gpu: nova-core: gsp: fix undefined behavior in command queue code

`driver_read_area` and `driver_write_area` are internal methods that
return slices containing the area of the command queue buffer that the
driver has exclusive read or write access, respectively.

While their returned value is correct and safe to use, internally they
temporarily create a reference to the whole command-buffer slice,
including GSP-owned regions. These regions can change without notice,
and thus creating a slice to them, even if never accessed, is undefined
behavior.

Fix this by making these methods create slices to valid regions only.

Fixes: 75f6b1de8133 ("gpu: nova-core: gsp: Add GSP command queue bindings and handling")
Reported-by: Danilo Krummrich <dakr@kernel.org>
Closes: https://lore.kernel.org/all/DH47AVPEKN06.3BERUSJIB4M1R@kernel.org/
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://patch.msgid.link/20260404-cmdq-ub-fix-v5-1-53d21f4752f5@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 2224896ccc89afa83ab0fb563cd0e622638a9459..569bb1a2501cff8c5952510cc422f7128c674510 100644 (file)
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -17,6 +17,7 @@ use kernel::{
     },
     new_mutex,
     prelude::*,
+    ptr,
     sync::{
         aref::ARef,
         Mutex, //
@@ -255,37 +256,46 @@ impl DmaGspMem {
     /// As the message queue is a circular buffer, the region may be discontiguous in memory. In
     /// that case the second slice will have a non-zero length.
     fn driver_write_area(&mut self) -> (&mut [[u8; GSP_PAGE_SIZE]], &mut [[u8; GSP_PAGE_SIZE]]) {
-        let tx = self.cpu_write_ptr() as usize;
-        let rx = self.gsp_read_ptr() as usize;
+        let tx = self.cpu_write_ptr();
+        let rx = self.gsp_read_ptr();
 
-        // SAFETY:
-        // - We will only access the driver-owned part of the shared memory.
-        // - Per the safety statement of the function, no concurrent access will be performed.
-        let gsp_mem = unsafe { &mut *self.0.as_mut() };
-        // PANIC: per the invariant of `cpu_write_ptr`, `tx` is `< MSGQ_NUM_PAGES`.
-        let (before_tx, after_tx) = gsp_mem.cpuq.msgq.data.split_at_mut(tx);
-
-        // The area starting at `tx` and ending at `rx - 2` modulo MSGQ_NUM_PAGES, inclusive,
-        // belongs to the driver for writing.
-
-        if rx == 0 {
-            // Since `rx` is zero, leave an empty slot at end of the buffer.
-            let last = after_tx.len() - 1;
-            (&mut after_tx[..last], &mut [])
+        // Pointer to the first entry of the CPU message queue.
+        let data = ptr::project!(mut self.0.as_mut_ptr(), .cpuq.msgq.data[0]);
+
+        let (tail_end, wrap_end) = if rx == 0 {
+            // The write area is non-wrapping, and stops at the second-to-last entry of the command
+            // queue (to leave the last one empty).
+            (MSGQ_NUM_PAGES - 1, 0)
         } else if rx <= tx {
-            // The area is discontiguous and we leave an empty slot before `rx`.
-            // PANIC:
-            // - The index `rx - 1` is non-negative because `rx != 0` in this branch.
-            // - The index does not exceed `before_tx.len()` (which equals `tx`) because
-            //   `rx <= tx` in this branch.
-            (after_tx, &mut before_tx[..(rx - 1)])
+            // The write area wraps and continues until `rx - 1`.
+            (MSGQ_NUM_PAGES, rx - 1)
         } else {
-            // The area is contiguous and we leave an empty slot before `rx`.
-            // PANIC:
-            // - The index `rx - tx - 1` is non-negative because `rx > tx` in this branch.
-            // - The index does not exceed `after_tx.len()` (which is `MSGQ_NUM_PAGES - tx`)
-            //   because `rx < MSGQ_NUM_PAGES` by the `gsp_read_ptr` invariant.
-            (&mut after_tx[..(rx - tx - 1)], &mut [])
+            // The write area doesn't wrap and stops at `rx - 1`.
+            (rx - 1, 0)
+        };
+
+        // SAFETY:
+        // - `data` was created from a valid pointer, and `rx` and `tx` are in the
+        //   `0..MSGQ_NUM_PAGES` range per the invariants of `cpu_write_ptr` and `gsp_read_ptr`,
+        //   thus the created slices are valid.
+        // - The area starting at `tx` and ending at `rx - 2` modulo `MSGQ_NUM_PAGES`,
+        //   inclusive, belongs to the driver for writing and is not accessed concurrently by
+        //   the GSP.
+        // - The caller holds a reference to `self` for as long as the returned slices are live,
+        //   meaning the CPU write pointer cannot be advanced and thus that the returned area
+        //   remains exclusive to the CPU for the duration of the slices.
+        // - The created slices point to non-overlapping sub-ranges of `data` in all
+        //   branches (in the `rx <= tx` case, the second slice ends at `rx - 1` which is strictly
+        //   less than `tx` where the first slice starts; in the other cases the second slice is
+        //   empty), so creating two `&mut` references from them does not violate aliasing rules.
+        unsafe {
+            (
+                core::slice::from_raw_parts_mut(
+                    data.add(num::u32_as_usize(tx)),
+                    num::u32_as_usize(tail_end - tx),
+                ),
+                core::slice::from_raw_parts_mut(data, num::u32_as_usize(wrap_end)),
+            )
         }
     }
 
@@ -308,26 +318,38 @@ impl DmaGspMem {
     /// As the message queue is a circular buffer, the region may be discontiguous in memory. In
     /// that case the second slice will have a non-zero length.
     fn driver_read_area(&self) -> (&[[u8; GSP_PAGE_SIZE]], &[[u8; GSP_PAGE_SIZE]]) {
-        let tx = self.gsp_write_ptr() as usize;
-        let rx = self.cpu_read_ptr() as usize;
+        let tx = self.gsp_write_ptr();
+        let rx = self.cpu_read_ptr();
 
-        // SAFETY:
-        // - We will only access the driver-owned part of the shared memory.
-        // - Per the safety statement of the function, no concurrent access will be performed.
-        let gsp_mem = unsafe { &*self.0.as_ptr() };
-        let data = &gsp_mem.gspq.msgq.data;
-
-        // The area starting at `rx` and ending at `tx - 1` modulo MSGQ_NUM_PAGES, inclusive,
-        // belongs to the driver for reading.
-        // PANIC:
-        // - per the invariant of `cpu_read_ptr`, `rx < MSGQ_NUM_PAGES`
-        // - per the invariant of `gsp_write_ptr`, `tx < MSGQ_NUM_PAGES`
-        if rx <= tx {
-            // The area is contiguous.
-            (&data[rx..tx], &[])
+        // Pointer to the first entry of the GSP message queue.
+        let data = ptr::project!(self.0.as_ptr(), .gspq.msgq.data[0]);
+
+        let (tail_end, wrap_end) = if rx <= tx {
+            // Read area is non-wrapping and stops right before `tx`.
+            (tx, 0)
         } else {
-            // The area is discontiguous.
-            (&data[rx..], &data[..tx])
+            // Read area is wrapping and stops right before `tx`.
+            (MSGQ_NUM_PAGES, tx)
+        };
+
+        // SAFETY:
+        // - `data` was created from a valid pointer, and `rx` and `tx` are in the
+        //   `0..MSGQ_NUM_PAGES` range per the invariants of `gsp_write_ptr` and `cpu_read_ptr`,
+        //   thus the created slices are valid.
+        // - The area starting at `rx` and ending at `tx - 1` modulo `MSGQ_NUM_PAGES`,
+        //   inclusive, belongs to the driver for reading and is not accessed concurrently by
+        //   the GSP.
+        // - The caller holds a reference to `self` for as long as the returned slices are live,
+        //   meaning the CPU read pointer cannot be advanced and thus that the returned area
+        //   remains exclusive to the CPU for the duration of the slices.
+        unsafe {
+            (
+                core::slice::from_raw_parts(
+                    data.add(num::u32_as_usize(rx)),
+                    num::u32_as_usize(tail_end - rx),
+                ),
+                core::slice::from_raw_parts(data, num::u32_as_usize(wrap_end)),
+            )
         }
     }