[PATCH v12 14/14] powerpc/64s/radix: Enable huge vmalloc mappings

[Nicholas Piggin]

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.

Cc: linuxppc-dev at lists.ozlabs.org
Acked-by: Michael Ellerman <mpe at ellerman.id.au>
Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
 .../admin-guide/kernel-parameters.txt         |  2 ++
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/kernel/module.c                  | 21 +++++++++++++++----
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a10b545c2070..d62df53e5200 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3225,6 +3225,8 @@
 
 	nohugeiomap	[KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
 
+	nohugevmalloc	[PPC] Disable kernel huge vmalloc mappings.
+
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 107bb4319e0e..781da6829ab7 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -181,6 +181,7 @@ config PPC
 	select GENERIC_GETTIMEOFDAY
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
+	select HAVE_ARCH_HUGE_VMALLOC		if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
 	select HAVE_ARCH_KASAN_VMALLOC		if PPC32 && PPC_PAGE_SHIFT <= 14
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index a211b0253cdb..07026335d24d 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -87,13 +87,26 @@ int module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
-#ifdef MODULES_VADDR
 void *module_alloc(unsigned long size)
 {
+	unsigned long start = VMALLOC_START;
+	unsigned long end = VMALLOC_END;
+
+#ifdef MODULES_VADDR
 	BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+	start = MODULES_VADDR;
+	end = MODULES_END;
+#endif
+
+	/*
+	 * 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, MODULES_VADDR, MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+	return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC,
+				    VM_NO_HUGE_VMAP | VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
-#endif
-- 
2.23.0