powerpc/64s/radix: Enable huge vmalloc mappings

This reduces TLB misses by nearly 30x on a `git diff` workload on a
2-node POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%, due
to vfs hashes being allocated with 2MB pages.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210503091755.613393-1-npiggin@gmail.com

1 files changed, 13 insertions, 5 deletions

diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index fab84024650c..3f35c8d20be7 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -8,6 +8,7 @@
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/bug.h>
 #include <asm/module.h>
 #include <linux/uaccess.h>
@@ -88,17 +89,22 @@ int module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
-#ifdef MODULES_VADDR
 static __always_inline void *
 __module_alloc(unsigned long size, unsigned long start, unsigned long end)
 {
-	return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
-				    __builtin_return_address(0));
+	/*
+	 * Don't do huge page allocations for modules yet until more testing
+	 * is done. STRICT_MODULE_RWX may require extra work to support this
+	 * too.
+	 */
+	return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL, PAGE_KERNEL_EXEC,
+				    VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP,
+				    NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 void *module_alloc(unsigned long size)
 {
+#ifdef MODULES_VADDR
 	unsigned long limit = (unsigned long)_etext - SZ_32M;
 	void *ptr = NULL;
 
@@ -112,5 +118,7 @@ void *module_alloc(unsigned long size)
 		ptr = __module_alloc(size, MODULES_VADDR, MODULES_END);
 
 	return ptr;
-}
+#else
+	return __module_alloc(size, VMALLOC_START, VMALLOC_END);
 #endif
+}