From 288bc54949fc2625a4fd811a188fb200cc498946 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 24 Feb 2017 14:59:16 -0800 Subject: [PATCH] mm/autonuma: let architecture override how the write bit should be stashed in a protnone pte. Patch series "Numabalancing preserve write fix", v2. This patch series address an issue w.r.t THP migration and autonuma preserve write feature. migrate_misplaced_transhuge_page() cannot deal with concurrent modification of the page. It does a page copy without following the migration pte sequence. IIUC, this was done to keep the migration simpler and at the time of implemenation we didn't had THP page cache which would have required a more elaborate migration scheme. That means thp autonuma migration expect the protnone with saved write to be done such that both kernel and user cannot update the page content. This patch series enables archs like ppc64 to do that. We are good with the hash translation mode with the current code, because we never create a hardware page table entry for a protnone pte. This patch (of 2): Autonuma preserves the write permission across numa fault to avoid taking a writefault after a numa fault (Commit: b191f9b106ea " mm: numa: preserve PTE write permissions across a NUMA hinting fault"). Architecture can implement protnone in different ways and some may choose to implement that by clearing Read/ Write/Exec bit of pte. Setting the write bit on such pte can result in wrong behaviour. Fix this up by allowing arch to override how to save the write bit on a protnone pte. [aneesh.kumar@linux.vnet.ibm.com: don't mark pte saved write in case of dirty_accountable] Link: http://lkml.kernel.org/r/1487942884-16517-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com [aneesh.kumar@linux.vnet.ibm.com: v3] Link: http://lkml.kernel.org/r/1487498625-10891-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1487050314-3892-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Acked-by: Michael Neuling Cc: Rik van Riel Cc: Mel Gorman Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 16 ++++++++++++++++ mm/huge_memory.c | 6 +++--- mm/memory.c | 2 +- mm/mprotect.c | 2 +- 4 files changed, 21 insertions(+), 5 deletions(-) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index a0aba0f9c57b..6265411eb2ed 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -225,6 +225,22 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres } #endif +#ifndef pte_savedwrite +#define pte_savedwrite pte_write +#endif + +#ifndef pte_mk_savedwrite +#define pte_mk_savedwrite pte_mkwrite +#endif + +#ifndef pmd_savedwrite +#define pmd_savedwrite pmd_write +#endif + +#ifndef pmd_mk_savedwrite +#define pmd_mk_savedwrite pmd_mkwrite +#endif + #ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pmdp_set_wrprotect(struct mm_struct *mm, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index efddd02141a8..92c2ee2dfcf8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1426,7 +1426,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) } /* See similar comment in do_numa_page for explanation */ - if (!pmd_write(pmd)) + if (!pmd_savedwrite(pmd)) flags |= TNF_NO_GROUP; /* @@ -1489,7 +1489,7 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); - was_writable = pmd_write(pmd); + was_writable = pmd_savedwrite(pmd); pmd = pmd_modify(pmd, vma->vm_page_prot); pmd = pmd_mkyoung(pmd); if (was_writable) @@ -1744,7 +1744,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd); entry = pmd_modify(entry, newprot); if (preserve_write) - entry = pmd_mkwrite(entry); + entry = pmd_mk_savedwrite(entry); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); BUG_ON(vma_is_anonymous(vma) && !preserve_write && diff --git a/mm/memory.c b/mm/memory.c index 0c759ba122e1..14fc0b40f0bb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3401,7 +3401,7 @@ static int do_numa_page(struct vm_fault *vmf) int target_nid; bool migrated = false; pte_t pte; - bool was_writable = pte_write(vmf->orig_pte); + bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* diff --git a/mm/mprotect.c b/mm/mprotect.c index a45b4dc6a7f5..848e946b08e5 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -99,7 +99,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = ptep_modify_prot_start(mm, addr, pte); ptent = pte_modify(ptent, newprot); if (preserve_write) - ptent = pte_mkwrite(ptent); + ptent = pte_mk_savedwrite(ptent); /* Avoid taking write faults for known dirty pages */ if (dirty_accountable && pte_dirty(ptent) &&