[PATCH 4/4] gpu: nova-core: gsp: cmdq: compute the queue regions from a count and a slot

[Alexandre Courbot <acourbot@nvidia.com>]

From: John Hubbard <jhubbard@nvidia.com>

The r000 firmware uses msgq v2, the queue layout that keeps the queue
pointers in BAR0 registers as counts that do not wrap at the ring size.
The r570 firmware's layout keeps the pointers in shared memory as
indices into the ring. The two layouts differ in where a pointer is
read and in how the size of the region that the driver may write, and
of the region that it may read, follows from a queue's write pointer
and read pointer. Splitting a region across the end of the ring is the
same in both, and whether a region wraps follows from the order of the
two pointers.

The functions for the writable region and for the readable region each
branched on the order of the write pointer and the read pointer. Each
branch chose where the two slices ended, and the function then built
the slices with open-coded pointer arithmetic. The SAFETY comments
argued the slice bounds branch by branch, so the switch to msgq v2
would have had to rewrite the branches and the argument along with the
pointer rules.

Compute the number of slots in a region and its start slot once. The
first slice ends at the end of the region or at the end of the ring,
whichever comes first, and the second slice carries the rest.

The number of slots comes from one helper per queue, which are the only
two places the msgq v2 switch needs to change. The two slices are built
with separate from_raw_parts calls over the slots the driver currently
owns, rather than by splitting a slice over the whole ring: a reference
spanning slots the GSP may be accessing would break the contract of
Coherent.

No functional changes.

Assisted-by: LLM
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Co-developed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
---
 drivers/gpu/nova-core/gsp/cmdq.rs | 96 +++++++++++++++++++--------------------
 1 file changed, 47 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index a271114fb54c..7350074a9f96 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -186,60 +186,64 @@ fn new(dev: &'a device::Device<device::Bound>, bar: Bar0<'a>) -> 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();
-        let rx = self.gsp_read_ptr();
+        let avail = self.cpuq_free_slots();
+        let w_slot = self.cpu_write_ptr();
 
         // Pointer to the first entry of the CPU message queue.
         let data = ptr::project!(mut self.mem.as_mut_ptr(), .cpuq.msgq.data[build: 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 write area wraps and continues until `rx - 1`.
-            (MSGQ_NUM_PAGES, rx - 1)
-        } else {
-            // The write area doesn't wrap and stops at `rx - 1`.
-            (rx - 1, 0)
-        };
+        // `w_slot` is below `MSGQ_NUM_PAGES` per the invariant of `cpu_write_ptr`, so the
+        // subtraction cannot underflow.
+        let in_after = avail.min(MSGQ_NUM_PAGES - w_slot);
+        let in_before = avail - in_after;
 
         // 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.
+        // - `data` was created from a valid pointer to `MSGQ_NUM_PAGES` entries.
+        // - The `in_after` entries starting at `w_slot` belong to the `avail` entries that the
+        //   driver is currently allowed to write, and so do the `in_before` first entries.
         // - 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.
+        // - The slices do not overlap: `avail` is at most `MSGQ_NUM_PAGES - 1`, so `in_before`
+        //   is strictly less than `w_slot` whenever it is non-zero.
         unsafe {
             (
                 core::slice::from_raw_parts_mut(
-                    data.add(num::u32_as_usize(tx)),
-                    num::u32_as_usize(tail_end - tx),
+                    data.add(num::u32_as_usize(w_slot)),
+                    num::u32_as_usize(in_after),
                 ),
-                core::slice::from_raw_parts_mut(data, num::u32_as_usize(wrap_end)),
+                core::slice::from_raw_parts_mut(data, num::u32_as_usize(in_before)),
             )
         }
     }
 
-    /// Returns the size of the region of the CPU message queue that the driver is currently allowed
-    /// to write to, in bytes.
-    fn driver_write_area_size(&self) -> usize {
+    /// Returns the number of slots of the CPU message queue that the driver is currently allowed
+    /// to write to.
+    fn cpuq_free_slots(&self) -> u32 {
         let tx = self.cpu_write_ptr();
         let rx = self.gsp_read_ptr();
 
         // `rx` and `tx` are both in `0..MSGQ_NUM_PAGES` per the invariants of `gsp_read_ptr` and
         // `cpu_write_ptr`. The minimum value case is where `rx == 0` and `tx == MSGQ_NUM_PAGES -
         // 1`, which gives `0 + MSGQ_NUM_PAGES - (MSGQ_NUM_PAGES - 1) - 1 == 0`.
-        let slots = (rx + MSGQ_NUM_PAGES - tx - 1) % MSGQ_NUM_PAGES;
-        num::u32_as_usize(slots) * GSP_PAGE_SIZE
+        (rx + MSGQ_NUM_PAGES - tx - 1) % MSGQ_NUM_PAGES
+    }
+
+    /// Returns the size of the region of the CPU message queue that the driver is currently allowed
+    /// to write to, in bytes.
+    fn driver_write_area_size(&self) -> usize {
+        num::u32_as_usize(self.cpuq_free_slots()) * GSP_PAGE_SIZE
+    }
+
+    /// Returns the number of slots of the GSP message queue that the driver is currently allowed
+    /// to read from.
+    fn gspq_readable_slots(&self) -> u32 {
+        let tx = self.gsp_write_ptr();
+        let rx = self.cpu_read_ptr();
+
+        // `rx` and `tx` are both in `0..MSGQ_NUM_PAGES` per the invariants of `gsp_write_ptr` and
+        // `cpu_read_ptr`, so the subtraction cannot underflow.
+        (tx + MSGQ_NUM_PAGES - rx) % MSGQ_NUM_PAGES
     }
 
     /// Returns the region of the GSP message queue that the driver is currently allowed to read
@@ -248,37 +252,31 @@ fn driver_write_area_size(&self) -> usize {
     /// 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();
-        let rx = self.cpu_read_ptr();
+        let avail = self.gspq_readable_slots();
+        let r_slot = self.cpu_read_ptr();
 
         // Pointer to the first entry of the GSP message queue.
         let data = ptr::project!(self.mem.as_ptr(), .gspq.msgq.data[build: 0]);
 
-        let (tail_end, wrap_end) = if rx <= tx {
-            // Read area is non-wrapping and stops right before `tx`.
-            (tx, 0)
-        } else {
-            // Read area is wrapping and stops right before `tx`.
-            (MSGQ_NUM_PAGES, tx)
-        };
+        // `r_slot` is below `MSGQ_NUM_PAGES` per the invariant of `cpu_read_ptr`, so the
+        // subtraction cannot underflow.
+        let in_after = avail.min(MSGQ_NUM_PAGES - r_slot);
+        let in_before = avail - in_after;
 
         // 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.
+        // - `data` was created from a valid pointer to `MSGQ_NUM_PAGES` entries.
+        // - The `in_after` entries starting at `r_slot` belong to the `avail` entries that the
+        //   driver is currently allowed to read, and so do the `in_before` first entries.
         // - 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),
+                    data.add(num::u32_as_usize(r_slot)),
+                    num::u32_as_usize(in_after),
                 ),
-                core::slice::from_raw_parts(data, num::u32_as_usize(wrap_end)),
+                core::slice::from_raw_parts(data, num::u32_as_usize(in_before)),
             )
         }
     }

-- 
2.56.0