linux-user: Implement aarch64 PR_SVE_SET/GET_VL

As an implementation choice, widening VL has zeroed the
previously inaccessible portion of the sve registers.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Acked-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20180303143823.27055-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

2 files changed, 42 insertions, 0 deletions

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 3fa8fdad21..36711cdb50 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -866,6 +866,7 @@ int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs,
 #ifdef TARGET_AARCH64
 int aarch64_cpu_gdb_read_register(CPUState *cpu, uint8_t *buf, int reg);
 int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg);
+void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq);
 #endif
 
 target_ulong do_arm_semihosting(CPUARMState *env);
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index dd9ba973f7..f12a485820 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -368,3 +368,44 @@ static void aarch64_cpu_register_types(void)
 }
 
 type_init(aarch64_cpu_register_types)
+
+/* The manual says that when SVE is enabled and VQ is widened the
+ * implementation is allowed to zero the previously inaccessible
+ * portion of the registers.  The corollary to that is that when
+ * SVE is enabled and VQ is narrowed we are also allowed to zero
+ * the now inaccessible portion of the registers.
+ *
+ * The intent of this is that no predicate bit beyond VQ is ever set.
+ * Which means that some operations on predicate registers themselves
+ * may operate on full uint64_t or even unrolled across the maximum
+ * uint64_t[4].  Performing 4 bits of host arithmetic unconditionally
+ * may well be cheaper than conditionals to restrict the operation
+ * to the relevant portion of a uint16_t[16].
+ *
+ * TODO: Need to call this for changes to the real system registers
+ * and EL state changes.
+ */
+void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq)
+{
+    int i, j;
+    uint64_t pmask;
+
+    assert(vq >= 1 && vq <= ARM_MAX_VQ);
+
+    /* Zap the high bits of the zregs.  */
+    for (i = 0; i < 32; i++) {
+        memset(&env->vfp.zregs[i].d[2 * vq], 0, 16 * (ARM_MAX_VQ - vq));
+    }
+
+    /* Zap the high bits of the pregs and ffr.  */
+    pmask = 0;
+    if (vq & 3) {
+        pmask = ~(-1ULL << (16 * (vq & 3)));
+    }
+    for (j = vq / 4; j < ARM_MAX_VQ / 4; j++) {
+        for (i = 0; i < 17; ++i) {
+            env->vfp.pregs[i].p[j] &= pmask;
+        }
+        pmask = 0;
+    }
+}