* [PATCH v8 1/6] plugins: save value during memory accesses
2024-09-10 17:20 [PATCH v8 0/6] plugins: access values during a memory read/write Pierrick Bouvier
@ 2024-09-10 17:20 ` Pierrick Bouvier
2024-09-10 17:20 ` [PATCH v8 2/6] plugins: extend API to get latest memory value accessed Pierrick Bouvier
` (4 subsequent siblings)
5 siblings, 0 replies; 9+ messages in thread
From: Pierrick Bouvier @ 2024-09-10 17:20 UTC (permalink / raw)
To: qemu-devel
Cc: Nicholas Piggin, Daniel Henrique Barboza, Alexandre Iooss,
Philippe Mathieu-Daudé, Alex Bennée, Eduardo Habkost,
Richard Henderson, Pierrick Bouvier, Paolo Bonzini,
Marcel Apfelbaum, Yanan Wang, Mahmoud Mandour, qemu-ppc, Zhao Liu
Different code paths handle memory accesses:
- tcg generated code
- load/store helpers
- atomic helpers
This value is saved in cpu->neg.plugin_mem_value_{high,low}. Values are
written only for accessed word size (upper bits are not set).
Atomic operations are doing read/write at the same time, so we generate
two memory callbacks instead of one, to allow plugins to access distinct
values.
For now, we can have access only up to 128 bits, thus split this in two
64 bits words. When QEMU will support wider operations, we'll be able to
reconsider this.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
---
accel/tcg/atomic_template.h | 66 ++++++++++++++++++++++++++++++-----
include/hw/core/cpu.h | 4 +++
include/qemu/plugin.h | 4 +++
plugins/core.c | 6 ++++
tcg/tcg-op-ldst.c | 66 +++++++++++++++++++++++++++++++----
accel/tcg/atomic_common.c.inc | 13 ++++++-
accel/tcg/ldst_common.c.inc | 38 ++++++++++++--------
7 files changed, 167 insertions(+), 30 deletions(-)
diff --git a/accel/tcg/atomic_template.h b/accel/tcg/atomic_template.h
index 1dc2151dafd..89593b2502f 100644
--- a/accel/tcg/atomic_template.h
+++ b/accel/tcg/atomic_template.h
@@ -53,6 +53,14 @@
# error unsupported data size
#endif
+#if DATA_SIZE == 16
+# define VALUE_LOW(val) int128_getlo(val)
+# define VALUE_HIGH(val) int128_gethi(val)
+#else
+# define VALUE_LOW(val) val
+# define VALUE_HIGH(val) 0
+#endif
+
#if DATA_SIZE >= 4
# define ABI_TYPE DATA_TYPE
#else
@@ -83,7 +91,12 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
ret = qatomic_cmpxchg__nocheck(haddr, cmpv, newv);
#endif
ATOMIC_MMU_CLEANUP;
- atomic_trace_rmw_post(env, addr, oi);
+ atomic_trace_rmw_post(env, addr,
+ VALUE_LOW(ret),
+ VALUE_HIGH(ret),
+ VALUE_LOW(newv),
+ VALUE_HIGH(newv),
+ oi);
return ret;
}
@@ -97,7 +110,12 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
ret = qatomic_xchg__nocheck(haddr, val);
ATOMIC_MMU_CLEANUP;
- atomic_trace_rmw_post(env, addr, oi);
+ atomic_trace_rmw_post(env, addr,
+ VALUE_LOW(ret),
+ VALUE_HIGH(ret),
+ VALUE_LOW(val),
+ VALUE_HIGH(val),
+ oi);
return ret;
}
@@ -109,7 +127,12 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
haddr = atomic_mmu_lookup(env_cpu(env), addr, oi, DATA_SIZE, retaddr); \
ret = qatomic_##X(haddr, val); \
ATOMIC_MMU_CLEANUP; \
- atomic_trace_rmw_post(env, addr, oi); \
+ atomic_trace_rmw_post(env, addr, \
+ VALUE_LOW(ret), \
+ VALUE_HIGH(ret), \
+ VALUE_LOW(val), \
+ VALUE_HIGH(val), \
+ oi); \
return ret; \
}
@@ -145,7 +168,12 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
cmp = qatomic_cmpxchg__nocheck(haddr, old, new); \
} while (cmp != old); \
ATOMIC_MMU_CLEANUP; \
- atomic_trace_rmw_post(env, addr, oi); \
+ atomic_trace_rmw_post(env, addr, \
+ VALUE_LOW(old), \
+ VALUE_HIGH(old), \
+ VALUE_LOW(xval), \
+ VALUE_HIGH(xval), \
+ oi); \
return RET; \
}
@@ -188,7 +216,12 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, abi_ptr addr,
ret = qatomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv));
#endif
ATOMIC_MMU_CLEANUP;
- atomic_trace_rmw_post(env, addr, oi);
+ atomic_trace_rmw_post(env, addr,
+ VALUE_LOW(ret),
+ VALUE_HIGH(ret),
+ VALUE_LOW(newv),
+ VALUE_HIGH(newv),
+ oi);
return BSWAP(ret);
}
@@ -202,7 +235,12 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, abi_ptr addr, ABI_TYPE val,
ret = qatomic_xchg__nocheck(haddr, BSWAP(val));
ATOMIC_MMU_CLEANUP;
- atomic_trace_rmw_post(env, addr, oi);
+ atomic_trace_rmw_post(env, addr,
+ VALUE_LOW(ret),
+ VALUE_HIGH(ret),
+ VALUE_LOW(val),
+ VALUE_HIGH(val),
+ oi);
return BSWAP(ret);
}
@@ -214,7 +252,12 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
haddr = atomic_mmu_lookup(env_cpu(env), addr, oi, DATA_SIZE, retaddr); \
ret = qatomic_##X(haddr, BSWAP(val)); \
ATOMIC_MMU_CLEANUP; \
- atomic_trace_rmw_post(env, addr, oi); \
+ atomic_trace_rmw_post(env, addr, \
+ VALUE_LOW(ret), \
+ VALUE_HIGH(ret), \
+ VALUE_LOW(val), \
+ VALUE_HIGH(val), \
+ oi); \
return BSWAP(ret); \
}
@@ -247,7 +290,12 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, abi_ptr addr, \
ldn = qatomic_cmpxchg__nocheck(haddr, ldo, BSWAP(new)); \
} while (ldo != ldn); \
ATOMIC_MMU_CLEANUP; \
- atomic_trace_rmw_post(env, addr, oi); \
+ atomic_trace_rmw_post(env, addr, \
+ VALUE_LOW(old), \
+ VALUE_HIGH(old), \
+ VALUE_LOW(xval), \
+ VALUE_HIGH(xval), \
+ oi); \
return RET; \
}
@@ -281,3 +329,5 @@ GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new)
#undef SUFFIX
#undef DATA_SIZE
#undef SHIFT
+#undef VALUE_LOW
+#undef VALUE_HIGH
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index 1c9c775df65..04e9ad49968 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -350,6 +350,8 @@ typedef union IcountDecr {
* from CPUArchState, via small negative offsets.
* @can_do_io: True if memory-mapped IO is allowed.
* @plugin_mem_cbs: active plugin memory callbacks
+ * @plugin_mem_value_low: 64 lower bits of latest accessed mem value.
+ * @plugin_mem_value_high: 64 higher bits of latest accessed mem value.
*/
typedef struct CPUNegativeOffsetState {
CPUTLB tlb;
@@ -358,6 +360,8 @@ typedef struct CPUNegativeOffsetState {
* The callback pointer are accessed via TCG (see gen_empty_mem_helper).
*/
GArray *plugin_mem_cbs;
+ uint64_t plugin_mem_value_low;
+ uint64_t plugin_mem_value_high;
#endif
IcountDecr icount_decr;
bool can_do_io;
diff --git a/include/qemu/plugin.h b/include/qemu/plugin.h
index af5f9db4692..9726a9ebf36 100644
--- a/include/qemu/plugin.h
+++ b/include/qemu/plugin.h
@@ -167,6 +167,8 @@ qemu_plugin_vcpu_syscall(CPUState *cpu, int64_t num, uint64_t a1,
void qemu_plugin_vcpu_syscall_ret(CPUState *cpu, int64_t num, int64_t ret);
void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr,
+ uint64_t value_low,
+ uint64_t value_high,
MemOpIdx oi, enum qemu_plugin_mem_rw rw);
void qemu_plugin_flush_cb(void);
@@ -251,6 +253,8 @@ void qemu_plugin_vcpu_syscall_ret(CPUState *cpu, int64_t num, int64_t ret)
{ }
static inline void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr,
+ uint64_t value_low,
+ uint64_t value_high,
MemOpIdx oi,
enum qemu_plugin_mem_rw rw)
{ }
diff --git a/plugins/core.c b/plugins/core.c
index 2897453cacb..bb105e8e688 100644
--- a/plugins/core.c
+++ b/plugins/core.c
@@ -602,6 +602,8 @@ void exec_inline_op(enum plugin_dyn_cb_type type,
}
void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr,
+ uint64_t value_low,
+ uint64_t value_high,
MemOpIdx oi, enum qemu_plugin_mem_rw rw)
{
GArray *arr = cpu->neg.plugin_mem_cbs;
@@ -610,6 +612,10 @@ void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr,
if (arr == NULL) {
return;
}
+
+ cpu->neg.plugin_mem_value_low = value_low;
+ cpu->neg.plugin_mem_value_high = value_high;
+
for (i = 0; i < arr->len; i++) {
struct qemu_plugin_dyn_cb *cb =
&g_array_index(arr, struct qemu_plugin_dyn_cb, i);
diff --git a/tcg/tcg-op-ldst.c b/tcg/tcg-op-ldst.c
index 85101602581..23dc807f119 100644
--- a/tcg/tcg-op-ldst.c
+++ b/tcg/tcg-op-ldst.c
@@ -148,11 +148,11 @@ static TCGv_i64 plugin_maybe_preserve_addr(TCGTemp *addr)
return NULL;
}
+#ifdef CONFIG_PLUGIN
static void
plugin_gen_mem_callbacks(TCGv_i64 copy_addr, TCGTemp *orig_addr, MemOpIdx oi,
enum qemu_plugin_mem_rw rw)
{
-#ifdef CONFIG_PLUGIN
if (tcg_ctx->plugin_insn != NULL) {
qemu_plugin_meminfo_t info = make_plugin_meminfo(oi, rw);
@@ -172,6 +172,54 @@ plugin_gen_mem_callbacks(TCGv_i64 copy_addr, TCGTemp *orig_addr, MemOpIdx oi,
}
}
}
+}
+#endif
+
+static void
+plugin_gen_mem_callbacks_i32(TCGv_i32 val,
+ TCGv_i64 copy_addr, TCGTemp *orig_addr,
+ MemOpIdx oi, enum qemu_plugin_mem_rw rw)
+{
+#ifdef CONFIG_PLUGIN
+ if (tcg_ctx->plugin_insn != NULL) {
+ tcg_gen_st_i32(val, tcg_env,
+ offsetof(CPUState, neg.plugin_mem_value_low) -
+ sizeof(CPUState) + (HOST_BIG_ENDIAN * 4));
+ plugin_gen_mem_callbacks(copy_addr, orig_addr, oi, rw);
+ }
+#endif
+}
+
+static void
+plugin_gen_mem_callbacks_i64(TCGv_i64 val,
+ TCGv_i64 copy_addr, TCGTemp *orig_addr,
+ MemOpIdx oi, enum qemu_plugin_mem_rw rw)
+{
+#ifdef CONFIG_PLUGIN
+ if (tcg_ctx->plugin_insn != NULL) {
+ tcg_gen_st_i64(val, tcg_env,
+ offsetof(CPUState, neg.plugin_mem_value_low) -
+ sizeof(CPUState));
+ plugin_gen_mem_callbacks(copy_addr, orig_addr, oi, rw);
+ }
+#endif
+}
+
+static void
+plugin_gen_mem_callbacks_i128(TCGv_i128 val,
+ TCGv_i64 copy_addr, TCGTemp *orig_addr,
+ MemOpIdx oi, enum qemu_plugin_mem_rw rw)
+{
+#ifdef CONFIG_PLUGIN
+ if (tcg_ctx->plugin_insn != NULL) {
+ tcg_gen_st_i64(TCGV128_LOW(val), tcg_env,
+ offsetof(CPUState, neg.plugin_mem_value_low) -
+ sizeof(CPUState));
+ tcg_gen_st_i64(TCGV128_HIGH(val), tcg_env,
+ offsetof(CPUState, neg.plugin_mem_value_high) -
+ sizeof(CPUState));
+ plugin_gen_mem_callbacks(copy_addr, orig_addr, oi, rw);
+ }
#endif
}
@@ -203,7 +251,8 @@ static void tcg_gen_qemu_ld_i32_int(TCGv_i32 val, TCGTemp *addr,
opc = INDEX_op_qemu_ld_a64_i32;
}
gen_ldst(opc, tcgv_i32_temp(val), NULL, addr, oi);
- plugin_gen_mem_callbacks(copy_addr, addr, orig_oi, QEMU_PLUGIN_MEM_R);
+ plugin_gen_mem_callbacks_i32(val, copy_addr, addr, orig_oi,
+ QEMU_PLUGIN_MEM_R);
if ((orig_memop ^ memop) & MO_BSWAP) {
switch (orig_memop & MO_SIZE) {
@@ -271,7 +320,7 @@ static void tcg_gen_qemu_st_i32_int(TCGv_i32 val, TCGTemp *addr,
}
}
gen_ldst(opc, tcgv_i32_temp(val), NULL, addr, oi);
- plugin_gen_mem_callbacks(NULL, addr, orig_oi, QEMU_PLUGIN_MEM_W);
+ plugin_gen_mem_callbacks_i32(val, NULL, addr, orig_oi, QEMU_PLUGIN_MEM_W);
if (swap) {
tcg_temp_free_i32(swap);
@@ -324,7 +373,8 @@ static void tcg_gen_qemu_ld_i64_int(TCGv_i64 val, TCGTemp *addr,
opc = INDEX_op_qemu_ld_a64_i64;
}
gen_ldst_i64(opc, val, addr, oi);
- plugin_gen_mem_callbacks(copy_addr, addr, orig_oi, QEMU_PLUGIN_MEM_R);
+ plugin_gen_mem_callbacks_i64(val, copy_addr, addr, orig_oi,
+ QEMU_PLUGIN_MEM_R);
if ((orig_memop ^ memop) & MO_BSWAP) {
int flags = (orig_memop & MO_SIGN
@@ -396,7 +446,7 @@ static void tcg_gen_qemu_st_i64_int(TCGv_i64 val, TCGTemp *addr,
opc = INDEX_op_qemu_st_a64_i64;
}
gen_ldst_i64(opc, val, addr, oi);
- plugin_gen_mem_callbacks(NULL, addr, orig_oi, QEMU_PLUGIN_MEM_W);
+ plugin_gen_mem_callbacks_i64(val, NULL, addr, orig_oi, QEMU_PLUGIN_MEM_W);
if (swap) {
tcg_temp_free_i64(swap);
@@ -606,7 +656,8 @@ static void tcg_gen_qemu_ld_i128_int(TCGv_i128 val, TCGTemp *addr,
tcg_constant_i32(orig_oi));
}
- plugin_gen_mem_callbacks(ext_addr, addr, orig_oi, QEMU_PLUGIN_MEM_R);
+ plugin_gen_mem_callbacks_i128(val, ext_addr, addr, orig_oi,
+ QEMU_PLUGIN_MEM_R);
}
void tcg_gen_qemu_ld_i128_chk(TCGv_i128 val, TCGTemp *addr, TCGArg idx,
@@ -722,7 +773,8 @@ static void tcg_gen_qemu_st_i128_int(TCGv_i128 val, TCGTemp *addr,
tcg_constant_i32(orig_oi));
}
- plugin_gen_mem_callbacks(ext_addr, addr, orig_oi, QEMU_PLUGIN_MEM_W);
+ plugin_gen_mem_callbacks_i128(val, ext_addr, addr, orig_oi,
+ QEMU_PLUGIN_MEM_W);
}
void tcg_gen_qemu_st_i128_chk(TCGv_i128 val, TCGTemp *addr, TCGArg idx,
diff --git a/accel/tcg/atomic_common.c.inc b/accel/tcg/atomic_common.c.inc
index 95a5c5ff12d..6056598c23d 100644
--- a/accel/tcg/atomic_common.c.inc
+++ b/accel/tcg/atomic_common.c.inc
@@ -14,9 +14,20 @@
*/
static void atomic_trace_rmw_post(CPUArchState *env, uint64_t addr,
+ uint64_t read_value_low,
+ uint64_t read_value_high,
+ uint64_t write_value_low,
+ uint64_t write_value_high,
MemOpIdx oi)
{
- qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_RW);
+ if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
+ qemu_plugin_vcpu_mem_cb(env_cpu(env), addr,
+ read_value_low, read_value_high,
+ oi, QEMU_PLUGIN_MEM_R);
+ qemu_plugin_vcpu_mem_cb(env_cpu(env), addr,
+ write_value_low, write_value_high,
+ oi, QEMU_PLUGIN_MEM_W);
+ }
}
/*
diff --git a/accel/tcg/ldst_common.c.inc b/accel/tcg/ldst_common.c.inc
index 87ceb954873..ebbf380d767 100644
--- a/accel/tcg/ldst_common.c.inc
+++ b/accel/tcg/ldst_common.c.inc
@@ -123,10 +123,15 @@ void helper_st_i128(CPUArchState *env, uint64_t addr, Int128 val, MemOpIdx oi)
* Load helpers for cpu_ldst.h
*/
-static void plugin_load_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
+static void plugin_load_cb(CPUArchState *env, abi_ptr addr,
+ uint64_t value_low,
+ uint64_t value_high,
+ MemOpIdx oi)
{
if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
- qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_R);
+ qemu_plugin_vcpu_mem_cb(env_cpu(env), addr,
+ value_low, value_high,
+ oi, QEMU_PLUGIN_MEM_R);
}
}
@@ -136,7 +141,7 @@ uint8_t cpu_ldb_mmu(CPUArchState *env, abi_ptr addr, MemOpIdx oi, uintptr_t ra)
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_UB);
ret = do_ld1_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
- plugin_load_cb(env, addr, oi);
+ plugin_load_cb(env, addr, ret, 0, oi);
return ret;
}
@@ -147,7 +152,7 @@ uint16_t cpu_ldw_mmu(CPUArchState *env, abi_ptr addr,
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
ret = do_ld2_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
- plugin_load_cb(env, addr, oi);
+ plugin_load_cb(env, addr, ret, 0, oi);
return ret;
}
@@ -158,7 +163,7 @@ uint32_t cpu_ldl_mmu(CPUArchState *env, abi_ptr addr,
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
ret = do_ld4_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
- plugin_load_cb(env, addr, oi);
+ plugin_load_cb(env, addr, ret, 0, oi);
return ret;
}
@@ -169,7 +174,7 @@ uint64_t cpu_ldq_mmu(CPUArchState *env, abi_ptr addr,
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
ret = do_ld8_mmu(env_cpu(env), addr, oi, ra, MMU_DATA_LOAD);
- plugin_load_cb(env, addr, oi);
+ plugin_load_cb(env, addr, ret, 0, oi);
return ret;
}
@@ -180,7 +185,7 @@ Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
ret = do_ld16_mmu(env_cpu(env), addr, oi, ra);
- plugin_load_cb(env, addr, oi);
+ plugin_load_cb(env, addr, int128_getlo(ret), int128_gethi(ret), oi);
return ret;
}
@@ -188,10 +193,15 @@ Int128 cpu_ld16_mmu(CPUArchState *env, abi_ptr addr,
* Store helpers for cpu_ldst.h
*/
-static void plugin_store_cb(CPUArchState *env, abi_ptr addr, MemOpIdx oi)
+static void plugin_store_cb(CPUArchState *env, abi_ptr addr,
+ uint64_t value_low,
+ uint64_t value_high,
+ MemOpIdx oi)
{
if (cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
- qemu_plugin_vcpu_mem_cb(env_cpu(env), addr, oi, QEMU_PLUGIN_MEM_W);
+ qemu_plugin_vcpu_mem_cb(env_cpu(env), addr,
+ value_low, value_high,
+ oi, QEMU_PLUGIN_MEM_W);
}
}
@@ -199,7 +209,7 @@ void cpu_stb_mmu(CPUArchState *env, abi_ptr addr, uint8_t val,
MemOpIdx oi, uintptr_t retaddr)
{
helper_stb_mmu(env, addr, val, oi, retaddr);
- plugin_store_cb(env, addr, oi);
+ plugin_store_cb(env, addr, val, 0, oi);
}
void cpu_stw_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
@@ -207,7 +217,7 @@ void cpu_stw_mmu(CPUArchState *env, abi_ptr addr, uint16_t val,
{
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_16);
do_st2_mmu(env_cpu(env), addr, val, oi, retaddr);
- plugin_store_cb(env, addr, oi);
+ plugin_store_cb(env, addr, val, 0, oi);
}
void cpu_stl_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
@@ -215,7 +225,7 @@ void cpu_stl_mmu(CPUArchState *env, abi_ptr addr, uint32_t val,
{
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_32);
do_st4_mmu(env_cpu(env), addr, val, oi, retaddr);
- plugin_store_cb(env, addr, oi);
+ plugin_store_cb(env, addr, val, 0, oi);
}
void cpu_stq_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
@@ -223,7 +233,7 @@ void cpu_stq_mmu(CPUArchState *env, abi_ptr addr, uint64_t val,
{
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_64);
do_st8_mmu(env_cpu(env), addr, val, oi, retaddr);
- plugin_store_cb(env, addr, oi);
+ plugin_store_cb(env, addr, val, 0, oi);
}
void cpu_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val,
@@ -231,7 +241,7 @@ void cpu_st16_mmu(CPUArchState *env, abi_ptr addr, Int128 val,
{
tcg_debug_assert((get_memop(oi) & MO_SIZE) == MO_128);
do_st16_mmu(env_cpu(env), addr, val, oi, retaddr);
- plugin_store_cb(env, addr, oi);
+ plugin_store_cb(env, addr, int128_getlo(val), int128_gethi(val), oi);
}
/*
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCH v8 6/6] tests/tcg/multiarch: add test for plugin memory access
2024-09-10 17:20 [PATCH v8 0/6] plugins: access values during a memory read/write Pierrick Bouvier
` (4 preceding siblings ...)
2024-09-10 17:20 ` [PATCH v8 5/6] tests/tcg/plugins/mem: add option to print memory accesses Pierrick Bouvier
@ 2024-09-10 17:20 ` Pierrick Bouvier
2024-09-11 17:13 ` Alex Bennée
5 siblings, 1 reply; 9+ messages in thread
From: Pierrick Bouvier @ 2024-09-10 17:20 UTC (permalink / raw)
To: qemu-devel
Cc: Nicholas Piggin, Daniel Henrique Barboza, Alexandre Iooss,
Philippe Mathieu-Daudé, Alex Bennée, Eduardo Habkost,
Richard Henderson, Pierrick Bouvier, Paolo Bonzini,
Marcel Apfelbaum, Yanan Wang, Mahmoud Mandour, qemu-ppc, Zhao Liu,
Xingtao Yao
Add an explicit test to check expected memory values are read/written.
8,16,32 load/store are tested for all arch.
64,128 load/store are tested for aarch64/x64.
atomic operations (8,16,32,64) are tested for x64 only.
By default, atomic accesses are non atomic if a single cpu is running,
so we force creation of a second one by creating a new thread first.
load/store helpers code path can't be triggered easily in user mode (no
softmmu), so we can't test it here.
Output of test-plugin-mem-access.c is the list of expected patterns in
plugin output. By reading stdout, we can compare to plugins output and
have a multiarch test.
Can be run with:
make -C build/tests/tcg/$ARCH-linux-user run-plugin-test-plugin-mem-access-with-libmem.so
Tested-by: Xingtao Yao <yaoxt.fnst@fujitsu.com>
Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
---
tests/tcg/multiarch/test-plugin-mem-access.c | 177 +++++++++++++++++++
tests/tcg/alpha/Makefile.target | 3 +
tests/tcg/multiarch/Makefile.target | 11 ++
tests/tcg/multiarch/check-plugin-output.sh | 36 ++++
tests/tcg/ppc64/Makefile.target | 5 +
5 files changed, 232 insertions(+)
create mode 100644 tests/tcg/multiarch/test-plugin-mem-access.c
create mode 100755 tests/tcg/multiarch/check-plugin-output.sh
diff --git a/tests/tcg/multiarch/test-plugin-mem-access.c b/tests/tcg/multiarch/test-plugin-mem-access.c
new file mode 100644
index 00000000000..057b9aac9f6
--- /dev/null
+++ b/tests/tcg/multiarch/test-plugin-mem-access.c
@@ -0,0 +1,177 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ *
+ * Check if we detect all memory accesses expected using plugin API.
+ * Used in conjunction with ./check-plugin-mem-access.sh check script.
+ * Output of this program is the list of patterns expected in plugin output.
+ *
+ * 8,16,32 load/store are tested for all arch.
+ * 64,128 load/store are tested for aarch64/x64.
+ * atomic operations (8,16,32,64) are tested for x64 only.
+ */
+
+#include <pthread.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#if defined(__x86_64__)
+#include <emmintrin.h>
+#elif defined(__aarch64__)
+#include <arm_neon.h>
+#endif /* __x86_64__ */
+
+static void *data;
+
+/* ,store_u8,.*,8,store,0xf1 */
+#define PRINT_EXPECTED(function, type, value, action) \
+do { \
+ printf(",%s,.*,%d,%s,%s\n", \
+ #function, (int) sizeof(type) * 8, action, value); \
+} \
+while (0)
+
+#define DEFINE_STORE(name, type, value) \
+ \
+static void print_expected_store_##name(void) \
+{ \
+ PRINT_EXPECTED(store_##name, type, #value, "store"); \
+} \
+ \
+static void store_##name(void) \
+{ \
+ *((type *)data) = value; \
+ print_expected_store_##name(); \
+}
+
+#define DEFINE_ATOMIC_OP(name, type, value) \
+ \
+static void print_expected_atomic_op_##name(void) \
+{ \
+ PRINT_EXPECTED(atomic_op_##name, type, "0x0*42", "load"); \
+ PRINT_EXPECTED(atomic_op_##name, type, #value, "store"); \
+} \
+ \
+static void atomic_op_##name(void) \
+{ \
+ *((type *)data) = 0x42; \
+ __sync_val_compare_and_swap((type *)data, 0x42, value); \
+ print_expected_atomic_op_##name(); \
+}
+
+#define DEFINE_LOAD(name, type, value) \
+ \
+static void print_expected_load_##name(void) \
+{ \
+ PRINT_EXPECTED(load_##name, type, #value, "load"); \
+} \
+ \
+static void load_##name(void) \
+{ \
+ \
+ /* volatile forces load to be generated. */ \
+ volatile type src = *((type *) data); \
+ volatile type dest = src; \
+ (void)src, (void)dest; \
+ print_expected_load_##name(); \
+}
+
+DEFINE_STORE(u8, uint8_t, 0xf1)
+DEFINE_LOAD(u8, uint8_t, 0xf1)
+DEFINE_STORE(u16, uint16_t, 0xf123)
+DEFINE_LOAD(u16, uint16_t, 0xf123)
+DEFINE_STORE(u32, uint32_t, 0xff112233)
+DEFINE_LOAD(u32, uint32_t, 0xff112233)
+
+#if defined(__x86_64__) || defined(__aarch64__)
+DEFINE_STORE(u64, uint64_t, 0xf123456789abcdef)
+DEFINE_LOAD(u64, uint64_t, 0xf123456789abcdef)
+
+static void print_expected_store_u128(void)
+{
+ PRINT_EXPECTED(store_u128, __int128,
+ "0xf122334455667788f123456789abcdef", "store");
+}
+
+static void store_u128(void)
+{
+#ifdef __x86_64__
+ _mm_store_si128(data, _mm_set_epi32(0xf1223344, 0x55667788,
+ 0xf1234567, 0x89abcdef));
+#else
+ const uint32_t init[4] = {0x89abcdef, 0xf1234567, 0x55667788, 0xf1223344};
+ uint32x4_t vec = vld1q_u32(init);
+ vst1q_u32(data, vec);
+#endif /* __x86_64__ */
+ print_expected_store_u128();
+}
+
+static void print_expected_load_u128(void)
+{
+ PRINT_EXPECTED(load_u128, __int128,
+ "0xf122334455667788f123456789abcdef", "load");
+}
+
+static void load_u128(void)
+{
+#ifdef __x86_64__
+ __m128i var = _mm_load_si128(data);
+#else
+ uint32x4_t var = vld1q_u32(data);
+#endif
+ (void) var;
+ print_expected_load_u128();
+}
+#endif /* __x86_64__ || __aarch64__ */
+
+#if defined(__x86_64__)
+DEFINE_ATOMIC_OP(u8, uint8_t, 0xf1)
+DEFINE_ATOMIC_OP(u16, uint16_t, 0xf123)
+DEFINE_ATOMIC_OP(u32, uint32_t, 0xff112233)
+DEFINE_ATOMIC_OP(u64, uint64_t, 0xf123456789abcdef)
+#endif /* __x86_64__ */
+
+static void *f(void *p)
+{
+ return NULL;
+}
+
+int main(void)
+{
+ /*
+ * We force creation of a second thread to enable cpu flag CF_PARALLEL.
+ * This will generate atomic operations when needed.
+ */
+ pthread_t thread;
+ pthread_create(&thread, NULL, &f, NULL);
+ pthread_join(thread, NULL);
+
+ /* allocate storage up to 128 bits */
+ data = malloc(16);
+
+ store_u8();
+ load_u8();
+
+ store_u16();
+ load_u16();
+
+ store_u32();
+ load_u32();
+
+#if defined(__x86_64__) || defined(__aarch64__)
+ store_u64();
+ load_u64();
+
+ store_u128();
+ load_u128();
+#endif /* __x86_64__ || __aarch64__ */
+
+#if defined(__x86_64__)
+ atomic_op_u8();
+ atomic_op_u16();
+ atomic_op_u32();
+ atomic_op_u64();
+#endif /* __x86_64__ */
+
+ free(data);
+}
diff --git a/tests/tcg/alpha/Makefile.target b/tests/tcg/alpha/Makefile.target
index fdd7ddf64ec..36d8ed1eaea 100644
--- a/tests/tcg/alpha/Makefile.target
+++ b/tests/tcg/alpha/Makefile.target
@@ -12,4 +12,7 @@ test-cmov: EXTRA_CFLAGS=-DTEST_CMOV
test-cmov: test-cond.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+# Force generation of byte read/write
+test-plugin-mem-access: CFLAGS+=-mbwx
+
run-test-cmov: test-cmov
diff --git a/tests/tcg/multiarch/Makefile.target b/tests/tcg/multiarch/Makefile.target
index 5e3391ec9d2..78b83d5575a 100644
--- a/tests/tcg/multiarch/Makefile.target
+++ b/tests/tcg/multiarch/Makefile.target
@@ -170,5 +170,16 @@ run-plugin-semiconsole-with-%:
TESTS += semihosting semiconsole
endif
+# Test plugin memory access instrumentation
+run-plugin-test-plugin-mem-access-with-libmem.so: \
+ PLUGIN_ARGS=$(COMMA)print-accesses=true
+run-plugin-test-plugin-mem-access-with-libmem.so: \
+ CHECK_PLUGIN_OUTPUT_COMMAND= \
+ $(SRC_PATH)/tests/tcg/multiarch/check-plugin-output.sh \
+ $(QEMU) $<
+
+test-plugin-mem-access: CFLAGS+=-pthread -O0
+test-plugin-mem-access: LDFLAGS+=-pthread -O0
+
# Update TESTS
TESTS += $(MULTIARCH_TESTS)
diff --git a/tests/tcg/multiarch/check-plugin-output.sh b/tests/tcg/multiarch/check-plugin-output.sh
new file mode 100755
index 00000000000..80607f04b5d
--- /dev/null
+++ b/tests/tcg/multiarch/check-plugin-output.sh
@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+
+# This script runs a given executable using qemu, and compare its standard
+# output with an expected plugin output.
+# Each line of output is searched (as a regexp) in the expected plugin output.
+
+set -euo pipefail
+
+die()
+{
+ echo "$@" 1>&2
+ exit 1
+}
+
+check()
+{
+ file=$1
+ pattern=$2
+ grep "$pattern" "$file" > /dev/null || die "\"$pattern\" not found in $file"
+}
+
+[ $# -eq 3 ] || die "usage: qemu_bin exe plugin_out_file"
+
+qemu_bin=$1; shift
+exe=$1;shift
+plugin_out=$1; shift
+
+expected()
+{
+ $qemu_bin $exe ||
+ die "running $exe failed"
+}
+
+expected | while read line; do
+ check "$plugin_out" "$line"
+done
diff --git a/tests/tcg/ppc64/Makefile.target b/tests/tcg/ppc64/Makefile.target
index 509a20be2b0..1940886c737 100644
--- a/tests/tcg/ppc64/Makefile.target
+++ b/tests/tcg/ppc64/Makefile.target
@@ -55,4 +55,9 @@ PPC64_TESTS += signal_save_restore_xer
PPC64_TESTS += xxspltw
PPC64_TESTS += test-aes
+# ppc64 ABI uses function descriptors, and thus, QEMU can't find symbol for a
+# given instruction. Thus, we don't check output of mem-access plugin.
+run-plugin-test-plugin-mem-access-with-libmem.so: \
+ CHECK_PLUGIN_OUTPUT_COMMAND=
+
TESTS += $(PPC64_TESTS)
--
2.39.2
^ permalink raw reply related [flat|nested] 9+ messages in thread