+ mm-introduce-do_set_pmd.patch added to -mm tree

* + mm-introduce-do_set_pmd.patch added to -mm tree
@ 2016-06-07 21:03 akpm
  0 siblings, 0 replies; 2+ messages in thread
From: akpm @ 2016-06-07 21:03 UTC (permalink / raw)
  To: kirill.shutemov, aarcange, andreslc, aneesh.kumar, cl,
	dave.hansen, hughd, jmarchan, n-horiguchi, peterz, quning,
	sasha.levin, vbabka, yang.shi, mm-commits


The patch titled
     Subject: mm: introduce do_set_pmd()
has been added to the -mm tree.  Its filename is
     mm-introduce-do_set_pmd.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/mm-introduce-do_set_pmd.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/mm-introduce-do_set_pmd.patch

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/SubmitChecklist when testing your code ***

The -mm tree is included into linux-next and is updated
there every 3-4 working days

------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: mm: introduce do_set_pmd()

With postponed page table allocation we have chance to setup huge pages.
do_set_pte() calls do_set_pmd() if following criteria met:

 - page is compound;
 - pmd entry in pmd_none();
 - vma has suitable size and alignment;

Link: http://lkml.kernel.org/r/1465297246-98985-7-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@gentwo.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Yang Shi <yang.shi@linaro.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Ning Qu <quning@gmail.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/huge_mm.h |    2 +
 mm/huge_memory.c        |    5 --
 mm/memory.c             |   72 +++++++++++++++++++++++++++++++++++++-
 mm/migrate.c            |    3 -
 4 files changed, 74 insertions(+), 8 deletions(-)

diff -puN include/linux/huge_mm.h~mm-introduce-do_set_pmd include/linux/huge_mm.h

--- a/include/linux/huge_mm.h~mm-introduce-do_set_pmd
+++ a/include/linux/huge_mm.h
@@ -143,6 +143,8 @@ static inline bool is_huge_zero_pmd(pmd_
 struct page *get_huge_zero_page(void);
 void put_huge_zero_page(void);
 
+#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff -puN mm/huge_memory.c~mm-introduce-do_set_pmd mm/huge_memory.c
--- a/mm/huge_memory.c~mm-introduce-do_set_pmd
+++ a/mm/huge_memory.c
@@ -796,11 +796,6 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struc
 	return pmd;
 }
 
-static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
-{
-	return pmd_mkhuge(mk_pmd(page, prot));
-}
-
 static inline struct list_head *page_deferred_list(struct page *page)
 {
 	/*
diff -puN mm/memory.c~mm-introduce-do_set_pmd mm/memory.c
--- a/mm/memory.c~mm-introduce-do_set_pmd
+++ a/mm/memory.c
@@ -2921,6 +2921,66 @@ map_pte:
 	return 0;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1)
+static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
+		unsigned long haddr)
+{
+	if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) !=
+			(vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK))
+		return false;
+	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+		return false;
+	return true;
+}
+
+static int do_set_pmd(struct fault_env *fe, struct page *page)
+{
+	struct vm_area_struct *vma = fe->vma;
+	bool write = fe->flags & FAULT_FLAG_WRITE;
+	unsigned long haddr = fe->address & HPAGE_PMD_MASK;
+	pmd_t entry;
+	int i, ret;
+
+	if (!transhuge_vma_suitable(vma, haddr))
+		return VM_FAULT_FALLBACK;
+
+	ret = VM_FAULT_FALLBACK;
+	page = compound_head(page);
+
+	fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
+	if (unlikely(!pmd_none(*fe->pmd)))
+		goto out;
+
+	for (i = 0; i < HPAGE_PMD_NR; i++)
+		flush_icache_page(vma, page + i);
+
+	entry = mk_huge_pmd(page, vma->vm_page_prot);
+	if (write)
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+
+	add_mm_counter(vma->vm_mm, MM_FILEPAGES, HPAGE_PMD_NR);
+	page_add_file_rmap(page, true);
+
+	set_pmd_at(vma->vm_mm, haddr, fe->pmd, entry);
+
+	update_mmu_cache_pmd(vma, haddr, fe->pmd);
+
+	/* fault is handled */
+	ret = 0;
+out:
+	spin_unlock(fe->ptl);
+	return ret;
+}
+#else
+static int do_set_pmd(struct fault_env *fe, struct page *page)
+{
+	BUILD_BUG();
+	return 0;
+}
+#endif
+
 /**
  * alloc_set_pte - setup new PTE entry for given page and add reverse page
  * mapping. If needed, the fucntion allocates page table or use pre-allocated.
@@ -2940,9 +3000,19 @@ int alloc_set_pte(struct fault_env *fe,
 	struct vm_area_struct *vma = fe->vma;
 	bool write = fe->flags & FAULT_FLAG_WRITE;
 	pte_t entry;
+	int ret;
+
+	if (pmd_none(*fe->pmd) && PageTransCompound(page)) {
+		/* THP on COW? */
+		VM_BUG_ON_PAGE(memcg, page);
+
+		ret = do_set_pmd(fe, page);
+		if (ret != VM_FAULT_FALLBACK)
+			return ret;
+	}
 
 	if (!fe->pte) {
-		int ret = pte_alloc_one_map(fe);
+		ret = pte_alloc_one_map(fe);
 		if (ret)
 			return ret;
 	}
diff -puN mm/migrate.c~mm-introduce-do_set_pmd mm/migrate.c
--- a/mm/migrate.c~mm-introduce-do_set_pmd
+++ a/mm/migrate.c
@@ -1984,8 +1984,7 @@ fail_putback:
 	}
 
 	orig_entry = *pmd;
-	entry = mk_pmd(new_page, vma->vm_page_prot);
-	entry = pmd_mkhuge(entry);
+	entry = mk_huge_pmd(new_page, vma->vm_page_prot);
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
 	/*
_

Patches currently in -mm which might be from kirill.shutemov@linux.intel.com are

mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-2.patch
mm-make-swapin-readahead-to-improve-thp-collapse-rate-fix-3.patch
mm-thp-make-swapin-readahead-under-down_read-of-mmap_sem-fix.patch
thp-mlock-update-unevictable-lrutxt.patch
mm-do-not-pass-mm_struct-into-handle_mm_fault.patch
mm-introduce-fault_env.patch
mm-postpone-page-table-allocation-until-we-have-page-to-map.patch
rmap-support-file-thp.patch
mm-introduce-do_set_pmd.patch
thp-vmstats-add-counters-for-huge-file-pages.patch
thp-support-file-pages-in-zap_huge_pmd.patch
thp-handle-file-pages-in-split_huge_pmd.patch
thp-handle-file-cow-faults.patch
thp-skip-file-huge-pmd-on-copy_huge_pmd.patch
thp-prepare-change_huge_pmd-for-file-thp.patch
thp-run-vma_adjust_trans_huge-outside-i_mmap_rwsem.patch
thp-file-pages-support-for-split_huge_page.patch
thp-mlock-do-not-mlock-pte-mapped-file-huge-pages.patch
vmscan-split-file-huge-pages-before-paging-them-out.patch
page-flags-relax-policy-for-pg_mappedtodisk-and-pg_reclaim.patch
radix-tree-implement-radix_tree_maybe_preload_order.patch
filemap-prepare-find-and-delete-operations-for-huge-pages.patch
truncate-handle-file-thp.patch
mm-rmap-account-shmem-thp-pages.patch
shmem-prepare-huge=-mount-option-and-sysfs-knob.patch
shmem-add-huge-pages-support.patch
shmem-thp-respect-madv_nohugepage-for-file-mappings.patch
thp-extract-khugepaged-from-mm-huge_memoryc.patch
khugepaged-move-up_readmmap_sem-out-of-khugepaged_alloc_page.patch
shmem-make-shmem_inode_info-lock-irq-safe.patch
khugepaged-add-support-of-collapse-for-tmpfs-shmem-pages.patch
thp-introduce-config_transparent_huge_pagecache.patch
shmem-split-huge-pages-beyond-i_size-under-memory-pressure.patch
thp-update-documentation-vm-transhugefilesystems-proctxt.patch
a.patch


^ permalink raw reply	[flat|nested] 2+ messages in thread