@@ -301,7 +301,7 @@ CPUArchState *cpu_copy(CPUArchState *env);
* be signaled by probe_access_flags().
*/
#define TLB_INVALID_MASK (1 << (TARGET_PAGE_BITS_MIN - 1))
-#define TLB_MMIO 0
+#define TLB_MMIO (1 << (TARGET_PAGE_BITS_MIN - 2))
#define TLB_WATCHPOINT 0
#else
@@ -983,6 +983,23 @@ void cpu_watchpoint_remove_by_ref(CPUState *cpu, CPUWatchpoint *watchpoint);
void cpu_watchpoint_remove_all(CPUState *cpu, int mask);
#endif
+/**
+ * cpu_plugin_mem_cbs_enabled() - are plugin memory callbacks enabled?
+ * @cs: CPUState pointer
+ *
+ * The memory callbacks are installed if a plugin has instrumented an
+ * instruction for memory. This can be useful to know if you want to
+ * force a slow path for a series of memory accesses.
+ */
+static inline bool cpu_plugin_mem_cbs_enabled(const CPUState *cpu)
+{
+#ifdef CONFIG_PLUGIN
+ return !!cpu->plugin_mem_cbs;
+#else
+ return false;
+#endif
+}
+
/**
* cpu_get_address_space:
* @cpu: CPU to get address space from
@@ -1540,7 +1540,9 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr,
*pfull = &env_tlb(env)->d[mmu_idx].fulltlb[index];
/* Fold all "mmio-like" bits into TLB_MMIO. This is not RAM. */
- if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))) {
+ if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY))
+ ||
+ (access_type != MMU_INST_FETCH && cpu_plugin_mem_cbs_enabled(env_cpu(env)))) {
*phost = NULL;
return TLB_MMIO;
}
@@ -745,6 +745,10 @@ static int probe_access_internal(CPUArchState *env, target_ulong addr,
if (guest_addr_valid_untagged(addr)) {
int page_flags = page_get_flags(addr);
if (page_flags & acc_flag) {
+ if ((acc_flag == PAGE_READ || acc_flag == PAGE_WRITE)
+ && cpu_plugin_mem_cbs_enabled(env_cpu(env))) {
+ return TLB_MMIO;
+ }
return 0; /* success */
}
maperr = !(page_flags & PAGE_VALID);
@@ -767,7 +771,7 @@ int probe_access_flags(CPUArchState *env, target_ulong addr, int size,
g_assert(-(addr | TARGET_PAGE_MASK) >= size);
flags = probe_access_internal(env, addr, size, access_type, nonfault, ra);
- *phost = flags ? NULL : g2h(env_cpu(env), addr);
+ *phost = (flags & TLB_INVALID_MASK) ? NULL : g2h(env_cpu(env), addr);
return flags;
}
@@ -5688,9 +5688,6 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
flags = info.page[0].flags | info.page[1].flags;
if (unlikely(flags != 0)) {
-#ifdef CONFIG_USER_ONLY
- g_assert_not_reached();
-#else
/*
* At least one page includes MMIO.
* Any bus operation can fail with cpu_transaction_failed,
@@ -5727,7 +5724,6 @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr,
memcpy(&env->vfp.zregs[(rd + i) & 31], &scratch[i], reg_max);
}
return;
-#endif
}
/* The entire operation is in RAM, on valid pages. */
@@ -80,6 +80,14 @@ sha512-vector: sha512.c
TESTS += sha512-vector
+ifneq ($(CROSS_CC_HAS_SVE),)
+sha512-sve: CFLAGS=-O3 -march=armv8.1-a+sve
+sha512-sve: sha512.c
+ $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS)
+
+TESTS += sha512-sve
+endif
+
ifeq ($(HOST_GDB_SUPPORTS_ARCH),y)
GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
The lack of SVE memory instrumentation has been an omission in plugin handling since it was introduced. Fortunately we can utilise the probe_* functions to force all all memory access to follow the slow path. We do this by checking the access type and presence of plugin memory callbacks and if set return the TLB_MMIO flag. We have to jump through a few hoops in user mode to re-use the flag but it was the desired effect: ./qemu-system-aarch64 -display none -serial mon:stdio \ -M virt -cpu max -semihosting-config enable=on \ -kernel ./tests/tcg/aarch64-softmmu/memory-sve \ -plugin ./contrib/plugins/libexeclog.so,ifilter=st1w,afilter=0x40001808 -d plugin gives (disas doesn't currently understand st1w): 0, 0x40001808, 0xe54342a0, ".byte 0xa0, 0x42, 0x43, 0xe5", store, 0x40213010, RAM, store, 0x40213014, RAM, store, 0x40213018, RAM And for user-mode: ./qemu-aarch64 \ -plugin contrib/plugins/libexeclog.so,afilter=0x4007c0 \ -d plugin \ ./tests/tcg/aarch64-linux-user/sha512-sve gives: 1..10 ok 1 - do_test(&tests[i]) 0, 0x4007c0, 0xa4004b80, ".byte 0x80, 0x4b, 0x00, 0xa4", load, 0x5500800370, load, 0x5500800371, load, 0x5500800372, load, 0x5500800373, load, 0x5500800374, load, 0x5500800375, load, 0x5500800376, load, 0x5500800377, load, 0x5500800378, load, 0x5500800379, load, 0x550080037a, load, 0x550080037b, load, 0x550080037c, load, 0x550080037d, load, 0x550080037e, load, 0x550080037f, load, 0x5500800380, load, 0x5500800381, load, 0x5500800382, load, 0x5500800383, load, 0x5500800384, load, 0x5500800385, load, 0x5500800386, lo ad, 0x5500800387, load, 0x5500800388, load, 0x5500800389, load, 0x550080038a, load, 0x550080038b, load, 0x550080038c, load, 0x550080038d, load, 0x550080038e, load, 0x550080038f, load, 0x5500800390, load, 0x5500800391, load, 0x5500800392, load, 0x5500800393, load, 0x5500800394, load, 0x5500800395, load, 0x5500800396, load, 0x5500800397, load, 0x5500800398, load, 0x5500800399, load, 0x550080039a, load, 0x550080039b, load, 0x550080039c, load, 0x550080039d, load, 0x550080039e, load, 0x550080039f, load, 0x55008003a0, load, 0x55008003a1, load, 0x55008003a2, load, 0x55008003a3, load, 0x55008003a4, load, 0x55008003a5, load, 0x55008003a6, load, 0x55008003a7, load, 0x55008003a8, load, 0x55008003a9, load, 0x55008003aa, load, 0x55008003ab, load, 0x55008003ac, load, 0x55008003ad, load, 0x55008003ae, load, 0x55008003af (4007c0 is the ld1b in the sha512-sve) Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Cc: Robert Henry <robhenry@microsoft.com> Cc: Aaron Lindsay <aaron@os.amperecomputing.com> --- include/exec/cpu-all.h | 2 +- include/hw/core/cpu.h | 17 +++++++++++++++++ accel/tcg/cputlb.c | 4 +++- accel/tcg/user-exec.c | 6 +++++- target/arm/tcg/sve_helper.c | 4 ---- tests/tcg/aarch64/Makefile.target | 8 ++++++++ 6 files changed, 34 insertions(+), 7 deletions(-)