arm64: module: mandate MODULE_PLTS

Contemporary kernels and modules can be relatively large, especially
when common debug options are enabled. Using GCC 12.1.0, a v6.3-rc7
defconfig kernel is ~38M, and with PROVE_LOCKING + KASAN_INLINE enabled
this expands to ~117M. Shanker reports [1] that the NVIDIA GPU driver
alone can consume 110M of module space in some configurations.

Both KASLR and ARM64_ERRATUM_843419 select MODULE_PLTS, so anyone
wanting a kernel to have KASLR or run on Cortex-A53 will have
MODULE_PLTS selected. This is the case in defconfig and distribution
kernels (e.g. Debian, Android, etc).

Practically speaking, this means we're very likely to need MODULE_PLTS
and while it's almost guaranteed that MODULE_PLTS will be selected, it
is possible to disable support, and we have to maintain some awkward
special cases for such unusual configurations.

This patch removes the MODULE_PLTS config option, with the support code
always enabled if MODULES is selected. This results in a slight
simplification, and will allow for further improvement in subsequent
patches.

For any config which currently selects MODULE_PLTS, there will be no
functional change as a result of this patch.

[1] https://lore.kernel.org/linux-arm-kernel/159ceeab-09af-3174-5058-445bc8dcf85b@nvidia.com/

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Cc: Shanker Donthineni <sdonthineni@nvidia.com>
Cc: Will Deacon <will@kernel.org>
Tested-by: Shanker Donthineni <sdonthineni@nvidia.com>
Link: https://lore.kernel.org/r/20230530110328.2213762-6-mark.rutland@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

6 files changed, 19 insertions, 49 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b1201d25a8a4..a6002084f09c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -207,6 +207,7 @@ config ARM64
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KVM
+	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -577,7 +578,6 @@ config ARM64_ERRATUM_845719
 config ARM64_ERRATUM_843419
 	bool "Cortex-A53: 843419: A load or store might access an incorrect address"
 	default y
-	select ARM64_MODULE_PLTS if MODULES
 	help
 	  This option links the kernel with '--fix-cortex-a53-843419' and
 	  enables PLT support to replace certain ADRP instructions, which can
@@ -2107,26 +2107,6 @@ config ARM64_SME
 	  register state capable of holding two dimensional matrix tiles to
 	  enable various matrix operations.
 
-config ARM64_MODULE_PLTS
-	bool "Use PLTs to allow module memory to spill over into vmalloc area"
-	depends on MODULES
-	select HAVE_MOD_ARCH_SPECIFIC
-	help
-	  Allocate PLTs when loading modules so that jumps and calls whose
-	  targets are too far away for their relative offsets to be encoded
-	  in the instructions themselves can be bounced via veneers in the
-	  module's PLT. This allows modules to be allocated in the generic
-	  vmalloc area after the dedicated module memory area has been
-	  exhausted.
-
-	  When running with address space randomization (KASLR), the module
-	  region itself may be too far away for ordinary relative jumps and
-	  calls, and so in that case, module PLTs are required and cannot be
-	  disabled.
-
-	  Specific errata workaround(s) might also force module PLTs to be
-	  enabled (ARM64_ERRATUM_843419).
-
 config ARM64_PSEUDO_NMI
 	bool "Support for NMI-like interrupts"
 	select ARM_GIC_V3
@@ -2167,7 +2147,6 @@ config RELOCATABLE
 
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image"
-	select ARM64_MODULE_PLTS if MODULES
 	select RELOCATABLE
 	help
 	  Randomizes the virtual address at which the kernel image is
@@ -2198,9 +2177,8 @@ config RANDOMIZE_MODULE_REGION_FULL
 	  When this option is not set, the module region will be randomized over
 	  a limited range that contains the [_stext, _etext] interval of the
 	  core kernel, so branch relocations are almost always in range unless
-	  ARM64_MODULE_PLTS is enabled and the region is exhausted. In this
-	  particular case of region exhaustion, modules might be able to fall
-	  back to a larger 2GB area.
+	  the region is exhausted. In this particular case of region
+	  exhaustion, modules might be able to fall back to a larger 2GB area.
 
 config CC_HAVE_STACKPROTECTOR_SYSREG
 	def_bool $(cc-option,-mstack-protector-guard=sysreg -mstack-protector-guard-reg=sp_el0 -mstack-protector-guard-offset=0)
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 3e7dcc5fa2f2..bfa6638b4c93 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -7,7 +7,6 @@
 
 #include <asm-generic/module.h>
 
-#ifdef CONFIG_ARM64_MODULE_PLTS
 struct mod_plt_sec {
 	int			plt_shndx;
 	int			plt_num_entries;
@@ -21,7 +20,6 @@ struct mod_arch_specific {
 	/* for CONFIG_DYNAMIC_FTRACE */
 	struct plt_entry	*ftrace_trampolines;
 };
-#endif
 
 u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
 			  void *loc, const Elf64_Rela *rela,
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index dbba4b7559aa..b9ae8349e35d 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -1,9 +1,7 @@
 SECTIONS {
-#ifdef CONFIG_ARM64_MODULE_PLTS
 	.plt 0 : { BYTE(0) }
 	.init.plt 0 : { BYTE(0) }
 	.text.ftrace_trampoline 0 : { BYTE(0) }
-#endif
 
 #ifdef CONFIG_KASAN_SW_TAGS
 	/*
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7c2bb4e72476..3864a64e2b2b 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -42,8 +42,7 @@ obj-$(CONFIG_COMPAT)			+= sigreturn32.o
 obj-$(CONFIG_COMPAT_ALIGNMENT_FIXUPS)	+= compat_alignment.o
 obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
-obj-$(CONFIG_MODULES)			+= module.o
-obj-$(CONFIG_ARM64_MODULE_PLTS)		+= module-plts.o
+obj-$(CONFIG_MODULES)			+= module.o module-plts.o
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 432626c866a8..a650f5e11fc5 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -197,7 +197,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 static struct plt_entry *get_ftrace_plt(struct module *mod)
 {
-#ifdef CONFIG_ARM64_MODULE_PLTS
+#ifdef CONFIG_MODULES
 	struct plt_entry *plt = mod->arch.ftrace_trampolines;
 
 	return &plt[FTRACE_PLT_IDX];
@@ -249,7 +249,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	 * must use a PLT to reach it. We can only place PLTs for modules, and
 	 * only when module PLT support is built-in.
 	 */
-	if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+	if (!IS_ENABLED(CONFIG_MODULES))
 		return false;
 
 	/*
@@ -431,10 +431,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	 *
 	 * Note: 'mod' is only set at module load time.
 	 */
-	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) &&
-	    IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) {
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) && mod)
 		return aarch64_insn_patch_text_nosync((void *)pc, new);
-	}
 
 	if (!ftrace_find_callable_addr(rec, mod, &addr))
 		return -EINVAL;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 51fd8abd9b74..f64636c2fd05 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -73,25 +73,26 @@ subsys_initcall(kaslr_module_init)
 void *module_alloc(unsigned long size)
 {
 	u64 module_alloc_end = module_alloc_base + MODULES_VSIZE;
-	gfp_t gfp_mask = GFP_KERNEL;
 	void *p;
 
-	/* Silence the initial allocation */
-	if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
-		gfp_mask |= __GFP_NOWARN;
-
+	/*
+	 * Where possible, prefer to allocate within direct branch range of the
+	 * kernel such that no PLTs are necessary. This may fail, so we pass
+	 * __GFP_NOWARN to silence the resulting warning.
+	 */
 	p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
-				module_alloc_end, gfp_mask, PAGE_KERNEL, 0,
-				NUMA_NO_NODE, __builtin_return_address(0));
+				module_alloc_end, GFP_KERNEL | __GFP_NOWARN,
+				PAGE_KERNEL, 0, NUMA_NO_NODE,
+				__builtin_return_address(0));
 
-	if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) {
+	if (!p) {
 		p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
 				module_alloc_base + SZ_2G, GFP_KERNEL,
 				PAGE_KERNEL, 0, NUMA_NO_NODE,
 				__builtin_return_address(0));
 	}
 
-	if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) {
+	if (p && (kasan_alloc_module_shadow(p, size, GFP_KERNEL) < 0)) {
 		vfree(p);
 		return NULL;
 	}
@@ -479,9 +480,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_AARCH64_CALL26:
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
 					     AARCH64_INSN_IMM_26);
-
-			if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
-			    ovf == -ERANGE) {
+			if (ovf == -ERANGE) {
 				val = module_emit_plt_entry(me, sechdrs, loc, &rel[i], sym);
 				if (!val)
 					return -ENOEXEC;
@@ -518,7 +517,7 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
 				  const Elf_Shdr *sechdrs,
 				  struct module *mod)
 {
-#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE)
+#if defined(CONFIG_DYNAMIC_FTRACE)
 	const Elf_Shdr *s;
 	struct plt_entry *plts;