Somewhat presentable I guess?

tex/misc/w15_slides.tex

@@ -108,7 +108,13 @@
             synchronization with CPU cache.
         }
         \item {
-            We cannot assume MMU to magically automatically maintain coherence.
+            We cannot assume MMU to magically maintain coherence.
+            \begin{itemize}
+                \item {
+                    This seems the case for x86\_64 (cache-coherent DMA), but
+                    not ARM64.
+                }
+            \end{itemize}
         }
         \item {
             At transportation time:
@@ -379,7 +385,7 @@
 \section{3. Progress}
 
 \begin{frame}
-    \frametitle{Progress}
+    \frametitle{3. Progress}
     \begin{itemize}
         \item {
             Goal: in-kernel implementation of software cache-coherency via
@@ -408,10 +414,35 @@
             ARMv8 defines two levels of cache coherence:
             \begin{itemize}
                 \item {
-                    \textit{Point-of-Unification}:
+                    \textit{Point-of-Unification}: Within a core, instruction
+                    cache, data cache, and TLB all agree in the copy seen for a
+                    particular address.
+                    \begin{itemize}
+                        \item Notably, changing PTE requires PoU.
+                    \end{itemize}
                 }
                 \item {
-                    \textit{Point-of-Coherence}:
+                    \textit{Point-of-Coherence}: Between all DMA-capable
+                    peripherals (CPU or otherwise), they all agree in the copy
+                    seen for a particular address.
+                }
+            \end{itemize}
+            For this thesis's purposes, strive for PoC.
+        }
+        \item {
+            Operations to achieve the latter are encapsulated in the Linux
+            kernel as \texttt{(d|i)cache\_(clean|inval)\_poc}.
+            \begin{itemize}
+                \item Declared under \texttt{arch/arm64/include/asm/cacheflush.h}.
+                \item Defined in \texttt{arch/arm64/mm/cache.S}.
+                \item {
+                    Takes virtual address wrt. \textit{current} address space to
+                    writeback/invalidate cache entries.
+                }
+                \item {
+                    Problem: Can only be called in process context (for userspace
+                    virtual addresses) or in all contexts
+                    (for kernel virtual addresses)?
                 }
             \end{itemize}
         }
@@ -420,21 +451,106 @@
 
 \begin{frame}
     \frametitle{Kernel Patch for On-demand Coherency}
-
+    \begin{itemize}
-
+        \item {
-
+            Problem: These symbols are not exported -- not intended for driver
+            use.
+        }
+        \item {
+            Temporary solution: re-export them via patching the kernel.
+            \begin{itemize}
+                \item Note: Kernel version v6.7.0
+                \item {
+                    Longish-term solution: arrange kernel module code in a way
+                    that takes advantage of existing driver API
+                    (e.g., via DMA API, for example \textit{smbdirect}).
+                }
+            \end{itemize}
+        }
+        \item {
+            Implements wrapper function \texttt{\_\_dcache\_clean\_poc} to
+            re-export \texttt{dcache\_clean\_poc} into driver namespace.
+        }
+        \item {
+            Exports symbol into separate header file.
+        }
+    \end{itemize}
 \end{frame}
 
 \begin{frame}
     \frametitle{Proof-of-Concept Kernel Module}
-
+    \begin{itemize}
-
+        \item {
-
+            Dynamically allocates \texttt{GFP\_USER} pages and remaps to
+            userspace on \texttt{mmap}.
+            \begin{itemize}
+                \item {
+                    \texttt{GFP\_USER} so (for convenience) pages can be
+                    directly addressable in kernelspace (via kernel page table).
+                }
+                \item {
+                    Pages are lazily allocated and shared between multiple
+                    processes (i.e., user address spaces).
+                }
+                \item {
+                    Exposed as character device \texttt{/dev/my\_shmem}.
+                }
+            \end{itemize}
+        }
+        \item Around 300+ LoC.
+        \item {
+            Problem: flawed premise for testing cache writeback!
+            \begin{itemize}
+                \item {
+                    Summary: CPU datapath differs from DMA datapath, common cache
+                    coherency maintenance operations are already performed
+                    in common file/virtual memory area operation code.
+                }
+                \item {
+                    Idea: perform cache write-back on \texttt{vm\_ops->close}.
+                }
+                \item {
+                    Reality: virtual memory area already cleaned from cache and
+                    removed from address space prior to calling
+                    \texttt{vm\_ops->close}.
+                }
+                \item {
+                    Fix: Implement custom \texttt{ioctl}?
+                }
+            \end{itemize}
+        }
+    \end{itemize}
 \end{frame}
 
 % Part 4: Future Work
 % =============================================================================
+\section{4. Future Work}
+
+\begin{frame}
+    \frametitle{4. Future Work}
+    \begin{enumerate}
+        \item {
+            Incorporate cache coherence mechanism into the larger project.
+        }
+        \item {
+            Implement memory model within the larger project. This involves:
+            \begin{itemize}
+                \item {
+                    Making adjustment to message type and structure specifications
+                    for better inter-operation with RDMA.
+                }
+                \item {
+                    Implement memory model programmatically.
+                }
+            \end{itemize}
+        }
+    \end{enumerate}
+\end{frame}
 
 % References
+\begin{frame}
+    \frametitle{References}
+    \printbibliography
+\end{frame}
 
 \end{document}