Merge branch 'main' of https://github.com/janishutz/eth-summaries

semester3/spca/code-examples/00_c/00_basics/00_intro.c

@@ -13,4 +13,5 @@ int main( int argc, char *argv[] ) {
         printf( "Arg %d: %s\n", i, argv[ i ] ); // Outputs the i-th argument from CLI
 
     get_user_input_int( "Select a number" ); // Function calls as in any other language
+    return 0;                                // Return a POSIX exit code
 }

semester3/spca/code-examples/00_c/00_basics/01_func.c

@@ -1,9 +1,11 @@
 #include "01_func.h"
+#include <stdio.h>
 
 int get_user_input_int( char prompt[] ) {
     int input_data;
-    printf( "%s", prompt );     // Always wrap strings like this for printf
-    scanf( "%d", &input_data ); // Get user input from CLI
+    printf( "%s", prompt );           // Always wrap strings like this for printf
+    scanf( "%d", &input_data );       // Get user input from CLI
+    int input_data_copy = input_data; // Value copied
 
     // If statements just like any other language
     if ( input_data )
@@ -11,6 +13,7 @@ int get_user_input_int( char prompt[] ) {
     else
         printf( "Input is zero" );
 
+    // Switch statements just like in any other language
     switch ( input_data ) {
         case 5:
             printf( "You win!" );
@@ -21,17 +24,20 @@ int get_user_input_int( char prompt[] ) {
             printf( "No win" ); // Case for any not covered input
     }
 
-    int input_data_copy = input_data;
-
     while ( input_data > 1 ) {
         input_data -= 1;
         printf( "Hello World\n" );
     }
 
+    // Inversed while loop (executes at least once)
     do {
         input_data -= 1;
         printf( "Bye World\n" );
+        if ( input_data_copy == 0 )
+            goto this_is_a_label;
     } while ( input_data_copy > 1 );
 
+this_is_a_label:
+    printf( "Jumped to label" );
     return 0;
 }

semester3/spca/code-examples/00_c/00_basics/02_declarations.c

@@ -0,0 +1,33 @@
+int my_int;              // Allocates memory on the stack.
+                         // Variable is global (read / writable by entire program)
+static int my_local_int; // only available locally (in this file)
+extern const char *var;  // Defined in some other file
+const int MY_CONST = 10; // constant (immutable), convention: SCREAM_CASE
+
+enum { ONE, TWO } num; // Enum. ONE will get value 0, TWO has value 1
+
+enum { O = 2, T = 1 } n; // Enum with values specified
+
+// Structs are like classes, but contain no logic
+struct MyStruct {
+        int el1;
+        int el2;
+};
+
+int fun( int j ) {
+    static int i = 0;              // Persists across calls of fun
+    short my_var = 1;              // Block scoped (deallocated when going out of scope)
+    int my_var_dbl = (int) my_var; // Explicit casting (works between almost all types)
+    return i;
+}
+
+int main( int argc, char *argv[] ) {
+    if ( ( my_local_int = fun( 10 ) ) ) {
+        // Every c statement is also an expression, i.e. you can do the above!
+    }
+    struct MyStruct test;            // Allocate memory on stack for struct
+    struct MyStruct *test_p = &test; // Pointer to memory where test resides
+    test.el1 = 1;                    // Direct element access
+    test_p->el2 = 2;                 // Via pointer
+    return 0;
+}

semester3/spca/code-examples/00_c/00_basics/03_arrays.c

@@ -0,0 +1,20 @@
+#include <stdint.h>
+#include <stdio.h>
+
+int main( int argc, char *argv[] ) {
+    int data[ 10 ];                  // Initialize array of 10 integers
+    data[ 5 ] = 5;                   // element 5 is now 5
+    *data = 10;                      // element 0 is now 5
+    printf( "%d\n", data[ 0 ] );     // print element 0 (prints 10)
+    printf( "%d\n", *data );         // equivalent as above
+    printf( "%d\n", data[ 5 ] );     // print element 5 (prints 5)
+    printf( "%d\n", *( data + 5 ) ); // equivalent as above
+    int multidim[ 5 ][ 5 ];          // 2-dimensional array
+                                     // We can iterate over it using two for-loops
+    int init_array[ 2 ][ 2 ] = {
+        {1, 2},
+        {3, 4}
+    };                       // We can initialize an array like this
+    int empty_arr[ 4 ] = {}; // Initialized to 0
+    return 0;
+}

semester3/spca/code-examples/00_c/00_basics/04_strings.c

@@ -0,0 +1,15 @@
+#include <stdio.h>
+#include <string.h>
+
+int main( int argc, char *argv[] ) {
+    char hello[ 6 ] = "hello";                           // Using double quotes
+    char world[ 6 ] = { 'w', 'o', 'r', 'l', 'd', '\0' }; // As array
+
+    char src[ 12 ], dest[ 12 ];
+    strncpy( src, "ETHZ", 12 );     // Copy strings (extra elements will be set to \0)
+    strncpy( dest, src, 12 );       // Copy strings (last arg is first n chars to copy)
+    if ( strncmp( src, dest, 12 ) ) // Compare two strings. Returns 1 if src > dest
+        printf( "Hello World" );
+    strncat( dest, " is in ZH", 12 ); // Concatenate strings
+    return 0;
+}

semester3/spca/code-examples/00_c/01_preprocessor/00_macros.c

@@ -0,0 +1,28 @@
+#include <stdio.h>
+#include <stdlib.h>
+#define FOO      BAZ
+#define BAR( x ) ( x + 3 )
+#define SKIP_SPACES( p )                                        \
+    do {                                                        \
+        while ( p > 0 ) { p--; }                                \
+    } while ( 0 )
+#define COMMAND( c ) { #c, c##_command } // Produces { "<val(c)>", "<val(c)>_command" }
+
+#ifdef FOO // If macro is defined, ifndef for if not defined
+    #define COURSE "SPCA"
+#else
+    #define COURSE "Systems Programming and Computer Architecture"
+#endif
+
+#if 1
+    #define OUT HELLO // if statement
+#endif
+
+int main( int argc, char *argv[] ) {
+    int i = 10;
+    SKIP_SPACES( i );
+
+    printf( "%s", COURSE );
+
+    return EXIT_SUCCESS;
+}

semester3/spca/parts/00_c/00_intro.tex

@@ -13,3 +13,5 @@ This of course leads to \texttt{C} performing excellently and there are many pro
 but instead optimized \texttt{C} code that is then compiled into machine code using a \texttt{C} compiler.
 This has a number of benefits, most notably that \texttt{C} compilers can produce very efficient assembly,
 as lots of effort is put into the \texttt{C} compilers by the hardware manufacturers.
+
+There are many great \lC\ tutorials out there, a simple one (as for many other languages too) can be found \hlhref{https://www.w3schools.com/c/index.php}{here}

semester3/spca/parts/00_c/01_basics/00_intro.tex

@@ -1,13 +1,12 @@
-\subsection{The Syntax}
+\subsection{Basics}
 \texttt{C} uses a very similar syntax as many other programming languages, like \texttt{Java}, \texttt{JavaScript} and many more\dots
 to be precise, it is \textit{them} that use the \texttt{C} syntax, not the other way around. So:
-\inputcodewithfilename{c}{code-examples/00_c/}{00_intro.c}
+\inputcodewithfilename{c}{code-examples/00_c/00_basics/}{00_intro.c}
 
 In \texttt{C} we are referring to the implementation of a function as a \bi{(function) definition} (correspondingly, \textit{variable definition}, if the variable is initialized)
 and to the definition of the function signature (or variables, without initializing them) as the \bi{(function) declaration} (or, correspondingly, \textit{variable declaration}).
 
 \texttt{C} code is usuallt split into the source files, ending in \texttt{.c} (where the local functions and variables are declared, as well as all function definitions)
-and the header files, ending in \texttt{.h}, where the external declarations are defined. Usually, no definition of functions are in the \texttt{.h} files
-\inputcodewithfilename{c}{code-examples/00_c/}{01_func.h}
-
-\inputcodewithfilename{c}{code-examples/00_c/}{01_func.c}
+and the header files, ending in \texttt{.h}, usually sharing the filename of the source file, where the external declarations are defined.
+By convention, no definition of functions are in the \texttt{.h} files, and neither variables, but there is nothing preventing you from putting them there.
+\inputcodewithfilename{c}{code-examples/00_c/00_basics/}{01_func.h}

semester3/spca/parts/00_c/01_basics/01_control-flow.tex

@@ -0,0 +1,14 @@
+\newpage
+\subsubsection{Control Flow}
+Many of the control-flow structures of \texttt{C} can be found in the below code snippet.
+A note of caution when using goto: It is almost never a good idea (can lead to unexpected behaviour, is hard to maintain, etc).
+Where it however is very handy is for error recovery (and cleanup functions) and early termination of multiple loops (jumping out of a loop).
+So, for example, if you have to run multiple functions to set something up and one of them fails,
+you can jump to a label and have all cleanup code execute that you have specified there.
+And because the labels are (as in Assembly) simply skipped over during execution, you can make very nice cleanup code.
+We can also use \texttt{continue} and \texttt{break} statements similarly to \texttt{Java}, they do not however accept labels.
+(Reminder: \texttt{continue} skips the loop body and goes to the next iteration)
+
+\inputcodewithfilename{c}{code-examples/00_c/00_basics/}{01_func.c}
+
+

semester3/spca/parts/00_c/01_basics/02_declarations.tex

@@ -0,0 +1,39 @@
+\newpage
+\subsubsection{Declarations}
+We have already seen a few examples for how \texttt{C} handles declarations.
+In concept they are similar (and scoping works the same) to most other \texttt{C}-like programming languages, including \texttt{Java}.
+\inputcodewithfilename{c}{code-examples/00_c/00_basics/}{02_declarations.c}
+
+A peculiarity of \texttt{C} is that the bit-count is not defined by the language, but rather the hardware it is compiled for.
+\begin{fullTable}{llll}{\texttt{C} data type & typical 32-bit & ia32  & x86-64}{Comparison of byte-sizes for each datatype on different architectures}
+    \texttt{char}               & 1              & 1     & 1       \\
+    \texttt{short}              & 2              & 2     & 2       \\
+    \texttt{int}                & 4              & 4     & 4       \\
+    \texttt{long}               & 4              & 4     & 8       \\
+    \texttt{long long}          & 8              & 8     & 8       \\
+    \texttt{float}              & 4              & 4     & 4       \\
+    \texttt{double}             & 4              & 8     & 8       \\
+    \texttt{long double}        & 8              & 10/12 & 16      \\
+\end{fullTable}
+
+\drmvspace
+By default, integers in \lC\ are \texttt{signed}, to declare an unsigned integer, use \texttt{unsigned int}.
+Since it is hard and annoying to remember the number of bytes that are in each data type, \texttt{C99} has introduced the extended integer types,
+which can be imported from \texttt{stdint.h} and are of form \texttt{int<bit count>\_t} and \texttt{uint<bit count>\_t},
+where we substitute the \texttt{<bit count>} with the number of bits (have to correspond to a valid type of course).
+
+Another notable difference of \texttt{C} compared to other languages is that \texttt{C} doesn't natively have a \texttt{boolean} type,
+by convention a \texttt{short} is used to represent it, where any non-zero value means \texttt{true} and \texttt{0} means \texttt{false}.
+Since boolean types are quite handy, the \texttt{!} syntax for negation turns any non-zero value of any integer type into zero and vice-versa.
+\texttt{C99} has added support for a bool type via \texttt{stdbool.h}, which however is still an integer.
+
+Notably, \texttt{C} doesn't have a very rigid type system and lower bit-count types are implicitly cast to higher bit-count data types, i.e.
+if you add a \texttt{short} and an \texttt{int}, the \texttt{short} is cast to \texttt{short} (bits 16-31 are set to $0$) and the two are added.
+Explicit casting between almost all types is also supported.
+Some will force a change of bit representation, but most won't (notably, when casting to and from \texttt{float}-like types, minus to \texttt{void})
+
+Another important feature is that every \lC\ statement is also an expression, see above code block for example.
+
+The \texttt{void} type has \bi{no} value and is used for untyped pointers and declaring functions with no return value
+
+It is also possible to define a custom type using \texttt{typedef <type it represents> <name of the new type>}

semester3/spca/parts/00_c/01_basics/03_operators.tex

@@ -0,0 +1,45 @@
+\subsubsection{Operators}
+The list of operators in \lC\ is similar to the one of \texttt{Java}, etc.
+In Table \ref{tab:c-operators}, you can see an overview of the operators, sorted by precedence in descending order.
+You may notice that the \verb|&| and \verb|*| operators appear twice. The higher precedence occurrence is the address operator and dereference, respectively,
+and the lower precedence is \texttt{bitwise and} and \texttt{multiplication}, respectively.
+
+Very low precedence belongs to boolean operators \verb|&&| and \texttt{||}, as well as the ternary operator and assignment operators
+\begin{table}[h!]
+    \begin{tables}{ll}{Operator                                  & Associativity}
+              \texttt{() [] -> .}                            & Left-to-right                \\
+              \verb|! ~ ++ -- + - * & (type) sizeof|         & Right-to-left  \\
+              \verb|* / %|                                   & Left-to-right  \\
+              \verb|+ -|                                     & Left-to-right  \\
+              \verb|<< >>|                                   & Left-to-right  \\
+              \verb|< <= >= >|                               & Left-to-right  \\
+              \verb|== !=|                                   & Left-to-right  \\
+              \verb|&| (logical and)                         & Left-to-right  \\
+              \verb|^| (logical xor)                         & Left-to-right  \\
+              \texttt{|} (logical or)                        & Left-to-right                \\
+              \verb|&&| (boolean and)                        & Left-to-right  \\
+              \texttt{||} (boolean or)                       & Left-to-right                \\
+              \texttt{? :} (ternary)                         & Right-to-left                \\
+              \verb|= += -= *= /= %= &= ^=||\verb|= <<= >>=| & Right-to-left  \\
+              \verb|,|                                       & Left-to-right  \\
+    \end{tables}
+    \caption{\lC\ operators ordered in descending order by precedence}
+    \label{tab:c-operators}
+\end{table}
+
+\shade{blue}{Associativity} 
+\begin{itemize}
+    \item Left-to-right: $A + B + C \mapsto (A + B) + C$
+    \item Right-to-left: \texttt{A += B += C} $\mapsto$ \texttt{(A += B) += C}
+\end{itemize}
+
+As it should be, boolean and, as well as boolean or support early termination.
+
+The ternary operator works as in other programming languages \verb|result = expr ? res_true : res_false;|
+
+As previously touched on, every statement is also an expression, i.e. the following works
+\mint{c}|printf("%s", x = foo(y)); // prints output of foo(y) and x has that value|
+
+Pre-increment (\texttt{++i}, new value returned) and post-increment (\texttt{i++}, old value returned) are also supported by \lC.
+
+\lC\ has an \texttt{assert} statement, but do not use it for error handling. The basic syntax is \texttt{assert( expr );}

semester3/spca/parts/00_c/01_basics/04_arrays.tex

@@ -0,0 +1,7 @@
+\newpage
+\subsubsection{Arrays}
+\lC\ compiler does not do any array bound checks! Thus, always check array bounds.
+Unlike some other programming languages, arrays are \bi{not} dynamic length.
+
+The below snippet includes already some pointer arithmetic tricks. The variable \texttt{data} is a pointer to the first element of the array.
+\inputcodewithfilename{c}{code-examples/00_c/00_basics/}{03_arrays.c}

semester3/spca/parts/00_c/01_basics/05_strings.tex

@@ -0,0 +1,6 @@
+\subsubsection{Strings}
+\lC\ doesn't have a \texttt{string} data type, but rather, strings are represented (when using \texttt{ASCII}) as \texttt{char} arrays,
+with length of the array $n + 1$ (where $n$ is the number of characters of the string).
+The extra element is the termination character, called the \texttt{null character}, denoted \verb|\0|.
+To determine the actual length of the string (as it may be padded), we can use \verb|strnlen(str, maxlen)| from \texttt{string.h}
+\inputcodewithfilename{c}{code-examples/00_c/00_basics/}{04_strings.c}

semester3/spca/parts/00_c/01_basics/06_integers.tex

@@ -0,0 +1,39 @@
+\subsubsection{Integers in C}
+As a reminder, integers are encoded as follows in big endian notation, with $x_i$ being the $i$-th bit and $w$ being the number of bits used to represent the number:
+\begin{itemize}[noitemsep]
+    \item \bi{Unsigned}: $\displaystyle \sum_{i = 0}^{w - 1} x_i \cdot 2^i$
+    \item \bi{Signed}: $\displaystyle -x_{w - 1} \cdot 2^{w - 1} + \sum_{i = 0}^{w - 1} x_i \cdot 2^i$ (two's complement notation, with $x_{w - 1}$ being the sign-bit)
+\end{itemize}
+The minimum number representable is $0$ and $-2^{w - 1}$, respectively, whereas the maximum number representable is $2^w - 1$ and $2^{w - 1} - 1$.
+\verb|limits.h| defines constants for the minimum and maximum values of different types, e.g. \verb|ULONG_MAX| or \verb|LONG_MAX| and \verb|LONG_MIN|
+
+We can use the shift operators to multiply and divide by two. Shift operations are usually \textit{much} cheaper than multiplication and division.
+Left shift (\texttt{u << k} in \lC) always fills with zeros and throws away the extra bits on the left (equivalent to multiplication by $2^k$),
+whereas right shift (\texttt{u >> k} in \lC) is implementation-defined,
+either arithmetic (fill with most significant bit, division by $2^k$. This however rounds incorrectly, see below)
+or logical shift (fill with zeros, unsigned division by $2^k$).
+
+Signed division using arithmetic right shifts has the issue of incorrect rounding when number is $< 0$.
+Instead, we represent $s / 2^k = s + (2^k - 1) \texttt{ >> } k$ for $s < 0$ and $s / 2^k = s >> k$ for $s > 0$
+
+\bi{In expressions, signed values are implicitly cast to unsigned}
+
+This can lead to all sorts of nasty exploits (e.g. provide $-1$ as the argument to \texttt{memcpy} and watch it burn, this was an actual exploit in FreeBSD)
+
+\fhlc{Cyan}{Addition \& Subtraction}
+
+A nice property of the two's complement notation is that addition and subtraction works exactly the same as in normal notation, due to over- and underflow.
+This also obviously means that it implements modular arithmetic, i.e.
+\mrmvspace
+\begin{align*}
+    \texttt{Add}_w (u, v) = u + v \text{ mod } 2^w \ \text{ and } \ \texttt{Sub}_w (u, v) = u - v \text{ mod } 2^w
+\end{align*}
+
+\mrmvspace
+\fhlc{Cyan}{Multiplication \& Division}
+
+Unsigned multiplication with addition forms a commutative ring.
+Again, it is doing modular arithmetic and
+\begin{align*}
+    \texttt{UMult}_w (u, v) = u \cdot v \text{ mod } 2^w
+\end{align*}

semester3/spca/parts/00_c/01_basics/07_pointers.tex

@@ -0,0 +1 @@
+\subsubsection{Pointers}

semester3/spca/parts/00_c/02_preprocessor.tex

@@ -0,0 +1,28 @@
+\newpage
+\subsection{The C preprocessor}
+To have \texttt{gcc} stop compiliation after running through \texttt{cpp}, the \texttt{C preprocessor}, use \texttt{gcc -E <file name>}.
+
+Imports in \lC\ are handled by the preprocessor, that for each \verb|#include <file1.h>|, the preprocessor simply copies the contents of the file recursively into one file.
+
+Depending on if we use \verb|#include <file1.h>| or \verb|#include "file1.h"| the preprocessor will search for the file either in the system headers or in the project directory.
+Be wary of including files twice, as the preprocessor will recursively include all files (i.e. it will include files from the files we included)
+
+The \lC\ preprocessor gives us what are called \texttt{preprocessor macros}, which have the format \verb|#define NAME SUBSTITUTION|.
+\rmvspace
+
+\inputcodewithfilename{c}{code-examples/00_c/01_preprocessor/}{00_macros.c}
+
+To avoid issues with semicolons at the end of preprocessor macros that wrap statements that cannot end in semicolons, we can use a concept called semicolon swallowing.
+For that, we wrap the statements in a \texttt{do \dots\ while(0)} loop, which is removed by the compiler on compile, also taking with it the semicolon.
+
+There are also a number of predefined macros:
+\begin{itemize}[noitemsep]
+    \item \verb|__FILE__|: Filename of processed file
+    \item \verb|__LINE__|: Line number of this usage of macro
+    \item \verb|__DATE__|: Date of processing
+    \item \verb|__TIME__|: Time of processing
+    \item \verb|__STDC__|: Set if ANSI Standard \lC\ compiler is used
+    \item \verb|__STDC_VERSION__|: The version of Standard \lC\ being compiled
+    \item \dots many more
+\end{itemize}
+In headers, we typically use \verb|#ifndef __FILENAME_H_| followed by a \verb|#define __FILENAME_H_| or the like to check if the header was already included before

semester3/spca/spca-summary.tex

@@ -7,6 +7,8 @@
 \usepackage{lmodern}
 \setFontType{sans}
 
+\newcommand{\lC}{\texttt{C}}
+
 \begin{document}
 \startDocument
 \usetcolorboxes
@@ -58,7 +60,15 @@
 \newsection
 \section{The C Programming Language}
 \input{parts/00_c/00_intro.tex}
-\input{parts/00_c/01_syntax.tex}
+\input{parts/00_c/01_basics/00_intro.tex}
+\input{parts/00_c/01_basics/01_control-flow.tex}
+\input{parts/00_c/01_basics/02_declarations.tex}
+\input{parts/00_c/01_basics/03_operators.tex}
+\input{parts/00_c/01_basics/04_arrays.tex}
+\input{parts/00_c/01_basics/05_strings.tex}
+\input{parts/00_c/01_basics/06_integers.tex}
+\input{parts/00_c/01_basics/07_pointers.tex}
+\input{parts/00_c/02_preprocessor.tex}
 
 
 % ── Intro to x86 asm ────────────────────────────────────────────────