Re: [PATCH v13 14/14] powerpc/64s/radix: Enable huge vmalloc mappings
From: Christophe Leroy <hidden>
Date: 2021-04-15 10:24:02
Also in:
linux-arch, linux-mm, lkml
Hi Nick, Le 17/03/2021 à 07:24, Nicholas Piggin a écrit :
quoted hunk ↗ jump to hunk
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@lists.ozlabs.org Acked-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> --- .../admin-guide/kernel-parameters.txt | 2 ++ arch/powerpc/Kconfig | 1 + arch/powerpc/kernel/module.c | 22 +++++++++++++++---- 3 files changed, 21 insertions(+), 4 deletions(-)--- 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>@@ -87,13 +88,26 @@ 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,
I think you should add the following in <asm/pgtable.h> #ifndef MODULES_VADDR #define MODULES_VADDR VMALLOC_START #define MODULES_END VMALLOC_END #endif And leave module_alloc() as is (just removing the enclosing #ifdef MODULES_VADDR and adding the VM_NO_HUGE_VMAP flag) This would minimise the conflits with the changes I did in powerpc/next reported by Stephen R.
+ 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