Traditional (Insecure):
┌────────────────────────────────┐
│  Stack                         │  Executable!
│  ├─ Return addresses           │  ← Attacker can inject shellcode
│  └─ Local variables            │
├────────────────────────────────┤
│  Heap                          │  Executable!
│  ├─ Malloc'd buffers           │  ← Attacker can put code here
│  └─ Dynamic data               │
├────────────────────────────────┤
│  Data/BSS                      │  Executable!
└────────────────────────────────┘

With NX/DEP:
┌────────────────────────────────┐
│  Stack (NX bit set)            │  NOT Executable
│  ├─ Return addresses           │  ← Shellcode won't execute!
│  └─ Local variables            │
├────────────────────────────────┤
│  Heap (NX bit set)             │  NOT Executable
│  ├─ Malloc'd buffers           │
│  └─ Dynamic data               │
├────────────────────────────────┤
│  Data/BSS (NX bit set)         │  NOT Executable
├────────────────────────────────┤
│  Text (executable)             │  Executable
│  └─ Program code               │
└────────────────────────────────┘

// Kernel sets page table entry (PTE) NX bit

// x86-64 page table entry structure
struct pte {
    unsigned long present : 1;     // Page is in memory
    unsigned long rw : 1;          // Read/Write permission
    unsigned long user : 1;        // User-mode accessible
    unsigned long pwt : 1;         // Page write-through
    unsigned long pcd : 1;         // Page cache disabled
    unsigned long accessed : 1;    // Page was accessed
    unsigned long dirty : 1;       // Page was written
    unsigned long pat : 1;         // Page attribute table
    unsigned long global : 1;      // Global page
    unsigned long avail : 3;       // Available for OS use
    unsigned long pfn : 40;        // Physical frame number
    unsigned long avail2 : 11;     // Available
    unsigned long nx : 1;          // NO-EXECUTE bit (bit 63)
};

// Kernel code for stack allocation (simplified from mm/mmap.c)
unsigned long do_mmap(struct file *file, unsigned long addr,
                     unsigned long len, unsigned long prot,
                     unsigned long flags, unsigned long pgoff) {
    struct vm_area_struct *vma;

    vma = vm_area_alloc(current->mm);
    vma->vm_start = addr;
    vma->vm_end = addr + len;

    // Stack protection: read/write but NOT executable
    if (flags & MAP_STACK) {
        vma->vm_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
        // NX bit will be set in page table entries
    }

    // Code segment: executable but NOT writable
    if (prot & PROT_EXEC) {
        vma->vm_flags |= VM_EXEC;
        vma->vm_flags &= ~VM_WRITE;  // W^X: Write XOR Execute
    }

    return addr;
}

# Check if NX is enabled
dmesg | grep NX
# NX (Execute Disable) protection: active

# Check process memory maps
cat /proc/self/maps
# 7ffff7dd1000-7ffff7df3000 r-xp ... /lib/x86_64-linux-gnu/ld-2.31.so  (executable)
# 7ffff7df3000-7ffff7df4000 r--p ... /lib/x86_64-linux-gnu/ld-2.31.so  (read-only)
# 7ffffffde000-7ffffffff000 rw-p ... [stack]                           (no 'x'!)

# Check if binary has NX enabled
readelf -l /bin/ls | grep GNU_STACK
# GNU_STACK      0x000000 0x00000000 0x00000000 0x00000 0x00000 RW  0x10
#                                                                 ^^^ (RW, not RWE)

Without ASLR (Predictable):
┌─────────────────────────────────┐
│ Stack:         0x7ffffffde000    │  ← Always same address!
│ Heap:          0x555555559000    │  ← Attacker knows these
│ libc:          0x7ffff7a0d000    │  ← Can hardcode in exploit
│ Program:       0x555555554000    │
│ vDSO:          0x7ffff7fc9000    │
└─────────────────────────────────┘

With ASLR (Randomized):
Run 1:                            Run 2:
┌─────────────────────────────┐  ┌─────────────────────────────┐
│ Stack:    0x7ffc9e3a2000    │  │ Stack:    0x7ffe1b8d6000    │
│ Heap:     0x5643ab123000    │  │ Heap:     0x55e2d9abc000    │
│ libc:     0x7f8a2e456000    │  │ libc:     0x7f3c81de2000    │
│ Program:  0x5643ab11f000    │  │ Program:  0x55e2d9ab8000    │
│ vDSO:     0x7f8a2f1c3000    │  │ vDSO:     0x7f3c82b4f000    │
└─────────────────────────────┘  └─────────────────────────────┘
                ↑ Different every time! ↑

// Simplified from arch/x86/mm/mmap.c

unsigned long arch_mmap_rnd(void) {
    unsigned long rnd;

    // Get random bits from kernel PRNG
    if (mmap_is_ia32()) {
        rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
    } else {
        rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
    }

    return rnd << PAGE_SHIFT;  // Align to page boundary
}

unsigned long arch_get_unmapped_area(struct file *filp,
                                    unsigned long addr,
                                    unsigned long len,
                                    unsigned long pgoff,
                                    unsigned long flags) {
    struct mm_struct *mm = current->mm;
    struct vm_area_struct *vma;
    unsigned long start_addr;

    // Add random offset
    if (!(flags & MAP_FIXED)) {
        // Random offset for ASLR
        start_addr = mm->mmap_base + arch_mmap_rnd();
    } else {
        start_addr = addr;
    }

    // Find free region starting at randomized address
    vma = find_vma(mm, start_addr);
    // ... allocation logic ...

    return start_addr;
}

ASLR Entropy (bits of randomness):

Stack:      19 bits (on x86-64)  = 524,288 possible locations
Heap:       13 bits              = 8,192 possible locations
Libraries:  28 bits              = 268 million possible locations
PIE binary: 28 bits              = 268 million possible locations

Formula: Brute force attempts = 2^(entropy_bits)

Example: 28 bits → attacker needs avg 2^27 = 134 million attempts
If each attempt crashes the program (1 sec delay):
  134 million seconds = 1,551 days!

But if process doesn't crash (fork server):
  Attacker can brute force in minutes!

// Kernel virtual address randomization (from arch/x86/boot/compressed/kaslr.c)

void choose_random_location(unsigned long input,
                           unsigned long input_size,
                           unsigned long *output,
                           unsigned long output_size,
                           unsigned long *virt_addr) {
    unsigned long random_addr, min_addr;

    // Get entropy from:
    // 1. RDRAND/RDSEED (CPU instructions)
    // 2. RDTSC (timestamp counter)
    // 3. Boot parameters
    random_addr = get_random_long();

    // Align and constrain to valid kernel address range
    min_addr = min(*output, *virt_addr);
    random_addr = find_random_phys_addr(min_addr, output_size);

    *output = random_addr;
    *virt_addr = random_addr + __START_KERNEL_map;
}

# View ASLR setting
cat /proc/sys/kernel/randomize_va_space
# 0 = Disabled
# 1 = Randomize stack, libraries, mmap
# 2 = Full randomization (includes heap)

# Enable full ASLR
echo 2 | sudo tee /proc/sys/kernel/randomize_va_space

# Test ASLR
for i in {1..5}; do cat /proc/self/maps | grep stack; done
# 7ffc12345000-7ffc12366000 (different)
# 7ffe9abcd000-7ffe9abee000 (different)
# 7ffd45678000-7ffd45699000 (different)

Stack Layout with Canary:
─────────────────────────

High Address
┌──────────────────────┐
│  Return Address      │  ← Protected by canary!
├──────────────────────┤
│  Saved Frame Pointer │
├──────────────────────┤
│  CANARY (random)     │  ← __stack_chk_guard
├──────────────────────┤
│  Local Variables     │  ← Buffer overflow starts here
│  char buf[100];      │
└──────────────────────┘
Low Address

Attack Scenario:
1. Attacker overflows buf
2. Overwrites canary (but doesn't know correct value)
3. Function returns
4. Kernel checks: canary == __stack_chk_guard?
5. Mismatch → Stack smashing detected! → Abort

// Original vulnerable code
void vulnerable_function(char *input) {
    char buffer[64];
    strcpy(buffer, input);  // Buffer overflow!
}

// Compiled with -fstack-protector-strong
void vulnerable_function(char *input) {
    char buffer[64];
    unsigned long canary = __stack_chk_guard;  // Load canary

    strcpy(buffer, input);

    if (canary != __stack_chk_guard) {
        __stack_chk_fail();  // Stack smashing detected!
    }
}

// __stack_chk_fail() implementation (in glibc)
void __attribute__((noreturn)) __stack_chk_fail(void) {
    __fortify_fail("stack smashing detected");
}

void __attribute__((noreturn)) __fortify_fail(const char *msg) {
    // Log the error
    syslog(LOG_CRIT, "%s: %s terminated", __progname, msg);

    // Terminate immediately
    abort();
}

# -fstack-protector: Protect functions with vulnerable buffers
gcc -fstack-protector vulnerable.c

# -fstack-protector-strong: Protect more functions (recommended)
gcc -fstack-protector-strong vulnerable.c

# -fstack-protector-all: Protect ALL functions (performance cost)
gcc -fstack-protector-all vulnerable.c

# Check if binary has stack protector
readelf -s /bin/ls | grep stack_chk
#    123: 00000000000060a0     8 OBJECT  GLOBAL DEFAULT   25 __stack_chk_fail@@GLIBC_2.4

// Vulnerable code
struct ops {
    void (*process)(char *data);
};

struct ops *vtable = malloc(sizeof(struct ops));
vtable->process = legitimate_function;

// ... buffer overflow ...
// Attacker overwrites vtable->process to point to shellcode

vtable->process(data);  // Calls shellcode!

// Compiler generates CFI check before indirect call

// Original code
vtable->process(data);

// Compiled with CFI
void *target = vtable->process;

// Check 1: Is target a valid code address?
if (!is_valid_code_address(target)) {
    cfi_violation();
}

// Check 2: Is target in allowed set for this call site?
if (!is_allowed_target(call_site_id, target)) {
    cfi_violation();
}

// Perform call
((void (*)(char *))target)(data);

Function Signature-Based CFI:

void func_a(int x);           ← Set 1: void (int)
void func_b(int x);           ←
int func_c(int x, int y);     ← Set 2: int (int, int)
int func_d(int x, int y);     ←
void func_e(void);            ← Set 3: void (void)

Rule: Indirect call with signature void(int) can only jump to Set 1.

Implementation:
1. Compiler assigns ID to each function signature
2. Compiler tags each function with its ID
3. Before indirect call, check ID matches expected signature

# Compile with CFI
clang -fsanitize=cfi -flto program.c

# CFI variants
-fsanitize=cfi-icall     # Indirect calls
-fsanitize=cfi-vcall     # Virtual function calls (C++)
-fsanitize=cfi-cast      # Bad casts

# Generate CFI violation report
UBSAN_OPTIONS=print_stacktrace=1 ./program

# Example violation
SUMMARY: UndefinedBehaviorSanitizer: cfi-check-fail
pc 0x55f8a2b3c4d5 in main program.c:42

Regular Stack           Shadow Stack (Protected)
─────────────────       ────────────────────────
┌─────────────┐         ┌─────────────┐
│  Ret Addr 3 │ ◄──────►│  Ret Addr 3 │  (Copy)
├─────────────┤         ├─────────────┤
│  Locals     │         │             │
├─────────────┤         │             │
│  Ret Addr 2 │ ◄──────►│  Ret Addr 2 │
├─────────────┤         ├─────────────┤
│  Locals     │         │             │
├─────────────┤         │             │
│  Ret Addr 1 │ ◄──────►│  Ret Addr 1 │
└─────────────┘         └─────────────┘
     ↑                         ↑
  Writable!              Read-Only!
  (Attacker can          (CPU enforced,
   modify)                not accessible)

On Function Return:
1. Pop return address from regular stack → addr_stack
2. Pop return address from shadow stack → addr_shadow
3. Compare: addr_stack == addr_shadow?
4. Mismatch → #CP exception (Control Protection) → Crash

// CPU features for shadow stack
#define X86_FEATURE_SHSTK  (1 << 7)   // Shadow stack
#define X86_FEATURE_IBT    (1 << 20)  // Indirect branch tracking

// Enable shadow stack (kernel code)
void cet_enable(void) {
    u64 msr_val;

    // Check if CPU supports CET
    if (!boot_cpu_has(X86_FEATURE_SHSTK))
        return;

    // Enable in MSR
    rdmsrl(MSR_IA32_S_CET, msr_val);
    msr_val |= MSR_IA32_CET_SHSTK_EN;  // Enable shadow stack
    wrmsrl(MSR_IA32_S_CET, msr_val);

    // Allocate shadow stack for current thread
    unsigned long ssp = alloc_shstk();  // Shadow stack pointer
    wrmsrl(MSR_IA32_PL3_SSP, ssp);
}

// Shadow stack operations (new x86 instructions)
// INCSSP - Increment shadow stack pointer
// RDSSP  - Read shadow stack pointer
// SAVEPREVSSP - Save previous SSP
// RSTORSSP - Restore SSP
// WRSSD/WRSSQ - Write to shadow stack
// SETSSBSY - Mark shadow stack busy

// ARM PAuth uses cryptographic signing of return addresses

// On function prologue:
// PAC (Pointer Authentication Code) = sign(return_addr, context_key)
// Store: PAC || return_addr on stack

// On function epilogue:
// Verify: sign(return_addr, context_key) == PAC?
// If mismatch → Fault

// ARM instructions
PACIA  X30, SP   // Sign return address (X30) with stack pointer (SP)
RETAA            // Authenticate and return

// Implemented in libc (not hardware-protected)

__thread void *shadow_stack[1024];
__thread int shadow_stack_ptr = 0;

void function_entry(void *return_addr) {
    shadow_stack[shadow_stack_ptr++] = return_addr;
}

void function_exit(void *return_addr) {
    void *expected = shadow_stack[--shadow_stack_ptr];
    if (return_addr != expected) {
        abort();  // Stack corruption detected
    }
}

// Weakness: Attacker can corrupt shadow_stack too if memory bug exists
// Strength: Works on CPUs without hardware support

User/Group/Other Permissions:

File: /etc/shadow
Owner: root
Group: shadow
Permissions: rw-r-----
             │││││││││
             ││││││││└─ Other: no permissions
             │││││││└── Other: no permissions
             ││││││└─── Other: no permissions
             │││││└──── Group: read
             ││││└───── Group: no write
             │││└────── Group: no execute
             ││└─────── Owner: read
             │└──────── Owner: write
             └───────── Owner: no execute

Problem: All-or-nothing root privileges!
- Process needs root to bind port 80 → runs fully as root
- Process needs root to read /etc/shadow → runs fully as root

// From /usr/include/linux/capability.h

#define CAP_CHOWN            0   // Change file ownership
#define CAP_DAC_OVERRIDE     1   // Bypass file permission checks
#define CAP_DAC_READ_SEARCH  2   // Bypass read/search permissions
#define CAP_FOWNER           3   // Bypass permission checks on file operations
#define CAP_FSETID           4   // Don't clear setuid/setgid bits
#define CAP_KILL             5   // Bypass permission checks for sending signals
#define CAP_SETGID           6   // Make arbitrary setgid calls
#define CAP_SETUID           7   // Make arbitrary setuid calls
#define CAP_NET_BIND_SERVICE 10  // Bind to ports < 1024
#define CAP_NET_RAW          13  // Use RAW and PACKET sockets
#define CAP_SYS_ADMIN        21  // Lots of system admin operations
#define CAP_SYS_PTRACE       19  // Trace arbitrary processes
#define CAP_SYS_MODULE       16  // Load/unload kernel modules
// ... 41 capabilities total ...

// Each process has 5 capability sets

struct cred {
    // ...
    kernel_cap_t cap_inheritable;  // Inherited by exec'd programs
    kernel_cap_t cap_permitted;    // Can be enabled (superset)
    kernel_cap_t cap_effective;    // Actually active NOW
    kernel_cap_t cap_bset;         // Bounding set (limits inheritable)
    kernel_cap_t cap_ambient;      // Ambient set (new in Linux 4.3)
};

// Each set is a 64-bit bitmask (2^64 possible capabilities)
typedef struct {
    __u32 cap[_LINUX_CAPABILITY_U32S_3];  // 2 × 32 bits
} kernel_cap_t;

Permitted (P):   Capabilities the process CAN use
Effective (E):   Capabilities CURRENTLY active
Inheritable (I): Capabilities that can be inherited across exec
Ambient (A):     Capabilities automatically granted after exec
Bounding (B):    Upper limit on capabilities (cannot gain capabilities not in B)

On exec():
P' = (P & I) | (F_permitted & F_inheritable) | A
E' = F_effective ? P' : A
I' = I
A' = A & P' & I'

Where F_* are file capabilities (set on executable)

#include <seccomp.h>

int main() {
    scmp_filter_ctx ctx;

    // Create filter: default action = KILL
    ctx = seccomp_init(SCMP_ACT_KILL);

    // Allow essential syscalls
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(read), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(write), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(exit), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(exit_group), 0);

    // Allow open only for specific file
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(open), 1,
                     SCMP_A0(SCMP_CMP_EQ, (scmp_datum_t)"/tmp/allowed.txt"));

    // Load filter into kernel
    seccomp_load(ctx);

    // After this point, any syscall not explicitly allowed → SIGSYS (kill)

    open("/tmp/allowed.txt", O_RDONLY);  // ✓ Allowed
    open("/etc/passwd", O_RDONLY);       // ✗ Killed!

    seccomp_release(ctx);
    return 0;
}

// Compile: gcc -o sandbox sandbox.c -lseccomp

#include <linux/filter.h>
#include <linux/seccomp.h>
#include <sys/prctl.h>

void install_seccomp_filter() {
    struct sock_filter filter[] = {
        // Load syscall number
        BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
                 offsetof(struct seccomp_data, nr)),

        // Allow exit syscall
        BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_exit, 0, 1),
        BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),

        // Allow write syscall
        BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_write, 0, 1),
        BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),

        // Kill on any other syscall
        BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_KILL),
    };

    struct sock_fprog prog = {
        .len = sizeof(filter) / sizeof(filter[0]),
        .filter = filter,
    };

    // Enable seccomp
    prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);  // Cannot gain privileges
    prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
}

int main() {
    install_seccomp_filter();

    write(1, "Hello\n", 6);  // ✓ Allowed
    getpid();                 // ✗ Killed (SIGSYS)

    return 0;
}

# Chrome sandbox
ps aux | grep chrome
# ... --type=renderer --enable-sandbox ...

# Docker seccomp profile
docker run --security-opt seccomp=default.json alpine sh

# systemd service with seccomp
cat /etc/systemd/system/myservice.service
# [Service]
# SystemCallFilter=@system-service
# SystemCallFilter=~@privileged @resources

# View seccomp status of process
grep Seccomp /proc/self/status
# Seccomp: 2  (mode 2 = filter active)

DAC says: "Can user alice read file.txt?"
  → Check: alice's UID vs file owner, group, permissions

SELinux says: "Can process with label X access file with label Y?"
  → Check: Policy rules for (process_label, file_label, operation)

Both must succeed for access!

┌─────────────────────────────────────────────────┐
│              SELinux Policy                      │
│  ┌───────────────────────────────────────────┐  │
│  │  Type Enforcement (TE) Rules              │  │
│  │  allow httpd_t http_port_t:tcp_socket bind│  │
│  │  allow httpd_t httpd_sys_content_t:file r │  │
│  └───────────────────────────────────────────┘  │
│  ┌───────────────────────────────────────────┐  │
│  │  Security Contexts (Labels)               │  │
│  │  user:role:type:level                     │  │
│  │  system_u:system_r:httpd_t:s0             │  │
│  └───────────────────────────────────────────┘  │
└─────────────────────────────────────────────────┘
                     ↓
         ┌──────────────────────┐
         │  LSM (Linux Security │
         │  Module) Framework   │
         └──────────────────────┘
                     ↓
      Kernel enforces at runtime

# View file context
ls -Z /var/www/html/index.html
# system_u:object_r:httpd_sys_content_t:s0 /var/www/html/index.html
#    │        │           │              │
#    │        │           │              └─ MLS level (sensitivity)
#    │        │           └─ Type (most important!)
#    │        └─ Role
#    └─ User

# View process context
ps -Z 1234
# system_u:system_r:httpd_t:s0 /usr/sbin/httpd

# Change file context
chcon -t httpd_sys_content_t /var/www/html/newfile.html

# Restore default contexts
restorecon -Rv /var/www/html/

# From /etc/selinux/targeted/policy/policy.conf (compiled binary)

# Allow httpd to bind TCP sockets on http_port_t (port 80, 443)
allow httpd_t http_port_t:tcp_socket { bind listen };

# Allow httpd to read files labeled httpd_sys_content_t
allow httpd_t httpd_sys_content_t:file { read getattr open };

# Allow httpd to write to log files
allow httpd_t httpd_log_t:file { write append create };

# Deny (example)
# If no rule allows, default is deny!
# httpd_t trying to access user_home_t → DENIED

# View denials
ausearch -m avc -ts recent

# Example denial
type=AVC msg=audit(1234567890.123:456): avc: denied { read } for pid=1234
  comm="httpd" name="secret.txt" dev="sda1" ino=123456
  scontext=system_u:system_r:httpd_t:s0
  tcontext=system_u:object_r:user_home_t:s0
  tclass=file permissive=0

# Translation: httpd_t tried to read user_home_t file → DENIED

# Generate policy module to allow
audit2allow -a -M mypolicy
# module mypolicy 1.0;
# require {
#     type httpd_t;
#     type user_home_t;
#     class file read;
# }
# allow httpd_t user_home_t:file read;

# Install policy module
semodule -i mypolicy.pp

# List loaded modules
semodule -l

# Remove module
semodule -r mypolicy

# List all booleans
getsebool -a | grep httpd
# httpd_can_network_connect --> off
# httpd_can_network_connect_db --> off
# httpd_enable_cgi --> on

# Enable httpd network connections
setsebool -P httpd_can_network_connect on

# -P makes it persistent across reboot

SELinux: "Process with label X can access file with label Y"
  → Requires labeling entire filesystem

AppArmor: "Process can access /var/www/* with read permission"
  → Based on filesystem paths (easier to understand)

# /etc/apparmor.d/usr.sbin.nginx
#include <tunables/global>

/usr/sbin/nginx {
  #include <abstractions/base>
  #include <abstractions/nameservice>

  capability dac_override,
  capability net_bind_service,
  capability setgid,
  capability setuid,

  /etc/nginx/** r,
  /var/log/nginx/** rw,
  /var/www/** r,
  /run/nginx.pid rw,

  # Network
  network inet stream,
  network inet6 stream,

  # Deny everything else (default)
}

# Enforce mode
aa-enforce /usr/sbin/nginx

# Complain mode (log-only)
aa-complain /usr/sbin/nginx

# Disable profile
aa-disable /usr/sbin/nginx

# View status
aa-status
# apparmor module is loaded.
# 12 profiles are loaded.
# 10 profiles are in enforce mode.
# 2 profiles are in complain mode.

# Generate profile automatically
aa-genprof /usr/bin/myapp

# Steps:
# 1. Runs app in learning mode
# 2. Exercise all app functionality
# 3. Reviews logged accesses
# 4. Generates profile

# Manually create profile
cat > /etc/apparmor.d/usr.bin.myapp <<EOF
/usr/bin/myapp {
  #include <abstractions/base>

  /etc/myapp/** r,
  /var/lib/myapp/** rw,
  /tmp/** rw,

  capability net_bind_service,

  deny /etc/shadow r,
}
EOF

# Load profile
apparmor_parser -r /etc/apparmor.d/usr.bin.myapp

// Vulnerable code
if (x < array1_size) {         // Bounds check
    y = array2[array1[x]];     // Out-of-bounds access
}

Without Speculation:
1. Check: x < array1_size?
2. If true, execute access
3. If false, skip

With Speculation (vulnerable):
1. CPU predicts branch will be taken
2. Speculatively executes: y = array2[array1[x]]
   Even if x >= array1_size!
3. Loads array1[x] (out of bounds!)
4. Uses it to index array2
5. array2[...] brought into cache ← SIDE EFFECT!
6. Branch misprediction detected
7. Architectural state rolled back
8. BUT: Cache state NOT rolled back!

Attacker observes cache timing → leaks array1[x]!

// Leak kernel memory from user space

// 1. Flush cache
clflush(probe_array);

// 2. Access kernel memory (should fault, but speculatively executes)
char kernel_byte = *(char *)kernel_address;

// 3. Use leaked byte to index array
char dummy = probe_array[kernel_byte * 4096];
// This brings probe_array[kernel_byte * 4096] into cache

// 4. Branch misprediction, exception raised
// But probe_array[...] is NOW in cache!

// 5. Time accesses to probe_array
for (int i = 0; i < 256; i++) {
    t0 = rdtsc();
    dummy = probe_array[i * 4096];
    t1 = rdtsc();

    if (t1 - t0 < THRESHOLD) {
        // Cache hit! i == kernel_byte
        printf("Leaked kernel byte: 0x%02x\n", i);
    }
}

// Result: Leaked kernel memory byte-by-byte at ~100 KB/s!

Without KPTI:
┌────────────────────────────────────┐
│  User Page Tables                  │
│  ┌──────────────────────────────┐  │
│  │  User Space Mappings          │  │
│  │  0x00000000 - 0x7fffffffffff  │  │
│  ├──────────────────────────────┤  │
│  │  Kernel Space Mappings        │  │
│  │  0xffff800000000000 - ...     │  │ ← Meltdown can read this!
│  └──────────────────────────────┘  │
└────────────────────────────────────┘

With KPTI (two sets of page tables):
┌────────────────────────────────────┐
│  User Page Tables                  │
│  ┌──────────────────────────────┐  │
│  │  User Space Mappings          │  │
│  ├──────────────────────────────┤  │
│  │  Minimal Kernel (entry/exit)  │  │ ← Only small trampoline
│  └──────────────────────────────┘  │
└────────────────────────────────────┘

┌────────────────────────────────────┐
│  Kernel Page Tables                │
│  ┌──────────────────────────────┐  │
│  │  User Space Mappings          │  │
│  ├──────────────────────────────┤  │
│  │  Full Kernel Space            │  │ ← Full kernel mapped
│  └──────────────────────────────┘  │
└────────────────────────────────────┘

On syscall: Switch from User PT → Kernel PT (CR3 register swap)
On return:  Switch from Kernel PT → User PT

Cost: ~5-30% performance penalty (context switch overhead)

// Enable KPTI
void pti_init(void) {
    if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
        return;  // CPU not vulnerable

    pr_info("Kernel/User page tables isolation: enabled\n");

    // Allocate separate user page tables
    pgd_t *user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL);

    // Copy user space mappings
    clone_pgd_range(user_pgd, kernel_pgd, KERNEL_PGD_PTRS);

    // Map minimal kernel trampolines (entry/exit stubs)
    map_entry_trampoline(user_pgd);

    // Install user page tables
    current->mm->pgd = user_pgd;
}

// Syscall entry: switch to kernel page tables
ENTRY(entry_SYSCALL_64)
    swapgs                        // Swap GS (per-CPU data)
    movq %rsp, PER_CPU_VAR(rsp_scratch)
    movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

    /* Switch page tables */
    movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
    SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp  // Load kernel CR3

    /* ... handle syscall ... */

    SWITCH_TO_USER_CR3 scratch_reg=%rsp    // Load user CR3
    swapgs
    sysretq
END(entry_SYSCALL_64)

// Branch Target Injection (Spectre v2)

// Victim code
if (x < array1_size) {
    y = array2[array1[x] * 256];
}

// Attacker code
void attack() {
    // 1. Train branch predictor
    for (int i = 0; i < 1000; i++) {
        victim_function(valid_x);  // Train: branch TAKEN
    }

    // 2. Flush cache
    clflush(probe_array);

    // 3. Call with malicious x
    victim_function(malicious_x);  // x >= array1_size

    // CPU speculatively executes (branch predictor says TAKEN)
    // Leaks out-of-bounds memory into cache

    // 4. Time side-channel to recover
    for (int i = 0; i < 256; i++) {
        t0 = rdtsc();
        dummy = probe_array[i * 256];
        t1 = rdtsc();

        if (t1 - t0 < THRESHOLD) {
            printf("Leaked: 0x%02x\n", i);
        }
    }
}

// Result: Can leak arbitrary memory across privilege boundaries!

; Traditional indirect jump (vulnerable)
jmp *%rax

; Retpoline (safe)
call retpoline_label
retpoline_label:
    pause          ; Prevent speculation
    lfence         ; Serialize execution
    jmp retpoline_label  ; Infinite loop (never executed)

; CPU's return stack buffer prevents speculation
; Indirect jump converted to return instruction

// Compiler flag
KBUILD_CFLAGS += -mindirect-branch=thunk-extern
KBUILD_CFLAGS += -mindirect-branch-register

// Generated code
// Before:
//   call *%rax
// After:
//   call __x86_indirect_thunk_rax

__x86_indirect_thunk_rax:
    call retpoline_label
retpoline_label:
    pause
    lfence
    jmp retpoline_label
    mov %rax, (%rsp)  // Never executed, but tricks CPU
    ret

# Check CPU vulnerabilities
cat /sys/devices/system/cpu/vulnerabilities/*

# meltdown: Mitigation: PTI
# spectre_v1: Mitigation: usercopy/swapgs barriers and __user pointer sanitization
# spectre_v2: Mitigation: Full generic retpoline, IBPB: conditional, IBRS_FW, RSB filling

# IBRS (Indirect Branch Restricted Speculation)
# IBPB (Indirect Branch Predictor Barrier)
# STIBP (Single Thread Indirect Branch Predictors)
# SSBD (Speculative Store Bypass Disable)

# Disable mitigations (for benchmarking)
# WARNING: Insecure!
echo 0 > /sys/kernel/debug/x86/pti_enabled
echo 0 > /sys/kernel/debug/x86/retp_enabled

DRAM Organization:
┌─────────────────────────────────┐
│  Bank 0                         │
│  ┌───────────────────────────┐  │
│  │ Row 0   [data]            │  │
│  │ Row 1   [data] ← Target   │  │ ← Victim row
│  │ Row 2   [data]            │  │ ← Hammered (read repeatedly)
│  │ Row 3   [data] ← Target   │  │ ← Victim row
│  │ ...                       │  │
│  └───────────────────────────┘  │
└─────────────────────────────────┘

Attack:
1. Find adjacent rows in DRAM
2. Rapidly read from Row 2 (millions of times)
3. Electrical interference causes bit flips in Row 1 and Row 3
4. Attacker doesn't directly access victim rows!

// Rowhammer exploit (simplified)

// 1. Spray memory with target pattern
char *spray[1000];
for (int i = 0; i < 1000; i++) {
    spray[i] = mmap(NULL, 4096, PROT_READ | PROT_WRITE,
                    MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
    memset(spray[i], 0xFF, 4096);  // All bits set
}

// 2. Find adjacent rows (via DRAM addressing)
uint64_t *hammer_addr1 = find_row_address(2);
uint64_t *hammer_addr2 = find_row_address(4);

// 3. Hammer rows
for (int i = 0; i < 1000000; i++) {
    *hammer_addr1;  // Read (causes DRAM row activation)
    *hammer_addr2;
    clflush(hammer_addr1);  // Evict from cache (force DRAM access)
    clflush(hammer_addr2);
}

// 4. Check for bit flips in victim rows
for (int i = 0; i < 1000; i++) {
    for (int j = 0; j < 4096; j++) {
        if (spray[i][j] != 0xFF) {
            printf("Bit flip at %p: 0x%02x\n", &spray[i][j], spray[i][j]);
        }
    }
}

// Real attacks:
// - Flip bit in page table → gain access to kernel memory
// - Flip bit in SELinux context → privilege escalation
// - Flip bit in RSA key → factor private key

// 7 types of namespaces

#define CLONE_NEWNS     0x00020000  // Mount namespace
#define CLONE_NEWUTS    0x04000000  // UTS (hostname) namespace
#define CLONE_NEWIPC    0x08000000  // IPC namespace
#define CLONE_NEWPID    0x20000000  // PID namespace
#define CLONE_NEWNET    0x40000000  // Network namespace
#define CLONE_NEWUSER   0x10000000  // User namespace
#define CLONE_NEWCGROUP 0x02000000  // Cgroup namespace

#define _GNU_SOURCE
#include <sched.h>
#include <unistd.h>
#include <sys/mount.h>

int sandbox_init(void *arg) {
    // New mount namespace
    mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL);

    // New hostname
    sethostname("sandbox", 7);

    // New root filesystem
    chroot("/var/sandbox");
    chdir("/");

    // Execute sandboxed program
    execl("/bin/sh", "sh", NULL);

    return 0;
}

int main() {
    char stack[4096];

    // Create new namespaces
    int flags = CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWPID |
                CLONE_NEWNET | CLONE_NEWIPC;

    // Clone process with new namespaces
    clone(sandbox_init, stack + sizeof(stack), flags | SIGCHLD, NULL);

    wait(NULL);
    return 0;
}

// Parent namespace
// PID 1: init
// PID 123: parent
// PID 124: child (clone with CLONE_NEWPID)

// Inside child's PID namespace
getpid();  // Returns 1 (child is PID 1 in its namespace)

// Child can only see processes in its namespace
ps aux  // Only shows processes in this namespace

// Parent can still see child
// PID 124 in parent namespace == PID 1 in child namespace

# Create new network namespace
ip netns add sandbox

# Execute command in namespace
ip netns exec sandbox ip link list
# 1: lo: <LOOPBACK> state DOWN
# (Only loopback, no network access!)

# Create virtual interface pair
ip link add veth0 type veth peer name veth1

# Move veth1 to sandbox namespace
ip link set veth1 netns sandbox

# Configure networking
ip addr add 10.0.0.1/24 dev veth0
ip link set veth0 up

ip netns exec sandbox ip addr add 10.0.0.2/24 dev veth1
ip netns exec sandbox ip link set veth1 up

# Now sandbox can communicate via veth interface

Chrome Architecture:
────────────────────

┌───────────────────────────────────────────────┐
│             Browser Process                    │
│  - Runs with full privileges                  │
│  - Manages windows, tabs, plugins             │
│  - Opens files, sockets on behalf of renderers│
│  - Passes FDs via SCM_RIGHTS                  │
└────────────┬──────────────────────────────────┘
             │
     ┌───────┼───────┬──────────┐
     │       │       │          │
┌────▼─────┐ │  ┌────▼─────┐  ┌▼──────────┐
│ Renderer │ │  │ Renderer │  │   GPU     │
│ (Tab 1)  │ │  │ (Tab 2)  │  │  Process  │
│          │ │  │          │  │           │
│ Sandbox: │ │  │ Sandbox: │  │ Sandbox:  │
│ - seccomp│ │  │ - seccomp│  │ - seccomp │
│ - No FS  │ │  │ - No FS  │  │ - Limited │
│ - No net │ │  │ - No net │  │   access  │
└──────────┘ │  └──────────┘  └───────────┘
             │
        ┌────▼─────┐
        │  Plugin  │
        │ Process  │
        │ (Flash)  │
        │ Sandbox  │
        └──────────┘

Sandbox Restrictions (Linux):
1. Seccomp-BPF: Allow only ~30 syscalls
2. Namespaces: PID, NET, IPC isolation
3. chroot: Fake root filesystem
4. No setuid/setgid
5. No capabilities
6. Read-only /proc, /sys

// Renderer process startup

void RendererMain() {
    // 1. Drop all capabilities
    drop_all_capabilities();

    // 2. Enter namespaces
    unshare(CLONE_NEWPID | CLONE_NEWNET | CLONE_NEWIPC);

    // 3. chroot to empty directory
    chroot("/var/empty");
    chdir("/");

    // 4. Install seccomp filter
    install_renderer_seccomp_filter();

    // 5. Drop privileges
    setuid(nobody_uid);
    setgid(nobody_gid);

    // 6. Enable no_new_privs
    prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);

    // 7. Run renderer
    RunRendererLoop();
}

void install_renderer_seccomp_filter() {
    // Allow only essential syscalls
    scmp_filter_ctx ctx = seccomp_init(SCMP_ACT_KILL);

    // Read/write/close
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(read), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(write), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(close), 0);

    // Memory management
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(mmap), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(munmap), 0);

    // IPC (to browser process)
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(recvmsg), 0);
    seccomp_rule_add(ctx, SCMP_ACT_ALLOW, SCMP_SYS(sendmsg), 0);

    // DENY: open, socket, execve, fork, etc.

    seccomp_load(ctx);
}

// Browser monitors renderer health

void MonitorRenderer(int renderer_pid) {
    // Check if renderer tries forbidden syscalls
    ptrace(PTRACE_SEIZE, renderer_pid, NULL, PTRACE_O_TRACESECCOMP);

    while (1) {
        int status;
        waitpid(renderer_pid, &status, 0);

        if (WIFSTOPPED(status) && status >> 8 == (SIGTRAP | (PTRACE_EVENT_SECCOMP << 8))) {
            // Seccomp violation detected!
            struct user_regs_struct regs;
            ptrace(PTRACE_GETREGS, renderer_pid, NULL, &regs);

            long syscall_nr = regs.orig_rax;
            log_security_violation(renderer_pid, syscall_nr);

            // Kill malicious renderer
            kill(renderer_pid, SIGKILL);
            respawn_renderer();
        }
    }
}