gpu-paging: Allow for more than one buffer to be swapped at a timertss22-aegpu-paging

This uses a very primitive linear disk sector allocation scheme.
Sectors are only reused when userspace resets assignment to 0 with
an NVGPU_AS_IOCTL_SWAP_RESET ioctl (which invalidates all current
swap buffers).

This sector assignment scheme is sufficient for use in a TimeWall-
like system, where all allocations are assumed to be static after
after task system release. This is not suitable for a system with
dynamic allocations, unless userspace manually resets swap state
regularly (benchmarks run a reset at start for example).

Support for dynamic allocations is on the backlog.

No significant speed impact.

Benchmarks, 100 iters, after:
gpu_paging_speed, write: 186.0ms +/- 3.51
gpu_paging_speed, read: 162.7ms +/- 2.58
gpu_paging_overhead_speed, write start: 35.4ms +/- 4.47
gpu_paging_overhead_speed, write finish: 3.3ms +/- 0.18
gpu_paging_overhead_speed, read start: 69.8ms +/- 6.42
gpu_paging_overhead_speed, read finish: 43.2ms +/- 0.91

1 files changed, 3 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/include/nvgpu/linux/vm.h b/drivers/gpu/nvgpu/include/nvgpu/linux/vm.h
index 85abce6f..4fa4242c 100644
--- a/drivers/gpu/nvgpu/include/nvgpu/linux/vm.h
+++ b/drivers/gpu/nvgpu/include/nvgpu/linux/vm.h
@@ -51,7 +51,10 @@ struct nvgpu_mapped_buf_priv {
         struct sg_table *sgt;
         // For fast reverse lookup (FD -> mapped_buf)
         struct list_head nvmap_priv_entry;
+        // To allow waiting on swap I/O completion
         struct completion swap_io_done;
+        // Sector assignment for swapped-out data
+        sector_t swap_sector;
 };
 
 /* NVGPU_AS_MAP_BUFFER_FLAGS_DIRECT_KIND_CTRL must be set */