target/arm: Use uint32_t instead of bitmap for sve vq's

The bitmap need only hold 15 bits; bitmap is over-complicated.
We can simplify operations quite a bit with plain logical ops.

The introduction of SVE_VQ_POW2_MAP eliminates the need for
looping in order to search for powers of two.  Simply perform
the logical ops and use count leading or trailing zeros as
required to find the result.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220607203306.657998-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 56 insertions, 61 deletions

diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index cce68dd82a..15665c962b 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -355,8 +355,11 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
      * any of the above.  Finally, if SVE is not disabled, then at least one
      * vector length must be enabled.
      */
-    DECLARE_BITMAP(tmp, ARM_MAX_VQ);
-    uint32_t vq, max_vq = 0;
+    uint32_t vq_map = cpu->sve_vq_map;
+    uint32_t vq_init = cpu->sve_vq_init;
+    uint32_t vq_supported;
+    uint32_t vq_mask = 0;
+    uint32_t tmp, vq, max_vq = 0;
 
     /*
      * CPU models specify a set of supported vector lengths which are
@@ -364,10 +367,16 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
      * in the supported bitmap results in an error.  When KVM is enabled we
      * fetch the supported bitmap from the host.
      */
-    if (kvm_enabled() && kvm_arm_sve_supported()) {
-        kvm_arm_sve_get_vls(CPU(cpu), cpu->sve_vq_supported);
-    } else if (kvm_enabled()) {
-        assert(!cpu_isar_feature(aa64_sve, cpu));
+    if (kvm_enabled()) {
+        if (kvm_arm_sve_supported()) {
+            cpu->sve_vq_supported = kvm_arm_sve_get_vls(CPU(cpu));
+            vq_supported = cpu->sve_vq_supported;
+        } else {
+            assert(!cpu_isar_feature(aa64_sve, cpu));
+            vq_supported = 0;
+        }
+    } else {
+        vq_supported = cpu->sve_vq_supported;
     }
 
     /*
@@ -375,8 +384,9 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
      * From the properties, sve_vq_map<N> implies sve_vq_init<N>.
      * Check first for any sve<N> enabled.
      */
-    if (!bitmap_empty(cpu->sve_vq_map, ARM_MAX_VQ)) {
-        max_vq = find_last_bit(cpu->sve_vq_map, ARM_MAX_VQ) + 1;
+    if (vq_map != 0) {
+        max_vq = 32 - clz32(vq_map);
+        vq_mask = MAKE_64BIT_MASK(0, max_vq);
 
         if (cpu->sve_max_vq && max_vq > cpu->sve_max_vq) {
             error_setg(errp, "cannot enable sve%d", max_vq * 128);
@@ -392,15 +402,10 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
              * For KVM we have to automatically enable all supported unitialized
              * lengths, even when the smaller lengths are not all powers-of-two.
              */
-            bitmap_andnot(tmp, cpu->sve_vq_supported, cpu->sve_vq_init, max_vq);
-            bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq);
+            vq_map |= vq_supported & ~vq_init & vq_mask;
         } else {
             /* Propagate enabled bits down through required powers-of-two. */
-            for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) {
-                if (!test_bit(vq - 1, cpu->sve_vq_init)) {
-                    set_bit(vq - 1, cpu->sve_vq_map);
-                }
-            }
+            vq_map |= SVE_VQ_POW2_MAP & ~vq_init & vq_mask;
         }
     } else if (cpu->sve_max_vq == 0) {
         /*
@@ -413,25 +418,18 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
 
         if (kvm_enabled()) {
             /* Disabling a supported length disables all larger lengths. */
-            for (vq = 1; vq <= ARM_MAX_VQ; ++vq) {
-                if (test_bit(vq - 1, cpu->sve_vq_init) &&
-                    test_bit(vq - 1, cpu->sve_vq_supported)) {
-                    break;
-                }
-            }
+            tmp = vq_init & vq_supported;
         } else {
             /* Disabling a power-of-two disables all larger lengths. */
-            for (vq = 1; vq <= ARM_MAX_VQ; vq <<= 1) {
-                if (test_bit(vq - 1, cpu->sve_vq_init)) {
-                    break;
-                }
-            }
+            tmp = vq_init & SVE_VQ_POW2_MAP;
         }
+        vq = ctz32(tmp) + 1;
 
         max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ;
-        bitmap_andnot(cpu->sve_vq_map, cpu->sve_vq_supported,
-                      cpu->sve_vq_init, max_vq);
-        if (max_vq == 0 || bitmap_empty(cpu->sve_vq_map, max_vq)) {
+        vq_mask = MAKE_64BIT_MASK(0, max_vq);
+        vq_map = vq_supported & ~vq_init & vq_mask;
+
+        if (max_vq == 0 || vq_map == 0) {
             error_setg(errp, "cannot disable sve%d", vq * 128);
             error_append_hint(errp, "Disabling sve%d results in all "
                               "vector lengths being disabled.\n",
@@ -441,7 +439,8 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
             return;
         }
 
-        max_vq = find_last_bit(cpu->sve_vq_map, max_vq) + 1;
+        max_vq = 32 - clz32(vq_map);
+        vq_mask = MAKE_64BIT_MASK(0, max_vq);
     }
 
     /*
@@ -451,9 +450,9 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
      */
     if (cpu->sve_max_vq != 0) {
         max_vq = cpu->sve_max_vq;
+        vq_mask = MAKE_64BIT_MASK(0, max_vq);
 
-        if (!test_bit(max_vq - 1, cpu->sve_vq_map) &&
-            test_bit(max_vq - 1, cpu->sve_vq_init)) {
+        if (vq_init & ~vq_map & (1 << (max_vq - 1))) {
             error_setg(errp, "cannot disable sve%d", max_vq * 128);
             error_append_hint(errp, "The maximum vector length must be "
                               "enabled, sve-max-vq=%d (%d bits)\n",
@@ -462,8 +461,7 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
         }
 
         /* Set all bits not explicitly set within sve-max-vq. */
-        bitmap_complement(tmp, cpu->sve_vq_init, max_vq);
-        bitmap_or(cpu->sve_vq_map, cpu->sve_vq_map, tmp, max_vq);
+        vq_map |= ~vq_init & vq_mask;
     }
 
     /*
@@ -472,13 +470,14 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
      * are clear, just in case anybody looks.
      */
     assert(max_vq != 0);
-    bitmap_clear(cpu->sve_vq_map, max_vq, ARM_MAX_VQ - max_vq);
+    assert(vq_mask != 0);
+    vq_map &= vq_mask;
 
     /* Ensure the set of lengths matches what is supported. */
-    bitmap_xor(tmp, cpu->sve_vq_map, cpu->sve_vq_supported, max_vq);
-    if (!bitmap_empty(tmp, max_vq)) {
-        vq = find_last_bit(tmp, max_vq) + 1;
-        if (test_bit(vq - 1, cpu->sve_vq_map)) {
+    tmp = vq_map ^ (vq_supported & vq_mask);
+    if (tmp) {
+        vq = 32 - clz32(tmp);
+        if (vq_map & (1 << (vq - 1))) {
             if (cpu->sve_max_vq) {
                 error_setg(errp, "cannot set sve-max-vq=%d", cpu->sve_max_vq);
                 error_append_hint(errp, "This CPU does not support "
@@ -502,15 +501,15 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
                 return;
             } else {
                 /* Ensure all required powers-of-two are enabled. */
-                for (vq = pow2floor(max_vq); vq >= 1; vq >>= 1) {
-                    if (!test_bit(vq - 1, cpu->sve_vq_map)) {
-                        error_setg(errp, "cannot disable sve%d", vq * 128);
-                        error_append_hint(errp, "sve%d is required as it "
-                                          "is a power-of-two length smaller "
-                                          "than the maximum, sve%d\n",
-                                          vq * 128, max_vq * 128);
-                        return;
-                    }
+                tmp = SVE_VQ_POW2_MAP & vq_mask & ~vq_map;
+                if (tmp) {
+                    vq = 32 - clz32(tmp);
+                    error_setg(errp, "cannot disable sve%d", vq * 128);
+                    error_append_hint(errp, "sve%d is required as it "
+                                      "is a power-of-two length smaller "
+                                      "than the maximum, sve%d\n",
+                                      vq * 128, max_vq * 128);
+                    return;
                 }
             }
         }
@@ -530,6 +529,7 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
 
     /* From now on sve_max_vq is the actual maximum supported length. */
     cpu->sve_max_vq = max_vq;
+    cpu->sve_vq_map = vq_map;
 }
 
 static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name,
@@ -590,7 +590,7 @@ static void cpu_arm_get_sve_vq(Object *obj, Visitor *v, const char *name,
     if (!cpu_isar_feature(aa64_sve, cpu)) {
         value = false;
     } else {
-        value = test_bit(vq - 1, cpu->sve_vq_map);
+        value = extract32(cpu->sve_vq_map, vq - 1, 1);
     }
     visit_type_bool(v, name, &value, errp);
 }
@@ -612,12 +612,8 @@ static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name,
         return;
     }
 
-    if (value) {
-        set_bit(vq - 1, cpu->sve_vq_map);
-    } else {
-        clear_bit(vq - 1, cpu->sve_vq_map);
-    }
-    set_bit(vq - 1, cpu->sve_vq_init);
+    cpu->sve_vq_map = deposit32(cpu->sve_vq_map, vq - 1, 1, value);
+    cpu->sve_vq_init |= 1 << (vq - 1);
 }
 
 static bool cpu_arm_get_sve(Object *obj, Error **errp)
@@ -979,7 +975,7 @@ static void aarch64_max_initfn(Object *obj)
     cpu->dcz_blocksize = 7; /*  512 bytes */
 #endif
 
-    bitmap_fill(cpu->sve_vq_supported, ARM_MAX_VQ);
+    cpu->sve_vq_supported = MAKE_64BIT_MASK(0, ARM_MAX_VQ);
 
     aarch64_add_pauth_properties(obj);
     aarch64_add_sve_properties(obj);
@@ -1026,12 +1022,11 @@ static void aarch64_a64fx_initfn(Object *obj)
     cpu->gic_vprebits = 5;
     cpu->gic_pribits = 5;
 
-    /* Suppport of A64FX's vector length are 128,256 and 512bit only */
+    /* The A64FX supports only 128, 256 and 512 bit vector lengths */
     aarch64_add_sve_properties(obj);
-    bitmap_zero(cpu->sve_vq_supported, ARM_MAX_VQ);
-    set_bit(0, cpu->sve_vq_supported); /* 128bit */
-    set_bit(1, cpu->sve_vq_supported); /* 256bit */
-    set_bit(3, cpu->sve_vq_supported); /* 512bit */
+    cpu->sve_vq_supported = (1 << 0)  /* 128bit */
+                          | (1 << 1)  /* 256bit */
+                          | (1 << 3); /* 512bit */
 
     cpu->isar.reset_pmcr_el0 = 0x46014040;