mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2026-01-27 11:55:10 +00:00
The mm_struct contains a function pointer *get_unmapped_area(), which is set to either arch_get_unmapped_area() or arch_get_unmapped_area_topdown() during the initialization of the mm. Since the function pointer only ever points to two functions that are named the same across all arch's, a function pointer is not really required. In addition future changes will want to add versions of the functions that take additional arguments. So to save a pointers worth of bytes in mm_struct, and prevent adding additional function pointers to mm_struct in future changes, remove it and keep the information about which get_unmapped_area() to use in a flag. Add the new flag to MMF_INIT_MASK so it doesn't get clobbered on fork by mmf_init_flags(). Most MM flags get clobbered on fork. In the pre-existing behavior mm->get_unmapped_area() would get copied to the new mm in dup_mm(), so not clobbering the flag preserves the existing behavior around inheriting the topdown-ness. Introduce a helper, mm_get_unmapped_area(), to easily convert code that refers to the old function pointer to instead select and call either arch_get_unmapped_area() or arch_get_unmapped_area_topdown() based on the flag. Then drop the mm->get_unmapped_area() function pointer. Leave the get_unmapped_area() pointer in struct file_operations alone. The main purpose of this change is to reorganize in preparation for future changes, but it also converts the calls of mm->get_unmapped_area() from indirect branches into a direct ones. The stress-ng bigheap benchmark calls realloc a lot, which calls through get_unmapped_area() in the kernel. On x86, the change yielded a ~1% improvement there on a retpoline config. In testing a few x86 configs, removing the pointer unfortunately didn't result in any actual size reductions in the compiled layout of mm_struct. But depending on compiler or arch alignment requirements, the change could shrink the size of mm_struct. Link: https://lkml.kernel.org/r/20240326021656.202649-3-rick.p.edgecombe@intel.com Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com> Acked-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar@kernel.org> Cc: Borislav Petkov (AMD) <bp@alien8.de> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Deepak Gupta <debug@rivosinc.com> Cc: Guo Ren <guoren@kernel.org> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin (Intel) <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Kees Cook <keescook@chromium.org> Cc: Mark Brown <broonie@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
149 lines
3.7 KiB
C
149 lines
3.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* IA-32 Huge TLB Page Support for Kernel.
|
|
*
|
|
* Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/compat.h>
|
|
#include <asm/mman.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/elf.h>
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
|
|
unsigned long addr, unsigned long len,
|
|
unsigned long pgoff, unsigned long flags)
|
|
{
|
|
struct hstate *h = hstate_file(file);
|
|
struct vm_unmapped_area_info info;
|
|
|
|
info.flags = 0;
|
|
info.length = len;
|
|
info.low_limit = get_mmap_base(1);
|
|
|
|
/*
|
|
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
|
|
* in the full address space.
|
|
*/
|
|
info.high_limit = in_32bit_syscall() ?
|
|
task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
|
|
|
|
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
|
|
info.align_offset = 0;
|
|
return vm_unmapped_area(&info);
|
|
}
|
|
|
|
static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
|
|
unsigned long addr, unsigned long len,
|
|
unsigned long pgoff, unsigned long flags)
|
|
{
|
|
struct hstate *h = hstate_file(file);
|
|
struct vm_unmapped_area_info info;
|
|
|
|
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
|
|
info.length = len;
|
|
info.low_limit = PAGE_SIZE;
|
|
info.high_limit = get_mmap_base(0);
|
|
|
|
/*
|
|
* If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
|
|
* in the full address space.
|
|
*/
|
|
if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
|
|
info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
|
|
|
|
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
|
|
info.align_offset = 0;
|
|
addr = vm_unmapped_area(&info);
|
|
|
|
/*
|
|
* A failed mmap() very likely causes application failure,
|
|
* so fall back to the bottom-up function here. This scenario
|
|
* can happen with large stack limits and large mmap()
|
|
* allocations.
|
|
*/
|
|
if (addr & ~PAGE_MASK) {
|
|
VM_BUG_ON(addr != -ENOMEM);
|
|
info.flags = 0;
|
|
info.low_limit = TASK_UNMAPPED_BASE;
|
|
info.high_limit = TASK_SIZE_LOW;
|
|
addr = vm_unmapped_area(&info);
|
|
}
|
|
|
|
return addr;
|
|
}
|
|
|
|
unsigned long
|
|
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long pgoff, unsigned long flags)
|
|
{
|
|
struct hstate *h = hstate_file(file);
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
|
|
if (len & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
|
|
if (len > TASK_SIZE)
|
|
return -ENOMEM;
|
|
|
|
/* No address checking. See comment at mmap_address_hint_valid() */
|
|
if (flags & MAP_FIXED) {
|
|
if (prepare_hugepage_range(file, addr, len))
|
|
return -EINVAL;
|
|
return addr;
|
|
}
|
|
|
|
if (addr) {
|
|
addr &= huge_page_mask(h);
|
|
if (!mmap_address_hint_valid(addr, len))
|
|
goto get_unmapped_area;
|
|
|
|
vma = find_vma(mm, addr);
|
|
if (!vma || addr + len <= vm_start_gap(vma))
|
|
return addr;
|
|
}
|
|
|
|
get_unmapped_area:
|
|
if (!test_bit(MMF_TOPDOWN, &mm->flags))
|
|
return hugetlb_get_unmapped_area_bottomup(file, addr, len,
|
|
pgoff, flags);
|
|
else
|
|
return hugetlb_get_unmapped_area_topdown(file, addr, len,
|
|
pgoff, flags);
|
|
}
|
|
#endif /* CONFIG_HUGETLB_PAGE */
|
|
|
|
#ifdef CONFIG_X86_64
|
|
bool __init arch_hugetlb_valid_size(unsigned long size)
|
|
{
|
|
if (size == PMD_SIZE)
|
|
return true;
|
|
else if (size == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES))
|
|
return true;
|
|
else
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_CONTIG_ALLOC
|
|
static __init int gigantic_pages_init(void)
|
|
{
|
|
/* With compaction or CMA we can allocate gigantic pages at runtime */
|
|
if (boot_cpu_has(X86_FEATURE_GBPAGES))
|
|
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
|
|
return 0;
|
|
}
|
|
arch_initcall(gigantic_pages_init);
|
|
#endif
|
|
#endif
|