Re: [PATCH] gpu: nova-core: gsp: fix undefined behavior in command queue code

["Alexandre Courbot" <acourbot@nvidia.com>]

On Thu Mar 19, 2026 at 3:41 PM JST, Eliot Courtney wrote:
> On Thu Mar 19, 2026 at 2:36 PM JST, Alexandre Courbot wrote:
>> `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 of 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 is undefined behavior.
>>
>> Fix this by replacing the slice logic with pointer arithmetic and
>> creating slices to valid regions only. It relies on unsafe code, but
>> should be mostly replaced by `IoView` and `IoSlice` once they land.
>>
>> Fixes: 75f6b1de8133 ("gpu: nova-core: gsp: Add GSP command queue bindings and handling")
>> Suggested-by: Danilo Krummrich <dakr@kernel.org>
>> Link: https://lore.kernel.org/all/DH47AVPEKN06.3BERUSJIB4M1R@kernel.org/
>> Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
>> ---
>>  drivers/gpu/nova-core/gsp/cmdq.rs | 135 ++++++++++++++++++++++++++++----------
>>  1 file changed, 100 insertions(+), 35 deletions(-)
>>
>> diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
>> index d36a62ba1c60..4200e7986774 100644
>> --- a/drivers/gpu/nova-core/gsp/cmdq.rs
>> +++ b/drivers/gpu/nova-core/gsp/cmdq.rs
>> @@ -251,38 +251,77 @@ fn new(dev: &device::Device<device::Bound>) -> Result<Self> {
>>      /// 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 = num::u32_as_usize(self.cpu_write_ptr());
>> +        let rx = num::u32_as_usize(self.gsp_read_ptr());
>> +        // Number of pages between `tx` and the end of the command queue.
>> +        // PANIC: Per the invariant of `cpu_write_ptr`, `tx < MSGQ_NUM_PAGES`.
>> +        let after_tx_len = num::u32_as_usize(MSGQ_NUM_PAGES) - tx;
>>  
>> +        // Pointer to the start of the CPU message queue.
>> +        //
>>          // SAFETY:
>> -        // - The `CoherentAllocation` contains exactly one object.
>> -        // - 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 = &mut unsafe { self.0.as_slice_mut(0, 1) }.unwrap()[0];
>> -        // 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);
>> +        // - `self.0` contains exactly one element.
>> +        // - `cpuq.msgq.data[0]` is within the bounds of that element.
>> +        let data = unsafe { &raw mut (*self.0.start_ptr_mut()).cpuq.msgq.data[0] };
>>  
>> -        // The area starting at `tx` and ending at `rx - 2` modulo MSGQ_NUM_PAGES, inclusive,
>> -        // belongs to the driver for writing.
>> +        // Safety/Panic comments to be referenced by the code below.
>> +        //
>> +        // SAFETY[1]:
>> +        // - `data` points to an array of `MSGQ_NUM_PAGES` elements.
>> +        // - 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.
>> +        // - `tx + after_tx_len` == `MSGQ_NUM_PAGES`.
>> +        //
>> +        // PANIC[1]:
>> +        // - Per the invariant of `cpu_write_ptr`, `tx < MSGQ_NUM_PAGES`.
>> +        // - Per the invariant of `gsp_read_ptr`, `rx < MSGQ_NUM_PAGES`.
>>  
>>          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 [])
>> +            (
>> +                // SAFETY: See SAFETY[1].
>> +                unsafe {
>> +                    core::slice::from_raw_parts_mut(
>> +                        data.add(tx),
>> +                        // Since `rx` is zero, leave an empty slot at end of the buffer.
>> +                        // PANIC: See PANIC[1].
>> +                        after_tx_len - 1,
>> +                    )
>> +                },
>> +                &mut [],
>> +            )
>>          } 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)])
>> +            (
>> +                // SAFETY: See SAFETY[1].
>> +                unsafe { core::slice::from_raw_parts_mut(data.add(tx), after_tx_len) },
>> +                // SAFETY: See SAFETY[1].
>> +                unsafe {
>> +                    core::slice::from_raw_parts_mut(
>> +                        data,
>> +                        // Leave one empty slot before `rx`.
>> +                        // PANIC:
>> +                        // - See PANIC[1].
>> +                        // - `rx - 1` is non-negative because `rx != 0` in this branch.
>> +                        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 [])
>> +            (
>> +                // SAFETY: See SAFETY[1].
>> +                unsafe {
>> +                    core::slice::from_raw_parts_mut(
>> +                        data.add(tx),
>> +                        // PANIC:
>> +                        // - See PANIC[1].
>> +                        // - `rx - tx - 1` is non-negative because `rx > tx` in this branch.
>> +                        rx - tx - 1,
>> +                    )
>> +                },
>> +                &mut [],
>> +            )
>>          }
>>      }
>>  
>> @@ -308,24 +347,50 @@ fn driver_write_area_size(&self) -> usize {
>>          let tx = self.gsp_write_ptr() as usize;
>>          let rx = self.cpu_read_ptr() as usize;
>
> Should we use u32_as_usize here too?

Absolutely - I forgot to update that part (although arguably that could
be a separate patch).