Commit 620b4e90 authored by Matthew Wilcox's avatar Matthew Wilcox Committed by Linus Torvalds
Browse files

s390: use _refcount for pgtables 

Patch series "Rearrange struct page", v6.

As presented at LSFMM, this patch-set rearranges struct page to give
more contiguous usable space to users who have allocated a struct page
for their own purposes.  For a graphical view of before-and-after, see
the first two tabs of

  https://docs.google.com/spreadsheets/d/1tvCszs_7FXrjei9_mtFiKV6nW1FLnYyvPvW-qNZhdog/edit?usp=sharing

Highlights:
 - deferred_list now really exists in struct page instead of just a comment.
 - hmm_data also exists in struct page instead of being a nasty hack.
 - x86's PGD pages have a real pointer to the mm_struct.
 - VMalloc pages now have all sorts of extra information stored in them
   to help with debugging and tuning.
 - rcu_head is no longer tied to slab in case anyone else wants to
   free pages by RCU.
 - slub's counters no longer share space with _refcount.
 - slub's freelist+counters are now naturally dword aligned.
 - slub loses a parameter to a lot of functions and a sysfs file.

This patch (of 17):

s390 borrows the storage used for _mapcount in struct page in order to
account whether the bottom or top half is being used for 2kB page tables.
I want to use that for something else, so use the top byte of _refcount
instead of the bottom byte of _mapcount.  _refcount may temporarily be
incremented by other CPUs that see a stale pointer to this page in the
page cache, but each CPU can only increment it by one, and there are no
systems with 2^24 CPUs today, so they will not change the upper byte of
_refcount.  We do have to be a little careful not to lose any of their
writes (as they will subsequently decrement the counter).

Link: http://lkml.kernel.org/r/20180518194519.3820-2-willy@infradead.org


Signed-off-by: default avatarMatthew Wilcox <mawilcox@microsoft.com>
Acked-by: default avatarMartin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent e67d4ca7

arch/s390/mm/pgalloc.c

+12 −9
Original line number Diff line number Diff line
@@ -190,14 +190,15 @@ unsigned long *page_table_alloc(struct mm_struct *mm) 
		if (!list_empty(&mm->context.pgtable_list)) {

			page = list_first_entry(&mm->context.pgtable_list,

						struct page, lru);

			mask = atomic_read(&page->_mapcount);

			mask = atomic_read(&page->_refcount) >> 24;

			mask = (mask | (mask >> 4)) & 3;

			if (mask != 3) {

				table = (unsigned long *) page_to_phys(page);

				bit = mask & 1;		/* =1 -> second 2K */

				if (bit)

					table += PTRS_PER_PTE;

				atomic_xor_bits(&page->_mapcount, 1U << bit);

				atomic_xor_bits(&page->_refcount,

							1U << (bit + 24));

				list_del(&page->lru);

			}

		}
@@ -218,12 +219,12 @@ unsigned long *page_table_alloc(struct mm_struct *mm) 
	table = (unsigned long *) page_to_phys(page);

	if (mm_alloc_pgste(mm)) {

		/* Return 4K page table with PGSTEs */

		atomic_set(&page->_mapcount, 3);

		atomic_xor_bits(&page->_refcount, 3 << 24);

		memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE);

		memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE);

	} else {

		/* Return the first 2K fragment of the page */

		atomic_set(&page->_mapcount, 1);

		atomic_xor_bits(&page->_refcount, 1 << 24);

		memset64((u64 *)table, _PAGE_INVALID, 2 * PTRS_PER_PTE);

		spin_lock_bh(&mm->context.lock);

		list_add(&page->lru, &mm->context.pgtable_list);
@@ -242,7 +243,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) 
		/* Free 2K page table fragment of a 4K page */

		bit = (__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t));

		spin_lock_bh(&mm->context.lock);

		mask = atomic_xor_bits(&page->_mapcount, 1U << bit);

		mask = atomic_xor_bits(&page->_refcount, 1U << (bit + 24));

		mask >>= 24;

		if (mask & 3)

			list_add(&page->lru, &mm->context.pgtable_list);

		else
@@ -253,7 +255,6 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) 
	}



	pgtable_page_dtor(page);

	atomic_set(&page->_mapcount, -1);

	__free_page(page);

}
@@ -274,7 +275,8 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table, 
	}

	bit = (__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t));

	spin_lock_bh(&mm->context.lock);

	mask = atomic_xor_bits(&page->_mapcount, 0x11U << bit);

	mask = atomic_xor_bits(&page->_refcount, 0x11U << (bit + 24));

	mask >>= 24;

	if (mask & 3)

		list_add_tail(&page->lru, &mm->context.pgtable_list);

	else
@@ -296,12 +298,13 @@ static void __tlb_remove_table(void *_table) 
		break;

	case 1:		/* lower 2K of a 4K page table */

	case 2:		/* higher 2K of a 4K page table */

		if (atomic_xor_bits(&page->_mapcount, mask << 4) != 0)

		mask = atomic_xor_bits(&page->_refcount, mask << (4 + 24));

		mask >>= 24;

		if (mask != 0)

			break;

		/* fallthrough */

	case 3:		/* 4K page table with pgstes */

		pgtable_page_dtor(page);

		atomic_set(&page->_mapcount, -1);

		__free_page(page);

		break;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE