Commit e0d23cdc authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next 

Pull x86 mm update from Ingo Molnar:

 - speed up 256 GB PCI BAR ioremap()s

 - speed up PTE swapout page reclaim case

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, ioremap: Speed up check for RAM pages
  x86/mm: In the PTE swapout page reclaim case clear the accessed bit instead of flushing the TLB
parents c33c4054 c81c8a1e

arch/x86/mm/ioremap.c

+19 −7
Original line number Diff line number Diff line
@@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, 
	return err;

}



static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,

			       void *arg)

{

	unsigned long i;



	for (i = 0; i < nr_pages; ++i)

		if (pfn_valid(start_pfn + i) &&

		    !PageReserved(pfn_to_page(start_pfn + i)))

			return 1;



	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);



	return 0;

}



/*

 * Remap an arbitrary physical address space into the kernel virtual

 * address space. Needed when the kernel wants to access high addresses
@@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, 
	/*

	 * Don't allow anybody to remap normal RAM that we're using..

	 */

	pfn      = phys_addr >> PAGE_SHIFT;

	last_pfn = last_addr >> PAGE_SHIFT;

	for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) {

		int is_ram = page_is_ram(pfn);



		if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn)))

	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,

				  __ioremap_check_ram) == 1)

		return NULL;

		WARN_ON_ONCE(is_ram);

	}



	/*

	 * Mappings have to be page-aligned

arch/x86/mm/pgtable.c

+14 −7
Original line number Diff line number Diff line
@@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, 
int ptep_clear_flush_young(struct vm_area_struct *vma,

			   unsigned long address, pte_t *ptep)

{

	int young;



	young = ptep_test_and_clear_young(vma, address, ptep);

	if (young)

		flush_tlb_page(vma, address);



	return young;

	/*

	 * On x86 CPUs, clearing the accessed bit without a TLB flush

	 * doesn't cause data corruption. [ It could cause incorrect

	 * page aging and the (mistaken) reclaim of hot pages, but the

	 * chance of that should be relatively low. ]

	 *

	 * So as a performance optimization don't flush the TLB when

	 * clearing the accessed bit, it will eventually be flushed by

	 * a context switch or a VM operation anyway. [ In the rare

	 * event of it not getting flushed for a long time the delay

	 * shouldn't really matter because there's no real memory

	 * pressure for swapout to react to. ]

	 */

	return ptep_test_and_clear_young(vma, address, ptep);

}



#ifdef CONFIG_TRANSPARENT_HUGEPAGE

CRA Git | Maintained and supported by SUSTech CRA and CCSE