rust: add find_bit_benchmark_rust module.

Microbenchmark protected by a config FIND_BIT_BENCHMARK_RUST,
following `find_bit_benchmark.c` but testing the Rust Bitmap API.

We add a fill_random() method protected by the config in order to
maintain the abstraction.

The sample output from the benchmark, both C and Rust version:

find_bit_benchmark.c output:
```
Start testing find_bit() with random-filled bitmap
[ 438.101937] find_next_bit: 860188 ns, 163419 iterations
[ 438.109471] find_next_zero_bit: 912342 ns, 164262 iterations
[ 438.116820] find_last_bit: 726003 ns, 163419 iterations
[ 438.130509] find_nth_bit: 7056993 ns, 16269 iterations
[ 438.139099] find_first_bit: 1963272 ns, 16270 iterations
[ 438.173043] find_first_and_bit: 27314224 ns, 32654 iterations
[ 438.180065] find_next_and_bit: 398752 ns, 73705 iterations
[ 438.186689]
Start testing find_bit() with sparse bitmap
[ 438.193375] find_next_bit: 9675 ns, 656 iterations
[ 438.201765] find_next_zero_bit: 1766136 ns, 327025 iterations
[ 438.208429] find_last_bit: 9017 ns, 656 iterations
[ 438.217816] find_nth_bit: 2749742 ns, 655 iterations
[ 438.225168] find_first_bit: 721799 ns, 656 iterations
[ 438.231797] find_first_and_bit: 2819 ns, 1 iterations
[ 438.238441] find_next_and_bit: 3159 ns, 1 iterations
```

find_bit_benchmark_rust.rs output:
```
[ 451.182459] find_bit_benchmark_rust:
[ 451.186688] Start testing find_bit() Rust with random-filled bitmap
[ 451.194450] next_bit: 777950 ns, 163644 iterations
[ 451.201997] next_zero_bit: 918889 ns, 164036 iterations
[ 451.208642] Start testing find_bit() Rust with sparse bitmap
[ 451.214300] next_bit: 9181 ns, 654 iterations
[ 451.222806] next_zero_bit: 1855504 ns, 327026 iterations
```

Here are the results from 32 samples, with 95% confidence interval.
The microbenchmark was built with RUST_BITMAP_HARDENED=n and run on a
machine that did not execute other processes.

Random-filled bitmap:
+-----------+-------+-----------+--------------+-----------+-----------+
| Benchmark | Lang | Mean (ms) | Std Dev (ms) | 95% CI Lo | 95% CI Hi |
+-----------+-------+-----------+--------------+-----------+-----------+
| find_bit/ | C | 825.07 | 53.89 | 806.40 | 843.74 |
| next_bit | Rust | 870.91 | 46.29 | 854.88 | 886.95 |
+-----------+-------+-----------+--------------+-----------+-----------+
| find_zero/| C | 933.56 | 56.34 | 914.04 | 953.08 |
| next_zero | Rust | 945.85 | 60.44 | 924.91 | 966.79 |
+-----------+-------+-----------+--------------+-----------+-----------+

Rust appears 5.5% slower for next_bit, 1.3% slower for next_zero.

Sparse bitmap:
+-----------+-------+-----------+--------------+-----------+-----------+
| Benchmark | Lang | Mean (ms) | Std Dev (ms) | 95% CI Lo | 95% CI Hi |
+-----------+-------+-----------+--------------+-----------+-----------+
| find_bit/ | C | 13.17 | 6.21 | 11.01 | 15.32 |
| next_bit | Rust | 14.30 | 8.27 | 11.43 | 17.17 |
+-----------+-------+-----------+--------------+-----------+-----------+
| find_zero/| C | 1859.31 | 82.30 | 1830.80 | 1887.83 |
| next_zero | Rust | 1908.09 | 139.82 | 1859.65 | 1956.54 |
+-----------+-------+-----------+--------------+-----------+-----------+

Rust appears 8.5% slower for next_bit, 2.6% slower for next_zero.

In summary, taking the arithmetic mean of all slow-downs, we can say
the Rust API has a 4.5% slowdown.

Suggested-by: Alice Ryhl <[e-mail]>
Suggested-by: Yury Norov (NVIDIA) <[e-mail]>
Reviewed-by: Yury Norov (NVIDIA) <[e-mail]>
Reviewed-by: Alice Ryhl <[e-mail]>
Signed-off-by: Burak Emir <[e-mail]>
Signed-off-by: Yury Norov (NVIDIA) <[e-mail]>

MAINTAINERS

···
 M:	Burak Emir <[e-mail]>
 R:	Yury Norov <[e-mail]>
 S:	Maintained
+F:	lib/find_bit_benchmark_rust.rs
 F:	rust/kernel/bitmap.rs
 
 BITOPS API

lib/Kconfig.debug

···
 
 	  If unsure, say N.
 
+config FIND_BIT_BENCHMARK_RUST
+	tristate "Test find_bit functions in Rust"
+	depends on RUST
+	help
+	  This builds the "find_bit_benchmark_rust" module. It is a micro
+          benchmark that measures the performance of Rust functions that
+          correspond to the find_*_bit() operations in C. It follows the
+          FIND_BIT_BENCHMARK closely but will in general not yield same
+          numbers due to extra bounds checks and overhead of foreign
+          function calls.
+
+	  If unsure, say N.
+
 config TEST_FIRMWARE
 	tristate "Test firmware loading via userspace interface"
 	depends on FW_LOADER

lib/Makefile

···
 obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_FIND_BIT_BENCHMARK) += find_bit_benchmark.o
+obj-$(CONFIG_FIND_BIT_BENCHMARK_RUST) += find_bit_benchmark_rust.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 test_dhry-objs := dhry_1.o dhry_2.o dhry_run.o
 obj-$(CONFIG_TEST_DHRY) += test_dhry.o

lib/find_bit_benchmark_rust.rs

···
+// SPDX-License-Identifier: GPL-2.0
+//! Benchmark for find_bit-like methods in Bitmap Rust API.
+
+use kernel::alloc::flags::GFP_KERNEL;
+use kernel::bindings;
+use kernel::bitmap::BitmapVec;
+use kernel::error::{code, Result};
+use kernel::prelude::module;
+use kernel::time::{Instant, Monotonic};
+use kernel::ThisModule;
+use kernel::{pr_cont, pr_err};
+
+const BITMAP_LEN: usize = 4096 * 8 * 10;
+// Reciprocal of the fraction of bits that are set in sparse bitmap.
+const SPARSENESS: usize = 500;
+
+/// Test module that benchmarks performance of traversing bitmaps.
+struct Benchmark();
+
+fn test_next_bit(bitmap: &BitmapVec) {
+    let time = Instant::<Monotonic>::now();
+    let mut cnt = 0;
+    let mut i = 0;
+
+    while let Some(index) = bitmap.next_bit(i) {
+        cnt += 1;
+        i = index + 1;
+        // CONFIG_RUST_BITMAP_HARDENED enforces strict bounds.
+        if i == BITMAP_LEN {
+            break;
+        }
+    }
+
+    let delta = time.elapsed();
+    pr_cont!(
+        "\nnext_bit:           {:18} ns, {:6} iterations",
+        delta.as_nanos(),
+        cnt
+    );
+}
+
+fn test_next_zero_bit(bitmap: &BitmapVec) {
+    let time = Instant::<Monotonic>::now();
+    let mut cnt = 0;
+    let mut i = 0;
+
+    while let Some(index) = bitmap.next_zero_bit(i) {
+        cnt += 1;
+        i = index + 1;
+        // CONFIG_RUST_BITMAP_HARDENED enforces strict bounds.
+        if i == BITMAP_LEN {
+            break;
+        }
+    }
+
+    let delta = time.elapsed();
+    pr_cont!(
+        "\nnext_zero_bit:      {:18} ns, {:6} iterations",
+        delta.as_nanos(),
+        cnt
+    );
+}
+
+fn find_bit_test() {
+    pr_err!("Benchmark");
+    pr_cont!("\nStart testing find_bit() Rust with random-filled bitmap");
+
+    let mut bitmap = BitmapVec::new(BITMAP_LEN, GFP_KERNEL).expect("alloc bitmap failed");
+    bitmap.fill_random();
+
+    test_next_bit(&bitmap);
+    test_next_zero_bit(&bitmap);
+
+    pr_cont!("\nStart testing find_bit() Rust with sparse bitmap");
+
+    let mut bitmap = BitmapVec::new(BITMAP_LEN, GFP_KERNEL).expect("alloc sparse bitmap failed");
+    let nbits = BITMAP_LEN / SPARSENESS;
+    for _i in 0..nbits {
+        // SAFETY: __get_random_u32_below is safe to call with any u32 argument.
+        let bit =
+            unsafe { bindings::__get_random_u32_below(BITMAP_LEN.try_into().unwrap()) as usize };
+        bitmap.set_bit(bit);
+    }
+
+    test_next_bit(&bitmap);
+    test_next_zero_bit(&bitmap);
+    pr_cont!("\n");
+}
+
+impl kernel::Module for Benchmark {
+    fn init(_module: &'static ThisModule) -> Result<Self> {
+        find_bit_test();
+        // Return error so test module can be inserted again without rmmod.
+        Err(code::EINVAL)
+    }
+}
+
+module! {
+    type: Benchmark,
+    name: "find_bit_benchmark_rust",
+    authors: ["Burak Emir <[e-mail]>"],
+    description: "Module with benchmark for bitmap Rust API",
+    license: "GPL v2",
+}

rust/bindings/bindings_helper.h

···
 #include <linux/pm_opp.h>
 #include <linux/poll.h>
 #include <linux/property.h>
+#include <linux/random.h>
 #include <linux/refcount.h>
 #include <linux/regulator/consumer.h>
 #include <linux/sched.h>

rust/kernel/bitmap.rs

···
     pub fn len(&self) -> usize {
         self.nbits
     }
+
+    /// Fills this `Bitmap` with random bits.
+    #[cfg(CONFIG_FIND_BIT_BENCHMARK_RUST)]
+    pub fn fill_random(&mut self) {
+        // SAFETY: `self.as_mut_ptr` points to either an array of the
+        // appropriate length or one usize.
+        unsafe {
+            bindings::get_random_bytes(
+                self.as_mut_ptr().cast::<ffi::c_void>(),
+                usize::div_ceil(self.nbits, bindings::BITS_PER_LONG as usize)
+                    * bindings::BITS_PER_LONG as usize
+                    / 8,
+            );
+        }
+    }
 }
 
 impl Bitmap {