0 && pkt_has_store_s1 &&
((env->slot_cancelled & (1 << 1)) == 0)) {
- HELPER(probe_noshuf_load)(env, vaddr, size, MMU_USER_IDX);
- HELPER(commit_store)(env, 1);
+ probe_read(env, vaddr, size, MMU_USER_IDX, ra);
+ commit_store(env, 1, ra);
}
}
-uint8_t mem_load1(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr)
-{
- uintptr_t ra = GETPC();
- check_noshuf(env, pkt_has_store_s1, slot, vaddr, 1);
- return cpu_ldub_data_ra(env, vaddr, ra);
-}
-
-uint16_t mem_load2(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr)
-{
- uintptr_t ra = GETPC();
- check_noshuf(env, pkt_has_store_s1, slot, vaddr, 2);
- return cpu_lduw_data_ra(env, vaddr, ra);
-}
-
-uint32_t mem_load4(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr)
-{
- uintptr_t ra = GETPC();
- check_noshuf(env, pkt_has_store_s1, slot, vaddr, 4);
- return cpu_ldl_data_ra(env, vaddr, ra);
-}
-
-uint64_t mem_load8(CPUHexagonState *env, bool pkt_has_store_s1,
- uint32_t slot, target_ulong vaddr)
-{
- uintptr_t ra = GETPC();
- check_noshuf(env, pkt_has_store_s1, slot, vaddr, 8);
- return cpu_ldq_data_ra(env, vaddr, ra);
-}
-
/* Floating point */
float64 HELPER(conv_sf2df)(CPUHexagonState *env, float32 RsV)
{
As docs/devel/loads-stores.rst states: ``GETPC()`` should be used with great care: calling it in other functions that are *not* the top level ``HELPER(foo)`` will cause unexpected behavior. Instead, the value of ``GETPC()`` should be read from the helper and passed if needed to the functions that the helper calls. Let's fix the GETPC() usage in Hexagon, making sure it's always called from top level helpers and passed down to the places where it's needed. There are a few snippets where that is not currently the case: - probe_store(), which is only called from two helpers, so it's easy to move GETPC() up. - mem_load*() functions, which are also called directly from helpers, but through the MEM_LOAD*() set of macros. Note that this are only used when compiling with --disable-hexagon-idef-parser. In this case, we also take this opportunity to simplify the code, unifying the mem_load*() functions. - HELPER(probe_hvx_stores), when called from another helper, ends up using its own GETPC() expansion instead of the top level caller. Signed-off-by: Matheus Tavares Bernardino <quic_mathbern@quicinc.com> --- v2: https://lore.kernel.org/qemu-devel/93a2ca786530cbc8a94f7c7a6451f4f1f47c8a9b.1688581908.git.quic_mathbern@quicinc.com/ Changes in v3: also included fix for nested helper call in probe_hvx_stores, which I had missed in previous iterations. target/hexagon/macros.h | 19 +++++----- target/hexagon/op_helper.h | 11 ++---- target/hexagon/op_helper.c | 74 ++++++++++++++------------------------ 3 files changed, 38 insertions(+), 66 deletions(-)