arm64: mm: add support for WXN memory translation attribute

The AArch64 virtual memory system supports a global WXN control, which
can be enabled to make all writable mappings implicitly no-exec. This is
a useful hardening feature, as it prevents mistakes in managing page
table permissions from being exploited to attack the system.

When enabled at EL1, the restrictions apply to both EL1 and EL0. EL1 is
completely under our control, and has been cleaned up to allow WXN to be
enabled from boot onwards. EL0 is not under our control, but given that
widely deployed security features such as selinux or PaX already limit
the ability of user space to create mappings that are writable and
executable at the same time, the impact of enabling this for EL0 is
expected to be limited. (For this reason, common user space libraries
that have a legitimate need for manipulating executable code already
carry fallbacks such as [0].)

If enabled at compile time, the feature can still be disabled at boot if
needed, by passing arm64.nowxn on the kernel command line.

[0] https://github.com/libffi/libffi/blob/master/src/closures.c#L440

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-88-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/Kconfig

@@ -1608,6 +1608,17 @@ config RODATA_FULL_DEFAULT_ENABLED
 	  This requires the linear region to be mapped down to pages,
 	  which may adversely affect performance in some cases.
 
+config ARM64_WXN
+	bool "Enable WXN attribute so all writable mappings are non-exec"
+	help
+	  Set the WXN bit in the SCTLR system register so that all writable
+	  mappings are treated as if the PXN/UXN bit is set as well.
+	  If this is set to Y, it can still be disabled at runtime by
+	  passing 'arm64.nowxn' on the kernel command line.
+
+	  This should only be set if no software needs to be supported that
+	  relies on being able to execute from writable mappings.
+
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
 	help

arch/arm64/include/asm/cpufeature.h

@@ -18,6 +18,7 @@
 #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR	0
 #define ARM64_SW_FEATURE_OVERRIDE_HVHE		4
 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF	8
+#define ARM64_SW_FEATURE_OVERRIDE_NOWXN		12
 
 #ifndef __ASSEMBLY__
 
@@ -962,6 +963,13 @@ static inline bool kaslr_disabled_cmdline(void)
 	return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR);
 }
 
+static inline bool arm64_wxn_enabled(void)
+{
+	if (!IS_ENABLED(CONFIG_ARM64_WXN))
+		return false;
+	return !arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOWXN);
+}
+
 u32 get_kvm_ipa_limit(void);
 void dump_cpu_features(void);
 

arch/arm64/include/asm/mman.h

@@ -35,11 +35,40 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
 }
 #define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
 
+static inline bool arm64_check_wx_prot(unsigned long prot,
+				       struct task_struct *tsk)
+{
+	/*
+	 * When we are running with SCTLR_ELx.WXN==1, writable mappings are
+	 * implicitly non-executable. This means we should reject such mappings
+	 * when user space attempts to create them using mmap() or mprotect().
+	 */
+	if (arm64_wxn_enabled() &&
+	    ((prot & (PROT_WRITE | PROT_EXEC)) == (PROT_WRITE | PROT_EXEC))) {
+		/*
+		 * User space libraries such as libffi carry elaborate
+		 * heuristics to decide whether it is worth it to even attempt
+		 * to create writable executable mappings, as PaX or selinux
+		 * enabled systems will outright reject it. They will usually
+		 * fall back to something else (e.g., two separate shared
+		 * mmap()s of a temporary file) on failure.
+		 */
+		pr_info_ratelimited(
+			"process %s (%d) attempted to create PROT_WRITE+PROT_EXEC mapping\n",
+			tsk->comm, tsk->pid);
+		return false;
+	}
+	return true;
+}
+
 static inline bool arch_validate_prot(unsigned long prot,
 	unsigned long addr __always_unused)
 {
 	unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
 
+	if (!arm64_check_wx_prot(prot, current))
+		return false;
+
 	if (system_supports_bti())
 		supported |= PROT_BTI;
 
@@ -50,6 +79,13 @@ static inline bool arch_validate_prot(unsigned long prot,
 }
 #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
 
+static inline bool arch_validate_mmap_prot(unsigned long prot,
+					   unsigned long addr)
+{
+	return arm64_check_wx_prot(prot, current);
+}
+#define arch_validate_mmap_prot arch_validate_mmap_prot
+
 static inline bool arch_validate_flags(unsigned long vm_flags)
 {
 	if (!system_supports_mte())

arch/arm64/include/asm/mmu_context.h

@@ -20,13 +20,41 @@
 #include <asm/cpufeature.h>
 #include <asm/daifflags.h>
 #include <asm/proc-fns.h>
-#include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
 #include <asm/sysreg.h>
 #include <asm/tlbflush.h>
 
 extern bool rodata_full;
 
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
+static inline void arch_unmap(struct mm_struct *mm,
+			unsigned long start, unsigned long end)
+{
+}
+
+static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
+		bool write, bool execute, bool foreign)
+{
+	if (IS_ENABLED(CONFIG_ARM64_WXN) && execute &&
+	    (vma->vm_flags & (VM_WRITE | VM_EXEC)) == (VM_WRITE | VM_EXEC)) {
+		pr_warn_ratelimited(
+			"process %s (%d) attempted to execute from writable memory\n",
+			current->comm, current->pid);
+		/* disallow unless the nowxn override is set */
+		return !arm64_wxn_enabled();
+	}
+	return true;
+}
+
 static inline void contextidr_thread_switch(struct task_struct *next)
 {
 	if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))

arch/arm64/kernel/pi/idreg-override.c

@@ -189,6 +189,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = {
 		FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL),
 		FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter),
 		FIELD("rodataoff", ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF, NULL),
+		FIELD("nowxn", ARM64_SW_FEATURE_OVERRIDE_NOWXN, NULL),
 		{}
 	},
 };
@@ -221,8 +222,9 @@ static const struct {
 	{ "arm64.nomops",		"id_aa64isar2.mops=0" },
 	{ "arm64.nomte",		"id_aa64pfr1.mte=0" },
 	{ "nokaslr",			"arm64_sw.nokaslr=1" },
-	{ "rodata=off",			"arm64_sw.rodataoff=1" },
+	{ "rodata=off",			"arm64_sw.rodataoff=1 arm64_sw.nowxn=1" },
 	{ "arm64.nolva",		"id_aa64mmfr2.varange=0" },
+	{ "arm64.nowxn",		"arm64_sw.nowxn=1" },
 };
 
 static int __init parse_hexdigit(const char *p, u64 *v)

arch/arm64/kernel/pi/map_kernel.c

@@ -132,6 +132,25 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level)
 	idmap_cpu_replace_ttbr1(swapper_pg_dir);
 }
 
+static void noinline __section(".idmap.text") disable_wxn(void)
+{
+	u64 sctlr = read_sysreg(sctlr_el1) & ~SCTLR_ELx_WXN;
+
+	/*
+	 * We cannot safely clear the WXN bit while the MMU and caches are on,
+	 * so turn the MMU off, flush the TLBs and turn it on again but with
+	 * the WXN bit cleared this time.
+	 */
+	asm("	msr	sctlr_el1, %0		;"
+	    "	isb				;"
+	    "	tlbi    vmalle1			;"
+	    "	dsb     nsh			;"
+	    "	isb				;"
+	    "	msr     sctlr_el1, %1		;"
+	    "	isb				;"
+	    ::	"r"(sctlr & ~SCTLR_ELx_M), "r"(sctlr));
+}
+
 static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr)
 {
 	u64 sctlr = read_sysreg(sctlr_el1);
@@ -229,6 +248,10 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 	if (va_bits > VA_BITS_MIN)
 		sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits));
 
+	if (IS_ENABLED(CONFIG_ARM64_WXN) &&
+	    arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOWXN))
+		disable_wxn();
+
 	/*
 	 * The virtual KASLR displacement modulo 2MiB is decided by the
 	 * physical placement of the image, as otherwise, we might not be able

arch/arm64/mm/proc.S

@@ -546,6 +546,12 @@ alternative_else_nop_endif
 	 * Prepare SCTLR
 	 */
 	mov_q	x0, INIT_SCTLR_EL1_MMU_ON
+#ifdef CONFIG_ARM64_WXN
+	ldr_l	x1, arm64_sw_feature_override + FTR_OVR_VAL_OFFSET
+	tst	x1, #0xf << ARM64_SW_FEATURE_OVERRIDE_NOWXN
+	orr	x1, x0, #SCTLR_ELx_WXN
+	csel	x0, x0, x1, ne
+#endif
 	ret					// return to head.S
 
 	.unreq	mair