Add support for mul[s/d]f3vfp and div[s/d]f3vfp

Here using `"C"` the compiler will use `"aapcs"` or `"aapcs-vfp"`
depending on target configuration.

Of course this translates in a call to `__aeabi_fdiv` / `__aeabi_fmul`
on non-HF targets.

On `eabi` targets with +vfpv2/vfpv3 LLVM generate:

   vmov	s0, r1
   vmov	s2, r0
   vdiv.f32	s0, s2, s0
   vmov	r0, s0
   bx	lr

On `eabihf` targets with +vfpv3-d16/d32/f32 +fp-only-sp LLVM generate:

  vdiv.f32	s0, s0, s1
  bx	lr

That's exactly what We need for [div/mul][s/d]f3vfp.S

README.md

@@ -96,9 +96,9 @@ features = ["c"]
 - [x] arm/aeabi_memset.S
 - [x] arm/aeabi_uidivmod.S
 - [x] arm/aeabi_uldivmod.S
-- [ ] arm/divdf3vfp.S
+- [x] arm/divdf3vfp.S
 - [ ] arm/divmodsi4.S (generic version is done)
-- [ ] arm/divsf3vfp.S
+- [x] arm/divsf3vfp.S
 - [ ] arm/divsi3.S (generic version is done)
 - [ ] arm/eqdf2vfp.S
 - [ ] arm/eqsf2vfp.S
@@ -120,8 +120,8 @@ features = ["c"]
 - [ ] arm/ltdf2vfp.S
 - [ ] arm/ltsf2vfp.S
 - [ ] arm/modsi3.S (generic version is done)
-- [ ] arm/muldf3vfp.S
+- [x] arm/muldf3vfp.S
-- [ ] arm/mulsf3vfp.S
+- [x] arm/mulsf3vfp.S
 - [ ] arm/nedf2vfp.S
 - [ ] arm/negdf2vfp.S
 - [ ] arm/negsf2vfp.S

build.rs

@@ -5511,8 +5511,6 @@ mod c {
                     &[
                         "arm/adddf3vfp.S",
                         "arm/addsf3vfp.S",
-                        "arm/divdf3vfp.S",
-                        "arm/divsf3vfp.S",
                         "arm/eqdf2vfp.S",
                         "arm/eqsf2vfp.S",
                         "arm/extendsfdf2vfp.S",
@@ -5532,8 +5530,6 @@ mod c {
                         "arm/lesf2vfp.S",
                         "arm/ltdf2vfp.S",
                         "arm/ltsf2vfp.S",
-                        "arm/muldf3vfp.S",
-                        "arm/mulsf3vfp.S",
                         "arm/nedf2vfp.S",
                         "arm/nesf2vfp.S",
                         "arm/restore_vfp_d8_d15_regs.S",

src/float/div.rs

@@ -454,4 +454,11 @@ intrinsics! {
         div64(a, b)
     }
 
+    pub extern "C" fn __divsf3vfp(a: f32, b: f32) -> f32 {
+        a / b
+    }
+
+    pub extern "C" fn __divdf3vfp(a: f64, b: f64) -> f64 {
+        a / b
+    }
 }

src/float/mul.rs

@@ -188,4 +188,12 @@ intrinsics! {
     pub extern "C" fn __muldf3(a: f64, b: f64) -> f64 {
         mul(a, b)
     }
+
+    pub extern "C" fn __mulsf3vfp(a: f32, b: f32) -> f32 {
+        a * b
+    }
+
+    pub extern "C" fn __muldf3vfp(a: f64, b: f64) -> f64 {
+        a * b
+    }
 }