[RFC PATCH 5/6] arm64: execmem: enable EXECMEM_ROX_CACHE on supported CPUs

[Adrian Barnaś]

Enable EXECMEM_ROX_CACHE support for ARM64 systems that implement
the bbml2_no_abort CPU feature.

Using the ROX cache brings a performance boost by reducing linear region
fragmentation caused by strict memory permissions (e.g., W^X enforcement).
Grouping executable code (which is read-only in the linear region alias)
into PMD-sized block mappings reduces TLB pressure and page table size.

This is only enabled on systems with bbml2_no_abort, as splitting
these large blocks to make pages writable during module loading would
otherwise risk triggering TLB Conflict Aborts.

Signed-off-by: Adrian Barnaś <abarnas at google.com>
---
 arch/arm64/Kconfig   |  1 +
 arch/arm64/mm/init.c | 22 +++++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 38dba5f7e4d2..79c347ab841e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -285,6 +285,7 @@ config ARM64
 	select USER_STACKTRACE_SUPPORT
 	select VDSO_GETRANDOM
 	select VMAP_STACK
+	select ARCH_HAS_EXECMEM_ROX
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 71aa745e0bef..8269d7747b84 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -420,6 +420,12 @@ void execmem_fill_trapping_insns(void *ptr, size_t size)
 
 	flush_icache_range((unsigned long)ptr, (unsigned long)ptr + size);
 }
+
+#define MODULE_TEXT_FLAG	EXECMEM_ROX_CACHE
+#define MODULE_TEXT_PGPROT	PAGE_KERNEL_ROX
+#else
+#define MODULE_TEXT_FLAG	(0)
+#define MODULE_TEXT_PGPROT	PAGE_KERNEL
 #endif
 
 static u64 module_direct_base __ro_after_init = 0;
@@ -511,6 +517,8 @@ struct execmem_info __init *execmem_arch_setup(void)
 {
 	unsigned long fallback_start = 0, fallback_end = 0;
 	unsigned long start = 0, end = 0;
+	enum execmem_range_flags module_text_flags = 0;
+	pgprot_t module_text_pgprot = PAGE_KERNEL;
 
 	module_init_limits();
 
@@ -531,12 +539,24 @@ struct execmem_info __init *execmem_arch_setup(void)
 		end = module_plt_base + SZ_2G;
 	}
 
+	/*
+	 * The ROX Cache requires bbml2_no_abort because it uses large block
+	 * mappings. On systems without this guarantee, splitting these blocks
+	 * to make pages writable for module loading can trigger TLB Conflict
+	 * Aborts.
+	 */
+	if (system_supports_bbml2_noabort()) {
+		module_text_flags = MODULE_TEXT_FLAG;
+		module_text_pgprot = MODULE_TEXT_PGPROT;
+	}
+
 	execmem_info = (struct execmem_info){
 		.ranges = {
 			[EXECMEM_MODULE_TEXT] = {
 				.start	= start,
 				.end	= end,
-				.pgprot	= PAGE_KERNEL,
+				.flags = module_text_flags,
+				.pgprot	= module_text_pgprot,
 				.alignment = 1,
 				.fallback_start	= fallback_start,
 				.fallback_end	= fallback_end,
-- 
2.54.0.1136.gdb2ca164c4-goog