[PATCH v4 7/9] rust: percpu: Support non-zeroable types for DynamicPerCpu

[Mitchell Levy <levymitchell0@gmail.com>]

Add functionality to `PerCpuPtr` to compute pointers to per-CPU variable
slots on other CPUs. Use this facility to initialize per-CPU variables
on all possible CPUs when a dynamic per-CPU variable is created with a
non-zeroable type. Since `RefCell` and other `Cell`-like types fall into
this category, `impl CheckedPerCpu` on `DynamicPerCpu` for these
`InteriorMutable` types since they can now be used. Add examples of
these usages to `samples/rust/rust_percpu.rs`. Add a test to ensure
dynamic per-CPU variables properly drop their contents, done here since
non-trivially dropped types often aren't `Zeroable`.

Signed-off-by: Mitchell Levy <levymitchell0@gmail.com>
---
 rust/kernel/percpu/dynamic.rs |  44 +++++++++++++++++
 samples/rust/rust_percpu.rs   | 109 +++++++++++++++++++++++++++++++++++++++---
 2 files changed, 146 insertions(+), 7 deletions(-)

diff --git a/rust/kernel/percpu/dynamic.rs b/rust/kernel/percpu/dynamic.rs
index 1863f31a2817..a74c8841aeb2 100644
--- a/rust/kernel/percpu/dynamic.rs
+++ b/rust/kernel/percpu/dynamic.rs
@@ -89,6 +89,36 @@ pub fn new_zero(flags: Flags) -> Option<Self> {
     }
 }
 
+impl<T: Clone> DynamicPerCpu<T> {
+    /// Allocates a new per-CPU variable
+    ///
+    /// # Arguments
+    /// * `val` - The initial value of the per-CPU variable on all CPUs.
+    /// * `flags` - Flags used to allocate an [`Arc`] that keeps track of the underlying
+    ///   [`PerCpuAllocation`].
+    pub fn new_with(val: &T, flags: Flags) -> Option<Self> {
+        let alloc: PerCpuAllocation<T> = PerCpuAllocation::new_uninit()?;
+        let ptr = alloc.0;
+
+        for cpu in Cpumask::possible_cpus().iter() {
+            let remote_ptr = ptr.get_remote_ptr(cpu);
+            // SAFETY: `remote_ptr` is valid because `ptr` points to a live allocation and `cpu`
+            // appears in `Cpumask::possible_cpus()`.
+            //
+            // Each CPU's slot corresponding to `ptr` is currently uninitialized, and no one else
+            // has a reference to it. Therefore, we can freely write to it without worrying about
+            // the need to drop what was there or whether we're racing with someone else.
+            unsafe {
+                (*remote_ptr).write(val.clone());
+            }
+        }
+
+        let arc = Arc::new(alloc, flags).ok()?;
+
+        Some(Self { alloc: Some(arc) })
+    }
+}
+
 impl<T> PerCpu<T> for DynamicPerCpu<T> {
     unsafe fn get_mut(&mut self, guard: CpuGuard) -> PerCpuToken<'_, T> {
         // SAFETY:
@@ -105,6 +135,20 @@ unsafe fn get_mut(&mut self, guard: CpuGuard) -> PerCpuToken<'_, T> {
     }
 }
 
+impl<T: InteriorMutable> CheckedPerCpu<T> for DynamicPerCpu<T> {
+    fn get(&mut self, guard: CpuGuard) -> CheckedPerCpuToken<'_, T> {
+        // SAFETY:
+        // 1. Invariants of this type assure that `alloc` is `Some`.
+        // 2. The invariants of `DynamicPerCpu` ensure that the contents of the allocation are
+        //    initialized on each CPU.
+        // 3. The existence of a reference to the `PerCpuAllocation` ensures that the allocation is
+        //    live.
+        // 4. The invariants of `DynamicPerCpu` ensure that the allocation is sized and aligned for
+        //    a `T`.
+        unsafe { CheckedPerCpuToken::new(guard, &self.alloc.as_ref().unwrap_unchecked().0) }
+    }
+}
+
 impl<T> Drop for DynamicPerCpu<T> {
     fn drop(&mut self) {
         // SAFETY: This type's invariant ensures that `self.alloc` is `Some`.
diff --git a/samples/rust/rust_percpu.rs b/samples/rust/rust_percpu.rs
index 98ca1c781b6b..be70ee2e513f 100644
--- a/samples/rust/rust_percpu.rs
+++ b/samples/rust/rust_percpu.rs
@@ -11,6 +11,7 @@
     percpu::{cpu_guard::*, *},
     pr_info,
     prelude::*,
+    sync::Arc,
 };
 
 module! {
@@ -130,13 +131,81 @@ fn init(_module: &'static ThisModule) -> Result<Self, Error> {
 
         // SAFETY: No prerequisites for on_each_cpu.
         unsafe {
-            on_each_cpu(Some(inc_percpu), (&raw mut test).cast(), 0);
-            on_each_cpu(Some(inc_percpu), (&raw mut test).cast(), 0);
-            on_each_cpu(Some(inc_percpu), (&raw mut test).cast(), 0);
-            on_each_cpu(Some(inc_percpu), (&raw mut test).cast(), 1);
-            on_each_cpu(Some(check_percpu), (&raw mut test).cast(), 1);
+            on_each_cpu(Some(inc_percpu_u64), (&raw mut test).cast(), 0);
+            on_each_cpu(Some(inc_percpu_u64), (&raw mut test).cast(), 0);
+            on_each_cpu(Some(inc_percpu_u64), (&raw mut test).cast(), 0);
+            on_each_cpu(Some(inc_percpu_u64), (&raw mut test).cast(), 1);
+            on_each_cpu(Some(check_percpu_u64), (&raw mut test).cast(), 1);
         }
 
+        let mut checked: DynamicPerCpu<RefCell<u64>> =
+            DynamicPerCpu::new_with(&RefCell::new(100), GFP_KERNEL).unwrap();
+
+        // SAFETY: No prerequisites for on_each_cpu.
+        unsafe {
+            on_each_cpu(Some(inc_percpu_refcell_u64), (&raw mut checked).cast(), 0);
+            on_each_cpu(Some(inc_percpu_refcell_u64), (&raw mut checked).cast(), 0);
+            on_each_cpu(Some(inc_percpu_refcell_u64), (&raw mut checked).cast(), 0);
+            on_each_cpu(Some(inc_percpu_refcell_u64), (&raw mut checked).cast(), 1);
+            on_each_cpu(Some(check_percpu_refcell_u64), (&raw mut checked).cast(), 1);
+        }
+
+        checked.get(CpuGuard::new()).with(|val: &RefCell<u64>| {
+            assert!(*val.borrow() == 104);
+
+            let mut checked_native = 0;
+            *val.borrow_mut() = 0;
+
+            checked_native += 1;
+            *val.borrow_mut() += 1;
+            pr_info!(
+                "Checked native: {}, *checked: {}\n",
+                checked_native,
+                val.borrow()
+            );
+            assert!(checked_native == *val.borrow() && checked_native == 1);
+
+            checked_native = checked_native.wrapping_add((-1i64) as u64);
+            val.replace_with(|old: &mut u64| old.wrapping_add((-1i64) as u64));
+            pr_info!(
+                "Checked native: {}, *checked: {}\n",
+                checked_native,
+                val.borrow()
+            );
+            assert!(checked_native == *val.borrow() && checked_native == 0);
+
+            checked_native = checked_native.wrapping_add((-1i64) as u64);
+            val.replace_with(|old: &mut u64| old.wrapping_add((-1i64) as u64));
+            pr_info!(
+                "Checked native: {}, *checked: {}\n",
+                checked_native,
+                val.borrow()
+            );
+            assert!(checked_native == *val.borrow() && checked_native == (-1i64) as u64);
+
+            checked_native = 0;
+            *val.borrow_mut() = 0;
+
+            checked_native = checked_native.wrapping_sub(1);
+            val.replace_with(|old: &mut u64| old.wrapping_sub(1));
+            pr_info!(
+                "Checked native: {}, *checked: {}\n",
+                checked_native,
+                val.borrow()
+            );
+            assert!(checked_native == *val.borrow() && checked_native == (-1i64) as u64);
+            assert!(checked_native == *val.borrow() && checked_native == u64::MAX);
+        });
+
+        let arc = Arc::new(0, GFP_KERNEL).unwrap();
+        {
+            let _arc_pcpu: DynamicPerCpu<Arc<u64>> =
+                DynamicPerCpu::new_with(&arc, GFP_KERNEL).unwrap();
+        }
+        // `arc` should be unique, since all the clones on each CPU should be dropped when
+        // `_arc_pcpu` is dropped
+        assert!(arc.into_unique_or_drop().is_some());
+
         pr_info!("rust dynamic percpu test done\n");
 
         // Return Err to unload the module
@@ -144,7 +213,7 @@ fn init(_module: &'static ThisModule) -> Result<Self, Error> {
     }
 }
 
-extern "C" fn inc_percpu(info: *mut c_void) {
+extern "C" fn inc_percpu_u64(info: *mut c_void) {
     // SAFETY: We know that info is a void *const DynamicPerCpu<u64> and DynamicPerCpu<u64> is Send.
     let mut pcpu = unsafe { (*(info as *const DynamicPerCpu<u64>)).clone() };
     pr_info!("Incrementing on {}\n", CpuId::current().as_u32());
@@ -153,7 +222,7 @@ extern "C" fn inc_percpu(info: *mut c_void) {
     unsafe { pcpu.get_mut(CpuGuard::new()) }.with(|val: &mut u64| *val += 1);
 }
 
-extern "C" fn check_percpu(info: *mut c_void) {
+extern "C" fn check_percpu_u64(info: *mut c_void) {
     // SAFETY: We know that info is a void *const DynamicPerCpu<u64> and DynamicPerCpu<u64> is Send.
     let mut pcpu = unsafe { (*(info as *const DynamicPerCpu<u64>)).clone() };
     pr_info!("Asserting on {}\n", CpuId::current().as_u32());
@@ -161,3 +230,29 @@ extern "C" fn check_percpu(info: *mut c_void) {
     // SAFETY: We don't have multiple clones of pcpu in scope
     unsafe { pcpu.get_mut(CpuGuard::new()) }.with(|val: &mut u64| assert!(*val == 4));
 }
+
+extern "C" fn inc_percpu_refcell_u64(info: *mut c_void) {
+    // SAFETY: We know that info is a void *const DynamicPerCpu<RefCell<u64>> and
+    // DynamicPerCpu<RefCell<u64>> is Send.
+    let mut pcpu = unsafe { (*(info as *const DynamicPerCpu<RefCell<u64>>)).clone() };
+    // SAFETY: smp_processor_id has no preconditions
+    pr_info!("Incrementing on {}\n", CpuId::current().as_u32());
+
+    pcpu.get(CpuGuard::new()).with(|val: &RefCell<u64>| {
+        let mut val = val.borrow_mut();
+        *val += 1;
+    });
+}
+
+extern "C" fn check_percpu_refcell_u64(info: *mut c_void) {
+    // SAFETY: We know that info is a void *const DynamicPerCpu<RefCell<u64>> and
+    // DynamicPerCpu<RefCell<u64>> is Send.
+    let mut pcpu = unsafe { (*(info as *const DynamicPerCpu<RefCell<u64>>)).clone() };
+    // SAFETY: smp_processor_id has no preconditions
+    pr_info!("Asserting on {}\n", CpuId::current().as_u32());
+
+    pcpu.get(CpuGuard::new()).with(|val: &RefCell<u64>| {
+        let val = val.borrow();
+        assert!(*val == 104);
+    });
+}

-- 
2.34.1