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

Commit Message

Nicholas Piggin Feb. 2, 2021, 11:05 a.m. UTC

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: [e-mail]
Acked-by: Michael Ellerman <[e-mail]>
Signed-off-by: Nicholas Piggin <[e-mail]>
---
 .../admin-guide/kernel-parameters.txt         |  2 ++
 arch/powerpc/Kconfig                          |  1 +
 arch/powerpc/kernel/module.c                  | 21 +++++++++++++++----
 3 files changed, 20 insertions(+), 4 deletions(-)

Comments

kernel test robot Feb. 2, 2021, 1:48 p.m. UTC | #1

Hi Nicholas,

I love your patch! Yet something to improve:

[auto build test ERROR on powerpc/next]
[also build test ERROR on arm64/for-next/core v5.11-rc6]
[cannot apply to hnaz-linux-mm/master next-20210125]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Nicholas-Piggin/huge-vmalloc-mappings/20210202-190833
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-mpc834x_mds_defconfig (attached as .config)
compiler: powerpc-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/0day-ci/linux/commit/ba7c3aca8bdba641f1cc3cd3da5c19da2b5f721a
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Nicholas-Piggin/huge-vmalloc-mappings/20210202-190833
        git checkout ba7c3aca8bdba641f1cc3cd3da5c19da2b5f721a
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=powerpc 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[e-mail]>

All errors (new ones prefixed by >>):

   In file included from arch/powerpc/include/asm/book3s/pgtable.h:8,
                    from arch/powerpc/include/asm/pgtable.h:18,
                    from include/linux/pgtable.h:6,
                    from arch/powerpc/include/asm/kup.h:50,
                    from arch/powerpc/include/asm/uaccess.h:9,
                    from include/linux/uaccess.h:11,
                    from arch/powerpc/kernel/module.c:13:
   arch/powerpc/kernel/module.c: In function 'module_alloc':
>> arch/powerpc/include/asm/book3s/32/pgtable.h:189:32: error: 'high_memory' undeclared (first use in this function)
     189 | #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
         |                                ^~~~~~~~~~~
   arch/powerpc/kernel/module.c:92:24: note: in expansion of macro 'VMALLOC_START'
      92 |  unsigned long start = VMALLOC_START;
         |                        ^~~~~~~~~~~~~
   arch/powerpc/include/asm/book3s/32/pgtable.h:189:32: note: each undeclared identifier is reported only once for each function it appears in
     189 | #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
         |                                ^~~~~~~~~~~
   arch/powerpc/kernel/module.c:92:24: note: in expansion of macro 'VMALLOC_START'
      92 |  unsigned long start = VMALLOC_START;
         |                        ^~~~~~~~~~~~~


vim +/high_memory +189 arch/powerpc/include/asm/book3s/32/pgtable.h

63b2bc619565ef Christophe Leroy 2019-02-21  188  
3dfcb315d81e66 Aneesh Kumar K.V 2015-12-01 @189  #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
3d4247fcc938d0 Christophe Leroy 2020-01-14  190  

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[e-mail]

Patch

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