Enable running arrow-array and arrow-arith with miri and avoid strict provenance warning (#5387)

* Use fallback for bigint division when running with miri

* Avoid warning about strict provenance when running with miri

* Enable miri in ci

Author: jhorstmann

.github/workflows/miri.sh

@@ -16,6 +16,5 @@ cargo miri test -p arrow-buffer
 cargo miri test -p arrow-data --features ffi
 cargo miri test -p arrow-schema --features ffi
 cargo miri test -p arrow-ord
-# inline assembly not supported by Miri
-# cargo miri test -p arrow-array
-# cargo miri test -p arrow-arith
+cargo miri test -p arrow-array
+cargo miri test -p arrow-arith

arrow-buffer/src/bigint/div.rs

@@ -189,7 +189,7 @@ fn div_rem_word(hi: u64, lo: u64, divisor: u64) -> (u64, u64) {
 
     // LLVM fails to use the div instruction as it is not able to prove
     // that hi < divisor, and therefore the result will fit into 64-bits
-    #[cfg(target_arch = "x86_64")]
+    #[cfg(all(target_arch = "x86_64", not(miri)))]
     unsafe {
         let mut quot = lo;
         let mut rem = hi;
@@ -202,7 +202,7 @@ fn div_rem_word(hi: u64, lo: u64, divisor: u64) -> (u64, u64) {
         );
         (quot, rem)
     }
-    #[cfg(not(target_arch = "x86_64"))]
+    #[cfg(any(not(target_arch = "x86_64"), miri))]
     {
         let x = (u128::from(hi) << 64) + u128::from(lo);
         let y = u128::from(divisor);

arrow-buffer/src/buffer/mutable.rs

@@ -480,7 +480,15 @@ fn dangling_ptr() -> NonNull<u8> {
     // SAFETY: ALIGNMENT is a non-zero usize which is then casted
     // to a *mut T. Therefore, `ptr` is not null and the conditions for
     // calling new_unchecked() are respected.
-    unsafe { NonNull::new_unchecked(ALIGNMENT as *mut u8) }
+    #[cfg(miri)]
+    {
+        // Since miri implies a nightly rust version we can use the unstable strict_provenance feature
+        unsafe { NonNull::new_unchecked(std::ptr::invalid_mut(ALIGNMENT)) }
+    }
+    #[cfg(not(miri))]
+    {
+        unsafe { NonNull::new_unchecked(ALIGNMENT as *mut u8) }
+    }
 }
 
 impl<A: ArrowNativeType> Extend<A> for MutableBuffer {

arrow-buffer/src/lib.rs

@@ -17,6 +17,9 @@
 
 //! Low-level buffer abstractions for [Apache Arrow Rust](https://docs.rs/arrow)
 
+// used by [`buffer::mutable::dangling_ptr`]
+#![cfg_attr(miri, feature(strict_provenance))]
+
 pub mod alloc;
 pub mod buffer;
 pub use buffer::*;